diff options
178 files changed, 7928 insertions, 2281 deletions
diff --git a/.gitignore b/.gitignore index 37b2fa8d3..b8128fab1 100644 --- a/.gitignore +++ b/.gitignore @@ -26,5 +26,6 @@ updates_key.pem *.m4a *.m4v *.part +*.swp test/testdata .tox @@ -6,10 +6,10 @@ clean: cleanall: clean rm -f youtube-dl youtube-dl.exe -PREFIX=/usr/local -BINDIR=$(PREFIX)/bin -MANDIR=$(PREFIX)/man -PYTHON=/usr/bin/env python +PREFIX ?= /usr/local +BINDIR ?= $(PREFIX)/bin +MANDIR ?= $(PREFIX)/man +PYTHON ?= /usr/bin/env python # set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local ifeq ($(PREFIX),/usr) @@ -12,11 +12,19 @@ To install it right away for all UNIX users (Linux, OS X, etc.), type: If you do not have curl, you can alternatively use a recent wget: - sudo wget https://yt-dl.org/downloads/2014.05.13/youtube-dl -O /usr/local/bin/youtube-dl + sudo wget https://yt-dl.org/downloads/latest/youtube-dl -O /usr/local/bin/youtube-dl sudo chmod a+x /usr/local/bin/youtube-dl Windows users can [download a .exe file](https://yt-dl.org/latest/youtube-dl.exe) and place it in their home directory or any other location on their [PATH](http://en.wikipedia.org/wiki/PATH_%28variable%29). +OS X users can install **youtube-dl** with [Homebrew](http://brew.sh/). + + brew install youtube-dl + +You can also use pip: + + sudo pip install youtube-dl + Alternatively, refer to the developer instructions below for how to check out and work with the git repository. For further options, including PGP signatures, see https://rg3.github.io/youtube-dl/download.html . # DESCRIPTION @@ -38,12 +46,6 @@ which means you can modify it, redistribute it or use it however you like. playlist or the command line) if an error occurs --dump-user-agent display the current browser identification - --user-agent UA specify a custom user agent - --referer REF specify a custom referer, use if the video - access is restricted to one domain - --add-header FIELD:VALUE specify a custom HTTP header and its value, - separated by a colon ':'. You can use this - option multiple times --list-extractors List all supported extractors and the URLs they would handle --extractor-descriptions Output descriptions of all supported @@ -51,35 +53,22 @@ which means you can modify it, redistribute it or use it however you like. --proxy URL Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection - --no-check-certificate Suppress HTTPS certificate validation. - --prefer-insecure Use an unencrypted connection to retrieve - information about the video. (Currently - supported only for YouTube) - --cache-dir DIR Location in the filesystem where youtube-dl - can store some downloaded information - permanently. By default $XDG_CACHE_HOME - /youtube-dl or ~/.cache/youtube-dl . At the - moment, only YouTube player files (for - videos with obfuscated signatures) are - cached, but that may change. - --no-cache-dir Disable filesystem caching --socket-timeout None Time to wait before giving up, in seconds - --bidi-workaround Work around terminals that lack - bidirectional text support. Requires bidiv - or fribidi executable in PATH --default-search PREFIX Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple". Use the value "auto" to let - youtube-dl guess. The default value "error" - just throws an error. + youtube-dl guess ("auto_warning" to emit a + warning when guessing). "error" just throws + an error. The default value "fixup_error" + repairs broken URLs, but emits an error if + this is not possible instead of searching. --ignore-config Do not read configuration files. When given in the global configuration file /etc /youtube-dl.conf: do not read the user configuration in ~/.config/youtube-dl.conf (%APPDATA%/youtube-dl/config.txt on Windows) - --encoding ENCODING Force the specified encoding (experimental) ## Video Selection: --playlist-start NUMBER playlist video to start at (default is 1) @@ -125,9 +114,9 @@ which means you can modify it, redistribute it or use it however you like. of SIZE. ## Filesystem Options: - -t, --title use title in file name (default) + -a, --batch-file FILE file containing URLs to download ('-' for + stdin) --id use only video ID in file name - -l, --literal [deprecated] alias of --title -A, --auto-number number downloaded files starting from 00000 -o, --output TEMPLATE output filename template. Use %(title)s to get the title, %(uploader)s for the @@ -160,18 +149,15 @@ which means you can modify it, redistribute it or use it however you like. --restrict-filenames Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames - -a, --batch-file FILE file containing URLs to download ('-' for - stdin) - --load-info FILE json file containing the video information - (created with the "--write-json" option) + -t, --title [deprecated] use title in file name + (default) + -l, --literal [deprecated] alias of --title -w, --no-overwrites do not overwrite files -c, --continue force resume of partially downloaded files. By default, youtube-dl will resume downloads if possible. --no-continue do not resume partially downloaded files (restart from beginning) - --cookies FILE file to read cookies from and dump cookie - jar in --no-part do not use .part files --no-mtime do not use the Last-modified header to set the file modification time @@ -181,6 +167,19 @@ which means you can modify it, redistribute it or use it however you like. --write-annotations write video annotations to a .annotation file --write-thumbnail write thumbnail image to disk + --load-info FILE json file containing the video information + (created with the "--write-json" option) + --cookies FILE file to read cookies from and dump cookie + jar in + --cache-dir DIR Location in the filesystem where youtube-dl + can store some downloaded information + permanently. By default $XDG_CACHE_HOME + /youtube-dl or ~/.cache/youtube-dl . At the + moment, only YouTube player files (for + videos with obfuscated signatures) are + cached, but that may change. + --no-cache-dir Disable filesystem caching + --rm-cache-dir Delete all filesystem cache files ## Verbosity / Simulation Options: -q, --quiet activates quiet mode @@ -210,6 +209,22 @@ which means you can modify it, redistribute it or use it however you like. problems --print-traffic Display sent and read HTTP traffic +## Workarounds: + --encoding ENCODING Force the specified encoding (experimental) + --no-check-certificate Suppress HTTPS certificate validation. + --prefer-insecure Use an unencrypted connection to retrieve + information about the video. (Currently + supported only for YouTube) + --user-agent UA specify a custom user agent + --referer REF specify a custom referer, use if the video + access is restricted to one domain + --add-header FIELD:VALUE specify a custom HTTP header and its value, + separated by a colon ':'. You can use this + option multiple times + --bidi-workaround Work around terminals that lack + bidirectional text support. Requires bidiv + or fribidi executable in PATH + ## Video Format Options: -f, --format FORMAT video format code, specify the order of preference using slashes: "-f 22/17/18". @@ -240,6 +255,7 @@ which means you can modify it, redistribute it or use it however you like. ## Authentication Options: -u, --username USERNAME account username -p, --password PASSWORD account password + -2, --twofactor TWOFACTOR two-factor auth code -n, --netrc use .netrc authentication data --video-password PASSWORD video password (vimeo, smotri) @@ -272,6 +288,10 @@ which means you can modify it, redistribute it or use it however you like. postprocessors (default) --prefer-ffmpeg Prefer ffmpeg over avconv for running the postprocessors + --exec CMD Execute a command on the file after + downloading, similar to find's -exec + syntax. Example: --exec 'adb push {} + /sdcard/Music/ && rm {}' # CONFIGURATION @@ -296,10 +316,12 @@ The current default template is `%(title)s-%(id)s.%(ext)s`. In some cases, you don't want special characters such as 中, spaces, or &, such as when transferring the downloaded filename to a Windows system or the filename through an 8bit-unsafe channel. In these cases, add the `--restrict-filenames` flag to get a shorter title: - $ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc - youtube-dl test video ''_ä↭𝕐.mp4 # All kinds of weird characters - $ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc --restrict-filenames - youtube-dl_test_video_.mp4 # A simple file name +```bash +$ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc +youtube-dl test video ''_ä↭𝕐.mp4 # All kinds of weird characters +$ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc --restrict-filenames +youtube-dl_test_video_.mp4 # A simple file name +``` # VIDEO SELECTION @@ -310,14 +332,16 @@ Videos can be filtered by their upload date using the options `--date`, `--dateb Examples: - # Download only the videos uploaded in the last 6 months - $ youtube-dl --dateafter now-6months +```bash +# Download only the videos uploaded in the last 6 months +$ youtube-dl --dateafter now-6months - # Download only the videos uploaded on January 1, 1970 - $ youtube-dl --date 19700101 +# Download only the videos uploaded on January 1, 1970 +$ youtube-dl --date 19700101 - $ # will only download the videos uploaded in the 200x decade - $ youtube-dl --dateafter 20000101 --datebefore 20091231 +$ # will only download the videos uploaded in the 200x decade +$ youtube-dl --dateafter 20000101 --datebefore 20091231 +``` # FAQ @@ -392,49 +416,49 @@ If you want to add support for a new site, you can follow this quick list (assum 2. Check out the source code with `git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git` 3. Start a new git branch with `cd youtube-dl; git checkout -b yourextractor` 4. Start with this simple template and save it to `youtube_dl/extractor/yourextractor.py`: - - # coding: utf-8 - from __future__ import unicode_literals - - import re - - from .common import InfoExtractor - - - class YourExtractorIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)' - _TEST = { - 'url': 'http://yourextractor.com/watch/42', - 'md5': 'TODO: md5 sum of the first 10KiB of the video file', - 'info_dict': { - 'id': '42', - 'ext': 'mp4', - 'title': 'Video title goes here', - # TODO more properties, either as: - # * A value - # * MD5 checksum; start the string with md5: - # * A regular expression; start the string with re: - # * Any Python type (for example int or float) - } + ```python + # coding: utf-8 + from __future__ import unicode_literals + + import re + + from .common import InfoExtractor + + + class YourExtractorIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://yourextractor.com/watch/42', + 'md5': 'TODO: md5 sum of the first 10KiB of the video file', + 'info_dict': { + 'id': '42', + 'ext': 'mp4', + 'title': 'Video title goes here', + 'thumbnail': 're:^https?://.*\.jpg$', + # TODO more properties, either as: + # * A value + # * MD5 checksum; start the string with md5: + # * A regular expression; start the string with re: + # * Any Python type (for example int or float) } + } - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - # TODO more code goes here, for example ... - webpage = self._download_webpage(url, video_id) - title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title') - - return { - 'id': video_id, - 'title': title, - # TODO more properties (see youtube_dl/extractor/common.py) - } + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + # TODO more code goes here, for example ... + webpage = self._download_webpage(url, video_id) + title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title') + return { + 'id': video_id, + 'title': title, + # TODO more properties (see youtube_dl/extractor/common.py) + } + ``` 5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py). -6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. +6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. 7. Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Add tests and code for as many as you want. 8. If you can, check the code with [pyflakes](https://pypi.python.org/pypi/pyflakes) (a good idea) and [pep8](https://pypi.python.org/pypi/pep8) (optional, ignore E501). 9. When the tests pass, [add](https://www.kernel.org/pub/software/scm/git/docs/git-add.html) the new files and [commit](https://www.kernel.org/pub/software/scm/git/docs/git-commit.html) them and [push](https://www.kernel.org/pub/software/scm/git/docs/git-push.html) the result, like this: diff --git a/test/helper.py b/test/helper.py index 230d2bd67..7f3ab8438 100644 --- a/test/helper.py +++ b/test/helper.py @@ -102,7 +102,11 @@ def expect_info_dict(self, expected_dict, got_dict): match_rex = re.compile(match_str) self.assertTrue( - isinstance(got, compat_str) and match_rex.match(got), + isinstance(got, compat_str), + u'Expected a %s object, but got %s for field %s' % ( + compat_str.__name__, type(got).__name__, info_field)) + self.assertTrue( + match_rex.match(got), u'field %s (value: %r) should match %r' % (info_field, got, match_str)) elif isinstance(expected, type): got = got_dict.get(info_field) @@ -117,8 +121,9 @@ def expect_info_dict(self, expected_dict, got_dict): u'invalid value for field %s, expected %r, got %r' % (info_field, expected, got)) # Check for the presence of mandatory fields - for key in ('id', 'url', 'title', 'ext'): - self.assertTrue(got_dict.get(key), 'Missing mandatory field %s' % key) + if got_dict.get('_type') != 'playlist': + for key in ('id', 'url', 'title', 'ext'): + self.assertTrue(got_dict.get(key), 'Missing mandatory field %s' % key) # Check for mandatory fields that are automatically set by YoutubeDL for key in ['webpage_url', 'extractor', 'extractor_key']: self.assertTrue(got_dict.get(key), u'Missing field: %s' % key) @@ -137,8 +142,8 @@ def expect_info_dict(self, expected_dict, got_dict): def assertRegexpMatches(self, text, regexp, msg=None): - if hasattr(self, 'assertRegexpMatches'): - return self.assertRegexpMatches(text, regexp, msg) + if hasattr(self, 'assertRegexp'): + return self.assertRegexp(text, regexp, msg) else: m = re.match(regexp, text) if not m: @@ -148,3 +153,10 @@ def assertRegexpMatches(self, text, regexp, msg=None): else: msg = note + ', ' + msg self.assertTrue(m, msg) + + +def assertGreaterEqual(self, got, expected, msg=None): + if not (got >= expected): + if msg is None: + msg = '%r not greater than or equal to %r' % (got, expected) + self.assertTrue(got >= expected, msg) diff --git a/test/parameters.json b/test/parameters.json index 487a46d56..098cd0cd0 100644 --- a/test/parameters.json +++ b/test/parameters.json @@ -27,7 +27,6 @@ "rejecttitle": null, "retries": 10, "simulate": false, - "skip_download": false, "subtitleslang": null, "subtitlesformat": "srt", "test": true, diff --git a/test/swftests/.gitignore b/test/swftests/.gitignore new file mode 100644 index 000000000..da97ff7ca --- /dev/null +++ b/test/swftests/.gitignore @@ -0,0 +1 @@ +*.swf diff --git a/test/swftests/ArrayAccess.as b/test/swftests/ArrayAccess.as new file mode 100644 index 000000000..e22caa386 --- /dev/null +++ b/test/swftests/ArrayAccess.as @@ -0,0 +1,19 @@ +// input: [["a", "b", "c", "d"]] +// output: ["c", "b", "a", "d"] + +package { +public class ArrayAccess { + public static function main(ar:Array):Array { + var aa:ArrayAccess = new ArrayAccess(); + return aa.f(ar, 2); + } + + private function f(ar:Array, num:Number):Array{ + var x:String = ar[0]; + var y:String = ar[num % ar.length]; + ar[0] = y; + ar[num] = x; + return ar; + } +} +} diff --git a/test/swftests/ClassCall.as b/test/swftests/ClassCall.as new file mode 100644 index 000000000..aef58daf3 --- /dev/null +++ b/test/swftests/ClassCall.as @@ -0,0 +1,17 @@ +// input: [] +// output: 121 + +package { +public class ClassCall { + public static function main():int{ + var f:OtherClass = new OtherClass(); + return f.func(100,20); + } +} +} + +class OtherClass { + public function func(x: int, y: int):int { + return x+y+1; + } +} diff --git a/test/swftests/ClassConstruction.as b/test/swftests/ClassConstruction.as new file mode 100644 index 000000000..436479f8f --- /dev/null +++ b/test/swftests/ClassConstruction.as @@ -0,0 +1,15 @@ +// input: [] +// output: 0 + +package { +public class ClassConstruction { + public static function main():int{ + var f:Foo = new Foo(); + return 0; + } +} +} + +class Foo { + +} diff --git a/test/swftests/LocalVars.as b/test/swftests/LocalVars.as new file mode 100644 index 000000000..b2911a9f3 --- /dev/null +++ b/test/swftests/LocalVars.as @@ -0,0 +1,13 @@ +// input: [1, 2] +// output: 3 + +package { +public class LocalVars { + public static function main(a:int, b:int):int{ + var c:int = a + b + b; + var d:int = c - b; + var e:int = d; + return e; + } +} +} diff --git a/test/swftests/PrivateCall.as b/test/swftests/PrivateCall.as new file mode 100644 index 000000000..f1c110a37 --- /dev/null +++ b/test/swftests/PrivateCall.as @@ -0,0 +1,21 @@ +// input: [] +// output: 9 + +package { +public class PrivateCall { + public static function main():int{ + var f:OtherClass = new OtherClass(); + return f.func(); + } +} +} + +class OtherClass { + private function pf():int { + return 9; + } + + public function func():int { + return this.pf(); + } +} diff --git a/test/swftests/StaticAssignment.as b/test/swftests/StaticAssignment.as new file mode 100644 index 000000000..b061c219d --- /dev/null +++ b/test/swftests/StaticAssignment.as @@ -0,0 +1,13 @@ +// input: [1] +// output: 1 + +package { +public class StaticAssignment { + public static var v:int; + + public static function main(a:int):int{ + v = a; + return v; + } +} +} diff --git a/test/swftests/StaticRetrieval.as b/test/swftests/StaticRetrieval.as new file mode 100644 index 000000000..c8352d819 --- /dev/null +++ b/test/swftests/StaticRetrieval.as @@ -0,0 +1,16 @@ +// input: [] +// output: 1 + +package { +public class StaticRetrieval { + public static var v:int; + + public static function main():int{ + if (v) { + return 0; + } else { + return 1; + } + } +} +} diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index e794cc97f..ab61e1976 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -221,7 +221,7 @@ class TestFormatSelection(unittest.TestCase): '138', '137', '248', '136', '247', '135', '246', '245', '244', '134', '243', '133', '242', '160', # Dash audio - '141', '172', '140', '139', '171', + '141', '172', '140', '171', '139', ] for f1id, f2id in zip(order, order[1:]): diff --git a/test/test_all_urls.py b/test/test_all_urls.py index 2bc81f020..84b05da39 100644 --- a/test/test_all_urls.py +++ b/test/test_all_urls.py @@ -15,7 +15,6 @@ from youtube_dl.extractor import ( FacebookIE, gen_extractors, JustinTVIE, - PBSIE, YoutubeIE, ) @@ -100,6 +99,7 @@ class TestAllURLsMatching(unittest.TestCase): def test_facebook_matching(self): self.assertTrue(FacebookIE.suitable('https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268')) + self.assertTrue(FacebookIE.suitable('https://www.facebook.com/cindyweather?fref=ts#!/photo.php?v=10152183998945793')) def test_no_duplicates(self): ies = gen_extractors() @@ -109,7 +109,9 @@ class TestAllURLsMatching(unittest.TestCase): if type(ie).__name__ in ('GenericIE', tc['name'] + 'IE'): self.assertTrue(ie.suitable(url), '%s should match URL %r' % (type(ie).__name__, url)) else: - self.assertFalse(ie.suitable(url), '%s should not match URL %r' % (type(ie).__name__, url)) + self.assertFalse( + ie.suitable(url), + '%s should not match URL %r . That URL belongs to %s.' % (type(ie).__name__, url, tc['name'])) def test_keywords(self): self.assertMatch(':ytsubs', ['youtube:subscriptions']) @@ -141,32 +143,6 @@ class TestAllURLsMatching(unittest.TestCase): self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['PBS']) self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['PBS']) - def test_ComedyCentralShows(self): - self.assertMatch( - 'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview', - ['ComedyCentralShows']) - self.assertMatch( - 'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news', - ['ComedyCentralShows']) - self.assertMatch( - 'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114', - ['ComedyCentralShows']) - self.assertMatch( - 'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3', - ['ComedyCentralShows']) - self.assertMatch( - 'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary', - ['ComedyCentralShows']) - self.assertMatch( - 'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall', - ['ComedyCentralShows']) - self.assertMatch( - 'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights', - ['ComedyCentralShows']) - self.assertMatch( - 'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food', - ['ComedyCentralShows']) - def test_yahoo_https(self): # https://github.com/rg3/youtube-dl/issues/2701 self.assertMatch( diff --git a/test/test_cache.py b/test/test_cache.py new file mode 100644 index 000000000..a16160142 --- /dev/null +++ b/test/test_cache.py @@ -0,0 +1,59 @@ +#!/usr/bin/env python +# coding: utf-8 + +from __future__ import unicode_literals + +import shutil + +# Allow direct execution +import os +import sys +import unittest +sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + + +from test.helper import FakeYDL +from youtube_dl.cache import Cache + + +def _is_empty(d): + return not bool(os.listdir(d)) + + +def _mkdir(d): + if not os.path.exists(d): + os.mkdir(d) + + +class TestCache(unittest.TestCase): + def setUp(self): + TEST_DIR = os.path.dirname(os.path.abspath(__file__)) + TESTDATA_DIR = os.path.join(TEST_DIR, 'testdata') + _mkdir(TESTDATA_DIR) + self.test_dir = os.path.join(TESTDATA_DIR, 'cache_test') + self.tearDown() + + def tearDown(self): + if os.path.exists(self.test_dir): + shutil.rmtree(self.test_dir) + + def test_cache(self): + ydl = FakeYDL({ + 'cachedir': self.test_dir, + }) + c = Cache(ydl) + obj = {'x': 1, 'y': ['ä', '\\a', True]} + self.assertEqual(c.load('test_cache', 'k.'), None) + c.store('test_cache', 'k.', obj) + self.assertEqual(c.load('test_cache', 'k2'), None) + self.assertFalse(_is_empty(self.test_dir)) + self.assertEqual(c.load('test_cache', 'k.'), obj) + self.assertEqual(c.load('test_cache', 'y'), None) + self.assertEqual(c.load('test_cache2', 'k.'), None) + c.remove() + self.assertFalse(os.path.exists(self.test_dir)) + self.assertEqual(c.load('test_cache', 'k.'), None) + + +if __name__ == '__main__': + unittest.main() diff --git a/test/test_download.py b/test/test_download.py index f171c10ba..2b8ac6975 100644 --- a/test/test_download.py +++ b/test/test_download.py @@ -7,10 +7,10 @@ import unittest sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) from test.helper import ( + assertGreaterEqual, get_params, gettestcases, expect_info_dict, - md5, try_rm, report_warning, ) @@ -24,11 +24,11 @@ import socket import youtube_dl.YoutubeDL from youtube_dl.utils import ( compat_http_client, - compat_str, compat_urllib_error, compat_HTTPError, DownloadError, ExtractorError, + format_bytes, UnavailableVideoError, ) from youtube_dl.extractor import get_info_extractor @@ -65,15 +65,21 @@ def generator(test_case): def test_template(self): ie = youtube_dl.extractor.get_info_extractor(test_case['name']) other_ies = [get_info_extractor(ie_key) for ie_key in test_case.get('add_ie', [])] + is_playlist = any(k.startswith('playlist') for k in test_case) + test_cases = test_case.get( + 'playlist', [] if is_playlist else [test_case]) + def print_skipping(reason): print('Skipping %s: %s' % (test_case['name'], reason)) if not ie.working(): print_skipping('IE marked as not _WORKING') return - if 'playlist' not in test_case: - info_dict = test_case.get('info_dict', {}) - if not test_case.get('file') and not (info_dict.get('id') and info_dict.get('ext')): + + for tc in test_cases: + info_dict = tc.get('info_dict', {}) + if not tc.get('file') and not (info_dict.get('id') and info_dict.get('ext')): raise Exception('Test definition incorrect. The output file cannot be known. Are both \'id\' and \'ext\' keys present?') + if 'skip' in test_case: print_skipping(test_case['skip']) return @@ -83,6 +89,9 @@ def generator(test_case): return params = get_params(test_case.get('params', {})) + if is_playlist and 'playlist' not in test_case: + params.setdefault('extract_flat', True) + params.setdefault('skip_download', True) ydl = YoutubeDL(params) ydl.add_default_info_extractors() @@ -95,9 +104,11 @@ def generator(test_case): def get_tc_filename(tc): return tc.get('file') or ydl.prepare_filename(tc.get('info_dict', {})) - test_cases = test_case.get('playlist', [test_case]) - def try_rm_tcs_files(): - for tc in test_cases: + res_dict = None + def try_rm_tcs_files(tcs=None): + if tcs is None: + tcs = test_cases + for tc in tcs: tc_filename = get_tc_filename(tc) try_rm(tc_filename) try_rm(tc_filename + '.part') @@ -107,7 +118,10 @@ def generator(test_case): try_num = 1 while True: try: - ydl.download([test_case['url']]) + # We're not using .download here sine that is just a shim + # for outside error handling, and returns the exit code + # instead of the result dict. + res_dict = ydl.extract_info(test_case['url']) except (DownloadError, ExtractorError) as err: # Check if the exception is not a network related one if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError, compat_http_client.BadStatusLine) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503): @@ -123,22 +137,62 @@ def generator(test_case): else: break + if is_playlist: + self.assertEqual(res_dict['_type'], 'playlist') + expect_info_dict(self, test_case.get('info_dict', {}), res_dict) + if 'playlist_mincount' in test_case: + assertGreaterEqual( + self, + len(res_dict['entries']), + test_case['playlist_mincount'], + 'Expected at least %d in playlist %s, but got only %d' % ( + test_case['playlist_mincount'], test_case['url'], + len(res_dict['entries']))) + if 'playlist_count' in test_case: + self.assertEqual( + len(res_dict['entries']), + test_case['playlist_count'], + 'Expected %d entries in playlist %s, but got %d.' % ( + test_case['playlist_count'], + test_case['url'], + len(res_dict['entries']), + )) + if 'playlist_duration_sum' in test_case: + got_duration = sum(e['duration'] for e in res_dict['entries']) + self.assertEqual( + test_case['playlist_duration_sum'], got_duration) + for tc in test_cases: tc_filename = get_tc_filename(tc) if not test_case.get('params', {}).get('skip_download', False): self.assertTrue(os.path.exists(tc_filename), msg='Missing file ' + tc_filename) self.assertTrue(tc_filename in finished_hook_called) + expected_minsize = tc.get('file_minsize', 10000) + if expected_minsize is not None: + if params.get('test'): + expected_minsize = max(expected_minsize, 10000) + got_fsize = os.path.getsize(tc_filename) + assertGreaterEqual( + self, got_fsize, expected_minsize, + 'Expected %s to be at least %s, but it\'s only %s ' % + (tc_filename, format_bytes(expected_minsize), + format_bytes(got_fsize))) + if 'md5' in tc: + md5_for_file = _file_md5(tc_filename) + self.assertEqual(md5_for_file, tc['md5']) info_json_fn = os.path.splitext(tc_filename)[0] + '.info.json' self.assertTrue(os.path.exists(info_json_fn)) - if 'md5' in tc: - md5_for_file = _file_md5(tc_filename) - self.assertEqual(md5_for_file, tc['md5']) with io.open(info_json_fn, encoding='utf-8') as infof: info_dict = json.load(infof) expect_info_dict(self, tc.get('info_dict', {}), info_dict) finally: try_rm_tcs_files() + if is_playlist and res_dict is not None: + # Remove all other files that may have been extracted if the + # extractor returns full results even with extract_flat + res_tcs = [{'info_dict': e} for e in res_dict['entries']] + try_rm_tcs_files(res_tcs) return test_template diff --git a/test/test_playlists.py b/test/test_playlists.py deleted file mode 100644 index 1a38a667b..000000000 --- a/test/test_playlists.py +++ /dev/null @@ -1,399 +0,0 @@ -#!/usr/bin/env python -# encoding: utf-8 - -from __future__ import unicode_literals - -# Allow direct execution -import os -import sys -import unittest -sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) - -from test.helper import ( - assertRegexpMatches, - expect_info_dict, - FakeYDL, -) - -from youtube_dl.extractor import ( - AcademicEarthCourseIE, - DailymotionPlaylistIE, - DailymotionUserIE, - VimeoChannelIE, - VimeoUserIE, - VimeoAlbumIE, - VimeoGroupsIE, - VineUserIE, - UstreamChannelIE, - SoundcloudSetIE, - SoundcloudUserIE, - SoundcloudPlaylistIE, - TeacherTubeUserIE, - LivestreamIE, - LivestreamOriginalIE, - NHLVideocenterIE, - BambuserChannelIE, - BandcampAlbumIE, - SmotriCommunityIE, - SmotriUserIE, - IviCompilationIE, - ImdbListIE, - KhanAcademyIE, - EveryonesMixtapeIE, - RutubeChannelIE, - RutubePersonIE, - GoogleSearchIE, - GenericIE, - TEDIE, - ToypicsUserIE, - XTubeUserIE, - InstagramUserIE, - CSpanIE, - AolIE, -) - - -class TestPlaylists(unittest.TestCase): - def assertIsPlaylist(self, info): - """Make sure the info has '_type' set to 'playlist'""" - self.assertEqual(info['_type'], 'playlist') - - def test_dailymotion_playlist(self): - dl = FakeYDL() - ie = DailymotionPlaylistIE(dl) - result = ie.extract('http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q') - self.assertIsPlaylist(result) - self.assertEqual(result['title'], 'SPORT') - self.assertTrue(len(result['entries']) > 20) - - def test_dailymotion_user(self): - dl = FakeYDL() - ie = DailymotionUserIE(dl) - result = ie.extract('https://www.dailymotion.com/user/nqtv') - self.assertIsPlaylist(result) - self.assertEqual(result['title'], 'Rémi Gaillard') - self.assertTrue(len(result['entries']) >= 100) - - def test_vimeo_channel(self): - dl = FakeYDL() - ie = VimeoChannelIE(dl) - result = ie.extract('http://vimeo.com/channels/tributes') - self.assertIsPlaylist(result) - self.assertEqual(result['title'], 'Vimeo Tributes') - self.assertTrue(len(result['entries']) > 24) - - def test_vimeo_user(self): - dl = FakeYDL() - ie = VimeoUserIE(dl) - result = ie.extract('http://vimeo.com/nkistudio/videos') - self.assertIsPlaylist(result) - self.assertEqual(result['title'], 'Nki') - self.assertTrue(len(result['entries']) > 65) - - def test_vimeo_album(self): - dl = FakeYDL() - ie = VimeoAlbumIE(dl) - result = ie.extract('http://vimeo.com/album/2632481') - self.assertIsPlaylist(result) - self.assertEqual(result['title'], 'Staff Favorites: November 2013') - self.assertTrue(len(result['entries']) > 12) - - def test_vimeo_groups(self): - dl = FakeYDL() - ie = VimeoGroupsIE(dl) - result = ie.extract('http://vimeo.com/groups/rolexawards') - self.assertIsPlaylist(result) - self.assertEqual(result['title'], 'Rolex Awards for Enterprise') - self.assertTrue(len(result['entries']) > 72) - - def test_vine_user(self): - dl = FakeYDL() - ie = VineUserIE(dl) - result = ie.extract('https://vine.co/Visa') - self.assertIsPlaylist(result) - self.assertTrue(len(result['entries']) >= 47) - - def test_ustream_channel(self): - dl = FakeYDL() - ie = UstreamChannelIE(dl) - result = ie.extract('http://www.ustream.tv/channel/channeljapan') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], '10874166') - self.assertTrue(len(result['entries']) >= 54) - - def test_soundcloud_set(self): - dl = FakeYDL() - ie = SoundcloudSetIE(dl) - result = ie.extract('https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep') - self.assertIsPlaylist(result) - self.assertEqual(result['title'], 'The Royal Concept EP') - self.assertTrue(len(result['entries']) >= 6) - - def test_soundcloud_user(self): - dl = FakeYDL() - ie = SoundcloudUserIE(dl) - result = ie.extract('https://soundcloud.com/the-concept-band') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], '9615865') - self.assertTrue(len(result['entries']) >= 12) - - def test_soundcloud_likes(self): - dl = FakeYDL() - ie = SoundcloudUserIE(dl) - result = ie.extract('https://soundcloud.com/the-concept-band/likes') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], '9615865') - self.assertTrue(len(result['entries']) >= 1) - - def test_soundcloud_playlist(self): - dl = FakeYDL() - ie = SoundcloudPlaylistIE(dl) - result = ie.extract('http://api.soundcloud.com/playlists/4110309') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], '4110309') - self.assertEqual(result['title'], 'TILT Brass - Bowery Poetry Club, August \'03 [Non-Site SCR 02]') - assertRegexpMatches( - self, result['description'], r'TILT Brass - Bowery Poetry Club') - self.assertEqual(len(result['entries']), 6) - - def test_livestream_event(self): - dl = FakeYDL() - ie = LivestreamIE(dl) - result = ie.extract('http://new.livestream.com/tedx/cityenglish') - self.assertIsPlaylist(result) - self.assertEqual(result['title'], 'TEDCity2.0 (English)') - self.assertTrue(len(result['entries']) >= 4) - - def test_livestreamoriginal_folder(self): - dl = FakeYDL() - ie = LivestreamOriginalIE(dl) - result = ie.extract('https://www.livestream.com/newplay/folder?dirId=a07bf706-d0e4-4e75-a747-b021d84f2fd3') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], 'a07bf706-d0e4-4e75-a747-b021d84f2fd3') - self.assertTrue(len(result['entries']) >= 28) - - def test_nhl_videocenter(self): - dl = FakeYDL() - ie = NHLVideocenterIE(dl) - result = ie.extract('http://video.canucks.nhl.com/videocenter/console?catid=999') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], '999') - self.assertEqual(result['title'], 'Highlights') - self.assertEqual(len(result['entries']), 12) - - def test_bambuser_channel(self): - dl = FakeYDL() - ie = BambuserChannelIE(dl) - result = ie.extract('http://bambuser.com/channel/pixelversity') - self.assertIsPlaylist(result) - self.assertEqual(result['title'], 'pixelversity') - self.assertTrue(len(result['entries']) >= 60) - - def test_bandcamp_album(self): - dl = FakeYDL() - ie = BandcampAlbumIE(dl) - result = ie.extract('http://mpallante.bandcamp.com/album/nightmare-night-ep') - self.assertIsPlaylist(result) - self.assertEqual(result['title'], 'Nightmare Night EP') - self.assertTrue(len(result['entries']) >= 4) - - def test_smotri_community(self): - dl = FakeYDL() - ie = SmotriCommunityIE(dl) - result = ie.extract('http://smotri.com/community/video/kommuna') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], 'kommuna') - self.assertEqual(result['title'], 'КПРФ') - self.assertTrue(len(result['entries']) >= 4) - - def test_smotri_user(self): - dl = FakeYDL() - ie = SmotriUserIE(dl) - result = ie.extract('http://smotri.com/user/inspector') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], 'inspector') - self.assertEqual(result['title'], 'Inspector') - self.assertTrue(len(result['entries']) >= 9) - - def test_AcademicEarthCourse(self): - dl = FakeYDL() - ie = AcademicEarthCourseIE(dl) - result = ie.extract('http://academicearth.org/playlists/laws-of-nature/') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], 'laws-of-nature') - self.assertEqual(result['title'], 'Laws of Nature') - self.assertEqual(result['description'],u'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.')# u"Today's websites are increasingly dynamic. Pages are no longer static HTML files but instead generated by scripts and database calls. User interfaces are more seamless, with technologies like Ajax replacing traditional page reloads. This course teaches students how to build dynamic websites with Ajax and with Linux, Apache, MySQL, and PHP (LAMP), one of today's most popular frameworks. Students learn how to set up domain names with DNS, how to structure pages with XHTML and CSS, how to program in JavaScript and PHP, how to configure Apache and MySQL, how to design and query databases with SQL, how to use Ajax with both XML and JSON, and how to build mashups. The course explores issues of security, scalability, and cross-browser support and also discusses enterprise-level deployments of websites, including third-party hosting, virtualization, colocation in data centers, firewalling, and load-balancing.") - self.assertEqual(len(result['entries']), 4) - - def test_ivi_compilation(self): - dl = FakeYDL() - ie = IviCompilationIE(dl) - result = ie.extract('http://www.ivi.ru/watch/dvoe_iz_lartsa') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], 'dvoe_iz_lartsa') - self.assertEqual(result['title'], 'Двое из ларца (2006 - 2008)') - self.assertTrue(len(result['entries']) >= 24) - - def test_ivi_compilation_season(self): - dl = FakeYDL() - ie = IviCompilationIE(dl) - result = ie.extract('http://www.ivi.ru/watch/dvoe_iz_lartsa/season1') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], 'dvoe_iz_lartsa/season1') - self.assertEqual(result['title'], 'Двое из ларца (2006 - 2008) 1 сезон') - self.assertTrue(len(result['entries']) >= 12) - - def test_imdb_list(self): - dl = FakeYDL() - ie = ImdbListIE(dl) - result = ie.extract('http://www.imdb.com/list/JFs9NWw6XI0') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], 'JFs9NWw6XI0') - self.assertEqual(result['title'], 'March 23, 2012 Releases') - self.assertEqual(len(result['entries']), 7) - - def test_khanacademy_topic(self): - dl = FakeYDL() - ie = KhanAcademyIE(dl) - result = ie.extract('https://www.khanacademy.org/math/applied-math/cryptography') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], 'cryptography') - self.assertEqual(result['title'], 'Journey into cryptography') - self.assertEqual(result['description'], 'How have humans protected their secret messages through history? What has changed today?') - self.assertTrue(len(result['entries']) >= 3) - - def test_EveryonesMixtape(self): - dl = FakeYDL() - ie = EveryonesMixtapeIE(dl) - result = ie.extract('http://everyonesmixtape.com/#/mix/m7m0jJAbMQi') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], 'm7m0jJAbMQi') - self.assertEqual(result['title'], 'Driving') - self.assertEqual(len(result['entries']), 24) - - def test_rutube_channel(self): - dl = FakeYDL() - ie = RutubeChannelIE(dl) - result = ie.extract('http://rutube.ru/tags/video/1800/') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], '1800') - self.assertTrue(len(result['entries']) >= 68) - - def test_rutube_person(self): - dl = FakeYDL() - ie = RutubePersonIE(dl) - result = ie.extract('http://rutube.ru/video/person/313878/') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], '313878') - self.assertTrue(len(result['entries']) >= 37) - - def test_multiple_brightcove_videos(self): - # https://github.com/rg3/youtube-dl/issues/2283 - dl = FakeYDL() - ie = GenericIE(dl) - result = ie.extract('http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], 'always-never-nuclear-command-and-control') - self.assertEqual(result['title'], 'Always/Never: A Little-Seen Movie About Nuclear Command and Control : The New Yorker') - self.assertEqual(len(result['entries']), 3) - - def test_GoogleSearch(self): - dl = FakeYDL() - ie = GoogleSearchIE(dl) - result = ie.extract('gvsearch15:python language') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], 'python language') - self.assertEqual(result['title'], 'python language') - self.assertEqual(len(result['entries']), 15) - - def test_generic_rss_feed(self): - dl = FakeYDL() - ie = GenericIE(dl) - result = ie.extract('http://phihag.de/2014/youtube-dl/rss.xml') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], 'http://phihag.de/2014/youtube-dl/rss.xml') - self.assertEqual(result['title'], 'Zero Punctuation') - self.assertTrue(len(result['entries']) > 10) - - def test_ted_playlist(self): - dl = FakeYDL() - ie = TEDIE(dl) - result = ie.extract('http://www.ted.com/playlists/who_are_the_hackers') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], '10') - self.assertEqual(result['title'], 'Who are the hackers?') - self.assertTrue(len(result['entries']) >= 6) - - def test_toypics_user(self): - dl = FakeYDL() - ie = ToypicsUserIE(dl) - result = ie.extract('http://videos.toypics.net/Mikey') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], 'Mikey') - self.assertTrue(len(result['entries']) >= 17) - - def test_xtube_user(self): - dl = FakeYDL() - ie = XTubeUserIE(dl) - result = ie.extract('http://www.xtube.com/community/profile.php?user=greenshowers') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], 'greenshowers') - self.assertTrue(len(result['entries']) >= 155) - - def test_InstagramUser(self): - dl = FakeYDL() - ie = InstagramUserIE(dl) - result = ie.extract('http://instagram.com/porsche') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], 'porsche') - self.assertTrue(len(result['entries']) >= 2) - test_video = next( - e for e in result['entries'] - if e['id'] == '614605558512799803_462752227') - dl.add_default_extra_info(test_video, ie, '(irrelevant URL)') - dl.process_video_result(test_video, download=False) - EXPECTED = { - 'id': '614605558512799803_462752227', - 'ext': 'mp4', - 'title': '#Porsche Intelligent Performance.', - 'thumbnail': 're:^https?://.*\.jpg', - 'uploader': 'Porsche', - 'uploader_id': 'porsche', - 'timestamp': 1387486713, - 'upload_date': '20131219', - } - expect_info_dict(self, EXPECTED, test_video) - - def test_CSpan_playlist(self): - dl = FakeYDL() - ie = CSpanIE(dl) - result = ie.extract( - 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], '342759') - self.assertEqual( - result['title'], 'General Motors Ignition Switch Recall') - whole_duration = sum(e['duration'] for e in result['entries']) - self.assertEqual(whole_duration, 14855) - - def test_aol_playlist(self): - dl = FakeYDL() - ie = AolIE(dl) - result = ie.extract( - 'http://on.aol.com/playlist/brace-yourself---todays-weirdest-news-152147?icid=OnHomepageC4_Omg_Img#_videoid=518184316') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], '152147') - self.assertEqual( - result['title'], 'Brace Yourself - Today\'s Weirdest News') - self.assertTrue(len(result['entries']) >= 10) - - def test_TeacherTubeUser(self): - dl = FakeYDL() - ie = TeacherTubeUserIE(dl) - result = ie.extract('http://www.teachertube.com/user/profile/rbhagwati2') - self.assertIsPlaylist(result) - self.assertEqual(result['id'], 'rbhagwati2') - self.assertTrue(len(result['entries']) >= 179) - -if __name__ == '__main__': - unittest.main() diff --git a/test/test_swfinterp.py b/test/test_swfinterp.py new file mode 100644 index 000000000..b42cd74c7 --- /dev/null +++ b/test/test_swfinterp.py @@ -0,0 +1,77 @@ +#!/usr/bin/env python + +# Allow direct execution +import os +import sys +import unittest +sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + + +import errno +import io +import json +import re +import subprocess + +from youtube_dl.swfinterp import SWFInterpreter + + +TEST_DIR = os.path.join( + os.path.dirname(os.path.abspath(__file__)), 'swftests') + + +class TestSWFInterpreter(unittest.TestCase): + pass + + +def _make_testfunc(testfile): + m = re.match(r'^(.*)\.(as)$', testfile) + if not m: + return + test_id = m.group(1) + + def test_func(self): + as_file = os.path.join(TEST_DIR, testfile) + swf_file = os.path.join(TEST_DIR, test_id + '.swf') + if ((not os.path.exists(swf_file)) + or os.path.getmtime(swf_file) < os.path.getmtime(as_file)): + # Recompile + try: + subprocess.check_call(['mxmlc', '-output', swf_file, as_file]) + except OSError as ose: + if ose.errno == errno.ENOENT: + print('mxmlc not found! Skipping test.') + return + raise + + with open(swf_file, 'rb') as swf_f: + swf_content = swf_f.read() + swfi = SWFInterpreter(swf_content) + + with io.open(as_file, 'r', encoding='utf-8') as as_f: + as_content = as_f.read() + + def _find_spec(key): + m = re.search( + r'(?m)^//\s*%s:\s*(.*?)\n' % re.escape(key), as_content) + if not m: + raise ValueError('Cannot find %s in %s' % (key, testfile)) + return json.loads(m.group(1)) + + input_args = _find_spec('input') + output = _find_spec('output') + + swf_class = swfi.extract_class(test_id) + func = swfi.extract_function(swf_class, 'main') + res = func(input_args) + self.assertEqual(res, output) + + test_func.__name__ = str('test_swf_' + test_id) + setattr(TestSWFInterpreter, test_func.__name__, test_func) + + +for testfile in os.listdir(TEST_DIR): + _make_testfunc(testfile) + +if __name__ == '__main__': + unittest.main() diff --git a/test/test_utils.py b/test/test_utils.py index 51eb0b6b9..8d8997977 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -1,6 +1,8 @@ #!/usr/bin/env python # coding: utf-8 +from __future__ import unicode_literals + # Allow direct execution import os import sys @@ -13,7 +15,6 @@ import io import json import xml.etree.ElementTree -#from youtube_dl.utils import htmlentity_transform from youtube_dl.utils import ( DateRange, encodeFilename, @@ -41,11 +42,6 @@ from youtube_dl.utils import ( uppercase_escape, ) -if sys.version_info < (3, 0): - _compat_str = lambda b: b.decode('unicode-escape') -else: - _compat_str = lambda s: s - class TestUtil(unittest.TestCase): def test_timeconvert(self): @@ -67,9 +63,9 @@ class TestUtil(unittest.TestCase): self.assertEqual('this - that', sanitize_filename('this: that')) self.assertEqual(sanitize_filename('AT&T'), 'AT&T') - aumlaut = _compat_str('\xe4') + aumlaut = 'ä' self.assertEqual(sanitize_filename(aumlaut), aumlaut) - tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430') + tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430' self.assertEqual(sanitize_filename(tests), tests) forbidden = '"\0\\/' @@ -91,9 +87,9 @@ class TestUtil(unittest.TestCase): self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True)) self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True)) - tests = _compat_str('a\xe4b\u4e2d\u56fd\u7684c') + tests = 'a\xe4b\u4e2d\u56fd\u7684c' self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c') - self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '') # No empty filename + self.assertTrue(sanitize_filename('\xf6', restricted=True) != '') # No empty filename forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#' for fc in forbidden: @@ -101,8 +97,8 @@ class TestUtil(unittest.TestCase): self.assertTrue(fbc not in sanitize_filename(fc, restricted=True)) # Handle a common case more neatly - self.assertEqual(sanitize_filename(_compat_str('\u5927\u58f0\u5e26 - Song'), restricted=True), 'Song') - self.assertEqual(sanitize_filename(_compat_str('\u603b\u7edf: Speech'), restricted=True), 'Speech') + self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song') + self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech') # .. but make sure the file name is never empty self.assertTrue(sanitize_filename('-', restricted=True) != '') self.assertTrue(sanitize_filename(':', restricted=True) != '') @@ -120,7 +116,9 @@ class TestUtil(unittest.TestCase): self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1]) def test_unescape_html(self): - self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;')) + self.assertEqual(unescapeHTML('%20;'), '%20;') + self.assertEqual( + unescapeHTML('é'), 'é') def test_daterange(self): _20century = DateRange("19000101","20000101") @@ -138,7 +136,7 @@ class TestUtil(unittest.TestCase): self.assertEqual(unified_strdate('1968-12-10'), '19681210') def test_find_xpath_attr(self): - testxml = u'''<root> + testxml = '''<root> <node/> <node x="a"/> <node x="a" y="c" /> @@ -151,18 +149,18 @@ class TestUtil(unittest.TestCase): self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2]) def test_meta_parser(self): - testhtml = u''' + testhtml = ''' <head> <meta name="description" content="foo & bar"> <meta content='Plato' name='author'/> </head> ''' get_meta = lambda name: get_meta_content(name, testhtml) - self.assertEqual(get_meta('description'), u'foo & bar') + self.assertEqual(get_meta('description'), 'foo & bar') self.assertEqual(get_meta('author'), 'Plato') def test_xpath_with_ns(self): - testxml = u'''<root xmlns:media="http://example.com/"> + testxml = '''<root xmlns:media="http://example.com/"> <media:song> <media:author>The Author</media:author> <url>http://server.com/download.mp3</url> @@ -171,8 +169,8 @@ class TestUtil(unittest.TestCase): doc = xml.etree.ElementTree.fromstring(testxml) find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'})) self.assertTrue(find('media:song') is not None) - self.assertEqual(find('media:song/media:author').text, u'The Author') - self.assertEqual(find('media:song/url').text, u'http://server.com/download.mp3') + self.assertEqual(find('media:song/media:author').text, 'The Author') + self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3') def test_smuggle_url(self): data = {u"ö": u"ö", u"abc": [3]} @@ -187,22 +185,22 @@ class TestUtil(unittest.TestCase): self.assertEqual(res_data, None) def test_shell_quote(self): - args = ['ffmpeg', '-i', encodeFilename(u'ñ€ß\'.mp4')] - self.assertEqual(shell_quote(args), u"""ffmpeg -i 'ñ€ß'"'"'.mp4'""") + args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')] + self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""") def test_str_to_int(self): self.assertEqual(str_to_int('123,456'), 123456) self.assertEqual(str_to_int('123.456'), 123456) def test_url_basename(self): - self.assertEqual(url_basename(u'http://foo.de/'), u'') - self.assertEqual(url_basename(u'http://foo.de/bar/baz'), u'baz') - self.assertEqual(url_basename(u'http://foo.de/bar/baz?x=y'), u'baz') - self.assertEqual(url_basename(u'http://foo.de/bar/baz#x=y'), u'baz') - self.assertEqual(url_basename(u'http://foo.de/bar/baz/'), u'baz') + self.assertEqual(url_basename('http://foo.de/'), '') + self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz') + self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz') + self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz') + self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz') self.assertEqual( - url_basename(u'http://media.w3.org/2010/05/sintel/trailer.mp4'), - u'trailer.mp4') + url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'), + 'trailer.mp4') def test_parse_duration(self): self.assertEqual(parse_duration(None), None) @@ -213,12 +211,16 @@ class TestUtil(unittest.TestCase): self.assertEqual(parse_duration('00:01:01'), 61) self.assertEqual(parse_duration('x:y'), None) self.assertEqual(parse_duration('3h11m53s'), 11513) + self.assertEqual(parse_duration('3h 11m 53s'), 11513) + self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513) + self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513) self.assertEqual(parse_duration('62m45s'), 3765) self.assertEqual(parse_duration('6m59s'), 419) self.assertEqual(parse_duration('49s'), 49) self.assertEqual(parse_duration('0h0m0s'), 0) self.assertEqual(parse_duration('0m0s'), 0) self.assertEqual(parse_duration('0s'), 0) + self.assertEqual(parse_duration('01:02:03.05'), 3723.05) def test_fix_xml_ampersands(self): self.assertEqual( @@ -255,16 +257,16 @@ class TestUtil(unittest.TestCase): testPL(5, 2, (20, 99), []) def test_struct_unpack(self): - self.assertEqual(struct_unpack(u'!B', b'\x00'), (0,)) + self.assertEqual(struct_unpack('!B', b'\x00'), (0,)) def test_read_batch_urls(self): - f = io.StringIO(u'''\xef\xbb\xbf foo + f = io.StringIO('''\xef\xbb\xbf foo bar\r baz # More after this line\r ; or after this bam''') - self.assertEqual(read_batch_urls(f), [u'foo', u'bar', u'baz', u'bam']) + self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam']) def test_urlencode_postdata(self): data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'}) @@ -280,9 +282,9 @@ class TestUtil(unittest.TestCase): d = json.loads(stripped) self.assertEqual(d, [{"id": "532cb", "x": 3}]) - def test_uppercase_escpae(self): - self.assertEqual(uppercase_escape(u'aä'), u'aä') - self.assertEqual(uppercase_escape(u'\\U0001d550'), u'𝕐') + def test_uppercase_escape(self): + self.assertEqual(uppercase_escape('aä'), 'aä') + self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐') if __name__ == '__main__': unittest.main() diff --git a/test/test_youtube_signature.py b/test/test_youtube_signature.py index d95533959..604e76ab6 100644 --- a/test/test_youtube_signature.py +++ b/test/test_youtube_signature.py @@ -1,5 +1,7 @@ #!/usr/bin/env python +from __future__ import unicode_literals + # Allow direct execution import os import sys @@ -16,35 +18,65 @@ from youtube_dl.utils import compat_str, compat_urlretrieve _TESTS = [ ( - u'https://s.ytimg.com/yts/jsbin/html5player-vflHOr_nV.js', - u'js', + 'https://s.ytimg.com/yts/jsbin/html5player-vflHOr_nV.js', + 'js', 86, - u'>=<;:/.-[+*)(\'&%$#"!ZYX0VUTSRQPONMLKJIHGFEDCBA\\yxwvutsrqponmlkjihgfedcba987654321', + '>=<;:/.-[+*)(\'&%$#"!ZYX0VUTSRQPONMLKJIHGFEDCBA\\yxwvutsrqponmlkjihgfedcba987654321', ), ( - u'https://s.ytimg.com/yts/jsbin/html5player-vfldJ8xgI.js', - u'js', + 'https://s.ytimg.com/yts/jsbin/html5player-vfldJ8xgI.js', + 'js', 85, - u'3456789a0cdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRS[UVWXYZ!"#$%&\'()*+,-./:;<=>?@', + '3456789a0cdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRS[UVWXYZ!"#$%&\'()*+,-./:;<=>?@', ), ( - u'https://s.ytimg.com/yts/jsbin/html5player-vfle-mVwz.js', - u'js', + 'https://s.ytimg.com/yts/jsbin/html5player-vfle-mVwz.js', + 'js', 90, - u']\\[@?>=<;:/.-,+*)(\'&%$#"hZYXWVUTSRQPONMLKJIHGFEDCBAzyxwvutsrqponmlkjiagfedcb39876', + ']\\[@?>=<;:/.-,+*)(\'&%$#"hZYXWVUTSRQPONMLKJIHGFEDCBAzyxwvutsrqponmlkjiagfedcb39876', + ), + ( + 'https://s.ytimg.com/yts/jsbin/html5player-en_US-vfl0Cbn9e.js', + 'js', + 84, + 'O1I3456789abcde0ghijklmnopqrstuvwxyzABCDEFGHfJKLMN2PQRSTUVW@YZ!"#$%&\'()*+,-./:;<=', + ), + ( + 'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js', + 'js', + '2ACFC7A61CA478CD21425E5A57EBD73DDC78E22A.2094302436B2D377D14A3BBA23022D023B8BC25AA', + 'A52CB8B320D22032ABB3A41D773D2B6342034902.A22E87CDD37DBE75A5E52412DC874AC16A7CFCA2', ), ( - u'https://s.ytimg.com/yts/jsbin/html5player-en_US-vfl0Cbn9e.js', - u'js', + 'http://s.ytimg.com/yts/swfbin/player-vfl5vIhK2/watch_as3.swf', + 'swf', + 86, + 'O1I3456789abcde0ghijklmnopqrstuvwxyzABCDEFGHfJKLMN2PQRSTUVWXY\\!"#$%&\'()*+,-./:;<=>?' + ), + ( + 'http://s.ytimg.com/yts/swfbin/player-vflmDyk47/watch_as3.swf', + 'swf', + 'F375F75BF2AFDAAF2666E43868D46816F83F13E81C46.3725A8218E446A0DECD33F79DC282994D6AA92C92C9', + '9C29AA6D499282CD97F33DCED0A644E8128A5273.64C18E31F38361864D86834E6662FAADFA2FB57F' + ), + ( + 'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflBb0OQx.js', + 'js', 84, - u'O1I3456789abcde0ghijklmnopqrstuvwxyzABCDEFGHfJKLMN2PQRSTUVW@YZ!"#$%&\'()*+,-./:;<=', + '123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQ0STUVWXYZ!"#$%&\'()*+,@./:;<=>' ), ( - u'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js', - u'js', - u'2ACFC7A61CA478CD21425E5A57EBD73DDC78E22A.2094302436B2D377D14A3BBA23022D023B8BC25AA', - u'A52CB8B320D22032ABB3A41D773D2B6342034902.A22E87CDD37DBE75A5E52412DC874AC16A7CFCA2', + 'https://s.ytimg.com/yts/jsbin/html5player-en_US-vfl9FYC6l.js', + 'js', + 83, + '123456789abcdefghijklmnopqr0tuvwxyzABCDETGHIJKLMNOPQRS>UVWXYZ!"#$%&\'()*+,-./:;<=F' ), + ( + 'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflCGk6yw/html5player.js', + 'js', + '4646B5181C6C3020DF1D9C7FCFEA.AD80ABF70C39BD369CCCAE780AFBB98FA6B6CB42766249D9488C288', + '82C8849D94266724DC6B6AF89BBFA087EACCD963.B93C07FBA084ACAEFCF7C9D1FD0203C6C1815B6B' + ) ] @@ -57,12 +89,12 @@ class TestSignature(unittest.TestCase): def make_tfunc(url, stype, sig_input, expected_sig): - basename = url.rpartition('/')[2] - m = re.match(r'.*-([a-zA-Z0-9_-]+)\.[a-z]+$', basename) - assert m, '%r should follow URL format' % basename + m = re.match(r'.*-([a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.[a-z]+$', url) + assert m, '%r should follow URL format' % url test_id = m.group(1) def test_func(self): + basename = 'player-%s.%s' % (test_id, stype) fn = os.path.join(self.TESTDATA_DIR, basename) if not os.path.exists(fn): diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py deleted file mode 100644 index 5c8e676a2..000000000 --- a/youtube_dl/FileDownloader.py +++ /dev/null @@ -1,12 +0,0 @@ -# Legacy file for backwards compatibility, use youtube_dl.downloader instead! -from .downloader import FileDownloader as RealFileDownloader -from .downloader import get_suitable_downloader - - -# This class reproduces the old behaviour of FileDownloader -class FileDownloader(RealFileDownloader): - def _do_download(self, filename, info_dict): - real_fd = get_suitable_downloader(info_dict)(self.ydl, self.params) - for ph in self._progress_hooks: - real_fd.add_progress_hook(ph) - return real_fd.download(filename, info_dict) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 3dff723b8..553bf559b 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -57,6 +57,7 @@ from .utils import ( YoutubeDLHandler, prepend_extension, ) +from .cache import Cache from .extractor import get_info_extractor, gen_extractors from .downloader import get_suitable_downloader from .postprocessor import FFmpegMergerPP @@ -133,7 +134,7 @@ class YoutubeDL(object): daterange: A DateRange object, download only if the upload_date is in the range. skip_download: Skip the actual download of the video file cachedir: Location of the cache files in the filesystem. - None to disable filesystem cache. + False to disable filesystem cache. noplaylist: Download single video instead of a playlist if in doubt. age_limit: An integer representing the user's age in years. Unsuitable videos for the given age are skipped. @@ -162,6 +163,7 @@ class YoutubeDL(object): default_search: Prepend this string if an input url is not valid. 'auto' for elaborate guessing encoding: Use this encoding instead of the system-specified. + extract_flat: Do not resolve URLs, return the immediate result. The following parameters are not used by YoutubeDL itself, they are used by the FileDownloader: @@ -171,6 +173,7 @@ class YoutubeDL(object): The following options are used by the post processors: prefer_ffmpeg: If True, use ffmpeg instead of avconv if both are available, otherwise prefer avconv. + exec_cmd: Arbitrary command to run after downloading """ params = None @@ -193,6 +196,7 @@ class YoutubeDL(object): self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] self._err_file = sys.stderr self.params = params + self.cache = Cache(self) if params.get('bidi_workaround', False): try: @@ -275,7 +279,7 @@ class YoutubeDL(object): return message assert hasattr(self, '_output_process') - assert type(message) == type('') + assert isinstance(message, compat_str) line_count = message.count('\n') + 1 self._output_process.stdin.write((message + '\n').encode('utf-8')) self._output_process.stdin.flush() @@ -303,7 +307,7 @@ class YoutubeDL(object): def to_stderr(self, message): """Print message to stderr.""" - assert type(message) == type('') + assert isinstance(message, compat_str) if self.params.get('logger'): self.params['logger'].error(message) else: @@ -423,7 +427,7 @@ class YoutubeDL(object): autonumber_templ = '%0' + str(autonumber_size) + 'd' template_dict['autonumber'] = autonumber_templ % self._num_downloads if template_dict.get('playlist_index') is not None: - template_dict['playlist_index'] = '%05d' % template_dict['playlist_index'] + template_dict['playlist_index'] = '%0*d' % (len(str(template_dict['n_entries'])), template_dict['playlist_index']) if template_dict.get('resolution') is None: if template_dict.get('width') and template_dict.get('height'): template_dict['resolution'] = '%dx%d' % (template_dict['width'], template_dict['height']) @@ -479,7 +483,10 @@ class YoutubeDL(object): return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views) age_limit = self.params.get('age_limit') if age_limit is not None: - if age_limit < info_dict.get('age_limit', 0): + actual_age_limit = info_dict.get('age_limit') + if actual_age_limit is None: + actual_age_limit = 0 + if age_limit < actual_age_limit: return 'Skipping "' + title + '" because it is age restricted' if self.in_download_archive(info_dict): return '%s has already been recorded in archive' % video_title @@ -558,7 +565,12 @@ class YoutubeDL(object): Returns the resolved ie_result. """ - result_type = ie_result.get('_type', 'video') # If not given we suppose it's a video, support the default old system + result_type = ie_result.get('_type', 'video') + + if self.params.get('extract_flat', False): + if result_type in ('url', 'url_transparent'): + return ie_result + if result_type == 'video': self.add_extra_info(ie_result, extra_info) return self.process_video_result(ie_result, download=download) @@ -627,6 +639,7 @@ class YoutubeDL(object): for i, entry in enumerate(entries, 1): self.to_screen('[download] Downloading video #%s of %s' % (i, n_entries)) extra = { + 'n_entries': n_entries, 'playlist': playlist, 'playlist_index': i + playliststart, 'extractor': ie_result['extractor'], @@ -849,7 +862,7 @@ class YoutubeDL(object): # Keep for backwards compatibility info_dict['stitle'] = info_dict['title'] - if not 'format' in info_dict: + if 'format' not in info_dict: info_dict['format'] = info_dict['ext'] reason = self._match_entry(info_dict) @@ -999,7 +1012,7 @@ class YoutubeDL(object): if info_dict.get('requested_formats') is not None: downloaded = [] success = True - merger = FFmpegMergerPP(self) + merger = FFmpegMergerPP(self, not self.params.get('keepvideo')) if not merger._get_executable(): postprocessors = [] self.report_warning('You have requested multiple ' @@ -1197,6 +1210,10 @@ class YoutubeDL(object): if res: res += ', ' res += format_bytes(fdict['filesize']) + elif fdict.get('filesize_approx') is not None: + if res: + res += ', ' + res += '~' + format_bytes(fdict['filesize_approx']) return res def list_formats(self, info_dict): @@ -1230,14 +1247,18 @@ class YoutubeDL(object): if not self.params.get('verbose'): return - write_string( + if type('') is not compat_str: + # Python 2.6 on SLES11 SP1 (https://github.com/rg3/youtube-dl/issues/3326) + self.report_warning( + 'Your Python is broken! Update to a newer and supported version') + + encoding_str = ( '[debug] Encodings: locale %s, fs %s, out %s, pref %s\n' % ( locale.getpreferredencoding(), sys.getfilesystemencoding(), sys.stdout.encoding, - self.get_encoding()), - encoding=None - ) + self.get_encoding())) + write_string(encoding_str, encoding=None) self._write_string('[debug] youtube-dl version ' + __version__ + '\n') try: diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 5e16a5491..8f1a1a232 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -64,17 +64,26 @@ __authors__ = ( 'Adam Malcontenti-Wilson', 'Tobias Bell', 'Naglis Jonaitis', + 'Charles Chen', + 'Hassaan Ali', + 'Dobrosław Żybort', + 'David Fabijan', + 'Sebastian Haas', + 'Alexander Kirk', + 'Erik Johnson', + 'Keith Beckman', + 'Ole Ernst', + 'Aaron McDaniel (mcd1992)', + 'Magnus Kolstad', ) __license__ = 'Public Domain' import codecs import io -import locale import optparse import os import random -import re import shlex import sys @@ -87,7 +96,6 @@ from .utils import ( decodeOption, get_term_width, DownloadError, - get_cachedir, MaxDownloadsReached, preferredencoding, read_batch_urls, @@ -97,7 +105,7 @@ from .utils import ( write_string, ) from .update import update_self -from .FileDownloader import ( +from .downloader import ( FileDownloader, ) from .extractor import gen_extractors @@ -111,6 +119,7 @@ from .postprocessor import ( FFmpegExtractAudioPP, FFmpegEmbedSubtitlePP, XAttrMetadataPP, + ExecAfterDownloadPP, ) @@ -222,6 +231,7 @@ def parseOpts(overrideArguments=None): downloader = optparse.OptionGroup(parser, 'Download Options') postproc = optparse.OptionGroup(parser, 'Post-processing Options') filesystem = optparse.OptionGroup(parser, 'Filesystem Options') + workarounds = optparse.OptionGroup(parser, 'Workarounds') verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options') general.add_option('-h', '--help', @@ -238,14 +248,6 @@ def parseOpts(overrideArguments=None): general.add_option('--dump-user-agent', action='store_true', dest='dump_user_agent', help='display the current browser identification', default=False) - general.add_option('--user-agent', - dest='user_agent', help='specify a custom user agent', metavar='UA') - general.add_option('--referer', - dest='referer', help='specify a custom referer, use if the video access is restricted to one domain', - metavar='REF', default=None) - general.add_option('--add-header', - dest='headers', help='specify a custom HTTP header and its value, separated by a colon \':\'. You can use this option multiple times', action="append", - metavar='FIELD:VALUE') general.add_option('--list-extractors', action='store_true', dest='list_extractors', help='List all supported extractors and the URLs they would handle', default=False) @@ -255,33 +257,17 @@ def parseOpts(overrideArguments=None): general.add_option( '--proxy', dest='proxy', default=None, metavar='URL', help='Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection') - general.add_option('--no-check-certificate', action='store_true', dest='no_check_certificate', default=False, help='Suppress HTTPS certificate validation.') - general.add_option( - '--prefer-insecure', '--prefer-unsecure', action='store_true', dest='prefer_insecure', - help='Use an unencrypted connection to retrieve information about the video. (Currently supported only for YouTube)') - general.add_option( - '--cache-dir', dest='cachedir', default=get_cachedir(), metavar='DIR', - help='Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may change.') - general.add_option( - '--no-cache-dir', action='store_const', const=None, dest='cachedir', - help='Disable filesystem caching') general.add_option( '--socket-timeout', dest='socket_timeout', type=float, default=None, help=u'Time to wait before giving up, in seconds') general.add_option( - '--bidi-workaround', dest='bidi_workaround', action='store_true', - help=u'Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH') - general.add_option( '--default-search', dest='default_search', metavar='PREFIX', - help='Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple". Use the value "auto" to let youtube-dl guess. The default value "error" just throws an error.') + help='Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple". Use the value "auto" to let youtube-dl guess ("auto_warning" to emit a warning when guessing). "error" just throws an error. The default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching.') general.add_option( '--ignore-config', action='store_true', help='Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: do not read the user configuration in ~/.config/youtube-dl.conf (%APPDATA%/youtube-dl/config.txt on Windows)') - general.add_option( - '--encoding', dest='encoding', metavar='ENCODING', - help='Force the specified encoding (experimental)') selection.add_option( '--playlist-start', @@ -333,6 +319,8 @@ def parseOpts(overrideArguments=None): dest='username', metavar='USERNAME', help='account username') authentication.add_option('-p', '--password', dest='password', metavar='PASSWORD', help='account password') + authentication.add_option('-2', '--twofactor', + dest='twofactor', metavar='TWOFACTOR', help='two-factor auth code') authentication.add_option('-n', '--netrc', action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False) authentication.add_option('--video-password', @@ -382,6 +370,33 @@ def parseOpts(overrideArguments=None): help='do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.', default=False) downloader.add_option('--test', action='store_true', dest='test', default=False, help=optparse.SUPPRESS_HELP) + workarounds.add_option( + '--encoding', dest='encoding', metavar='ENCODING', + help='Force the specified encoding (experimental)') + workarounds.add_option( + '--no-check-certificate', action='store_true', + dest='no_check_certificate', default=False, + help='Suppress HTTPS certificate validation.') + workarounds.add_option( + '--prefer-insecure', '--prefer-unsecure', action='store_true', dest='prefer_insecure', + help='Use an unencrypted connection to retrieve information about the video. (Currently supported only for YouTube)') + workarounds.add_option( + '--user-agent', metavar='UA', + dest='user_agent', help='specify a custom user agent') + workarounds.add_option( + '--referer', metavar='REF', + dest='referer', default=None, + help='specify a custom referer, use if the video access is restricted to one domain', + ) + workarounds.add_option( + '--add-header', metavar='FIELD:VALUE', + dest='headers', action='append', + help='specify a custom HTTP header and its value, separated by a colon \':\'. You can use this option multiple times', + ) + workarounds.add_option( + '--bidi-workaround', dest='bidi_workaround', action='store_true', + help=u'Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH') + verbosity.add_option('-q', '--quiet', action='store_true', dest='quiet', help='activates quiet mode', default=False) verbosity.add_option( @@ -439,12 +454,10 @@ def parseOpts(overrideArguments=None): help='Display sent and read HTTP traffic') - filesystem.add_option('-t', '--title', - action='store_true', dest='usetitle', help='use title in file name (default)', default=False) + filesystem.add_option('-a', '--batch-file', + dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)') filesystem.add_option('--id', action='store_true', dest='useid', help='use only video ID in file name', default=False) - filesystem.add_option('-l', '--literal', - action='store_true', dest='usetitle', help='[deprecated] alias of --title', default=False) filesystem.add_option('-A', '--auto-number', action='store_true', dest='autonumber', help='number downloaded files starting from 00000', default=False) @@ -470,11 +483,10 @@ def parseOpts(overrideArguments=None): filesystem.add_option('--restrict-filenames', action='store_true', dest='restrictfilenames', help='Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames', default=False) - filesystem.add_option('-a', '--batch-file', - dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)') - filesystem.add_option('--load-info', - dest='load_info_filename', metavar='FILE', - help='json file containing the video information (created with the "--write-json" option)') + filesystem.add_option('-t', '--title', + action='store_true', dest='usetitle', help='[deprecated] use title in file name (default)', default=False) + filesystem.add_option('-l', '--literal', + action='store_true', dest='usetitle', help='[deprecated] alias of --title', default=False) filesystem.add_option('-w', '--no-overwrites', action='store_true', dest='nooverwrites', help='do not overwrite files', default=False) filesystem.add_option('-c', '--continue', @@ -482,8 +494,6 @@ def parseOpts(overrideArguments=None): filesystem.add_option('--no-continue', action='store_false', dest='continue_dl', help='do not resume partially downloaded files (restart from beginning)') - filesystem.add_option('--cookies', - dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in') filesystem.add_option('--no-part', action='store_true', dest='nopart', help='do not use .part files', default=False) filesystem.add_option('--no-mtime', @@ -501,6 +511,20 @@ def parseOpts(overrideArguments=None): filesystem.add_option('--write-thumbnail', action='store_true', dest='writethumbnail', help='write thumbnail image to disk', default=False) + filesystem.add_option('--load-info', + dest='load_info_filename', metavar='FILE', + help='json file containing the video information (created with the "--write-json" option)') + filesystem.add_option('--cookies', + dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in') + filesystem.add_option( + '--cache-dir', dest='cachedir', default=None, metavar='DIR', + help='Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may change.') + filesystem.add_option( + '--no-cache-dir', action='store_const', const=False, dest='cachedir', + help='Disable filesystem caching') + filesystem.add_option( + '--rm-cache-dir', action='store_true', dest='rm_cachedir', + help='Delete all filesystem cache files') postproc.add_option('-x', '--extract-audio', action='store_true', dest='extractaudio', default=False, @@ -527,13 +551,16 @@ def parseOpts(overrideArguments=None): help='Prefer avconv over ffmpeg for running the postprocessors (default)') postproc.add_option('--prefer-ffmpeg', action='store_true', dest='prefer_ffmpeg', help='Prefer ffmpeg over avconv for running the postprocessors') - + postproc.add_option( + '--exec', metavar='CMD', dest='exec_cmd', + help='Execute a command on the file after downloading, similar to find\'s -exec syntax. Example: --exec \'adb push {} /sdcard/Music/ && rm {}\'' ) parser.add_option_group(general) parser.add_option_group(selection) parser.add_option_group(downloader) parser.add_option_group(filesystem) parser.add_option_group(verbosity) + parser.add_option_group(workarounds) parser.add_option_group(video_format) parser.add_option_group(subtitles) parser.add_option_group(authentication) @@ -633,7 +660,7 @@ def _real_main(argv=None): if desc is False: continue if hasattr(ie, 'SEARCH_KEY'): - _SEARCHES = (u'cute kittens', u'slithering pythons', u'falling cat', u'angry poodle', u'purple fish', u'running tortoise') + _SEARCHES = (u'cute kittens', u'slithering pythons', u'falling cat', u'angry poodle', u'purple fish', u'running tortoise', u'sleeping bunny') _COUNTS = (u'', u'5', u'10', u'all') desc += u' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES)) compat_print(desc) @@ -694,7 +721,7 @@ def _real_main(argv=None): date = DateRange.day(opts.date) else: date = DateRange(opts.dateafter, opts.datebefore) - if opts.default_search not in ('auto', 'auto_warning', None) and ':' not in opts.default_search: + if opts.default_search not in ('auto', 'auto_warning', 'error', 'fixup_error', None) and ':' not in opts.default_search: parser.error(u'--default-search invalid; did you forget a colon (:) at the end?') # Do not download videos when there are audio-only formats @@ -730,6 +757,7 @@ def _real_main(argv=None): 'usenetrc': opts.usenetrc, 'username': opts.username, 'password': opts.password, + 'twofactor': opts.twofactor, 'videopassword': opts.videopassword, 'quiet': (opts.quiet or any_printing), 'no_warnings': opts.no_warnings, @@ -806,6 +834,7 @@ def _real_main(argv=None): 'default_search': opts.default_search, 'youtube_include_dash_manifest': opts.youtube_include_dash_manifest, 'encoding': opts.encoding, + 'exec_cmd': opts.exec_cmd, } with YoutubeDL(ydl_opts) as ydl: @@ -829,13 +858,24 @@ def _real_main(argv=None): ydl.add_post_processor(FFmpegAudioFixPP()) ydl.add_post_processor(AtomicParsleyPP()) + + # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way. + # So if the user is able to remove the file before your postprocessor runs it might cause a few problems. + if opts.exec_cmd: + ydl.add_post_processor(ExecAfterDownloadPP( + verboseOutput=opts.verbose, exec_cmd=opts.exec_cmd)) + # Update version if opts.update_self: update_self(ydl.to_screen, opts.verbose) + # Remove cache dir + if opts.rm_cachedir: + ydl.cache.remove() + # Maybe do nothing if (len(all_urls) < 1) and (opts.load_info_filename is None): - if not opts.update_self: + if not (opts.update_self or opts.rm_cachedir): parser.error(u'you must provide at least one URL') else: sys.exit() diff --git a/youtube_dl/cache.py b/youtube_dl/cache.py new file mode 100644 index 000000000..79ff09f78 --- /dev/null +++ b/youtube_dl/cache.py @@ -0,0 +1,94 @@ +from __future__ import unicode_literals + +import errno +import io +import json +import os +import re +import shutil +import traceback + +from .utils import ( + write_json_file, +) + + +class Cache(object): + def __init__(self, ydl): + self._ydl = ydl + + def _get_root_dir(self): + res = self._ydl.params.get('cachedir') + if res is None: + cache_root = os.environ.get('XDG_CACHE_HOME', '~/.cache') + res = os.path.join(cache_root, 'youtube-dl') + return os.path.expanduser(res) + + def _get_cache_fn(self, section, key, dtype): + assert re.match(r'^[a-zA-Z0-9_.-]+$', section), \ + 'invalid section %r' % section + assert re.match(r'^[a-zA-Z0-9_.-]+$', key), 'invalid key %r' % key + return os.path.join( + self._get_root_dir(), section, '%s.%s' % (key, dtype)) + + @property + def enabled(self): + return self._ydl.params.get('cachedir') is not False + + def store(self, section, key, data, dtype='json'): + assert dtype in ('json',) + + if not self.enabled: + return + + fn = self._get_cache_fn(section, key, dtype) + try: + try: + os.makedirs(os.path.dirname(fn)) + except OSError as ose: + if ose.errno != errno.EEXIST: + raise + write_json_file(data, fn) + except Exception: + tb = traceback.format_exc() + self._ydl.report_warning( + 'Writing cache to %r failed: %s' % (fn, tb)) + + def load(self, section, key, dtype='json', default=None): + assert dtype in ('json',) + + if not self.enabled: + return default + + cache_fn = self._get_cache_fn(section, key, dtype) + try: + try: + with io.open(cache_fn, 'r', encoding='utf-8') as cachef: + return json.load(cachef) + except ValueError: + try: + file_size = os.path.getsize(cache_fn) + except (OSError, IOError) as oe: + file_size = str(oe) + self._ydl.report_warning( + 'Cache retrieval from %s failed (%s)' % (cache_fn, file_size)) + except IOError: + pass # No cache available + + return default + + def remove(self): + if not self.enabled: + self._ydl.to_screen('Cache is disabled (Did you combine --no-cache-dir and --rm-cache-dir?)') + return + + cachedir = self._get_root_dir() + if not any((term in cachedir) for term in ('cache', 'tmp')): + raise Exception('Not removing directory %s - this does not look like a cache dir' % cachedir) + + self._ydl.to_screen( + 'Removing cache dir %s .' % cachedir, skip_eol=True) + if os.path.exists(cachedir): + self._ydl.to_screen('.', skip_eol=True) + shutil.rmtree(cachedir) + self._ydl.to_screen('.') diff --git a/youtube_dl/downloader/common.py b/youtube_dl/downloader/common.py index 917f3450e..9ce97f5fe 100644 --- a/youtube_dl/downloader/common.py +++ b/youtube_dl/downloader/common.py @@ -292,7 +292,7 @@ class FileDownloader(object): def real_download(self, filename, info_dict): """Real download process. Redefine in subclasses.""" - raise NotImplementedError(u'This method must be implemented by sublcasses') + raise NotImplementedError(u'This method must be implemented by subclasses') def _hook_progress(self, status): for ph in self._progress_hooks: diff --git a/youtube_dl/downloader/f4m.py b/youtube_dl/downloader/f4m.py index e6be6ae6c..71353f607 100644 --- a/youtube_dl/downloader/f4m.py +++ b/youtube_dl/downloader/f4m.py @@ -220,6 +220,7 @@ class F4mFD(FileDownloader): def real_download(self, filename, info_dict): man_url = info_dict['url'] + requested_bitrate = info_dict.get('tbr') self.to_screen('[download] Downloading f4m manifest') manifest = self.ydl.urlopen(man_url).read() self.report_destination(filename) @@ -233,8 +234,14 @@ class F4mFD(FileDownloader): doc = etree.fromstring(manifest) formats = [(int(f.attrib.get('bitrate', -1)), f) for f in doc.findall(_add_ns('media'))] - formats = sorted(formats, key=lambda f: f[0]) - rate, media = formats[-1] + if requested_bitrate is None: + # get the best format + formats = sorted(formats, key=lambda f: f[0]) + rate, media = formats[-1] + else: + rate, media = list(filter( + lambda f: int(f[0]) == requested_bitrate, formats))[0] + base_url = compat_urlparse.urljoin(man_url, media.attrib['url']) bootstrap = base64.b64decode(doc.find(_add_ns('bootstrapInfo')).text) metadata = base64.b64decode(media.find(_add_ns('metadata')).text) diff --git a/youtube_dl/downloader/hls.py b/youtube_dl/downloader/hls.py index 9f29e2f81..32852f333 100644 --- a/youtube_dl/downloader/hls.py +++ b/youtube_dl/downloader/hls.py @@ -3,6 +3,7 @@ import subprocess from .common import FileDownloader from ..utils import ( + check_executable, encodeFilename, ) @@ -19,13 +20,11 @@ class HlsFD(FileDownloader): encodeFilename(tmpfilename, for_subprocess=True)] for program in ['avconv', 'ffmpeg']: - try: - subprocess.call([program, '-version'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT) + if check_executable(program, ['-version']): break - except (OSError, IOError): - pass else: self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found. Please install one.') + return False cmd = [program] + args retval = subprocess.call(cmd) @@ -42,5 +41,5 @@ class HlsFD(FileDownloader): return True else: self.to_stderr(u"\n") - self.report_error(u'ffmpeg exited with code %d' % retval) + self.report_error(u'%s exited with code %d' % (program, retval)) return False diff --git a/youtube_dl/downloader/http.py b/youtube_dl/downloader/http.py index f79e6a995..6caf7451e 100644 --- a/youtube_dl/downloader/http.py +++ b/youtube_dl/downloader/http.py @@ -27,8 +27,16 @@ class HttpFD(FileDownloader): headers['Youtubedl-user-agent'] = info_dict['user_agent'] if 'http_referer' in info_dict: headers['Referer'] = info_dict['http_referer'] - basic_request = compat_urllib_request.Request(url, None, headers) - request = compat_urllib_request.Request(url, None, headers) + add_headers = info_dict.get('http_headers') + if add_headers: + headers.update(add_headers) + data = info_dict.get('http_post_data') + http_method = info_dict.get('http_method') + basic_request = compat_urllib_request.Request(url, data, headers) + request = compat_urllib_request.Request(url, data, headers) + if http_method is not None: + basic_request.get_method = lambda: http_method + request.get_method = lambda: http_method is_test = self.params.get('test', False) @@ -185,7 +193,8 @@ class HttpFD(FileDownloader): self.to_stderr(u"\n") self.report_error(u'Did not get any data blocks') return False - stream.close() + if tmpfilename != u'-': + stream.close() self.report_finish(data_len_str, (time.time() - start)) if data_len is not None and byte_counter != data_len: raise ContentTooShortError(byte_counter, int(data_len)) diff --git a/youtube_dl/downloader/rtmp.py b/youtube_dl/downloader/rtmp.py index 68646709a..5eb108302 100644 --- a/youtube_dl/downloader/rtmp.py +++ b/youtube_dl/downloader/rtmp.py @@ -8,9 +8,10 @@ import time from .common import FileDownloader from ..utils import ( + check_executable, + compat_str, encodeFilename, format_bytes, - compat_str, ) @@ -103,9 +104,7 @@ class RtmpFD(FileDownloader): test = self.params.get('test', False) # Check for rtmpdump first - try: - subprocess.call(['rtmpdump', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT) - except (OSError, IOError): + if not check_executable('rtmpdump', ['-h']): self.report_error('RTMP download detected but "rtmpdump" could not be run. Please install it.') return False diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 18f73a890..f9077d969 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -1,13 +1,16 @@ +from .abc import ABCIE from .academicearth import AcademicEarthCourseIE from .addanime import AddAnimeIE +from .adultswim import AdultSwimIE from .aftonbladet import AftonbladetIE from .anitube import AnitubeIE +from .anysex import AnySexIE from .aol import AolIE from .allocine import AllocineIE from .aparat import AparatIE from .appletrailers import AppleTrailersIE from .archiveorg import ArchiveOrgIE -from .ard import ARDIE +from .ard import ARDIE, ARDMediathekIE from .arte import ( ArteTvIE, ArteTVPlus7IE, @@ -21,6 +24,7 @@ from .auengine import AUEngineIE from .bambuser import BambuserIE, BambuserChannelIE from .bandcamp import BandcampIE, BandcampAlbumIE from .bbccouk import BBCCoUkIE +from .beeg import BeegIE from .bilibili import BiliBiliIE from .blinkx import BlinkxIE from .bliptv import BlipTVIE, BlipTVUserIE @@ -52,6 +56,7 @@ from .cnn import ( from .collegehumor import CollegeHumorIE from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE from .condenast import CondeNastIE +from .cracked import CrackedIE from .criterion import CriterionIE from .crunchyroll import CrunchyrollIE from .cspan import CSpanIE @@ -62,9 +67,13 @@ from .dailymotion import ( DailymotionUserIE, ) from .daum import DaumIE +from .dbtv import DBTVIE +from .dfb import DFBIE from .dotsub import DotsubIE from .dreisat import DreiSatIE +from .drtuber import DrTuberIE from .drtv import DRTVIE +from .dump import DumpIE from .defense import DefenseGouvFrIE from .discovery import DiscoveryIE from .divxstage import DivxStageIE @@ -73,12 +82,18 @@ from .ebaumsworld import EbaumsWorldIE from .ehow import EHowIE from .eighttracks import EightTracksIE from .eitb import EitbIE +from .ellentv import ( + EllenTVIE, + EllenTVClipsIE, +) from .elpais import ElPaisIE -from .empflix import EmpflixIE +from .empflix import EMPFlixIE from .engadget import EngadgetIE +from .eporner import EpornerIE from .escapist import EscapistIE from .everyonesmixtape import EveryonesMixtapeIE from .exfm import ExfmIE +from .expotv import ExpoTVIE from .extremetube import ExtremeTubeIE from .facebook import FacebookIE from .faz import FazIE @@ -106,20 +121,28 @@ from .freesound import FreesoundIE from .freespeech import FreespeechIE from .funnyordie import FunnyOrDieIE from .gamekings import GamekingsIE -from .gameone import GameOneIE +from .gameone import ( + GameOneIE, + GameOnePlaylistIE, +) from .gamespot import GameSpotIE +from .gamestar import GameStarIE from .gametrailers import GametrailersIE from .gdcvault import GDCVaultIE from .generic import GenericIE +from .godtube import GodTubeIE from .googleplus import GooglePlusIE from .googlesearch import GoogleSearchIE from .gorillavid import GorillaVidIE from .goshgay import GoshgayIE +from .grooveshark import GroovesharkIE from .hark import HarkIE from .helsinki import HelsinkiIE from .hentaistigma import HentaiStigmaIE +from .hornbunny import HornBunnyIE from .hotnewhiphop import HotNewHipHopIE from .howcast import HowcastIE +from .howstuffworks import HowStuffWorksIE from .huffpost import HuffPostIE from .hypem import HypemIE from .iconosquare import IconosquareIE @@ -137,8 +160,10 @@ from .ivi import ( IviIE, IviCompilationIE ) +from .izlesene import IzleseneIE from .jadorecettepub import JadoreCettePubIE from .jeuxvideo import JeuxVideoIE +from .jove import JoveIE from .jukebox import JukeboxIE from .justintv import JustinTVIE from .jpopsukitv import JpopsukiIE @@ -148,6 +173,7 @@ from .khanacademy import KhanAcademyIE from .kickstarter import KickStarterIE from .keek import KeekIE from .kontrtube import KontrTubeIE +from .krasview import KrasViewIE from .ku6 import Ku6IE from .la7 import LA7IE from .lifenews import LifeNewsIE @@ -168,14 +194,19 @@ from .malemotion import MalemotionIE from .mdr import MDRIE from .metacafe import MetacafeIE from .metacritic import MetacriticIE +from .ministrygrid import MinistryGridIE from .mit import TechTVMITIE, MITIE, OCWMITIE +from .mitele import MiTeleIE from .mixcloud import MixcloudIE +from .mlb import MLBIE from .mpora import MporaIE from .mofosex import MofosexIE +from .mojvideo import MojvideoIE from .mooshare import MooshareIE from .morningstar import MorningstarIE from .motherless import MotherlessIE from .motorsport import MotorsportIE +from .movieclips import MovieClipsIE from .moviezine import MoviezineIE from .movshare import MovShareIE from .mtv import ( @@ -184,6 +215,7 @@ from .mtv import ( MTVIggyIE, ) from .musicplayon import MusicPlayOnIE +from .musicvault import MusicVaultIE from .muzu import MuzuTVIE from .myspace import MySpaceIE from .myspass import MySpassIE @@ -204,6 +236,7 @@ from .niconico import NiconicoIE from .ninegag import NineGagIE from .noco import NocoIE from .normalboots import NormalbootsIE +from .nosvideo import NosVideoIE from .novamov import NovaMovIE from .nowness import NownessIE from .nowvideo import NowVideoIE @@ -215,17 +248,23 @@ from .nrk import ( from .ntv import NTVIE from .nytimes import NYTimesIE from .nuvid import NuvidIE -from .oe1 import OE1IE from .ooyala import OoyalaIE -from .orf import ORFIE +from .orf import ( + ORFTVthekIE, + ORFOE1IE, + ORFFM4IE, +) from .parliamentliveuk import ParliamentLiveUKIE +from .patreon import PatreonIE from .pbs import PBSIE from .photobucket import PhotobucketIE +from .playfm import PlayFMIE from .playvid import PlayvidIE from .podomatic import PodomaticIE from .pornhd import PornHdIE from .pornhub import PornHubIE from .pornotube import PornotubeIE +from .promptfile import PromptFileIE from .prosiebensat1 import ProSiebenSat1IE from .pyvideo import PyvideoIE from .radiofrance import RadioFranceIE @@ -238,9 +277,10 @@ from .ro220 import Ro220IE from .rottentomatoes import RottenTomatoesIE from .roxwel import RoxwelIE from .rtbf import RTBFIE +from .rtlnl import RtlXlIE from .rtlnow import RTLnowIE from .rts import RTSIE -from .rtve import RTVEALaCartaIE +from .rtve import RTVEALaCartaIE, RTVELiveIE from .ruhd import RUHDIE from .rutube import ( RutubeIE, @@ -249,10 +289,13 @@ from .rutube import ( RutubePersonIE, ) from .rutv import RUTVIE +from .sapo import SapoIE from .savefrom import SaveFromIE +from .sbs import SBSIE from .scivee import SciVeeIE from .screencast import ScreencastIE from .servingsys import ServingSysIE +from .shared import SharedIE from .sina import SinaIE from .slideshare import SlideshareIE from .slutload import SlutloadIE @@ -262,6 +305,8 @@ from .smotri import ( SmotriUserIE, SmotriBroadcastIE, ) +from .snotr import SnotrIE +from .sockshare import SockshareIE from .sohu import SohuIE from .soundcloud import ( SoundcloudIE, @@ -279,10 +324,12 @@ from .spankwire import SpankwireIE from .spiegel import SpiegelIE from .spiegeltv import SpiegeltvIE from .spike import SpikeIE +from .sportdeutschland import SportDeutschlandIE from .stanfordoc import StanfordOpenClassroomIE from .steam import SteamIE from .streamcloud import StreamcloudIE from .streamcz import StreamCZIE +from .sunporno import SunPornoIE from .swrmediathek import SWRMediathekIE from .syfy import SyfyIE from .sztvhu import SztvHuIE @@ -302,6 +349,7 @@ from .theplatform import ThePlatformIE from .thisav import ThisAVIE from .tinypic import TinyPicIE from .tlc import TlcIE, TlcDeIE +from .tnaflix import TNAFlixIE from .toutv import TouTvIE from .toypics import ToypicsUserIE, ToypicsIE from .traileraddict import TrailerAddictIE @@ -313,6 +361,8 @@ from .tumblr import TumblrIE from .tutv import TutvIE from .tvigle import TvigleIE from .tvp import TvpIE +from .tvplay import TVPlayIE +from .ubu import UbuIE from .udemy import ( UdemyIE, UdemyCourseIE @@ -335,6 +385,7 @@ from .videofyme import VideofyMeIE from .videopremium import VideoPremiumIE from .videott import VideoTtIE from .videoweed import VideoWeedIE +from .vidme import VidmeIE from .vimeo import ( VimeoIE, VimeoChannelIE, @@ -352,11 +403,13 @@ from .vine import ( from .viki import VikiIE from .vk import VKIE from .vodlocker import VodlockerIE +from .vporn import VpornIE from .vube import VubeIE from .vuclip import VuClipIE from .vulture import VultureIE from .washingtonpost import WashingtonPostIE from .wat import WatIE +from .wayofthemaster import WayOfTheMasterIE from .wdr import ( WDRIE, WDRMobileIE, @@ -368,6 +421,7 @@ from .wistia import WistiaIE from .worldstarhiphop import WorldStarHipHopIE from .wrzuta import WrzutaIE from .xbef import XBefIE +from .xboxclips import XboxClipsIE from .xhamster import XHamsterIE from .xnxx import XNXXIE from .xvideos import XVideosIE @@ -397,6 +451,7 @@ from .youtube import ( YoutubeUserIE, YoutubeWatchLaterIE, ) + from .zdf import ZDFIE diff --git a/youtube_dl/extractor/abc.py b/youtube_dl/extractor/abc.py new file mode 100644 index 000000000..7d89f44ee --- /dev/null +++ b/youtube_dl/extractor/abc.py @@ -0,0 +1,48 @@ +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor + + +class ABCIE(InfoExtractor): + IE_NAME = 'abc.net.au' + _VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P<id>\d+)' + + _TEST = { + 'url': 'http://www.abc.net.au/news/2014-07-25/bringing-asylum-seekers-to-australia-would-give/5624716', + 'md5': 'dad6f8ad011a70d9ddf887ce6d5d0742', + 'info_dict': { + 'id': '5624716', + 'ext': 'mp4', + 'title': 'Bringing asylum seekers to Australia would give them right to asylum claims: professor', + 'description': 'md5:ba36fa5e27e5c9251fd929d339aea4af', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + + urls_info_json = self._search_regex( + r'inlineVideoData\.push\((.*?)\);', webpage, 'video urls', + flags=re.DOTALL) + urls_info = json.loads(urls_info_json.replace('\'', '"')) + formats = [{ + 'url': url_info['url'], + 'width': int(url_info['width']), + 'height': int(url_info['height']), + 'tbr': int(url_info['bitrate']), + 'filesize': int(url_info['filesize']), + } for url_info in urls_info] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': self._og_search_title(webpage), + 'formats': formats, + 'description': self._og_search_description(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + } diff --git a/youtube_dl/extractor/academicearth.py b/youtube_dl/extractor/academicearth.py index 59d3bbba4..c983ef0f5 100644 --- a/youtube_dl/extractor/academicearth.py +++ b/youtube_dl/extractor/academicearth.py @@ -7,6 +7,15 @@ from .common import InfoExtractor class AcademicEarthCourseIE(InfoExtractor): _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)' IE_NAME = 'AcademicEarth:Course' + _TEST = { + 'url': 'http://academicearth.org/playlists/laws-of-nature/', + 'info_dict': { + 'id': 'laws-of-nature', + 'title': 'Laws of Nature', + 'description': 'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.', + }, + 'playlist_count': 4, + } def _real_extract(self, url): m = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/adultswim.py b/youtube_dl/extractor/adultswim.py new file mode 100644 index 000000000..a00bfcb35 --- /dev/null +++ b/youtube_dl/extractor/adultswim.py @@ -0,0 +1,139 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + +class AdultSwimIE(InfoExtractor): + _VALID_URL = r'https?://video\.adultswim\.com/(?P<path>.+?)(?:\.html)?(?:\?.*)?(?:#.*)?$' + _TEST = { + 'url': 'http://video.adultswim.com/rick-and-morty/close-rick-counters-of-the-rick-kind.html?x=y#title', + 'playlist': [ + { + 'md5': '4da359ec73b58df4575cd01a610ba5dc', + 'info_dict': { + 'id': '8a250ba1450996e901453d7f02ca02f5', + 'ext': 'flv', + 'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 1', + 'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?', + 'uploader': 'Rick and Morty', + 'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg' + } + }, + { + 'md5': 'ffbdf55af9331c509d95350bd0cc1819', + 'info_dict': { + 'id': '8a250ba1450996e901453d7f4bd102f6', + 'ext': 'flv', + 'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 2', + 'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?', + 'uploader': 'Rick and Morty', + 'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg' + } + }, + { + 'md5': 'b92409635540304280b4b6c36bd14a0a', + 'info_dict': { + 'id': '8a250ba1450996e901453d7fa73c02f7', + 'ext': 'flv', + 'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 3', + 'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?', + 'uploader': 'Rick and Morty', + 'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg' + } + }, + { + 'md5': 'e8818891d60e47b29cd89d7b0278156d', + 'info_dict': { + 'id': '8a250ba1450996e901453d7fc8ba02f8', + 'ext': 'flv', + 'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 4', + 'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?', + 'uploader': 'Rick and Morty', + 'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg' + } + } + ] + } + + _video_extensions = { + '3500': 'flv', + '640': 'mp4', + '150': 'mp4', + 'ipad': 'm3u8', + 'iphone': 'm3u8' + } + _video_dimensions = { + '3500': (1280, 720), + '640': (480, 270), + '150': (320, 180) + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_path = mobj.group('path') + + webpage = self._download_webpage(url, video_path) + episode_id = self._html_search_regex(r'<link rel="video_src" href="http://i\.adultswim\.com/adultswim/adultswimtv/tools/swf/viralplayer.swf\?id=([0-9a-f]+?)"\s*/?\s*>', webpage, 'episode_id') + title = self._og_search_title(webpage) + + index_url = 'http://asfix.adultswim.com/asfix-svc/episodeSearch/getEpisodesByIDs?networkName=AS&ids=%s' % episode_id + idoc = self._download_xml(index_url, title, 'Downloading episode index', 'Unable to download episode index') + + episode_el = idoc.find('.//episode') + show_title = episode_el.attrib.get('collectionTitle') + episode_title = episode_el.attrib.get('title') + thumbnail = episode_el.attrib.get('thumbnailUrl') + description = episode_el.find('./description').text.strip() + + entries = [] + segment_els = episode_el.findall('./segments/segment') + + for part_num, segment_el in enumerate(segment_els): + segment_id = segment_el.attrib.get('id') + segment_title = '%s %s part %d' % (show_title, episode_title, part_num + 1) + thumbnail = segment_el.attrib.get('thumbnailUrl') + duration = segment_el.attrib.get('duration') + + segment_url = 'http://asfix.adultswim.com/asfix-svc/episodeservices/getCvpPlaylist?networkName=AS&id=%s' % segment_id + idoc = self._download_xml(segment_url, segment_title, 'Downloading segment information', 'Unable to download segment information') + + formats = [] + file_els = idoc.findall('.//files/file') + + for file_el in file_els: + bitrate = file_el.attrib.get('bitrate') + type = file_el.attrib.get('type') + width, height = self._video_dimensions.get(bitrate, (None, None)) + formats.append({ + 'format_id': '%s-%s' % (bitrate, type), + 'url': file_el.text, + 'ext': self._video_extensions.get(bitrate, 'mp4'), + # The bitrate may not be a number (for example: 'iphone') + 'tbr': int(bitrate) if bitrate.isdigit() else None, + 'height': height, + 'width': width + }) + + self._sort_formats(formats) + + entries.append({ + 'id': segment_id, + 'title': segment_title, + 'formats': formats, + 'uploader': show_title, + 'thumbnail': thumbnail, + 'duration': duration, + 'description': description + }) + + return { + '_type': 'playlist', + 'id': episode_id, + 'display_id': video_path, + 'entries': entries, + 'title': '%s %s' % (show_title, episode_title), + 'description': description, + 'thumbnail': thumbnail + } diff --git a/youtube_dl/extractor/allocine.py b/youtube_dl/extractor/allocine.py index 34f0cd49b..7bd797884 100644 --- a/youtube_dl/extractor/allocine.py +++ b/youtube_dl/extractor/allocine.py @@ -32,7 +32,7 @@ class AllocineIE(InfoExtractor): 'id': '19540403', 'ext': 'mp4', 'title': 'Planes 2 Bande-annonce VF', - 'description': 'md5:c4b1f7bd682a91de6491ada267ec0f4d', + 'description': 'md5:eeaffe7c2d634525e21159b93acf3b1e', 'thumbnail': 're:http://.*\.jpg', }, }, { @@ -42,7 +42,7 @@ class AllocineIE(InfoExtractor): 'id': '19544709', 'ext': 'mp4', 'title': 'Dragons 2 - Bande annonce finale VF', - 'description': 'md5:e74a4dc750894bac300ece46c7036490', + 'description': 'md5:71742e3a74b0d692c7fce0dd2017a4ac', 'thumbnail': 're:http://.*\.jpg', }, }] diff --git a/youtube_dl/extractor/anysex.py b/youtube_dl/extractor/anysex.py new file mode 100644 index 000000000..bc64423a3 --- /dev/null +++ b/youtube_dl/extractor/anysex.py @@ -0,0 +1,61 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + int_or_none, +) + + +class AnySexIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?anysex\.com/(?P<id>\d+)' + _TEST = { + 'url': 'http://anysex.com/156592/', + 'md5': '023e9fbb7f7987f5529a394c34ad3d3d', + 'info_dict': { + 'id': '156592', + 'ext': 'mp4', + 'title': 'Busty and sexy blondie in her bikini strips for you', + 'description': 'md5:de9e418178e2931c10b62966474e1383', + 'categories': ['Erotic'], + 'duration': 270, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex(r"video_url\s*:\s*'([^']+)'", webpage, 'video URL') + + title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title') + description = self._html_search_regex( + r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False) + thumbnail = self._html_search_regex( + r'preview_url\s*:\s*\'(.*?)\'', webpage, 'thumbnail', fatal=False) + + categories = re.findall( + r'<a href="http://anysex\.com/categories/[^"]+" title="[^"]*">([^<]+)</a>', webpage) + + duration = parse_duration(self._search_regex( + r'<b>Duration:</b> (\d+:\d+)', webpage, 'duration', fatal=False)) + view_count = int_or_none(self._html_search_regex( + r'<b>Views:</b> (\d+)', webpage, 'view count', fatal=False)) + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp4', + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'categories': categories, + 'duration': duration, + 'view_count': view_count, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/aol.py b/youtube_dl/extractor/aol.py index a7bfe5a5c..47f8e4157 100644 --- a/youtube_dl/extractor/aol.py +++ b/youtube_dl/extractor/aol.py @@ -21,7 +21,7 @@ class AolIE(InfoExtractor): (?:$|\?) ''' - _TEST = { + _TESTS = [{ 'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img', 'md5': '18ef68f48740e86ae94b98da815eec42', 'info_dict': { @@ -30,7 +30,14 @@ class AolIE(InfoExtractor): 'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam', }, 'add_ie': ['FiveMin'], - } + }, { + 'url': 'http://on.aol.com/playlist/brace-yourself---todays-weirdest-news-152147?icid=OnHomepageC4_Omg_Img#_videoid=518184316', + 'info_dict': { + 'id': '152147', + 'title': 'Brace Yourself - Today\'s Weirdest News', + }, + 'playlist_mincount': 10, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/aparat.py b/youtube_dl/extractor/aparat.py index 7e93bc4df..748608826 100644 --- a/youtube_dl/extractor/aparat.py +++ b/youtube_dl/extractor/aparat.py @@ -1,5 +1,7 @@ #coding: utf-8 +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -13,13 +15,14 @@ class AparatIE(InfoExtractor): _VALID_URL = r'^https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)' _TEST = { - u'url': u'http://www.aparat.com/v/wP8On', - u'file': u'wP8On.mp4', - u'md5': u'6714e0af7e0d875c5a39c4dc4ab46ad1', - u'info_dict': { - u"title": u"تیم گلکسی 11 - زومیت", + 'url': 'http://www.aparat.com/v/wP8On', + 'md5': '6714e0af7e0d875c5a39c4dc4ab46ad1', + 'info_dict': { + 'id': 'wP8On', + 'ext': 'mp4', + 'title': 'تیم گلکسی 11 - زومیت', }, - #u'skip': u'Extremely unreliable', + # 'skip': 'Extremely unreliable', } def _real_extract(self, url): @@ -29,8 +32,8 @@ class AparatIE(InfoExtractor): # Note: There is an easier-to-parse configuration at # http://www.aparat.com/video/video/config/videohash/%video_id # but the URL in there does not work - embed_url = (u'http://www.aparat.com/video/video/embed/videohash/' + - video_id + u'/vt/frame') + embed_url = ('http://www.aparat.com/video/video/embed/videohash/' + + video_id + '/vt/frame') webpage = self._download_webpage(embed_url, video_id) video_urls = re.findall(r'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage) diff --git a/youtube_dl/extractor/appletrailers.py b/youtube_dl/extractor/appletrailers.py index dc8657b67..4359b88d1 100644 --- a/youtube_dl/extractor/appletrailers.py +++ b/youtube_dl/extractor/appletrailers.py @@ -6,6 +6,7 @@ import json from .common import InfoExtractor from ..utils import ( compat_urlparse, + int_or_none, ) @@ -110,8 +111,8 @@ class AppleTrailersIE(InfoExtractor): formats.append({ 'url': format_url, 'format': format['type'], - 'width': format['width'], - 'height': int(format['height']), + 'width': int_or_none(format['width']), + 'height': int_or_none(format['height']), }) self._sort_formats(formats) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index b36a4d46a..ef94c7239 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -7,23 +7,38 @@ from .common import InfoExtractor from ..utils import ( determine_ext, ExtractorError, + qualities, + compat_urllib_parse_urlparse, + compat_urllib_parse, + int_or_none, + parse_duration, + unified_strdate, ) -class ARDIE(InfoExtractor): - _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?' +class ARDMediathekIE(InfoExtractor): + IE_NAME = 'ARD:mediathek' + _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?' - _TEST = { - 'url': 'http://www.ardmediathek.de/das-erste/guenther-jauch/edward-snowden-im-interview-held-oder-verraeter?documentId=19288786', - 'file': '19288786.mp4', - 'md5': '515bf47ce209fb3f5a61b7aad364634c', + _TESTS = [{ + 'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht', + 'file': '22429276.mp4', + 'md5': '469751912f1de0816a9fc9df8336476c', 'info_dict': { - 'title': 'Edward Snowden im Interview - Held oder Verräter?', - 'description': 'Edward Snowden hat alles aufs Spiel gesetzt, um die weltweite \xdcberwachung durch die Geheimdienste zu enttarnen. Nun stellt sich der ehemalige NSA-Mitarbeiter erstmals weltweit in einem TV-Interview den Fragen eines NDR-Journalisten. Die Sendung vom Sonntagabend.', - 'thumbnail': 'http://www.ardmediathek.de/ard/servlet/contentblob/19/28/87/90/19288790/bild/2250037', + 'title': 'Vertrauen ist gut, Spionieren ist besser - Geht so deutsch-amerikanische Freundschaft?', + 'description': 'Das Erste Mediathek [ARD]: Vertrauen ist gut, Spionieren ist besser - Geht so deutsch-amerikanische Freundschaft?, Anne Will, Über die Spionage-Affäre diskutieren Clemens Binninger, Katrin Göring-Eckardt, Georg Mascolo, Andrew B. Denison und Constanze Kurz.. Das Video zur Sendung Anne Will am Mittwoch, 16.07.2014', }, 'skip': 'Blocked outside of Germany', - } + }, { + 'url': 'http://www.ardmediathek.de/tv/Tatort/Das-Wunder-von-Wolbeck-Video-tgl-ab-20/Das-Erste/Video?documentId=22490580&bcastId=602916', + 'info_dict': { + 'id': '22490580', + 'ext': 'mp4', + 'title': 'Das Wunder von Wolbeck (Video tgl. ab 20 Uhr)', + 'description': 'Auf einem restaurierten Hof bei Wolbeck wird der Heilpraktiker Raffael Lembeck eines morgens von seiner Frau Stella tot aufgefunden. Das Opfer war offensichtlich in seiner Praxis zu Fall gekommen und ist dann verblutet, erklärt Prof. Boerne am Tatort.', + }, + 'skip': 'Blocked outside of Germany', + }] def _real_extract(self, url): # determine video id from url @@ -35,48 +50,78 @@ class ARDIE(InfoExtractor): else: video_id = m.group('video_id') + urlp = compat_urllib_parse_urlparse(url) + url = urlp._replace(path=compat_urllib_parse.quote(urlp.path.encode('utf-8'))).geturl() + webpage = self._download_webpage(url, video_id) + if '>Der gewünschte Beitrag ist nicht mehr verfügbar.<' in webpage: + raise ExtractorError('Video %s is no longer available' % video_id, expected=True) + title = self._html_search_regex( [r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>', r'<meta name="dcterms.title" content="(.*?)"/>', r'<h4 class="headline">(.*?)</h4>'], webpage, 'title') description = self._html_search_meta( - 'dcterms.abstract', webpage, 'description') - thumbnail = self._og_search_thumbnail(webpage) - - - media_info = self._download_json( - 'http://www.ardmediathek.de/play/media/%s' % video_id, video_id) - # The second element of the _mediaArray contains the standard http urls - streams = media_info['_mediaArray'][1]['_mediaStreamArray'] - if not streams: - if '"fsk"' in webpage: - raise ExtractorError('This video is only available after 20:00') - - formats = [] - - for s in streams: - if type(s['_stream']) == list: - for index, url in enumerate(s['_stream'][::-1]): - quality = s['_quality'] + index - formats.append({ - 'quality': quality, - 'url': url, - 'format_id': '%s-%s' % (determine_ext(url), quality) + 'dcterms.abstract', webpage, 'description', default=None) + if description is None: + description = self._html_search_meta( + 'description', webpage, 'meta description') + + # Thumbnail is sometimes not present. + # It is in the mobile version, but that seems to use a different URL + # structure altogether. + thumbnail = self._og_search_thumbnail(webpage, default=None) + + media_streams = re.findall(r'''(?x) + mediaCollection\.addMediaStream\([0-9]+,\s*[0-9]+,\s*"[^"]*",\s* + "([^"]+)"''', webpage) + + if media_streams: + QUALITIES = qualities(['lo', 'hi', 'hq']) + formats = [] + for furl in set(media_streams): + if furl.endswith('.f4m'): + fid = 'f4m' + else: + fid_m = re.match(r'.*\.([^.]+)\.[^.]+$', furl) + fid = fid_m.group(1) if fid_m else None + formats.append({ + 'quality': QUALITIES(fid), + 'format_id': fid, + 'url': furl, + }) + else: # request JSON file + media_info = self._download_json( + 'http://www.ardmediathek.de/play/media/%s' % video_id, video_id) + # The second element of the _mediaArray contains the standard http urls + streams = media_info['_mediaArray'][1]['_mediaStreamArray'] + if not streams: + if '"fsk"' in webpage: + raise ExtractorError('This video is only available after 20:00') + + formats = [] + for s in streams: + if type(s['_stream']) == list: + for index, url in enumerate(s['_stream'][::-1]): + quality = s['_quality'] + index + formats.append({ + 'quality': quality, + 'url': url, + 'format_id': '%s-%s' % (determine_ext(url), quality) }) - continue + continue - format = { - 'quality': s['_quality'], - 'url': s['_stream'], - } + format = { + 'quality': s['_quality'], + 'url': s['_stream'], + } - format['format_id'] = '%s-%s' % ( - determine_ext(format['url']), format['quality']) + format['format_id'] = '%s-%s' % ( + determine_ext(format['url']), format['quality']) - formats.append(format) + formats.append(format) self._sort_formats(formats) @@ -87,3 +132,60 @@ class ARDIE(InfoExtractor): 'formats': formats, 'thumbnail': thumbnail, } + + +class ARDIE(InfoExtractor): + _VALID_URL = '(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html' + _TEST = { + 'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html', + 'md5': 'd216c3a86493f9322545e045ddc3eb35', + 'info_dict': { + 'display_id': 'die-story-im-ersten-mission-unter-falscher-flagge', + 'id': '100', + 'ext': 'mp4', + 'duration': 2600, + 'title': 'Die Story im Ersten: Mission unter falscher Flagge', + 'upload_date': '20140804', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('display_id') + + player_url = mobj.group('mainurl') + '~playerXml.xml' + doc = self._download_xml(player_url, display_id) + video_node = doc.find('./video') + upload_date = unified_strdate(video_node.find('./broadcastDate').text) + thumbnail = video_node.find('.//teaserImage//variant/url').text + + formats = [] + for a in video_node.findall('.//asset'): + f = { + 'format_id': a.attrib['type'], + 'width': int_or_none(a.find('./frameWidth').text), + 'height': int_or_none(a.find('./frameHeight').text), + 'vbr': int_or_none(a.find('./bitrateVideo').text), + 'abr': int_or_none(a.find('./bitrateAudio').text), + 'vcodec': a.find('./codecVideo').text, + 'tbr': int_or_none(a.find('./totalBitrate').text), + } + if a.find('./serverPrefix').text: + f['url'] = a.find('./serverPrefix').text + f['playpath'] = a.find('./fileName').text + else: + f['url'] = a.find('./fileName').text + formats.append(f) + self._sort_formats(formats) + + return { + 'id': mobj.group('id'), + 'formats': formats, + 'display_id': display_id, + 'title': video_node.find('./title').text, + 'duration': parse_duration(video_node.find('./duration').text), + 'upload_date': upload_date, + 'thumbnail': thumbnail, + } + diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index 9591bad8a..957d35979 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -78,7 +78,8 @@ class ArteTVPlus7IE(InfoExtractor): def _extract_from_webpage(self, webpage, video_id, lang): json_url = self._html_search_regex( - r'arte_vp_url="(.*?)"', webpage, 'json vp url') + [r'arte_vp_url=["\'](.*?)["\']', r'data-url=["\']([^"]+)["\']'], + webpage, 'json vp url') return self._extract_from_json_url(json_url, video_id, lang) def _extract_from_json_url(self, json_url, video_id, lang): @@ -109,15 +110,19 @@ class ArteTVPlus7IE(InfoExtractor): regexes = [r'VO?%s' % l, r'VO?.-ST%s' % l] return any(re.match(r, f['versionCode']) for r in regexes) # Some formats may not be in the same language as the url + # TODO: Might want not to drop videos that does not match requested language + # but to process those formats with lower precedence formats = filter(_match_lang, all_formats) - formats = list(formats) # in python3 filter returns an iterator + formats = list(formats) # in python3 filter returns an iterator if not formats: # Some videos are only available in the 'Originalversion' # they aren't tagged as being in French or German - if all(f['versionCode'] == 'VO' or f['versionCode'] == 'VA' for f in all_formats): - formats = all_formats - else: - raise ExtractorError(u'The formats list is empty') + # Sometimes there are neither videos of requested lang code + # nor original version videos available + # For such cases we just take all_formats as is + formats = all_formats + if not formats: + raise ExtractorError('The formats list is empty') if re.match(r'[A-Z]Q', formats[0]['quality']) is not None: def sort_key(f): @@ -173,16 +178,26 @@ class ArteTVPlus7IE(InfoExtractor): # It also uses the arte_vp_url url from the webpage to extract the information class ArteTVCreativeIE(ArteTVPlus7IE): IE_NAME = 'arte.tv:creative' - _VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de)/magazine?/(?P<id>.+)' + _VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de)/(?:magazine?/)?(?P<id>[^?#]+)' - _TEST = { + _TESTS = [{ 'url': 'http://creative.arte.tv/de/magazin/agentur-amateur-corporate-design', 'info_dict': { - 'id': '050489-002', + 'id': '72176', 'ext': 'mp4', - 'title': 'Agentur Amateur / Agence Amateur #2 : Corporate Design', + 'title': 'Folge 2 - Corporate Design', + 'upload_date': '20131004', }, - } + }, { + 'url': 'http://creative.arte.tv/fr/Monty-Python-Reunion', + 'info_dict': { + 'id': '160676', + 'ext': 'mp4', + 'title': 'Monty Python live (mostly)', + 'description': 'Événement ! Quarante-cinq ans après leurs premiers succès, les légendaires Monty Python remontent sur scène.\n', + 'upload_date': '20140805', + } + }] class ArteTVFutureIE(ArteTVPlus7IE): diff --git a/youtube_dl/extractor/bambuser.py b/youtube_dl/extractor/bambuser.py index ccd31c4c7..de5d4faf3 100644 --- a/youtube_dl/extractor/bambuser.py +++ b/youtube_dl/extractor/bambuser.py @@ -59,6 +59,13 @@ class BambuserChannelIE(InfoExtractor): _VALID_URL = r'https?://bambuser\.com/channel/(?P<user>.*?)(?:/|#|\?|$)' # The maximum number we can get with each request _STEP = 50 + _TEST = { + 'url': 'http://bambuser.com/channel/pixelversity', + 'info_dict': { + 'title': 'pixelversity', + }, + 'playlist_mincount': 60, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -73,10 +80,10 @@ class BambuserChannelIE(InfoExtractor): req = compat_urllib_request.Request(req_url) # Without setting this header, we wouldn't get any result req.add_header('Referer', 'http://bambuser.com/channel/%s' % user) - info_json = self._download_webpage(req, user, - 'Downloading page %d' % i) - results = json.loads(info_json)['result'] - if len(results) == 0: + data = self._download_json( + req, user, 'Downloading page %d' % i) + results = data['result'] + if not results: break last_id = results[-1]['vid'] urls.extend(self.url_result(v['page'], 'Bambuser') for v in results) diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py index dcbbdef43..c569aa4d2 100644 --- a/youtube_dl/extractor/bandcamp.py +++ b/youtube_dl/extractor/bandcamp.py @@ -96,7 +96,7 @@ class BandcampAlbumIE(InfoExtractor): IE_NAME = 'Bandcamp:album' _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))' - _TEST = { + _TESTS = [{ 'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1', 'playlist': [ { @@ -118,7 +118,13 @@ class BandcampAlbumIE(InfoExtractor): 'playlistend': 2 }, 'skip': 'Bandcamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test' - } + }, { + 'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave', + 'info_dict': { + 'title': 'Hierophany of the Open Grave', + }, + 'playlist_mincount': 9, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py new file mode 100644 index 000000000..314e37f8b --- /dev/null +++ b/youtube_dl/extractor/beeg.py @@ -0,0 +1,65 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class BeegIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)' + _TEST = { + 'url': 'http://beeg.com/5416503', + 'md5': '634526ae978711f6b748fe0dd6c11f57', + 'info_dict': { + 'id': '5416503', + 'ext': 'mp4', + 'title': 'Sultry Striptease', + 'description': 'md5:6db3c6177972822aaba18652ff59c773', + 'categories': list, # NSFW + 'thumbnail': 're:https?://.*\.jpg$', + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + quality_arr = self._search_regex( + r'(?s)var\s+qualityArr\s*=\s*{\s*(.+?)\s*}', webpage, 'quality formats') + + formats = [{ + 'url': fmt[1], + 'format_id': fmt[0], + 'height': int(fmt[0][:-1]), + } for fmt in re.findall(r"'([^']+)'\s*:\s*'([^']+)'", quality_arr)] + + self._sort_formats(formats) + + title = self._html_search_regex( + r'<title>([^<]+)\s*-\s*beeg\.?</title>', webpage, 'title') + + description = self._html_search_regex( + r'<meta name="description" content="([^"]*)"', + webpage, 'description', fatal=False) + thumbnail = self._html_search_regex( + r'\'previewer.url\'\s*:\s*"([^"]*)"', + webpage, 'thumbnail', fatal=False) + + categories_str = self._html_search_regex( + r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False) + categories = ( + None if categories_str is None + else categories_str.split(',')) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'categories': categories, + 'formats': formats, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/blinkx.py b/youtube_dl/extractor/blinkx.py index 7d558e262..3e461e715 100644 --- a/youtube_dl/extractor/blinkx.py +++ b/youtube_dl/extractor/blinkx.py @@ -52,7 +52,7 @@ class BlinkxIE(InfoExtractor): 'height': int(m['h']), }) elif m['type'] == 'original': - duration = m['d'] + duration = float(m['d']) elif m['type'] == 'youtube': yt_id = m['link'] self.to_screen('Youtube video detected: %s' % yt_id) diff --git a/youtube_dl/extractor/bliptv.py b/youtube_dl/extractor/bliptv.py index acfc4ad73..57d17bea3 100644 --- a/youtube_dl/extractor/bliptv.py +++ b/youtube_dl/extractor/bliptv.py @@ -15,7 +15,7 @@ from ..utils import ( class BlipTVIE(SubtitlesInfoExtractor): - _VALID_URL = r'https?://(?:\w+\.)?blip\.tv/(?:(?:.+-|rss/flash/)(?P<id>\d+)|((?:play/|api\.swf#)(?P<lookup_id>[\da-zA-Z+]+)))' + _VALID_URL = r'https?://(?:\w+\.)?blip\.tv/(?:(?:.+-|rss/flash/)(?P<id>\d+)|((?:play/|api\.swf#)(?P<lookup_id>[\da-zA-Z+_]+)))' _TESTS = [ { @@ -49,6 +49,21 @@ class BlipTVIE(SubtitlesInfoExtractor): 'uploader_id': '792887', 'duration': 279, } + }, + { + # https://bugzilla.redhat.com/show_bug.cgi?id=967465 + 'url': 'http://a.blip.tv/api.swf#h6Uag5KbVwI', + 'md5': '314e87b1ebe7a48fcbfdd51b791ce5a6', + 'info_dict': { + 'id': '6573122', + 'ext': 'mov', + 'upload_date': '20130520', + 'description': 'Two hapless space marines argue over what to do when they realize they have an astronomically huge problem on their hands.', + 'title': 'Red vs. Blue Season 11 Trailer', + 'timestamp': 1369029609, + 'uploader': 'redvsblue', + 'uploader_id': '792887', + } } ] @@ -150,7 +165,7 @@ class BlipTVIE(SubtitlesInfoExtractor): class BlipTVUserIE(InfoExtractor): - _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$' + _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)(?!api\.swf)([^/]+)/*$' _PAGE_SIZE = 12 IE_NAME = 'blip.tv:user' diff --git a/youtube_dl/extractor/bloomberg.py b/youtube_dl/extractor/bloomberg.py index 25fb79e14..c51a97ce4 100644 --- a/youtube_dl/extractor/bloomberg.py +++ b/youtube_dl/extractor/bloomberg.py @@ -10,7 +10,7 @@ class BloombergIE(InfoExtractor): _TEST = { 'url': 'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html', - 'md5': '7bf08858ff7c203c870e8a6190e221e5', + # The md5 checksum changes 'info_dict': { 'id': 'qurhIVlJSB6hzkVi229d8g', 'ext': 'flv', @@ -31,8 +31,7 @@ class BloombergIE(InfoExtractor): return { 'id': name.split('-')[-1], 'title': title, - 'url': f4m_url, - 'ext': 'flv', + 'formats': self._extract_f4m_formats(f4m_url, name), 'description': self._og_search_description(webpage), 'thumbnail': self._og_search_thumbnail(webpage), } diff --git a/youtube_dl/extractor/br.py b/youtube_dl/extractor/br.py index 993360714..86f0c2861 100644 --- a/youtube_dl/extractor/br.py +++ b/youtube_dl/extractor/br.py @@ -7,12 +7,13 @@ from .common import InfoExtractor from ..utils import ( ExtractorError, int_or_none, + parse_duration, ) class BRIE(InfoExtractor): IE_DESC = 'Bayerischer Rundfunk Mediathek' - _VALID_URL = r'https?://(?:www\.)?br\.de/(?:[a-z0-9\-]+/)+(?P<id>[a-z0-9\-]+)\.html' + _VALID_URL = r'https?://(?:www\.)?br\.de/(?:[a-z0-9\-_]+/)+(?P<id>[a-z0-9\-_]+)\.html' _BASE_URL = 'http://www.br.de' _TESTS = [ @@ -22,8 +23,9 @@ class BRIE(InfoExtractor): 'info_dict': { 'id': '25e279aa-1ffd-40fd-9955-5325bd48a53a', 'ext': 'mp4', - 'title': 'Am 1. und 2. August in Oberammergau', - 'description': 'md5:dfd224e5aa6819bc1fcbb7826a932021', + 'title': 'Wenn das Traditions-Theater wackelt', + 'description': 'Heimatsound-Festival 2014: Wenn das Traditions-Theater wackelt', + 'duration': 34, } }, { @@ -34,6 +36,7 @@ class BRIE(InfoExtractor): 'ext': 'mp4', 'title': 'Über den Pass', 'description': 'Die Eroberung der Alpen: Über den Pass', + 'duration': 2588, } }, { @@ -44,6 +47,7 @@ class BRIE(InfoExtractor): 'ext': 'aac', 'title': '"Keine neuen Schulden im nächsten Jahr"', 'description': 'Haushaltsentwurf: "Keine neuen Schulden im nächsten Jahr"', + 'duration': 64, } }, { @@ -54,6 +58,7 @@ class BRIE(InfoExtractor): 'ext': 'mp4', 'title': 'Umweltbewusster Häuslebauer', 'description': 'Uwe Erdelt: Umweltbewusster Häuslebauer', + 'duration': 116, } }, { @@ -64,6 +69,7 @@ class BRIE(InfoExtractor): 'ext': 'mp4', 'title': 'Folge 1 - Metaphysik', 'description': 'Kant für Anfänger: Folge 1 - Metaphysik', + 'duration': 893, 'uploader': 'Eva Maria Steimle', 'upload_date': '20140117', } @@ -84,6 +90,7 @@ class BRIE(InfoExtractor): media = { 'id': xml_media.get('externalId'), 'title': xml_media.find('title').text, + 'duration': parse_duration(xml_media.find('duration').text), 'formats': self._extract_formats(xml_media.find('assets')), 'thumbnails': self._extract_thumbnails(xml_media.find('teaserImage/variants')), 'description': ' '.join(xml_media.find('shareTitle').text.splitlines()), diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 419951b62..294670386 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -154,12 +154,14 @@ class BrightcoveIE(InfoExtractor): def _extract_brightcove_urls(cls, webpage): """Return a list of all Brightcove URLs from the webpage """ - url_m = re.search(r'<meta\s+property="og:video"\s+content="(http://c.brightcove.com/[^"]+)"', webpage) + url_m = re.search( + r'<meta\s+property="og:video"\s+content="(https?://(?:secure|c)\.brightcove.com/[^"]+)"', + webpage) if url_m: url = unescapeHTML(url_m.group(1)) # Some sites don't add it, we can't download with this url, for example: # http://www.ktvu.com/videos/news/raw-video-caltrain-releases-video-of-man-almost/vCTZdY/ - if 'playerKey' in url: + if 'playerKey' in url or 'videoId' in url: return [url] matches = re.findall( @@ -188,9 +190,13 @@ class BrightcoveIE(InfoExtractor): referer = smuggled_data.get('Referer', url) return self._get_video_info( videoPlayer[0], query_str, query, referer=referer) - else: + elif 'playerKey' in query: player_key = query['playerKey'] return self._get_playlist_info(player_key[0]) + else: + raise ExtractorError( + 'Cannot find playerKey= variable. Did you forget quotes in a shell invocation?', + expected=True) def _get_video_info(self, video_id, query_str, query, referer=None): request_url = self._FEDERATED_URL_TEMPLATE % query_str @@ -202,6 +208,13 @@ class BrightcoveIE(InfoExtractor): req.add_header('Referer', referer) webpage = self._download_webpage(req, video_id) + error_msg = self._html_search_regex( + r"<h1>We're sorry.</h1>\s*<p>(.*?)</p>", webpage, + 'error message', default=None) + if error_msg is not None: + raise ExtractorError( + 'brightcove said: %s' % error_msg, expected=True) + self.report_extraction(video_id) info = self._search_regex(r'var experienceJSON = ({.*});', webpage, 'json') info = json.loads(info)['data'] diff --git a/youtube_dl/extractor/cbs.py b/youtube_dl/extractor/cbs.py index ac0315853..db48dc24f 100644 --- a/youtube_dl/extractor/cbs.py +++ b/youtube_dl/extractor/cbs.py @@ -1,24 +1,42 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor class CBSIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?cbs\.com/shows/[^/]+/video/(?P<id>[^/]+)/.*' + _VALID_URL = r'https?://(?:www\.)?cbs\.com/shows/[^/]+/(?:video|artist)/(?P<id>[^/]+)/.*' - _TEST = { - u'url': u'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/', - u'file': u'4JUVEwq3wUT7.flv', - u'info_dict': { - u'title': u'Connect Chat feat. Garth Brooks', - u'description': u'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!', - u'duration': 1495, + _TESTS = [{ + 'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/', + 'info_dict': { + 'id': '4JUVEwq3wUT7', + 'ext': 'flv', + 'title': 'Connect Chat feat. Garth Brooks', + 'description': 'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!', + 'duration': 1495, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + '_skip': 'Blocked outside the US', + }, { + 'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/', + 'info_dict': { + 'id': 'WWF_5KqY3PK1', + 'ext': 'flv', + 'title': 'Live on Letterman - St. Vincent', + 'description': 'Live On Letterman: St. Vincent in concert from New York\'s Ed Sullivan Theater on Tuesday, July 16, 2014.', + 'duration': 3221, }, - u'params': { + 'params': { # rtmp download - u'skip_download': True, + 'skip_download': True, }, - } + '_skip': 'Blocked outside the US', + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -26,5 +44,5 @@ class CBSIE(InfoExtractor): webpage = self._download_webpage(url, video_id) real_id = self._search_regex( r"video\.settings\.pid\s*=\s*'([^']+)';", - webpage, u'real video ID') + webpage, 'real video ID') return self.url_result(u'theplatform:%s' % real_id) diff --git a/youtube_dl/extractor/chilloutzone.py b/youtube_dl/extractor/chilloutzone.py index 02d5ba527..a62395d4b 100644 --- a/youtube_dl/extractor/chilloutzone.py +++ b/youtube_dl/extractor/chilloutzone.py @@ -42,7 +42,7 @@ class ChilloutzoneIE(InfoExtractor): 'id': '85523671', 'ext': 'mp4', 'title': 'The Sunday Times - Icons', - 'description': 'md5:3e1c0dc6047498d6728dcdaad0891762', + 'description': 'md5:a5f7ff82e2f7a9ed77473fe666954e84', 'uploader': 'Us', 'uploader_id': 'usfilms', 'upload_date': '20140131' diff --git a/youtube_dl/extractor/cliphunter.py b/youtube_dl/extractor/cliphunter.py index 58846e8e7..65c12136a 100644 --- a/youtube_dl/extractor/cliphunter.py +++ b/youtube_dl/extractor/cliphunter.py @@ -1,11 +1,13 @@ from __future__ import unicode_literals +import json import re from .common import InfoExtractor +from ..utils import int_or_none -translation_table = { +_translation_table = { 'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n', 'm': 'a', 'n': 'm', 'p': 'u', 'q': 't', 'r': 's', 'v': 'p', 'x': 'r', 'y': 'l', 'z': 'i', @@ -13,6 +15,10 @@ translation_table = { } +def _decode(s): + return ''.join(_translation_table.get(c, c) for c in s) + + class CliphunterIE(InfoExtractor): IE_NAME = 'cliphunter' @@ -22,10 +28,14 @@ class CliphunterIE(InfoExtractor): ''' _TEST = { 'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo', - 'file': '1012420.flv', - 'md5': '15e7740f30428abf70f4223478dc1225', + 'md5': 'a2ba71eebf523859fe527a61018f723e', 'info_dict': { + 'id': '1012420', + 'ext': 'mp4', 'title': 'Fun Jynx Maze solo', + 'thumbnail': 're:^https?://.*\.jpg$', + 'age_limit': 18, + 'duration': 1317, } } @@ -35,22 +45,55 @@ class CliphunterIE(InfoExtractor): webpage = self._download_webpage(url, video_id) + video_title = self._search_regex( + r'mediaTitle = "([^"]+)"', webpage, 'title') + pl_fiji = self._search_regex( r'pl_fiji = \'([^\']+)\'', webpage, 'video data') pl_c_qual = self._search_regex( r'pl_c_qual = "(.)"', webpage, 'video quality') - video_title = self._search_regex( - r'mediaTitle = "([^"]+)"', webpage, 'title') - - video_url = ''.join(translation_table.get(c, c) for c in pl_fiji) - + video_url = _decode(pl_fiji) formats = [{ 'url': video_url, - 'format_id': pl_c_qual, + 'format_id': 'default-%s' % pl_c_qual, }] + qualities_json = self._search_regex( + r'var pl_qualities\s*=\s*(.*?);\n', webpage, 'quality info') + qualities_data = json.loads(qualities_json) + + for i, t in enumerate( + re.findall(r"pl_fiji_([a-z0-9]+)\s*=\s*'([^']+')", webpage)): + quality_id, crypted_url = t + video_url = _decode(crypted_url) + f = { + 'format_id': quality_id, + 'url': video_url, + 'quality': i, + } + if quality_id in qualities_data: + qd = qualities_data[quality_id] + m = re.match( + r'''(?x)<b>(?P<width>[0-9]+)x(?P<height>[0-9]+)<\\/b> + \s*\(\s*(?P<tbr>[0-9]+)\s*kb\\/s''', qd) + if m: + f['width'] = int(m.group('width')) + f['height'] = int(m.group('height')) + f['tbr'] = int(m.group('tbr')) + formats.append(f) + self._sort_formats(formats) + + thumbnail = self._search_regex( + r"var\s+mov_thumb\s*=\s*'([^']+)';", + webpage, 'thumbnail', fatal=False) + duration = int_or_none(self._search_regex( + r'pl_dur\s*=\s*([0-9]+)', webpage, 'duration', fatal=False)) + return { 'id': video_id, 'title': video_title, 'formats': formats, + 'duration': duration, + 'age_limit': self._rta_search(webpage), + 'thumbnail': thumbnail, } diff --git a/youtube_dl/extractor/cnet.py b/youtube_dl/extractor/cnet.py index a94f42571..710d5009b 100644 --- a/youtube_dl/extractor/cnet.py +++ b/youtube_dl/extractor/cnet.py @@ -43,7 +43,11 @@ class CNETIE(InfoExtractor): raise ExtractorError('Cannot find video data') video_id = vdata['id'] - title = vdata['headline'] + title = vdata.get('headline') + if title is None: + title = vdata.get('title') + if title is None: + raise ExtractorError('Cannot find title!') description = vdata.get('dek') thumbnail = vdata.get('image', {}).get('path') author = vdata.get('author') diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py index 8af0abade..035046120 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -14,13 +14,13 @@ from ..utils import ( class ComedyCentralIE(MTVServicesInfoExtractor): - _VALID_URL = r'''(?x)https?://(?:www\.)?(comedycentral|cc)\.com/ - (video-clips|episodes|cc-studios|video-collections) + _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/ + (video-clips|episodes|cc-studios|video-collections|full-episodes) /(?P<title>.*)''' _FEED_URL = 'http://comedycentral.com/feeds/mrss/' _TEST = { - 'url': 'http://www.comedycentral.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother', + 'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother', 'md5': 'c4f48e9eda1b16dd10add0744344b6d8', 'info_dict': { 'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354', @@ -43,14 +43,14 @@ class ComedyCentralShowsIE(InfoExtractor): (?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/ ((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)| (?P<clip> - (?:(?:guests/[^/]+|videos|video-playlists|special-editions)/[^/]+/(?P<videotitle>[^/?#]+)) + (?:(?:guests/[^/]+|videos|video-playlists|special-editions|news-team/[^/]+)/[^/]+/(?P<videotitle>[^/?#]+)) |(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?)) |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)) )| (?P<interview> extended-interviews/(?P<interID>[0-9a-z]+)/(?:playlist_tds_extended_)?(?P<interview_title>.*?)(/.*?)?))) (?:[?#].*|$)''' - _TEST = { + _TESTS = [{ 'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart', 'md5': '4e2f5cb088a83cd8cdb7756132f9739d', 'info_dict': { @@ -61,7 +61,34 @@ class ComedyCentralShowsIE(InfoExtractor): 'uploader': 'thedailyshow', 'title': 'thedailyshow kristen-stewart part 1', } - } + }, { + 'url': 'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview', + 'only_matching': True, + }, { + 'url': 'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news', + 'only_matching': True, + }, { + 'url': 'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114', + 'only_matching': True, + }, { + 'url': 'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3', + 'only_matching': True, + }, { + 'url': 'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary', + 'only_matching': True, + }, { + 'url': 'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall', + 'only_matching': True, + }, { + 'url': 'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights', + 'only_matching': True, + }, { + 'url': 'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food', + 'only_matching': True, + }, { + 'url': 'http://thedailyshow.cc.com/news-team/michael-che/7wnfel/we-need-to-talk-about-israel', + 'only_matching': True, + }] _available_formats = ['3500', '2200', '1700', '1200', '750', '400'] @@ -185,6 +212,9 @@ class ComedyCentralShowsIE(InfoExtractor): 'ext': self._video_extensions.get(format, 'mp4'), 'height': h, 'width': w, + + 'format_note': 'HTTP 400 at the moment (patches welcome!)', + 'preference': -100, }) formats.append({ 'format_id': 'rtmp-%s' % format, diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index e68657314..929dd1e97 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import base64 import hashlib import json @@ -18,6 +20,7 @@ from ..utils import ( clean_html, compiled_regex_type, ExtractorError, + int_or_none, RegexNotFoundError, sanitize_filename, unescapeHTML, @@ -69,6 +72,7 @@ class InfoExtractor(object): * vcodec Name of the video codec in use * container Name of the container format * filesize The number of bytes, if known in advance + * filesize_approx An estimate for the number of bytes * player_url SWF Player URL (used for rtmpdump). * protocol The protocol that will be used for the actual download, lower-case. @@ -82,6 +86,12 @@ class InfoExtractor(object): format, irrespective of the file format. -1 for default (order by other properties), -2 or smaller for less than default. + * http_referer HTTP Referer header value to set. + * http_method HTTP method to use for the download. + * http_headers A dictionary of additional HTTP headers + to add to the request. + * http_post_data Additional data to send with a POST + request. url: Final video URL. ext: Video filename extension. format: The video format, defaults to ext (used for --get-format) @@ -106,7 +116,7 @@ class InfoExtractor(object): upload_date: Video upload date (YYYYMMDD). If not explicitly set, calculated from timestamp. uploader_id: Nickname or id of the video uploader. - location: Physical location of the video. + location: Physical location where the video was filmed. subtitles: The subtitle file contents as a dictionary in the format {language: subtitles}. duration: Length of the video in seconds, as an integer. @@ -194,17 +204,17 @@ class InfoExtractor(object): self.report_download_webpage(video_id) elif note is not False: if video_id is None: - self.to_screen(u'%s' % (note,)) + self.to_screen('%s' % (note,)) else: - self.to_screen(u'%s: %s' % (video_id, note)) + self.to_screen('%s: %s' % (video_id, note)) try: return self._downloader.urlopen(url_or_request) except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: if errnote is False: return False if errnote is None: - errnote = u'Unable to download webpage' - errmsg = u'%s: %s' % (errnote, compat_str(err)) + errnote = 'Unable to download webpage' + errmsg = '%s: %s' % (errnote, compat_str(err)) if fatal: raise ExtractorError(errmsg, sys.exc_info()[2], cause=err) else: @@ -241,7 +251,7 @@ class InfoExtractor(object): url = url_or_request.get_full_url() except AttributeError: url = url_or_request - self.to_screen(u'Dumping request to ' + url) + self.to_screen('Dumping request to ' + url) dump = base64.b64encode(webpage_bytes).decode('ascii') self._downloader.to_screen(dump) if self._downloader.params.get('write_pages', False): @@ -251,11 +261,11 @@ class InfoExtractor(object): url = url_or_request basen = '%s_%s' % (video_id, url) if len(basen) > 240: - h = u'___' + hashlib.md5(basen.encode('utf-8')).hexdigest() + h = '___' + hashlib.md5(basen.encode('utf-8')).hexdigest() basen = basen[:240 - len(h)] + h raw_filename = basen + '.dump' filename = sanitize_filename(raw_filename, restricted=True) - self.to_screen(u'Saving request to ' + filename) + self.to_screen('Saving request to ' + filename) with open(filename, 'wb') as outf: outf.write(webpage_bytes) @@ -264,14 +274,14 @@ class InfoExtractor(object): except LookupError: content = webpage_bytes.decode('utf-8', 'replace') - if (u'<title>Access to this site is blocked</title>' in content and - u'Websense' in content[:512]): - msg = u'Access to this webpage has been blocked by Websense filtering software in your network.' + if ('<title>Access to this site is blocked</title>' in content and + 'Websense' in content[:512]): + msg = 'Access to this webpage has been blocked by Websense filtering software in your network.' blocked_iframe = self._html_search_regex( r'<iframe src="([^"]+)"', content, - u'Websense information URL', default=None) + 'Websense information URL', default=None) if blocked_iframe: - msg += u' Visit %s for more details' % blocked_iframe + msg += ' Visit %s for more details' % blocked_iframe raise ExtractorError(msg, expected=True) return (content, urlh) @@ -286,7 +296,7 @@ class InfoExtractor(object): return content def _download_xml(self, url_or_request, video_id, - note=u'Downloading XML', errnote=u'Unable to download XML', + note='Downloading XML', errnote='Unable to download XML', transform_source=None, fatal=True): """Return the xml as an xml.etree.ElementTree.Element""" xml_string = self._download_webpage( @@ -298,10 +308,14 @@ class InfoExtractor(object): return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8')) def _download_json(self, url_or_request, video_id, - note=u'Downloading JSON metadata', - errnote=u'Unable to download JSON metadata', - transform_source=None): - json_string = self._download_webpage(url_or_request, video_id, note, errnote) + note='Downloading JSON metadata', + errnote='Unable to download JSON metadata', + transform_source=None, + fatal=True): + json_string = self._download_webpage( + url_or_request, video_id, note, errnote, fatal=fatal) + if (not fatal) and json_string is False: + return None if transform_source: json_string = transform_source(json_string) try: @@ -310,29 +324,29 @@ class InfoExtractor(object): raise ExtractorError('Failed to download JSON', cause=ve) def report_warning(self, msg, video_id=None): - idstr = u'' if video_id is None else u'%s: ' % video_id + idstr = '' if video_id is None else '%s: ' % video_id self._downloader.report_warning( - u'[%s] %s%s' % (self.IE_NAME, idstr, msg)) + '[%s] %s%s' % (self.IE_NAME, idstr, msg)) def to_screen(self, msg): """Print msg to screen, prefixing it with '[ie_name]'""" - self._downloader.to_screen(u'[%s] %s' % (self.IE_NAME, msg)) + self._downloader.to_screen('[%s] %s' % (self.IE_NAME, msg)) def report_extraction(self, id_or_name): """Report information extraction.""" - self.to_screen(u'%s: Extracting information' % id_or_name) + self.to_screen('%s: Extracting information' % id_or_name) def report_download_webpage(self, video_id): """Report webpage download.""" - self.to_screen(u'%s: Downloading webpage' % video_id) + self.to_screen('%s: Downloading webpage' % video_id) def report_age_confirmation(self): """Report attempt to confirm age.""" - self.to_screen(u'Confirming age') + self.to_screen('Confirming age') def report_login(self): """Report attempt to log in.""" - self.to_screen(u'Logging in') + self.to_screen('Logging in') #Methods for following #608 @staticmethod @@ -368,10 +382,11 @@ class InfoExtractor(object): else: for p in pattern: mobj = re.search(p, string, flags) - if mobj: break + if mobj: + break if os.name != 'nt' and sys.stderr.isatty(): - _name = u'\033[0;34m%s\033[0m' % name + _name = '\033[0;34m%s\033[0m' % name else: _name = name @@ -381,10 +396,10 @@ class InfoExtractor(object): elif default is not _NO_DEFAULT: return default elif fatal: - raise RegexNotFoundError(u'Unable to extract %s' % _name) + raise RegexNotFoundError('Unable to extract %s' % _name) else: - self._downloader.report_warning(u'unable to extract %s; ' - u'please report this issue on http://yt-dl.org/bug' % _name) + self._downloader.report_warning('unable to extract %s; ' + 'please report this issue on http://yt-dl.org/bug' % _name) return None def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0): @@ -423,10 +438,26 @@ class InfoExtractor(object): else: raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) except (IOError, netrc.NetrcParseError) as err: - self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err)) + self._downloader.report_warning('parsing .netrc: %s' % compat_str(err)) return (username, password) + def _get_tfa_info(self): + """ + Get the two-factor authentication info + TODO - asking the user will be required for sms/phone verify + currently just uses the command line option + If there's no info available, return None + """ + if self._downloader is None: + return None + downloader_params = self._downloader.params + + if downloader_params.get('twofactor', None) is not None: + return downloader_params['twofactor'] + + return None + # Helper functions for extracting OpenGraph info @staticmethod def _og_regexes(prop): @@ -447,7 +478,7 @@ class InfoExtractor(object): return unescapeHTML(escaped) def _og_search_thumbnail(self, html, **kargs): - return self._og_search_property('image', html, u'thumbnail url', fatal=False, **kargs) + return self._og_search_property('image', html, 'thumbnail url', fatal=False, **kargs) def _og_search_description(self, html, **kargs): return self._og_search_property('description', html, fatal=False, **kargs) @@ -456,8 +487,9 @@ class InfoExtractor(object): return self._og_search_property('title', html, **kargs) def _og_search_video_url(self, html, name='video url', secure=True, **kargs): - regexes = self._og_regexes('video') - if secure: regexes = self._og_regexes('video:secure_url') + regexes + regexes = self._og_regexes('video') + self._og_regexes('video:url') + if secure: + regexes = self._og_regexes('video:secure_url') + regexes return self._html_search_regex(regexes, html, name, **kargs) def _og_search_url(self, html, **kargs): @@ -468,7 +500,7 @@ class InfoExtractor(object): display_name = name return self._html_search_regex( r'''(?ix)<meta - (?=[^>]+(?:itemprop|name|property)=["\']%s["\']) + (?=[^>]+(?:itemprop|name|property)=["\']?%s["\']?) [^>]+content=["\']([^"\']+)["\']''' % re.escape(name), html, display_name, fatal=fatal, **kwargs) @@ -505,7 +537,7 @@ class InfoExtractor(object): def _sort_formats(self, formats): if not formats: - raise ExtractorError(u'No video formats found') + raise ExtractorError('No video formats found') def _formats_key(f): # TODO remove the following workaround @@ -525,9 +557,9 @@ class InfoExtractor(object): if f.get('vcodec') == 'none': # audio only if self._downloader.params.get('prefer_free_formats'): - ORDER = [u'aac', u'mp3', u'm4a', u'webm', u'ogg', u'opus'] + ORDER = ['aac', 'mp3', 'm4a', 'webm', 'ogg', 'opus'] else: - ORDER = [u'webm', u'opus', u'ogg', u'mp3', u'aac', u'm4a'] + ORDER = ['webm', 'opus', 'ogg', 'mp3', 'aac', 'm4a'] ext_preference = 0 try: audio_ext_preference = ORDER.index(f['ext']) @@ -535,9 +567,9 @@ class InfoExtractor(object): audio_ext_preference = -1 else: if self._downloader.params.get('prefer_free_formats'): - ORDER = [u'flv', u'mp4', u'webm'] + ORDER = ['flv', 'mp4', 'webm'] else: - ORDER = [u'webm', u'flv', u'mp4'] + ORDER = ['webm', 'flv', 'mp4'] try: ext_preference = ORDER.index(f['ext']) except ValueError: @@ -555,6 +587,7 @@ class InfoExtractor(object): f.get('abr') if f.get('abr') is not None else -1, audio_ext_preference, f.get('filesize') if f.get('filesize') is not None else -1, + f.get('filesize_approx') if f.get('filesize_approx') is not None else -1, f.get('format_id'), ) formats.sort(key=_formats_key) @@ -578,11 +611,88 @@ class InfoExtractor(object): def _sleep(self, timeout, video_id, msg_template=None): if msg_template is None: - msg_template = u'%(video_id)s: Waiting for %(timeout)s seconds' + msg_template = '%(video_id)s: Waiting for %(timeout)s seconds' msg = msg_template % {'video_id': video_id, 'timeout': timeout} self.to_screen(msg) time.sleep(timeout) + def _extract_f4m_formats(self, manifest_url, video_id): + manifest = self._download_xml( + manifest_url, video_id, 'Downloading f4m manifest', + 'Unable to download f4m manifest') + + formats = [] + media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media') + for i, media_el in enumerate(media_nodes): + tbr = int_or_none(media_el.attrib.get('bitrate')) + format_id = 'f4m-%d' % (i if tbr is None else tbr) + formats.append({ + 'format_id': format_id, + 'url': manifest_url, + 'ext': 'flv', + 'tbr': tbr, + 'width': int_or_none(media_el.attrib.get('width')), + 'height': int_or_none(media_el.attrib.get('height')), + }) + self._sort_formats(formats) + + return formats + + def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None): + formats = [{ + 'format_id': 'm3u8-meta', + 'url': m3u8_url, + 'ext': ext, + 'protocol': 'm3u8', + 'preference': -1, + 'resolution': 'multiple', + 'format_note': 'Quality selection URL', + }] + + m3u8_doc = self._download_webpage(m3u8_url, video_id) + last_info = None + kv_rex = re.compile( + r'(?P<key>[a-zA-Z_-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)') + for line in m3u8_doc.splitlines(): + if line.startswith('#EXT-X-STREAM-INF:'): + last_info = {} + for m in kv_rex.finditer(line): + v = m.group('val') + if v.startswith('"'): + v = v[1:-1] + last_info[m.group('key')] = v + elif line.startswith('#') or not line.strip(): + continue + else: + if last_info is None: + formats.append({'url': line}) + continue + tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000) + + f = { + 'format_id': 'm3u8-%d' % (tbr if tbr else len(formats)), + 'url': line.strip(), + 'tbr': tbr, + 'ext': ext, + } + codecs = last_info.get('CODECS') + if codecs: + # TODO: looks like video codec is not always necessarily goes first + va_codecs = codecs.split(',') + if va_codecs[0]: + f['vcodec'] = va_codecs[0].partition('.')[0] + if len(va_codecs) > 1 and va_codecs[1]: + f['acodec'] = va_codecs[1].partition('.')[0] + resolution = last_info.get('RESOLUTION') + if resolution: + width_str, height_str = resolution.split('x') + f['width'] = int(width_str) + f['height'] = int(height_str) + formats.append(f) + last_info = {} + self._sort_formats(formats) + return formats + class SearchInfoExtractor(InfoExtractor): """ @@ -602,7 +712,7 @@ class SearchInfoExtractor(InfoExtractor): def _real_extract(self, query): mobj = re.match(self._make_valid_url(), query) if mobj is None: - raise ExtractorError(u'Invalid search query "%s"' % query) + raise ExtractorError('Invalid search query "%s"' % query) prefix = mobj.group('prefix') query = mobj.group('query') @@ -613,9 +723,9 @@ class SearchInfoExtractor(InfoExtractor): else: n = int(prefix) if n <= 0: - raise ExtractorError(u'invalid download number %s for query "%s"' % (n, query)) + raise ExtractorError('invalid download number %s for query "%s"' % (n, query)) elif n > self._MAX_RESULTS: - self._downloader.report_warning(u'%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n)) + self._downloader.report_warning('%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n)) n = self._MAX_RESULTS return self._get_n_results(query, n) diff --git a/youtube_dl/extractor/cracked.py b/youtube_dl/extractor/cracked.py new file mode 100644 index 000000000..74b880ffc --- /dev/null +++ b/youtube_dl/extractor/cracked.py @@ -0,0 +1,65 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_iso8601, + str_to_int, +) + + +class CrackedIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?cracked\.com/video_(?P<id>\d+)_[\da-z-]+\.html' + _TEST = { + 'url': 'http://www.cracked.com/video_19006_4-plot-holes-you-didnt-notice-in-your-favorite-movies.html', + 'md5': '4b29a5eeec292cd5eca6388c7558db9e', + 'info_dict': { + 'id': '19006', + 'ext': 'mp4', + 'title': '4 Plot Holes You Didn\'t Notice in Your Favorite Movies', + 'description': 'md5:3b909e752661db86007d10e5ec2df769', + 'timestamp': 1405659600, + 'upload_date': '20140718', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex( + [r'var\s+CK_vidSrc\s*=\s*"([^"]+)"', r'<video\s+src="([^"]+)"'], webpage, 'video URL') + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + + timestamp = self._html_search_regex(r'<time datetime="([^"]+)"', webpage, 'upload date', fatal=False) + if timestamp: + timestamp = parse_iso8601(timestamp[:-6]) + + view_count = str_to_int(self._html_search_regex( + r'<span class="views" id="viewCounts">([\d,\.]+) Views</span>', webpage, 'view count', fatal=False)) + comment_count = str_to_int(self._html_search_regex( + r'<span id="commentCounts">([\d,\.]+)</span>', webpage, 'comment count', fatal=False)) + + m = re.search(r'_(?P<width>\d+)X(?P<height>\d+)\.mp4$', video_url) + if m: + width = int(m.group('width')) + height = int(m.group('height')) + else: + width = height = None + + return { + 'id': video_id, + 'url':video_url, + 'title': title, + 'description': description, + 'timestamp': timestamp, + 'view_count': view_count, + 'comment_count': comment_count, + 'height': height, + 'width': width, + }
\ No newline at end of file diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 026a9177e..4903764f7 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -5,6 +5,7 @@ import re import json import base64 import zlib +import xml.etree.ElementTree from hashlib import sha1 from math import pow, sqrt, floor @@ -17,6 +18,7 @@ from ..utils import ( intlist_to_bytes, unified_strdate, clean_html, + urlencode_postdata, ) from ..aes import ( aes_cbc_decrypt, @@ -51,6 +53,26 @@ class CrunchyrollIE(InfoExtractor): '1080': ('80', '108'), } + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + self.report_login() + login_url = 'https://www.crunchyroll.com/?a=formhandler' + data = urlencode_postdata({ + 'formname': 'RpcApiUser_Login', + 'name': username, + 'password': password, + }) + login_request = compat_urllib_request.Request(login_url, data) + login_request.add_header('Content-Type', 'application/x-www-form-urlencoded') + self._download_webpage(login_request, None, False, 'Wrong login info') + + + def _real_initialize(self): + self._login() + + def _decrypt_subtitles(self, data, iv, id): data = bytes_to_intlist(data) iv = bytes_to_intlist(iv) @@ -97,6 +119,75 @@ class CrunchyrollIE(InfoExtractor): output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text) return output + def _convert_subtitles_to_ass(self, subtitles): + output = '' + + def ass_bool(strvalue): + assvalue = '0' + if strvalue == '1': + assvalue = '-1' + return assvalue + + sub_root = xml.etree.ElementTree.fromstring(subtitles) + if not sub_root: + return output + + output = '[Script Info]\n' + output += 'Title: %s\n' % sub_root.attrib["title"] + output += 'ScriptType: v4.00+\n' + output += 'WrapStyle: %s\n' % sub_root.attrib["wrap_style"] + output += 'PlayResX: %s\n' % sub_root.attrib["play_res_x"] + output += 'PlayResY: %s\n' % sub_root.attrib["play_res_y"] + output += """ScaledBorderAndShadow: yes + +[V4+ Styles] +Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding +""" + for style in sub_root.findall('./styles/style'): + output += 'Style: ' + style.attrib["name"] + output += ',' + style.attrib["font_name"] + output += ',' + style.attrib["font_size"] + output += ',' + style.attrib["primary_colour"] + output += ',' + style.attrib["secondary_colour"] + output += ',' + style.attrib["outline_colour"] + output += ',' + style.attrib["back_colour"] + output += ',' + ass_bool(style.attrib["bold"]) + output += ',' + ass_bool(style.attrib["italic"]) + output += ',' + ass_bool(style.attrib["underline"]) + output += ',' + ass_bool(style.attrib["strikeout"]) + output += ',' + style.attrib["scale_x"] + output += ',' + style.attrib["scale_y"] + output += ',' + style.attrib["spacing"] + output += ',' + style.attrib["angle"] + output += ',' + style.attrib["border_style"] + output += ',' + style.attrib["outline"] + output += ',' + style.attrib["shadow"] + output += ',' + style.attrib["alignment"] + output += ',' + style.attrib["margin_l"] + output += ',' + style.attrib["margin_r"] + output += ',' + style.attrib["margin_v"] + output += ',' + style.attrib["encoding"] + output += '\n' + + output += """ +[Events] +Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text +""" + for event in sub_root.findall('./events/event'): + output += 'Dialogue: 0' + output += ',' + event.attrib["start"] + output += ',' + event.attrib["end"] + output += ',' + event.attrib["style"] + output += ',' + event.attrib["name"] + output += ',' + event.attrib["margin_l"] + output += ',' + event.attrib["margin_r"] + output += ',' + event.attrib["margin_v"] + output += ',' + event.attrib["effect"] + output += ',' + event.attrib["text"] + output += '\n' + + return output + def _real_extract(self,url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('video_id') @@ -158,6 +249,7 @@ class CrunchyrollIE(InfoExtractor): }) subtitles = {} + sub_format = self._downloader.params.get('subtitlesformat', 'srt') for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage): sub_page = self._download_webpage('http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id='+sub_id,\ video_id, note='Downloading subtitles for '+sub_name) @@ -174,7 +266,10 @@ class CrunchyrollIE(InfoExtractor): lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False) if not lang_code: continue - subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle) + if sub_format == 'ass': + subtitles[lang_code] = self._convert_subtitles_to_ass(subtitle) + else: + subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle) return { 'id': video_id, diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index b6552c542..541106684 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -34,6 +34,13 @@ class CSpanIE(InfoExtractor): 'title': 'International Health Care Models', 'description': 'md5:7a985a2d595dba00af3d9c9f0783c967', } + }, { + 'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall', + 'info_dict': { + 'id': '342759', + 'title': 'General Motors Ignition Switch Recall', + }, + 'playlist_duration_sum': 14855, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 5d0bfe454..66a8f16d9 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -1,3 +1,6 @@ +#coding: utf-8 +from __future__ import unicode_literals + import re import json import itertools @@ -28,51 +31,53 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): """Information Extractor for Dailymotion""" _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?video/(?P<id>[^/?_]+)' - IE_NAME = u'dailymotion' + IE_NAME = 'dailymotion' _FORMATS = [ - (u'stream_h264_ld_url', u'ld'), - (u'stream_h264_url', u'standard'), - (u'stream_h264_hq_url', u'hq'), - (u'stream_h264_hd_url', u'hd'), - (u'stream_h264_hd1080_url', u'hd180'), + ('stream_h264_ld_url', 'ld'), + ('stream_h264_url', 'standard'), + ('stream_h264_hq_url', 'hq'), + ('stream_h264_hd_url', 'hd'), + ('stream_h264_hd1080_url', 'hd180'), ] _TESTS = [ { - u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech', - u'file': u'x33vw9.mp4', - u'md5': u'392c4b85a60a90dc4792da41ce3144eb', - u'info_dict': { - u"uploader": u"Amphora Alex and Van .", - u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\"" + 'url': 'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech', + 'md5': '392c4b85a60a90dc4792da41ce3144eb', + 'info_dict': { + 'id': 'x33vw9', + 'ext': 'mp4', + 'uploader': 'Amphora Alex and Van .', + 'title': 'Tutoriel de Youtubeur"DL DES VIDEO DE YOUTUBE"', } }, # Vevo video { - u'url': u'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi', - u'file': u'USUV71301934.mp4', - u'info_dict': { - u'title': u'Roar (Official)', - u'uploader': u'Katy Perry', - u'upload_date': u'20130905', + 'url': 'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi', + 'info_dict': { + 'title': 'Roar (Official)', + 'id': 'USUV71301934', + 'ext': 'mp4', + 'uploader': 'Katy Perry', + 'upload_date': '20130905', }, - u'params': { - u'skip_download': True, + 'params': { + 'skip_download': True, }, - u'skip': u'VEVO is only available in some countries', + 'skip': 'VEVO is only available in some countries', }, # age-restricted video { - u'url': u'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband', - u'file': u'xyh2zz.mp4', - u'md5': u'0d667a7b9cebecc3c89ee93099c4159d', - u'info_dict': { - u'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]', - u'uploader': 'HotWaves1012', - u'age_limit': 18, + 'url': 'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband', + 'md5': '0d667a7b9cebecc3c89ee93099c4159d', + 'info_dict': { + 'id': 'xyh2zz', + 'ext': 'mp4', + 'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]', + 'uploader': 'HotWaves1012', + 'age_limit': 18, } - } ] @@ -97,8 +102,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): webpage) if m_vevo is not None: vevo_id = m_vevo.group('id') - self.to_screen(u'Vevo video detected: %s' % vevo_id) - return self.url_result(u'vevo:%s' % vevo_id, ie='Vevo') + self.to_screen('Vevo video detected: %s' % vevo_id) + return self.url_result('vevo:%s' % vevo_id, ie='Vevo') age_limit = self._rta_search(webpage) @@ -109,7 +114,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): embed_url = 'http://www.dailymotion.com/embed/video/%s' % video_id embed_page = self._download_webpage(embed_url, video_id, - u'Downloading embed page') + 'Downloading embed page') info = self._search_regex(r'var info = ({.*?}),$', embed_page, 'video info', flags=re.MULTILINE) info = json.loads(info) @@ -134,7 +139,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): 'height': height, }) if not formats: - raise ExtractorError(u'Unable to extract video URL') + raise ExtractorError('Unable to extract video URL') # subtitles video_subtitles = self.extract_subtitles(video_id, webpage) @@ -143,7 +148,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): return view_count = self._search_regex( - r'video_views_count[^>]+>\s+([\d\.,]+)', webpage, u'view count', fatal=False) + r'video_views_count[^>]+>\s+([\d\.,]+)', webpage, 'view count', fatal=False) if view_count is not None: view_count = str_to_int(view_count) @@ -165,28 +170,35 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id, video_id, note=False) except ExtractorError as err: - self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err)) + self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err)) return {} info = json.loads(sub_list) if (info['total'] > 0): sub_lang_list = dict((l['language'], l['url']) for l in info['list']) return sub_lang_list - self._downloader.report_warning(u'video doesn\'t have subtitles') + self._downloader.report_warning('video doesn\'t have subtitles') return {} class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): - IE_NAME = u'dailymotion:playlist' + IE_NAME = 'dailymotion:playlist' _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/' _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"' _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s' + _TESTS = [{ + 'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q', + 'info_dict': { + 'title': 'SPORT', + }, + 'playlist_mincount': 20, + }] def _extract_entries(self, id): video_ids = [] for pagenum in itertools.count(1): request = self._build_request(self._PAGE_TEMPLATE % (id, pagenum)) webpage = self._download_webpage(request, - id, u'Downloading page %s' % pagenum) + id, 'Downloading page %s' % pagenum) video_ids.extend(re.findall(r'data-xid="(.+?)"', webpage)) @@ -209,9 +221,17 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): class DailymotionUserIE(DailymotionPlaylistIE): - IE_NAME = u'dailymotion:user' + IE_NAME = 'dailymotion:user' _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)' _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s' + _TESTS = [{ + 'url': 'https://www.dailymotion.com/user/nqtv', + 'info_dict': { + 'id': 'nqtv', + 'title': 'Rémi Gaillard', + }, + 'playlist_mincount': 100, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -219,7 +239,7 @@ class DailymotionUserIE(DailymotionPlaylistIE): webpage = self._download_webpage(url, user) full_user = unescapeHTML(self._html_search_regex( r'<a class="nav-image" title="([^"]+)" href="/%s">' % re.escape(user), - webpage, u'user', flags=re.DOTALL)) + webpage, 'user')) return { '_type': 'playlist', diff --git a/youtube_dl/extractor/dbtv.py b/youtube_dl/extractor/dbtv.py new file mode 100644 index 000000000..1d3e2ff08 --- /dev/null +++ b/youtube_dl/extractor/dbtv.py @@ -0,0 +1,74 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + float_or_none, + int_or_none, + clean_html, +) + + +class DBTVIE(InfoExtractor): + _VALID_URL = r'http://dbtv\.no/(?P<id>[0-9]+)#(?P<display_id>.+)' + _TEST = { + 'url': 'http://dbtv.no/3649835190001#Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen', + 'md5': 'b89953ed25dacb6edb3ef6c6f430f8bc', + 'info_dict': { + 'id': '33100', + 'display_id': 'Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen', + 'ext': 'mp4', + 'title': 'Skulle teste ut fornøyelsespark, men kollegaen var bare opptatt av bikinikroppen', + 'description': 'md5:1504a54606c4dde3e4e61fc97aa857e0', + 'thumbnail': 're:https?://.*\.jpg$', + 'timestamp': 1404039863.438, + 'upload_date': '20140629', + 'duration': 69.544, + 'view_count': int, + 'categories': list, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + data = self._download_json( + 'http://api.dbtv.no/discovery/%s' % video_id, display_id) + + video = data['playlist'][0] + + formats = [{ + 'url': f['URL'], + 'vcodec': f.get('container'), + 'width': int_or_none(f.get('width')), + 'height': int_or_none(f.get('height')), + 'vbr': float_or_none(f.get('rate'), 1000), + 'filesize': int_or_none(f.get('size')), + } for f in video['renditions'] if 'URL' in f] + + if not formats: + for url_key, format_id in [('URL', 'mp4'), ('HLSURL', 'hls')]: + if url_key in video: + formats.append({ + 'url': video[url_key], + 'format_id': format_id, + }) + + self._sort_formats(formats) + + return { + 'id': video['id'], + 'display_id': display_id, + 'title': video['title'], + 'description': clean_html(video['desc']), + 'thumbnail': video.get('splash') or video.get('thumb'), + 'timestamp': float_or_none(video.get('publishedAt'), 1000), + 'duration': float_or_none(video.get('length'), 1000), + 'view_count': int_or_none(video.get('views')), + 'categories': video.get('tags'), + 'formats': formats, + } diff --git a/youtube_dl/extractor/dfb.py b/youtube_dl/extractor/dfb.py new file mode 100644 index 000000000..8049779b0 --- /dev/null +++ b/youtube_dl/extractor/dfb.py @@ -0,0 +1,44 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class DFBIE(InfoExtractor): + IE_NAME = 'tv.dfb.de' + _VALID_URL = r'https?://tv\.dfb\.de/video/[^/]+/(?P<id>\d+)' + + _TEST = { + 'url': 'http://tv.dfb.de/video/highlights-des-empfangs-in-berlin/9070/', + # The md5 is different each time + 'info_dict': { + 'id': '9070', + 'ext': 'flv', + 'title': 'Highlights des Empfangs in Berlin', + 'upload_date': '20140716', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + player_info = self._download_xml( + 'http://tv.dfb.de/server/hd_video.php?play=%s' % video_id, + video_id) + video_info = player_info.find('video') + + f4m_info = self._download_xml(self._proto_relative_url(video_info.find('url').text.strip()), video_id) + token_el = f4m_info.find('token') + manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + '&hdcore=3.2.0' + + return { + 'id': video_id, + 'title': video_info.find('title').text, + 'url': manifest_url, + 'ext': 'flv', + 'thumbnail': self._og_search_thumbnail(webpage), + 'upload_date': ''.join(video_info.find('time_date').text.split('.')[::-1]), + } diff --git a/youtube_dl/extractor/dropbox.py b/youtube_dl/extractor/dropbox.py index 41208c976..1e1763abf 100644 --- a/youtube_dl/extractor/dropbox.py +++ b/youtube_dl/extractor/dropbox.py @@ -5,25 +5,28 @@ import os.path import re from .common import InfoExtractor +from ..utils import compat_urllib_parse_unquote class DropboxIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?dropbox[.]com/s/(?P<id>[a-zA-Z0-9]{15})/(?P<title>[^?#]*)' _TEST = { - 'url': 'https://www.dropbox.com/s/0qr9sai2veej4f8/THE_DOCTOR_GAMES.mp4', - 'md5': '8ae17c51172fb7f93bdd6a214cc8c896', + 'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4?dl=0', 'info_dict': { - 'id': '0qr9sai2veej4f8', + 'id': 'nelirfsxnmcfbfh', 'ext': 'mp4', - 'title': 'THE_DOCTOR_GAMES' + 'title': 'youtube-dl test video \'ä"BaW_jenozKc' } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - title = os.path.splitext(mobj.group('title'))[0] - video_url = url + '?dl=1' + fn = compat_urllib_parse_unquote(mobj.group('title')) + title = os.path.splitext(fn)[0] + video_url = ( + re.sub(r'[?&]dl=0', '', url) + + ('?' if '?' in url else '&') + 'dl=1') return { 'id': video_id, diff --git a/youtube_dl/extractor/drtuber.py b/youtube_dl/extractor/drtuber.py new file mode 100644 index 000000000..d5bfd7f22 --- /dev/null +++ b/youtube_dl/extractor/drtuber.py @@ -0,0 +1,70 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import str_to_int + + +class DrTuberIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<display_id>[\w-]+)' + _TEST = { + 'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf', + 'md5': '93e680cf2536ad0dfb7e74d94a89facd', + 'info_dict': { + 'id': '1740434', + 'display_id': 'hot-perky-blonde-naked-golf', + 'ext': 'mp4', + 'title': 'Hot Perky Blonde Naked Golf', + 'like_count': int, + 'dislike_count': int, + 'comment_count': int, + 'categories': list, # NSFW + 'thumbnail': 're:https?://.*\.jpg$', + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + video_url = self._html_search_regex( + r'<source src="([^"]+)"', webpage, 'video URL') + + title = self._html_search_regex( + r'<title>([^<]+)\s*-\s*Free', webpage, 'title') + + thumbnail = self._html_search_regex( + r'poster="([^"]+)"', + webpage, 'thumbnail', fatal=False) + + like_count = str_to_int(self._html_search_regex( + r'<span id="rate_likes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>', + webpage, 'like count', fatal=False)) + dislike_count = str_to_int(self._html_search_regex( + r'<span id="rate_dislikes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>', + webpage, 'like count', fatal=False)) + comment_count = str_to_int(self._html_search_regex( + r'<span class="comments_count">([\d,\.]+)</span>', + webpage, 'comment count', fatal=False)) + + cats_str = self._html_search_regex( + r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False) + categories = None if cats_str is None else cats_str.split(' ') + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'like_count': like_count, + 'dislike_count': dislike_count, + 'comment_count': comment_count, + 'categories': categories, + 'age_limit': self._rta_search(webpage), + } diff --git a/youtube_dl/extractor/dump.py b/youtube_dl/extractor/dump.py new file mode 100644 index 000000000..6b651778a --- /dev/null +++ b/youtube_dl/extractor/dump.py @@ -0,0 +1,39 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class DumpIE(InfoExtractor): + _VALID_URL = r'^https?://(?:www\.)?dump\.com/(?P<id>[a-zA-Z0-9]+)/' + + _TEST = { + 'url': 'http://www.dump.com/oneus/', + 'md5': 'ad71704d1e67dfd9e81e3e8b42d69d99', + 'info_dict': { + 'id': 'oneus', + 'ext': 'flv', + 'title': "He's one of us.", + 'thumbnail': 're:^https?://.*\.jpg$', + }, + } + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url) + video_id = m.group('id') + + webpage = self._download_webpage(url, video_id) + video_url = self._search_regex( + r's1.addVariable\("file",\s*"([^"]+)"', webpage, 'video URL') + + thumb = self._og_search_thumbnail(webpage) + title = self._search_regex(r'<b>([^"]+)</b>', webpage, 'title') + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'thumbnail': thumb, + } diff --git a/youtube_dl/extractor/ebaumsworld.py b/youtube_dl/extractor/ebaumsworld.py index 877113d63..63c2549d3 100644 --- a/youtube_dl/extractor/ebaumsworld.py +++ b/youtube_dl/extractor/ebaumsworld.py @@ -1,19 +1,21 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor -from ..utils import determine_ext class EbaumsWorldIE(InfoExtractor): _VALID_URL = r'https?://www\.ebaumsworld\.com/video/watch/(?P<id>\d+)' _TEST = { - u'url': u'http://www.ebaumsworld.com/video/watch/83367677/', - u'file': u'83367677.mp4', - u'info_dict': { - u'title': u'A Giant Python Opens The Door', - u'description': u'This is how nightmares start...', - u'uploader': u'jihadpizza', + 'url': 'http://www.ebaumsworld.com/video/watch/83367677/', + 'info_dict': { + 'id': '83367677', + 'ext': 'mp4', + 'title': 'A Giant Python Opens The Door', + 'description': 'This is how nightmares start...', + 'uploader': 'jihadpizza', }, } @@ -28,7 +30,6 @@ class EbaumsWorldIE(InfoExtractor): 'id': video_id, 'title': config.find('title').text, 'url': video_url, - 'ext': determine_ext(video_url), 'description': config.find('description').text, 'thumbnail': config.find('image').text, 'uploader': config.find('username').text, diff --git a/youtube_dl/extractor/eighttracks.py b/youtube_dl/extractor/eighttracks.py index 88f5526b8..c1b4c729e 100644 --- a/youtube_dl/extractor/eighttracks.py +++ b/youtube_dl/extractor/eighttracks.py @@ -1,10 +1,13 @@ +# coding: utf-8 +from __future__ import unicode_literals + import json import random import re from .common import InfoExtractor from ..utils import ( - ExtractorError, + compat_str, ) @@ -12,86 +15,98 @@ class EightTracksIE(InfoExtractor): IE_NAME = '8tracks' _VALID_URL = r'https?://8tracks\.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$' _TEST = { - u"name": u"EightTracks", - u"url": u"http://8tracks.com/ytdl/youtube-dl-test-tracks-a", - u"playlist": [ + "name": "EightTracks", + "url": "http://8tracks.com/ytdl/youtube-dl-test-tracks-a", + "info_dict": { + 'id': '1336550', + 'display_id': 'youtube-dl-test-tracks-a', + "description": "test chars: \"'/\\ä↭", + "title": "youtube-dl test tracks \"'/\\ä↭<>", + }, + "playlist": [ { - u"file": u"11885610.m4a", - u"md5": u"96ce57f24389fc8734ce47f4c1abcc55", - u"info_dict": { - u"title": u"youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "96ce57f24389fc8734ce47f4c1abcc55", + "info_dict": { + "id": "11885610", + "ext": "m4a", + "title": "youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } }, { - u"file": u"11885608.m4a", - u"md5": u"4ab26f05c1f7291ea460a3920be8021f", - u"info_dict": { - u"title": u"youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "4ab26f05c1f7291ea460a3920be8021f", + "info_dict": { + "id": "11885608", + "ext": "m4a", + "title": "youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } }, { - u"file": u"11885679.m4a", - u"md5": u"d30b5b5f74217410f4689605c35d1fd7", - u"info_dict": { - u"title": u"youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "d30b5b5f74217410f4689605c35d1fd7", + "info_dict": { + "id": "11885679", + "ext": "m4a", + "title": "youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } }, { - u"file": u"11885680.m4a", - u"md5": u"4eb0a669317cd725f6bbd336a29f923a", - u"info_dict": { - u"title": u"youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "4eb0a669317cd725f6bbd336a29f923a", + "info_dict": { + "id": "11885680", + "ext": "m4a", + "title": "youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } }, { - u"file": u"11885682.m4a", - u"md5": u"1893e872e263a2705558d1d319ad19e8", - u"info_dict": { - u"title": u"PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "1893e872e263a2705558d1d319ad19e8", + "info_dict": { + "id": "11885682", + "ext": "m4a", + "title": "PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } }, { - u"file": u"11885683.m4a", - u"md5": u"b673c46f47a216ab1741ae8836af5899", - u"info_dict": { - u"title": u"PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "b673c46f47a216ab1741ae8836af5899", + "info_dict": { + "id": "11885683", + "ext": "m4a", + "title": "PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } }, { - u"file": u"11885684.m4a", - u"md5": u"1d74534e95df54986da7f5abf7d842b7", - u"info_dict": { - u"title": u"phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "1d74534e95df54986da7f5abf7d842b7", + "info_dict": { + "id": "11885684", + "ext": "m4a", + "title": "phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } }, { - u"file": u"11885685.m4a", - u"md5": u"f081f47af8f6ae782ed131d38b9cd1c0", - u"info_dict": { - u"title": u"phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad", - u"uploader_id": u"ytdl" + "md5": "f081f47af8f6ae782ed131d38b9cd1c0", + "info_dict": { + "id": "11885685", + "ext": "m4a", + "title": "phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad", + "uploader_id": "ytdl" } } ] } - def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) playlist_id = mobj.group('id') webpage = self._download_webpage(url, playlist_id) - json_like = self._search_regex(r"PAGE.mix = (.*?);\n", webpage, u'trax information', flags=re.DOTALL) + json_like = self._search_regex( + r"(?s)PAGE.mix = (.*?);\n", webpage, 'trax information') data = json.loads(json_like) session = str(random.randint(0, 1000000000)) @@ -99,21 +114,30 @@ class EightTracksIE(InfoExtractor): track_count = data['tracks_count'] first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id) next_url = first_url - res = [] + entries = [] for i in range(track_count): - api_json = self._download_webpage(next_url, playlist_id, - note=u'Downloading song information %s/%s' % (str(i+1), track_count), - errnote=u'Failed to download song information') + api_json = self._download_webpage( + next_url, playlist_id, + note='Downloading song information %d/%d' % (i + 1, track_count), + errnote='Failed to download song information') api_data = json.loads(api_json) - track_data = api_data[u'set']['track'] + track_data = api_data['set']['track'] info = { - 'id': track_data['id'], + 'id': compat_str(track_data['id']), 'url': track_data['track_file_stream_url'], 'title': track_data['performer'] + u' - ' + track_data['name'], 'raw_title': track_data['name'], 'uploader_id': data['user']['login'], 'ext': 'm4a', } - res.append(info) - next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (session, mix_id, track_data['id']) - return res + entries.append(info) + next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % ( + session, mix_id, track_data['id']) + return { + '_type': 'playlist', + 'entries': entries, + 'id': compat_str(mix_id), + 'display_id': playlist_id, + 'title': data.get('name'), + 'description': data.get('description'), + } diff --git a/youtube_dl/extractor/ellentv.py b/youtube_dl/extractor/ellentv.py new file mode 100644 index 000000000..3e7923648 --- /dev/null +++ b/youtube_dl/extractor/ellentv.py @@ -0,0 +1,79 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + parse_iso8601, +) + + +class EllenTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?ellentv\.com/videos/(?P<id>[a-z0-9_-]+)' + _TEST = { + 'url': 'http://www.ellentv.com/videos/0-7jqrsr18/', + 'md5': 'e4af06f3bf0d5f471921a18db5764642', + 'info_dict': { + 'id': '0-7jqrsr18', + 'ext': 'mp4', + 'title': 'What\'s Wrong with These Photos? A Whole Lot', + 'timestamp': 1406876400, + 'upload_date': '20140801', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + timestamp = parse_iso8601(self._search_regex( + r'<span class="publish-date"><time datetime="([^"]+)">', + webpage, 'timestamp')) + + return { + 'id': video_id, + 'title': self._og_search_title(webpage), + 'url': self._html_search_meta('VideoURL', webpage, 'url'), + 'timestamp': timestamp, + } + + +class EllenTVClipsIE(InfoExtractor): + IE_NAME = 'EllenTV:clips' + _VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)' + _TEST = { + 'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/', + 'info_dict': { + 'id': 'meryl-streep-vanessa-hudgens', + 'title': 'Meryl Streep, Vanessa Hudgens', + }, + 'playlist_mincount': 9, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + playlist_id = mobj.group('id') + + webpage = self._download_webpage(url, playlist_id) + playlist = self._extract_playlist(webpage) + + return { + '_type': 'playlist', + 'id': playlist_id, + 'title': self._og_search_title(webpage), + 'entries': self._extract_entries(playlist) + } + + def _extract_playlist(self, webpage): + json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json') + try: + return json.loads("[{" + json_string + "}]") + except ValueError as ve: + raise ExtractorError('Failed to download JSON', cause=ve) + + def _extract_entries(self, playlist): + return [self.url_result(item['url'], 'EllenTV') for item in playlist] diff --git a/youtube_dl/extractor/empflix.py b/youtube_dl/extractor/empflix.py index e6952588f..70f8efe27 100644 --- a/youtube_dl/extractor/empflix.py +++ b/youtube_dl/extractor/empflix.py @@ -1,54 +1,25 @@ from __future__ import unicode_literals -import re +from .tnaflix import TNAFlixIE -from .common import InfoExtractor +class EMPFlixIE(TNAFlixIE): + _VALID_URL = r'^https?://www\.empflix\.com/videos/(?P<display_id>[0-9a-zA-Z-]+)-(?P<id>[0-9]+)\.html' + + _TITLE_REGEX = r'name="title" value="(?P<title>[^"]*)"' + _DESCRIPTION_REGEX = r'name="description" value="([^"]*)"' + _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"' -class EmpflixIE(InfoExtractor): - _VALID_URL = r'^https?://www\.empflix\.com/videos/.*?-(?P<id>[0-9]+)\.html' _TEST = { 'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html', 'md5': 'b1bc15b6412d33902d6e5952035fcabc', 'info_dict': { 'id': '33051', + 'display_id': 'Amateur-Finger-Fuck', 'ext': 'mp4', 'title': 'Amateur Finger Fuck', 'description': 'Amateur solo finger fucking.', + 'thumbnail': 're:https?://.*\.jpg$', 'age_limit': 18, } } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - webpage = self._download_webpage(url, video_id) - age_limit = self._rta_search(webpage) - - video_title = self._html_search_regex( - r'name="title" value="(?P<title>[^"]*)"', webpage, 'title') - video_description = self._html_search_regex( - r'name="description" value="([^"]*)"', webpage, 'description', fatal=False) - - cfg_url = self._html_search_regex( - r'flashvars\.config = escape\("([^"]+)"', - webpage, 'flashvars.config') - - cfg_xml = self._download_xml( - cfg_url, video_id, note='Downloading metadata') - - formats = [ - { - 'url': item.find('videoLink').text, - 'format_id': item.find('res').text, - } for item in cfg_xml.findall('./quality/item') - ] - - return { - 'id': video_id, - 'title': video_title, - 'description': video_description, - 'formats': formats, - 'age_limit': age_limit, - } diff --git a/youtube_dl/extractor/eporner.py b/youtube_dl/extractor/eporner.py new file mode 100644 index 000000000..522aa3d63 --- /dev/null +++ b/youtube_dl/extractor/eporner.py @@ -0,0 +1,75 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + str_to_int, +) + + +class EpornerIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\d+)/(?P<display_id>[\w-]+)' + _TEST = { + 'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/', + 'md5': '3b427ae4b9d60619106de3185c2987cd', + 'info_dict': { + 'id': '95008', + 'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video', + 'ext': 'flv', + 'title': 'Infamous Tiffany Teen Strip Tease Video', + 'duration': 194, + 'view_count': int, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + title = self._html_search_regex( + r'<title>(.*?) - EPORNER', webpage, 'title') + + redirect_code = self._html_search_regex( + r'<script type="text/javascript" src="/config5/%s/([a-f\d]+)/">' % video_id, + webpage, 'redirect_code') + redirect_url = 'http://www.eporner.com/config5/%s/%s' % (video_id, redirect_code) + player_code = self._download_webpage( + redirect_url, display_id, note='Downloading player config') + + sources = self._search_regex( + r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', player_code, 'sources') + + formats = [] + for video_url, format_id in re.findall(r'file\s*:\s*"([^"]+)",\s*label\s*:\s*"([^"]+)"', sources): + fmt = { + 'url': video_url, + 'format_id': format_id, + } + m = re.search(r'^(\d+)', format_id) + if m: + fmt['height'] = int(m.group(1)) + formats.append(fmt) + self._sort_formats(formats) + + duration = parse_duration(self._search_regex( + r'class="mbtim">([0-9:]+)</div>', webpage, 'duration', + fatal=False)) + view_count = str_to_int(self._search_regex( + r'id="cinemaviews">\s*([0-9,]+)\s*<small>views', + webpage, 'view count', fatal=False)) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'duration': duration, + 'view_count': view_count, + 'formats': formats, + 'age_limit': self._rta_search(webpage), + } diff --git a/youtube_dl/extractor/escapist.py b/youtube_dl/extractor/escapist.py index 272dfe1f6..476fc22b9 100644 --- a/youtube_dl/extractor/escapist.py +++ b/youtube_dl/extractor/escapist.py @@ -36,7 +36,7 @@ class EscapistIE(InfoExtractor): r'<meta name="description" content="([^"]*)"', webpage, 'description', fatal=False) - playerUrl = self._og_search_video_url(webpage, name=u'player URL') + playerUrl = self._og_search_video_url(webpage, name='player URL') title = self._html_search_regex( r'<meta name="title" content="([^"]*)"', diff --git a/youtube_dl/extractor/everyonesmixtape.py b/youtube_dl/extractor/everyonesmixtape.py index 12829cbcc..d237a8281 100644 --- a/youtube_dl/extractor/everyonesmixtape.py +++ b/youtube_dl/extractor/everyonesmixtape.py @@ -12,10 +12,11 @@ from ..utils import ( class EveryonesMixtapeIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?everyonesmixtape\.com/#/mix/(?P<id>[0-9a-zA-Z]+)(?:/(?P<songnr>[0-9]))?$' - _TEST = { + _TESTS = [{ 'url': 'http://everyonesmixtape.com/#/mix/m7m0jJAbMQi/5', - 'file': '5bfseWNmlds.mp4', "info_dict": { + 'id': '5bfseWNmlds', + 'ext': 'mp4', "title": "Passion Pit - \"Sleepyhead\" (Official Music Video)", "uploader": "FKR.TV", "uploader_id": "frenchkissrecords", @@ -25,7 +26,14 @@ class EveryonesMixtapeIE(InfoExtractor): 'params': { 'skip_download': True, # This is simply YouTube } - } + }, { + 'url': 'http://everyonesmixtape.com/#/mix/m7m0jJAbMQi', + 'info_dict': { + 'id': 'm7m0jJAbMQi', + 'title': 'Driving', + }, + 'playlist_count': 24 + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/expotv.py b/youtube_dl/extractor/expotv.py new file mode 100644 index 000000000..a38b773e8 --- /dev/null +++ b/youtube_dl/extractor/expotv.py @@ -0,0 +1,73 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + unified_strdate, +) + + +class ExpoTVIE(InfoExtractor): + _VALID_URL = r'https?://www\.expotv\.com/videos/[^?#]*/(?P<id>[0-9]+)($|[?#])' + _TEST = { + 'url': 'http://www.expotv.com/videos/reviews/1/24/LinneCardscom/17561', + 'md5': '2985e6d7a392b2f7a05e0ca350fe41d0', + 'info_dict': { + 'id': '17561', + 'ext': 'mp4', + 'upload_date': '20060212', + 'title': 'My Favorite Online Scrapbook Store', + 'view_count': int, + 'description': 'You\'ll find most everything you need at this virtual store front.', + 'uploader': 'Anna T.', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + player_key = self._search_regex( + r'<param name="playerKey" value="([^"]+)"', webpage, 'player key') + config_url = 'http://client.expotv.com/video/config/%s/%s' % ( + video_id, player_key) + config = self._download_json( + config_url, video_id, + note='Downloading video configuration') + + formats = [{ + 'url': fcfg['file'], + 'height': int_or_none(fcfg.get('height')), + 'format_note': fcfg.get('label'), + 'ext': self._search_regex( + r'filename=.*\.([a-z0-9_A-Z]+)&', fcfg['file'], + 'file extension', default=None), + } for fcfg in config['sources']] + self._sort_formats(formats) + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = config.get('image') + view_count = int_or_none(self._search_regex( + r'<h5>Plays: ([0-9]+)</h5>', webpage, 'view counts')) + uploader = self._search_regex( + r'<div class="reviewer">\s*<img alt="([^"]+)"', webpage, 'uploader', + fatal=False) + upload_date = unified_strdate(self._search_regex( + r'<h5>Reviewed on ([0-9/.]+)</h5>', webpage, 'upload date', + fatal=False)) + + return { + 'id': video_id, + 'formats': formats, + 'title': title, + 'description': description, + 'view_count': view_count, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'upload_date': upload_date, + } diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index f0cd8f156..afb34ce51 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -20,15 +20,15 @@ from ..utils import ( class FacebookIE(InfoExtractor): _VALID_URL = r'''(?x) https?://(?:\w+\.)?facebook\.com/ - (?:[^#?]*\#!/)? - (?:video/video\.php|photo\.php|video/embed)\?(?:.*?) + (?:[^#]*?\#!/)? + (?:video/video\.php|photo\.php|video\.php|video/embed)\?(?:.*?) (?:v|video_id)=(?P<id>[0-9]+) (?:.*)''' _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1' _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1' _NETRC_MACHINE = 'facebook' IE_NAME = 'facebook' - _TEST = { + _TESTS = [{ 'url': 'https://www.facebook.com/photo.php?v=120708114770723', 'md5': '48975a41ccc4b7a581abd68651c1a5a8', 'info_dict': { @@ -37,7 +37,10 @@ class FacebookIE(InfoExtractor): 'duration': 279, 'title': 'PEOPLE ARE AWESOME 2013', } - } + }, { + 'url': 'https://www.facebook.com/video.php?v=10204634152394104', + 'only_matching': True, + }] def _login(self): (useremail, password) = self._get_login_info() @@ -76,7 +79,8 @@ class FacebookIE(InfoExtractor): check_form = { 'fb_dtsg': self._search_regex(r'name="fb_dtsg" value="(.+?)"', login_results, 'fb_dtsg'), - 'h': self._search_regex(r'name="h" value="(\w*?)"', login_results, 'h'), + 'h': self._search_regex( + r'name="h"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h'), 'name_action_selected': 'dont_save', } check_req = compat_urllib_request.Request(self._CHECKPOINT_URL, urlencode_postdata(check_form)) diff --git a/youtube_dl/extractor/firedrive.py b/youtube_dl/extractor/firedrive.py index d26145db1..af439ccfe 100644 --- a/youtube_dl/extractor/firedrive.py +++ b/youtube_dl/extractor/firedrive.py @@ -8,7 +8,6 @@ from ..utils import ( ExtractorError, compat_urllib_parse, compat_urllib_request, - determine_ext, ) @@ -43,7 +42,6 @@ class FiredriveIE(InfoExtractor): fields = dict(re.findall(r'''(?x)<input\s+ type="hidden"\s+ name="([^"]+)"\s+ - (?:id="[^"]+"\s+)? value="([^"]*)" ''', webpage)) @@ -67,7 +65,7 @@ class FiredriveIE(InfoExtractor): ext = self._search_regex(r'type:\s?\'([^\']+)\',', webpage, 'extension', fatal=False) video_url = self._search_regex( - r'file:\s?\'(http[^\']+)\',', webpage, 'file url') + r'file:\s?loadURL\(\'(http[^\']+)\'\),', webpage, 'file url') formats = [{ 'format_id': 'sd', diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index f3e0f38b7..1b0e8e5d5 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -19,17 +19,35 @@ class FranceTVBaseInfoExtractor(InfoExtractor): + video_id, video_id, 'Downloading XML config') manifest_url = info.find('videos/video/url').text - video_url = manifest_url.replace('manifest.f4m', 'index_2_av.m3u8') - video_url = video_url.replace('/z/', '/i/') + manifest_url = manifest_url.replace('/z/', '/i/') + + if manifest_url.startswith('rtmp'): + formats = [{'url': manifest_url, 'ext': 'flv'}] + else: + formats = [] + available_formats = self._search_regex(r'/[^,]*,(.*?),k\.mp4', manifest_url, 'available formats') + for index, format_descr in enumerate(available_formats.split(',')): + format_info = { + 'url': manifest_url.replace('manifest.f4m', 'index_%d_av.m3u8' % index), + 'ext': 'mp4', + } + m_resolution = re.search(r'(?P<width>\d+)x(?P<height>\d+)', format_descr) + if m_resolution is not None: + format_info.update({ + 'width': int(m_resolution.group('width')), + 'height': int(m_resolution.group('height')), + }) + formats.append(format_info) + thumbnail_path = info.find('image').text - return {'id': video_id, - 'ext': 'flv' if video_url.startswith('rtmp') else 'mp4', - 'url': video_url, - 'title': info.find('titre').text, - 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path), - 'description': info.find('synopsis').text, - } + return { + 'id': video_id, + 'title': info.find('titre').text, + 'formats': formats, + 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path), + 'description': info.find('synopsis').text, + } class PluzzIE(FranceTVBaseInfoExtractor): @@ -48,7 +66,7 @@ class PluzzIE(FranceTVBaseInfoExtractor): class FranceTvInfoIE(FranceTVBaseInfoExtractor): IE_NAME = 'francetvinfo.fr' - _VALID_URL = r'https?://www\.francetvinfo\.fr/.*/(?P<title>.+)\.html' + _VALID_URL = r'https?://(?:www|mobile)\.francetvinfo\.fr/.*/(?P<title>.+)\.html' _TESTS = [{ 'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html', @@ -211,7 +229,7 @@ class GenerationQuoiIE(InfoExtractor): class CultureboxIE(FranceTVBaseInfoExtractor): IE_NAME = 'culturebox.francetvinfo.fr' - _VALID_URL = r'https?://culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)' + _VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)' _TEST = { 'url': 'http://culturebox.francetvinfo.fr/einstein-on-the-beach-au-theatre-du-chatelet-146813', diff --git a/youtube_dl/extractor/funnyordie.py b/youtube_dl/extractor/funnyordie.py index 6e6b66660..721e5fce0 100644 --- a/youtube_dl/extractor/funnyordie.py +++ b/youtube_dl/extractor/funnyordie.py @@ -26,7 +26,7 @@ class FunnyOrDieIE(InfoExtractor): 'id': 'e402820827', 'ext': 'mp4', 'title': 'Please Use This Song (Jon Lajoie)', - 'description': 'md5:2ed27d364f5a805a6dba199faaf6681d', + 'description': 'Please use this to sell something. www.jonlajoie.com', 'thumbnail': 're:^http:.*\.jpg$', }, }] diff --git a/youtube_dl/extractor/gameone.py b/youtube_dl/extractor/gameone.py index b580f52fb..3022f539d 100644 --- a/youtube_dl/extractor/gameone.py +++ b/youtube_dl/extractor/gameone.py @@ -88,3 +88,28 @@ class GameOneIE(InfoExtractor): 'age_limit': age_limit, 'timestamp': timestamp, } + + +class GameOnePlaylistIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?gameone\.de(?:/tv)?/?$' + IE_NAME = 'gameone:playlist' + _TEST = { + 'url': 'http://www.gameone.de/tv', + 'info_dict': { + 'title': 'GameOne', + }, + 'playlist_mincount': 294, + } + + def _real_extract(self, url): + webpage = self._download_webpage('http://www.gameone.de/tv', 'TV') + max_id = max(map(int, re.findall(r'<a href="/tv/(\d+)"', webpage))) + entries = [ + self.url_result('http://www.gameone.de/tv/%d' % video_id, 'GameOne') + for video_id in range(max_id, 0, -1)] + + return { + '_type': 'playlist', + 'title': 'GameOne', + 'entries': entries, + } diff --git a/youtube_dl/extractor/gamestar.py b/youtube_dl/extractor/gamestar.py new file mode 100644 index 000000000..50f8fc7e7 --- /dev/null +++ b/youtube_dl/extractor/gamestar.py @@ -0,0 +1,74 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_duration, + str_to_int, + unified_strdate, +) + + +class GameStarIE(InfoExtractor): + _VALID_URL = r'http://www\.gamestar\.de/videos/.*,(?P<id>[0-9]+)\.html' + _TEST = { + 'url': 'http://www.gamestar.de/videos/trailer,3/hobbit-3-die-schlacht-der-fuenf-heere,76110.html', + 'md5': '96974ecbb7fd8d0d20fca5a00810cea7', + 'info_dict': { + 'id': '76110', + 'ext': 'mp4', + 'title': 'Hobbit 3: Die Schlacht der Fünf Heere - Teaser-Trailer zum dritten Teil', + 'description': 'Der Teaser-Trailer zu Hobbit 3: Die Schlacht der Fünf Heere zeigt einige Szenen aus dem dritten Teil der Saga und kündigt den vollständigen Trailer an.', + 'thumbnail': 'http://images.gamestar.de/images/idgwpgsgp/bdb/2494525/600x.jpg', + 'upload_date': '20140728', + 'duration': 17 + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + og_title = self._og_search_title(webpage) + title = og_title.replace(' - Video bei GameStar.de', '').strip() + + url = 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id + + description = self._og_search_description(webpage).strip() + + thumbnail = self._proto_relative_url( + self._og_search_thumbnail(webpage), scheme='http:') + + upload_date = unified_strdate(self._html_search_regex( + r'<span style="float:left;font-size:11px;">Datum: ([0-9]+\.[0-9]+\.[0-9]+) ', + webpage, 'upload_date', fatal=False)) + + duration = parse_duration(self._html_search_regex( + r' Länge: ([0-9]+:[0-9]+)</span>', webpage, 'duration', + fatal=False)) + + view_count = str_to_int(self._html_search_regex( + r' Zuschauer: ([0-9\.]+) ', webpage, + 'view_count', fatal=False)) + + comment_count = int_or_none(self._html_search_regex( + r'>Kommentieren \(([0-9]+)\)</a>', webpage, 'comment_count', + fatal=False)) + + return { + 'id': video_id, + 'title': title, + 'url': url, + 'ext': 'mp4', + 'thumbnail': thumbnail, + 'description': description, + 'upload_date': upload_date, + 'duration': duration, + 'view_count': view_count, + 'comment_count': comment_count + } diff --git a/youtube_dl/extractor/gdcvault.py b/youtube_dl/extractor/gdcvault.py index 89d5994ee..de14ae1fb 100644 --- a/youtube_dl/extractor/gdcvault.py +++ b/youtube_dl/extractor/gdcvault.py @@ -8,6 +8,7 @@ from ..utils import ( compat_urllib_request, ) + class GDCVaultIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)/(?P<name>(\w|-)+)' _TESTS = [ @@ -31,6 +32,15 @@ class GDCVaultIE(InfoExtractor): 'skip_download': True, # Requires rtmpdump } }, + { + 'url': 'http://www.gdcvault.com/play/1015301/Thexder-Meets-Windows-95-or', + 'md5': 'a5eb77996ef82118afbbe8e48731b98e', + 'info_dict': { + 'id': '1015301', + 'ext': 'flv', + 'title': 'Thexder Meets Windows 95, or Writing Great Games in the Windows 95 Environment', + } + } ] def _parse_mp4(self, xml_description): @@ -103,18 +113,40 @@ class GDCVaultIE(InfoExtractor): webpage_url = 'http://www.gdcvault.com/play/' + video_id start_page = self._download_webpage(webpage_url, video_id) - xml_root = self._html_search_regex(r'<iframe src="(?P<xml_root>.*?)player.html.*?".*?</iframe>', start_page, 'xml root', None, False) + direct_url = self._search_regex( + r's1\.addVariable\("file",\s*encodeURIComponent\("(/[^"]+)"\)\);', + start_page, 'url', default=None) + if direct_url: + video_url = 'http://www.gdcvault.com/' + direct_url + title = self._html_search_regex( + r'<td><strong>Session Name</strong></td>\s*<td>(.*?)</td>', + start_page, 'title') + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'flv', + 'title': title, + } + xml_root = self._html_search_regex( + r'<iframe src="(?P<xml_root>.*?)player.html.*?".*?</iframe>', + start_page, 'xml root', default=None) if xml_root is None: # Probably need to authenticate - start_page = self._login(webpage_url, video_id) - if start_page is None: + login_res = self._login(webpage_url, video_id) + if login_res is None: self.report_warning('Could not login.') else: + start_page = login_res # Grab the url from the authenticated page - xml_root = self._html_search_regex(r'<iframe src="(?P<xml_root>.*?)player.html.*?".*?</iframe>', start_page, 'xml root') + xml_root = self._html_search_regex( + r'<iframe src="(.*?)player.html.*?".*?</iframe>', + start_page, 'xml root') - xml_name = self._html_search_regex(r'<iframe src=".*?\?xml=(?P<xml_file>.+?\.xml).*?".*?</iframe>', start_page, 'xml filename', None, False) + xml_name = self._html_search_regex( + r'<iframe src=".*?\?xml=(.+?\.xml).*?".*?</iframe>', + start_page, 'xml filename', default=None) if xml_name is None: # Fallback to the older format xml_name = self._html_search_regex(r'<iframe src=".*?\?xmlURL=xml/(?P<xml_file>.+?\.xml).*?".*?</iframe>', start_page, 'xml filename') diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index f97b59845..1b7697870 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -8,18 +8,20 @@ import re from .common import InfoExtractor from .youtube import YoutubeIE from ..utils import ( - compat_urllib_error, compat_urllib_parse, - compat_urllib_request, compat_urlparse, compat_xml_parse_error, + determine_ext, ExtractorError, + float_or_none, HEADRequest, + orderedSet, parse_xml, smuggle_url, unescapeHTML, unified_strdate, + unsmuggle_url, url_basename, ) from .brightcove import BrightcoveIE @@ -289,6 +291,97 @@ class GenericIE(InfoExtractor): 'description': 'Mario\'s life in the fast lane has never looked so good.', }, }, + # YouTube embed via <data-embed-url=""> + { + 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM', + 'info_dict': { + 'id': 'jpSGZsgga_I', + 'ext': 'mp4', + 'title': 'Asphalt 8: Airborne - Launch Trailer', + 'uploader': 'Gameloft', + 'uploader_id': 'gameloft', + 'upload_date': '20130821', + 'description': 'md5:87bd95f13d8be3e7da87a5f2c443106a', + }, + 'params': { + 'skip_download': True, + } + }, + # Camtasia studio + { + 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/', + 'playlist': [{ + 'md5': '0c5e352edabf715d762b0ad4e6d9ee67', + 'info_dict': { + 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final', + 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1', + 'ext': 'flv', + 'duration': 2235.90, + } + }, { + 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63', + 'info_dict': { + 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP', + 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip', + 'ext': 'flv', + 'duration': 2235.93, + } + }], + 'info_dict': { + 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final', + } + }, + # Flowplayer + { + 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html', + 'md5': '9d65602bf31c6e20014319c7d07fba27', + 'info_dict': { + 'id': '5123ea6d5e5a7', + 'ext': 'mp4', + 'age_limit': 18, + 'uploader': 'www.handjobhub.com', + 'title': 'Busty Blonde Siri Tit Fuck While Wank at Handjob Hub', + } + }, + # RSS feed + { + 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml', + 'info_dict': { + 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml', + 'title': 'Zero Punctuation', + 'description': 're:' + }, + 'playlist_mincount': 11, + }, + # Multiple brightcove videos + # https://github.com/rg3/youtube-dl/issues/2283 + { + 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html', + 'info_dict': { + 'id': 'always-never', + 'title': 'Always / Never - The New Yorker', + }, + 'playlist_count': 3, + 'params': { + 'extract_flat': False, + 'skip_download': True, + } + }, + # MLB embed + { + 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/', + 'md5': '96f09a37e44da40dd083e12d9a683327', + 'info_dict': { + 'id': '33322633', + 'ext': 'mp4', + 'title': 'Ump changes call to ball', + 'description': 'md5:71c11215384298a172a6dcb4c2e20685', + 'duration': 48, + 'timestamp': 1401537900, + 'upload_date': '20140531', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, ] def report_download_webpage(self, video_id): @@ -301,58 +394,6 @@ class GenericIE(InfoExtractor): """Report information extraction.""" self._downloader.to_screen('[redirect] Following redirect to %s' % new_url) - def _send_head(self, url): - """Check if it is a redirect, like url shorteners, in case return the new url.""" - - class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler): - """ - Subclass the HTTPRedirectHandler to make it use our - HEADRequest also on the redirected URL - """ - def redirect_request(self, req, fp, code, msg, headers, newurl): - if code in (301, 302, 303, 307): - newurl = newurl.replace(' ', '%20') - newheaders = dict((k,v) for k,v in req.headers.items() - if k.lower() not in ("content-length", "content-type")) - try: - # This function was deprecated in python 3.3 and removed in 3.4 - origin_req_host = req.get_origin_req_host() - except AttributeError: - origin_req_host = req.origin_req_host - return HEADRequest(newurl, - headers=newheaders, - origin_req_host=origin_req_host, - unverifiable=True) - else: - raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp) - - class HTTPMethodFallback(compat_urllib_request.BaseHandler): - """ - Fallback to GET if HEAD is not allowed (405 HTTP error) - """ - def http_error_405(self, req, fp, code, msg, headers): - fp.read() - fp.close() - - newheaders = dict((k,v) for k,v in req.headers.items() - if k.lower() not in ("content-length", "content-type")) - return self.parent.open(compat_urllib_request.Request(req.get_full_url(), - headers=newheaders, - origin_req_host=req.get_origin_req_host(), - unverifiable=True)) - - # Build our opener - opener = compat_urllib_request.OpenerDirector() - for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler, - HTTPMethodFallback, HEADRedirectHandler, - compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]: - opener.add_handler(handler()) - - response = opener.open(HEADRequest(url)) - if response is None: - raise ExtractorError('Invalid URL protocol') - return response - def _extract_rss(self, url, video_id, doc): playlist_title = doc.find('./channel/title').text playlist_desc_el = doc.find('./channel/description') @@ -372,6 +413,43 @@ class GenericIE(InfoExtractor): 'entries': entries, } + def _extract_camtasia(self, url, video_id, webpage): + """ Returns None if no camtasia video can be found. """ + + camtasia_cfg = self._search_regex( + r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);', + webpage, 'camtasia configuration file', default=None) + if camtasia_cfg is None: + return None + + title = self._html_search_meta('DC.title', webpage, fatal=True) + + camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg) + camtasia_cfg = self._download_xml( + camtasia_url, video_id, + note='Downloading camtasia configuration', + errnote='Failed to download camtasia configuration') + fileset_node = camtasia_cfg.find('./playlist/array/fileset') + + entries = [] + for n in fileset_node.getchildren(): + url_n = n.find('./uri') + if url_n is None: + continue + + entries.append({ + 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0], + 'title': '%s - %s' % (title, n.tag), + 'url': compat_urlparse.urljoin(url, url_n.text), + 'duration': float_or_none(n.find('./duration').text), + }) + + return { + '_type': 'playlist', + 'entries': entries, + 'title': title, + } + def _real_extract(self, url): if url.startswith('//'): return { @@ -383,13 +461,13 @@ class GenericIE(InfoExtractor): if not parsed_url.scheme: default_search = self._downloader.params.get('default_search') if default_search is None: - default_search = 'error' + default_search = 'fixup_error' - if default_search in ('auto', 'auto_warning'): + if default_search in ('auto', 'auto_warning', 'fixup_error'): if '/' in url: self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http') return self.url_result('http://' + url) - else: + elif default_search != 'fixup_error': if default_search == 'auto_warning': if re.match(r'^(?:url|URL)$', url): raise ExtractorError( @@ -399,25 +477,40 @@ class GenericIE(InfoExtractor): self._downloader.report_warning( 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url) return self.url_result('ytsearch:' + url) - elif default_search == 'error': + + if default_search in ('error', 'fixup_error'): raise ExtractorError( ('%r is not a valid URL. ' - 'Set --default-search "ytseach" (or run youtube-dl "ytsearch:%s" ) to search YouTube' + 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube' ) % (url, url), expected=True) else: assert ':' in default_search return self.url_result(default_search + url) - video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0] + + url, smuggled_data = unsmuggle_url(url) + force_videoid = None + if smuggled_data and 'force_videoid' in smuggled_data: + force_videoid = smuggled_data['force_videoid'] + video_id = force_videoid + else: + video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0] self.to_screen('%s: Requesting header' % video_id) - try: - response = self._send_head(url) + head_req = HEADRequest(url) + response = self._request_webpage( + head_req, video_id, + note=False, errnote='Could not send HEAD request to %s' % url, + fatal=False) + if response is not False: # Check for redirect new_url = response.geturl() if url != new_url: self.report_following_redirect(new_url) + if force_videoid: + new_url = smuggle_url( + new_url, {'force_videoid': force_videoid}) return self.url_result(new_url) # Check for direct link to a video @@ -438,10 +531,6 @@ class GenericIE(InfoExtractor): 'upload_date': upload_date, } - except compat_urllib_error.HTTPError: - # This may be a stupid server that doesn't like HEAD, our UA, or so - pass - try: webpage = self._download_webpage(url, video_id) except ValueError: @@ -459,6 +548,11 @@ class GenericIE(InfoExtractor): except compat_xml_parse_error: pass + # Is it a Camtasia project? + camtasia_res = self._extract_camtasia(url, video_id, webpage) + if camtasia_res is not None: + return camtasia_res + # Sometimes embedded video player is hidden behind percent encoding # (e.g. https://github.com/rg3/youtube-dl/issues/2448) # Unescaping the whole page allows to handle those cases in a generic way @@ -474,10 +568,26 @@ class GenericIE(InfoExtractor): r'(?s)<title>(.*?)</title>', webpage, 'video title', default='video') + # Try to detect age limit automatically + age_limit = self._rta_search(webpage) + # And then there are the jokers who advertise that they use RTA, + # but actually don't. + AGE_LIMIT_MARKERS = [ + r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>', + ] + if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS): + age_limit = 18 + # video uploader is domain name video_uploader = self._search_regex( r'^(?:https?://)?([^/]*)/.*', url, 'video uploader') + # Helper method + def _playlist_from_matches(matches, getter, ie=None): + urlrs = orderedSet(self.url_result(getter(m), ie) for m in matches) + return self.playlist_result( + urlrs, playlist_id=video_id, playlist_title=video_title) + # Look for BrightCove: bc_urls = BrightcoveIE._extract_brightcove_urls(webpage) if bc_urls: @@ -513,6 +623,7 @@ class GenericIE(InfoExtractor): matches = re.findall(r'''(?x) (?: <iframe[^>]+?src=| + data-video-url=| <embed[^>]+?src=| embedSWF\(?:\s* ) @@ -521,19 +632,15 @@ class GenericIE(InfoExtractor): (?:embed|v)/.+?) \1''', webpage) if matches: - urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Youtube') - for tuppl in matches] - return self.playlist_result( - urlrs, playlist_id=video_id, playlist_title=video_title) + return _playlist_from_matches( + matches, lambda m: unescapeHTML(m[1]), ie='Youtube') # Look for embedded Dailymotion player matches = re.findall( r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage) if matches: - urlrs = [self.url_result(unescapeHTML(tuppl[1])) - for tuppl in matches] - return self.playlist_result( - urlrs, playlist_id=video_id, playlist_title=video_title) + return _playlist_from_matches( + matches, lambda m: unescapeHTML(m[1])) # Look for embedded Wistia player match = re.search( @@ -552,7 +659,7 @@ class GenericIE(InfoExtractor): mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage) if mobj: return self.url_result('http://blip.tv/a/a-'+mobj.group(1), 'BlipTV') - mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9]+)', webpage) + mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage) if mobj: return self.url_result(mobj.group(1), 'BlipTV') @@ -647,10 +754,8 @@ class GenericIE(InfoExtractor): # Look for funnyordie embed matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage) if matches: - urlrs = [self.url_result(unescapeHTML(eurl), 'FunnyOrDie') - for eurl in matches] - return self.playlist_result( - urlrs, playlist_id=video_id, playlist_title=video_title) + return _playlist_from_matches( + matches, getter=unescapeHTML, ie='FunnyOrDie') # Look for embedded RUTV player rutv_url = RUTVIE._extract_url(webpage) @@ -705,6 +810,26 @@ class GenericIE(InfoExtractor): url = unescapeHTML(mobj.group('url')) return self.url_result(url, ie='MTVServicesEmbedded') + # Look for embedded yahoo player + mobj = re.search( + r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1', + webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'Yahoo') + + # Look for embedded sbs.com.au player + mobj = re.search( + r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:www\.)sbs\.com\.au/ondemand/video/single/.+?)\1', + webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'SBS') + + mobj = re.search( + r'<iframe[^>]+?src=(["\'])(?P<url>https?://m\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1', + webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'MLB') + # Start with something easy: JW Player in SWFObject found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) if not found: @@ -723,6 +848,14 @@ class GenericIE(InfoExtractor): # Broaden the findall a little bit: JWPlayer JS loader found = re.findall(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage) if not found: + # Flow player + found = re.findall(r'''(?xs) + flowplayer\("[^"]+",\s* + \{[^}]+?\}\s*, + \s*{[^}]+? ["']?clip["']?\s*:\s*\{\s* + ["']?url["']?\s*:\s*["']([^"']+)["'] + ''', webpage) + if not found: # Try to find twitter cards info found = re.findall(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage) if not found: @@ -731,10 +864,16 @@ class GenericIE(InfoExtractor): m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage) # We only look in og:video if the MIME type is a video, don't try if it's a Flash player: if m_video_type is not None: - found = re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage) + def check_video(vurl): + vpath = compat_urlparse.urlparse(vurl).path + vext = determine_ext(vpath) + return '.' in vpath and vext not in ('swf', 'png', 'jpg') + found = list(filter( + check_video, + re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))) if not found: # HTML5 video - found = re.findall(r'(?s)<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage) + found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]+)? src="([^"]+)"', webpage) if not found: found = re.search( r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")' @@ -768,6 +907,7 @@ class GenericIE(InfoExtractor): 'url': video_url, 'uploader': video_uploader, 'title': video_title, + 'age_limit': age_limit, }) if len(entries) == 1: diff --git a/youtube_dl/extractor/godtube.py b/youtube_dl/extractor/godtube.py new file mode 100644 index 000000000..73bd6d890 --- /dev/null +++ b/youtube_dl/extractor/godtube.py @@ -0,0 +1,58 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + parse_iso8601, +) + + +class GodTubeIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?godtube\.com/watch/\?v=(?P<id>[\da-zA-Z]+)' + _TESTS = [ + { + 'url': 'https://www.godtube.com/watch/?v=0C0CNNNU', + 'md5': '77108c1e4ab58f48031101a1a2119789', + 'info_dict': { + 'id': '0C0CNNNU', + 'ext': 'mp4', + 'title': 'Woman at the well.', + 'duration': 159, + 'timestamp': 1205712000, + 'uploader': 'beverlybmusic', + 'upload_date': '20080317', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + config = self._download_xml( + 'http://www.godtube.com/resource/mediaplayer/%s.xml' % video_id.lower(), + video_id, 'Downloading player config XML') + + video_url = config.find('.//file').text + uploader = config.find('.//author').text + timestamp = parse_iso8601(config.find('.//date').text) + duration = parse_duration(config.find('.//duration').text) + thumbnail = config.find('.//image').text + + media = self._download_xml( + 'http://www.godtube.com/media/xml/?v=%s' % video_id, video_id, 'Downloading media XML') + + title = media.find('.//title').text + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'uploader': uploader, + 'duration': duration, + } diff --git a/youtube_dl/extractor/googlesearch.py b/youtube_dl/extractor/googlesearch.py index 383032d81..469e1f935 100644 --- a/youtube_dl/extractor/googlesearch.py +++ b/youtube_dl/extractor/googlesearch.py @@ -14,6 +14,14 @@ class GoogleSearchIE(SearchInfoExtractor): _MAX_RESULTS = 1000 IE_NAME = 'video.google:search' _SEARCH_KEY = 'gvsearch' + _TEST = { + 'url': 'gvsearch15:python language', + 'info_dict': { + 'id': 'python language', + 'title': 'python language', + }, + 'playlist_count': 15, + } def _get_n_results(self, query, n): """Get a specified number of results for a query""" diff --git a/youtube_dl/extractor/grooveshark.py b/youtube_dl/extractor/grooveshark.py new file mode 100644 index 000000000..726adff77 --- /dev/null +++ b/youtube_dl/extractor/grooveshark.py @@ -0,0 +1,190 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import time +import math +import os.path +import re + + +from .common import InfoExtractor +from ..utils import ExtractorError, compat_urllib_request, compat_html_parser + +from ..utils import ( + compat_urllib_parse, + compat_urlparse, +) + + +class GroovesharkHtmlParser(compat_html_parser.HTMLParser): + def __init__(self): + self._current_object = None + self.objects = [] + compat_html_parser.HTMLParser.__init__(self) + + def handle_starttag(self, tag, attrs): + attrs = dict((k, v) for k, v in attrs) + if tag == 'object': + self._current_object = {'attrs': attrs, 'params': []} + elif tag == 'param': + self._current_object['params'].append(attrs) + + def handle_endtag(self, tag): + if tag == 'object': + self.objects.append(self._current_object) + self._current_object = None + + @classmethod + def extract_object_tags(cls, html): + p = cls() + p.feed(html) + p.close() + return p.objects + + +class GroovesharkIE(InfoExtractor): + _VALID_URL = r'https?://(www\.)?grooveshark\.com/#!/s/([^/]+)/([^/]+)' + _TEST = { + 'url': 'http://grooveshark.com/#!/s/Jolene+Tenth+Key+Remix+Ft+Will+Sessions/6SS1DW?src=5', + 'md5': '7ecf8aefa59d6b2098517e1baa530023', + 'info_dict': { + 'id': '6SS1DW', + 'title': 'Jolene (Tenth Key Remix ft. Will Sessions)', + 'ext': 'mp3', + 'duration': 227, + } + } + + do_playerpage_request = True + do_bootstrap_request = True + + def _parse_target(self, target): + uri = compat_urlparse.urlparse(target) + hash = uri.fragment[1:].split('?')[0] + token = os.path.basename(hash.rstrip('/')) + return (uri, hash, token) + + def _build_bootstrap_url(self, target): + (uri, hash, token) = self._parse_target(target) + query = 'getCommunicationToken=1&hash=%s&%d' % (compat_urllib_parse.quote(hash, safe=''), self.ts) + return (compat_urlparse.urlunparse((uri.scheme, uri.netloc, '/preload.php', None, query, None)), token) + + def _build_meta_url(self, target): + (uri, hash, token) = self._parse_target(target) + query = 'hash=%s&%d' % (compat_urllib_parse.quote(hash, safe=''), self.ts) + return (compat_urlparse.urlunparse((uri.scheme, uri.netloc, '/preload.php', None, query, None)), token) + + def _build_stream_url(self, meta): + return compat_urlparse.urlunparse(('http', meta['streamKey']['ip'], '/stream.php', None, None, None)) + + def _build_swf_referer(self, target, obj): + (uri, _, _) = self._parse_target(target) + return compat_urlparse.urlunparse((uri.scheme, uri.netloc, obj['attrs']['data'], None, None, None)) + + def _transform_bootstrap(self, js): + return re.split('(?m)^\s*try\s*{', js)[0] \ + .split(' = ', 1)[1].strip().rstrip(';') + + def _transform_meta(self, js): + return js.split('\n')[0].split('=')[1].rstrip(';') + + def _get_meta(self, target): + (meta_url, token) = self._build_meta_url(target) + self.to_screen('Metadata URL: %s' % meta_url) + + headers = {'Referer': compat_urlparse.urldefrag(target)[0]} + req = compat_urllib_request.Request(meta_url, headers=headers) + res = self._download_json(req, token, + transform_source=self._transform_meta) + + if 'getStreamKeyWithSong' not in res: + raise ExtractorError( + 'Metadata not found. URL may be malformed, or Grooveshark API may have changed.') + + if res['getStreamKeyWithSong'] is None: + raise ExtractorError( + 'Metadata download failed, probably due to Grooveshark anti-abuse throttling. Wait at least an hour before retrying from this IP.', + expected=True) + + return res['getStreamKeyWithSong'] + + def _get_bootstrap(self, target): + (bootstrap_url, token) = self._build_bootstrap_url(target) + + headers = {'Referer': compat_urlparse.urldefrag(target)[0]} + req = compat_urllib_request.Request(bootstrap_url, headers=headers) + res = self._download_json(req, token, fatal=False, + note='Downloading player bootstrap data', + errnote='Unable to download player bootstrap data', + transform_source=self._transform_bootstrap) + return res + + def _get_playerpage(self, target): + (_, _, token) = self._parse_target(target) + + webpage = self._download_webpage( + target, token, + note='Downloading player page', + errnote='Unable to download player page', + fatal=False) + + if webpage is not None: + # Search (for example German) error message + error_msg = self._html_search_regex( + r'<div id="content">\s*<h2>(.*?)</h2>', webpage, + 'error message', default=None) + if error_msg is not None: + error_msg = error_msg.replace('\n', ' ') + raise ExtractorError('Grooveshark said: %s' % error_msg) + + if webpage is not None: + o = GroovesharkHtmlParser.extract_object_tags(webpage) + return (webpage, [x for x in o if x['attrs']['id'] == 'jsPlayerEmbed']) + + return (webpage, None) + + def _real_initialize(self): + self.ts = int(time.time() * 1000) # timestamp in millis + + def _real_extract(self, url): + (target_uri, _, token) = self._parse_target(url) + + # 1. Fill cookiejar by making a request to the player page + swf_referer = None + if self.do_playerpage_request: + (_, player_objs) = self._get_playerpage(url) + if player_objs is not None: + swf_referer = self._build_swf_referer(url, player_objs[0]) + self.to_screen('SWF Referer: %s' % swf_referer) + + # 2. Ask preload.php for swf bootstrap data to better mimic webapp + if self.do_bootstrap_request: + bootstrap = self._get_bootstrap(url) + self.to_screen('CommunicationToken: %s' % bootstrap['getCommunicationToken']) + + # 3. Ask preload.php for track metadata. + meta = self._get_meta(url) + + # 4. Construct stream request for track. + stream_url = self._build_stream_url(meta) + duration = int(math.ceil(float(meta['streamKey']['uSecs']) / 1000000)) + post_dict = {'streamKey': meta['streamKey']['streamKey']} + post_data = compat_urllib_parse.urlencode(post_dict).encode('utf-8') + headers = { + 'Content-Length': len(post_data), + 'Content-Type': 'application/x-www-form-urlencoded' + } + if swf_referer is not None: + headers['Referer'] = swf_referer + + return { + 'id': token, + 'title': meta['song']['Name'], + 'http_method': 'POST', + 'url': stream_url, + 'ext': 'mp3', + 'format': 'mp3 audio', + 'duration': duration, + 'http_post_data': post_data, + 'http_headers': headers, + } diff --git a/youtube_dl/extractor/hornbunny.py b/youtube_dl/extractor/hornbunny.py new file mode 100644 index 000000000..7e7714438 --- /dev/null +++ b/youtube_dl/extractor/hornbunny.py @@ -0,0 +1,56 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_duration, +) + + +class HornBunnyIE(InfoExtractor): + _VALID_URL = r'http?://(?:www\.)?hornbunny\.com/videos/(?P<title_dash>[a-z-]+)-(?P<id>\d+)\.html' + _TEST = { + 'url': 'http://hornbunny.com/videos/panty-slut-jerk-off-instruction-5227.html', + 'md5': '95e40865aedd08eff60272b704852ad7', + 'info_dict': { + 'id': '5227', + 'ext': 'flv', + 'title': 'panty slut jerk off instruction', + 'duration': 550, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage( + url, video_id, note='Downloading initial webpage') + title = self._html_search_regex( + r'class="title">(.*?)</h2>', webpage, 'title') + redirect_url = self._html_search_regex( + r'pg&settings=(.*?)\|0"\);', webpage, 'title') + webpage2 = self._download_webpage(redirect_url, video_id) + video_url = self._html_search_regex( + r'flvMask:(.*?);', webpage2, 'video_url') + + duration = parse_duration(self._search_regex( + r'<strong>Runtime:</strong>\s*([0-9:]+)</div>', + webpage, 'duration', fatal=False)) + view_count = int_or_none(self._search_regex( + r'<strong>Views:</strong>\s*(\d+)</div>', + webpage, 'view count', fatal=False)) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'ext': 'flv', + 'duration': duration, + 'view_count': view_count, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/howstuffworks.py b/youtube_dl/extractor/howstuffworks.py new file mode 100644 index 000000000..68684b997 --- /dev/null +++ b/youtube_dl/extractor/howstuffworks.py @@ -0,0 +1,134 @@ +from __future__ import unicode_literals + +import re +import json +import random +import string + +from .common import InfoExtractor +from ..utils import find_xpath_attr + + +class HowStuffWorksIE(InfoExtractor): + _VALID_URL = r'https?://[\da-z-]+\.howstuffworks\.com/(?:[^/]+/)*\d+-(?P<id>.+?)-video\.htm' + _TESTS = [ + { + 'url': 'http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm', + 'info_dict': { + 'id': '450221', + 'display_id': 'cool-jobs-iditarod-musher', + 'ext': 'flv', + 'title': 'Cool Jobs - Iditarod Musher', + 'description': 'md5:82bb58438a88027b8186a1fccb365f90', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + 'params': { + # md5 is not consistent + 'skip_download': True + } + }, + { + 'url': 'http://adventure.howstuffworks.com/39516-deadliest-catch-jakes-farewell-pots-video.htm', + 'info_dict': { + 'id': '553470', + 'display_id': 'deadliest-catch-jakes-farewell-pots', + 'ext': 'mp4', + 'title': 'Deadliest Catch: Jake\'s Farewell Pots', + 'description': 'md5:9632c346d5e43ee238028c9cefd8dbbc', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + 'params': { + # md5 is not consistent + 'skip_download': True + } + }, + { + 'url': 'http://entertainment.howstuffworks.com/arts/2706-sword-swallowing-1-by-dan-meyer-video.htm', + 'info_dict': { + 'id': '440011', + 'display_id': 'sword-swallowing-1-by-dan-meyer', + 'ext': 'flv', + 'title': 'Sword Swallowing #1 by Dan Meyer', + 'description': 'md5:b2409e88172913e2e7d3d1159b0ef735', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + 'params': { + # md5 is not consistent + 'skip_download': True + } + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('id') + webpage = self._download_webpage(url, display_id) + + content_id = self._search_regex(r'var siteSectionId="(\d+)";', webpage, 'content id') + + mp4 = self._search_regex( + r'''(?xs)var\s+clip\s*=\s*{\s* + .+?\s* + content_id\s*:\s*%s\s*,\s* + .+?\s* + mp4\s*:\s*\[(.*?),?\]\s* + };\s* + videoData\.push\(clip\);''' % content_id, + webpage, 'mp4', fatal=False, default=None) + + smil = self._download_xml( + 'http://services.media.howstuffworks.com/videos/%s/smil-service.smil' % content_id, + content_id, 'Downloading video SMIL') + + http_base = find_xpath_attr( + smil, + './{0}head/{0}meta'.format('{http://www.w3.org/2001/SMIL20/Language}'), + 'name', + 'httpBase').get('content') + + def random_string(str_len=0): + return ''.join([random.choice(string.ascii_uppercase) for _ in range(str_len)]) + + URL_SUFFIX = '?v=2.11.3&fp=LNX 11,2,202,356&r=%s&g=%s' % (random_string(5), random_string(12)) + + formats = [] + + if mp4: + for video in json.loads('[%s]' % mp4): + bitrate = video['bitrate'] + fmt = { + 'url': video['src'].replace('http://pmd.video.howstuffworks.com', http_base) + URL_SUFFIX, + 'format_id': bitrate, + } + m = re.search(r'(?P<vbr>\d+)[Kk]', bitrate) + if m: + fmt['vbr'] = int(m.group('vbr')) + formats.append(fmt) + else: + for video in smil.findall( + './/{0}body/{0}switch/{0}video'.format('{http://www.w3.org/2001/SMIL20/Language}')): + vbr = int(video.attrib['system-bitrate']) / 1000 + formats.append({ + 'url': '%s/%s%s' % (http_base, video.attrib['src'], URL_SUFFIX), + 'format_id': '%dk' % vbr, + 'vbr': vbr, + }) + + self._sort_formats(formats) + + title = self._og_search_title(webpage) + TITLE_SUFFIX = ' : HowStuffWorks' + if title.endswith(TITLE_SUFFIX): + title = title[:-len(TITLE_SUFFIX)] + + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail(webpage) + + return { + 'id': content_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/ign.py b/youtube_dl/extractor/ign.py index 1f42c6d3a..9e8b69f57 100644 --- a/youtube_dl/extractor/ign.py +++ b/youtube_dl/extractor/ign.py @@ -18,6 +18,7 @@ class IGNIE(InfoExtractor): _DESCRIPTION_RE = [ r'<span class="page-object-description">(.+?)</span>', r'id="my_show_video">.*?<p>(.*?)</p>', + r'<meta name="description" content="(.*?)"', ] _TESTS = [ @@ -55,6 +56,17 @@ class IGNIE(InfoExtractor): 'skip_download': True, }, }, + { + 'url': 'http://www.ign.com/articles/2014/08/15/rewind-theater-wild-trailer-gamescom-2014?watch', + 'md5': '4e9a0bda1e5eebd31ddcf86ec0b9b3c7', + 'info_dict': { + 'id': '078fdd005f6d3c02f63d795faa1b984f', + 'ext': 'mp4', + 'title': 'Rewind Theater - Wild Trailer Gamescom 2014', + 'description': 'Giant skeletons, bloody hunts, and captivating' + ' natural beauty take our breath away.', + }, + }, ] def _find_video_id(self, webpage): @@ -62,6 +74,7 @@ class IGNIE(InfoExtractor): r'data-video-id="(.+?)"', r'<object id="vid_(.+?)"', r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"', + r'class="hero-poster[^"]*?"[^>]*id="(.+?)"', ] return self._search_regex(res_id, webpage, 'video id') @@ -70,10 +83,7 @@ class IGNIE(InfoExtractor): name_or_id = mobj.group('name_or_id') page_type = mobj.group('type') webpage = self._download_webpage(url, name_or_id) - if page_type == 'articles': - video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, 'video url') - return self.url_result(video_url, ie='IGN') - elif page_type != 'video': + if page_type != 'video': multiple_urls = re.findall( '<param name="flashvars" value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]', webpage) diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 7cee505c0..4536db3bf 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -63,6 +63,14 @@ class ImdbListIE(InfoExtractor): IE_NAME = 'imdb:list' IE_DESC = 'Internet Movie Database lists' _VALID_URL = r'http://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})' + _TEST = { + 'url': 'http://www.imdb.com/list/JFs9NWw6XI0', + 'info_dict': { + 'id': 'JFs9NWw6XI0', + 'title': 'March 23, 2012 Releases', + }, + 'playlist_count': 7, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index b5372bf7a..5109f26ce 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -46,6 +46,30 @@ class InstagramUserIE(InfoExtractor): _VALID_URL = r'http://instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])' IE_DESC = 'Instagram user profile' IE_NAME = 'instagram:user' + _TEST = { + 'url': 'http://instagram.com/porsche', + 'info_dict': { + 'id': 'porsche', + 'title': 'porsche', + }, + 'playlist_mincount': 2, + 'playlist': [{ + 'info_dict': { + 'id': '614605558512799803_462752227', + 'ext': 'mp4', + 'title': '#Porsche Intelligent Performance.', + 'thumbnail': 're:^https?://.*\.jpg', + 'uploader': 'Porsche', + 'uploader_id': 'porsche', + 'timestamp': 1387486713, + 'upload_date': '20131219', + }, + }], + 'params': { + 'extract_flat': True, + 'skip_download': True, + } + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index 4027deb70..75b543b7c 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -127,6 +127,21 @@ class IviCompilationIE(InfoExtractor): IE_DESC = 'ivi.ru compilations' IE_NAME = 'ivi:compilation' _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$' + _TESTS = [{ + 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa', + 'info_dict': { + 'id': 'dvoe_iz_lartsa', + 'title': 'Двое из ларца (2006 - 2008)', + }, + 'playlist_mincount': 24, + }, { + 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/season1', + 'info_dict': { + 'id': 'dvoe_iz_lartsa/season1', + 'title': 'Двое из ларца (2006 - 2008) 1 сезон', + }, + 'playlist_mincount': 12, + }] def _extract_entries(self, html, compilation_id): return [self.url_result('http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), 'Ivi') diff --git a/youtube_dl/extractor/izlesene.py b/youtube_dl/extractor/izlesene.py new file mode 100644 index 000000000..79e8430b5 --- /dev/null +++ b/youtube_dl/extractor/izlesene.py @@ -0,0 +1,97 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + get_element_by_id, + parse_iso8601, + determine_ext, + int_or_none, + str_to_int, +) + + +class IzleseneIE(InfoExtractor): + _VALID_URL = r'https?://(?:(?:www|m)\.)?izlesene\.com/(?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)' + _STREAM_URL = 'http://panel.izlesene.com/api/streamurl/{id:}/{format:}' + _TEST = { + 'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694', + 'md5': '4384f9f0ea65086734b881085ee05ac2', + 'info_dict': { + 'id': '7599694', + 'ext': 'mp4', + 'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi', + 'description': 'Annesi oğluna doğum günü hediyesi olarak minecraft cd si alıyor, ve çocuk hunharca seviniyor', + 'thumbnail': 're:^http://.*\.jpg', + 'uploader_id': 'pelikzzle', + 'timestamp': 1404298698, + 'upload_date': '20140702', + 'duration': 95.395, + 'age_limit': 0, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + url = 'http://www.izlesene.com/video/%s' % video_id + + webpage = self._download_webpage(url, video_id) + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail(webpage) + + uploader = self._html_search_regex( + r"adduserUsername\s*=\s*'([^']+)';", webpage, 'uploader', fatal=False, default='') + timestamp = parse_iso8601(self._html_search_meta( + 'uploadDate', webpage, 'upload date', fatal=False)) + + duration = int_or_none(self._html_search_regex( + r'"videoduration"\s*:\s*"([^"]+)"', webpage, 'duration', fatal=False)) + if duration: + duration /= 1000.0 + + view_count = str_to_int(get_element_by_id('videoViewCount', webpage)) + comment_count = self._html_search_regex( + r'comment_count\s*=\s*\'([^\']+)\';', webpage, 'uploader', fatal=False) + + family_friendly = self._html_search_meta( + 'isFamilyFriendly', webpage, 'age limit', fatal=False) + + content_url = self._html_search_meta( + 'contentURL', webpage, 'content URL', fatal=False) + ext = determine_ext(content_url, 'mp4') + + # Might be empty for some videos. + qualities = self._html_search_regex( + r'"quality"\s*:\s*"([^"]+)"', webpage, 'qualities', fatal=False, default='') + + formats = [] + for quality in qualities.split('|'): + json = self._download_json( + self._STREAM_URL.format(id=video_id, format=quality), video_id, + note='Getting video URL for "%s" quality' % quality, + errnote='Failed to get video URL for "%s" quality' % quality + ) + formats.append({ + 'url': json.get('streamurl'), + 'ext': ext, + 'format_id': '%sp' % quality if quality else 'sd', + }) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'uploader_id': uploader, + 'timestamp': timestamp, + 'duration': duration, + 'view_count': int_or_none(view_count), + 'comment_count': int_or_none(comment_count), + 'age_limit': 18 if family_friendly == 'False' else 0, + 'formats': formats, + } diff --git a/youtube_dl/extractor/jove.py b/youtube_dl/extractor/jove.py new file mode 100644 index 000000000..cf73cd753 --- /dev/null +++ b/youtube_dl/extractor/jove.py @@ -0,0 +1,80 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + unified_strdate +) + + +class JoveIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?jove\.com/video/(?P<id>[0-9]+)' + _CHAPTERS_URL = 'http://www.jove.com/video-chapters?videoid={video_id:}' + _TESTS = [ + { + 'url': 'http://www.jove.com/video/2744/electrode-positioning-montage-transcranial-direct-current', + 'md5': '93723888d82dbd6ba8b3d7d0cd65dd2b', + 'info_dict': { + 'id': '2744', + 'ext': 'mp4', + 'title': 'Electrode Positioning and Montage in Transcranial Direct Current Stimulation', + 'description': 'md5:015dd4509649c0908bc27f049e0262c6', + 'thumbnail': 're:^https?://.*\.png$', + 'upload_date': '20110523', + } + }, + { + 'url': 'http://www.jove.com/video/51796/culturing-caenorhabditis-elegans-axenic-liquid-media-creation', + 'md5': '914aeb356f416811d911996434811beb', + 'info_dict': { + 'id': '51796', + 'ext': 'mp4', + 'title': 'Culturing Caenorhabditis elegans in Axenic Liquid Media and Creation of Transgenic Worms by Microparticle Bombardment', + 'description': 'md5:35ff029261900583970c4023b70f1dc9', + 'thumbnail': 're:^https?://.*\.png$', + 'upload_date': '20140802', + } + }, + + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + chapters_id = self._html_search_regex( + r'/video-chapters\?videoid=([0-9]+)', webpage, 'chapters id') + + chapters_xml = self._download_xml( + self._CHAPTERS_URL.format(video_id=chapters_id), + video_id, note='Downloading chapters XML', + errnote='Failed to download chapters XML') + + video_url = chapters_xml.attrib.get('video') + if not video_url: + raise ExtractorError('Failed to get the video URL') + + title = self._html_search_meta('citation_title', webpage, 'title') + thumbnail = self._og_search_thumbnail(webpage) + description = self._html_search_regex( + r'<div id="section_body_summary"><p class="jove_content">(.+?)</p>', + webpage, 'description', fatal=False) + publish_date = unified_strdate(self._html_search_meta( + 'citation_publication_date', webpage, 'publish date', fatal=False)) + comment_count = self._html_search_regex( + r'<meta name="num_comments" content="(\d+) Comments?"', + webpage, 'comment count', fatal=False) + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'thumbnail': thumbnail, + 'description': description, + 'upload_date': publish_date, + 'comment_count': comment_count, + } diff --git a/youtube_dl/extractor/justintv.py b/youtube_dl/extractor/justintv.py index 7083db12e..27017e89f 100644 --- a/youtube_dl/extractor/justintv.py +++ b/youtube_dl/extractor/justintv.py @@ -1,5 +1,6 @@ from __future__ import unicode_literals +import itertools import json import os import re @@ -43,10 +44,11 @@ class JustinTVIE(InfoExtractor): } # Return count of items, list of *valid* items - def _parse_page(self, url, video_id): - info_json = self._download_webpage(url, video_id, - 'Downloading video info JSON', - 'unable to download video info JSON') + def _parse_page(self, url, video_id, counter): + info_json = self._download_webpage( + url, video_id, + 'Downloading video info JSON on page %d' % counter, + 'Unable to download video info JSON %d' % counter) response = json.loads(info_json) if type(response) != list: @@ -138,11 +140,10 @@ class JustinTVIE(InfoExtractor): entries = [] offset = 0 limit = self._JUSTIN_PAGE_LIMIT - while True: - if paged: - self.report_download_page(video_id, offset) + for counter in itertools.count(1): page_url = api + ('?offset=%d&limit=%d' % (offset, limit)) - page_count, page_info = self._parse_page(page_url, video_id) + page_count, page_info = self._parse_page( + page_url, video_id, counter) entries.extend(page_info) if not paged or page_count != limit: break diff --git a/youtube_dl/extractor/khanacademy.py b/youtube_dl/extractor/khanacademy.py index 772bb5671..04bac7517 100644 --- a/youtube_dl/extractor/khanacademy.py +++ b/youtube_dl/extractor/khanacademy.py @@ -12,18 +12,27 @@ class KhanAcademyIE(InfoExtractor): _VALID_URL = r'^https?://(?:www\.)?khanacademy\.org/(?P<key>[^/]+)/(?:[^/]+/){,2}(?P<id>[^?#/]+)(?:$|[?#])' IE_NAME = 'KhanAcademy' - _TEST = { + _TESTS = [{ 'url': 'http://www.khanacademy.org/video/one-time-pad', - 'file': 'one-time-pad.mp4', 'md5': '7021db7f2d47d4fff89b13177cb1e8f4', 'info_dict': { + 'id': 'one-time-pad', + 'ext': 'mp4', 'title': 'The one-time pad', 'description': 'The perfect cipher', 'duration': 176, 'uploader': 'Brit Cruise', 'upload_date': '20120411', } - } + }, { + 'url': 'https://www.khanacademy.org/math/applied-math/cryptography', + 'info_dict': { + 'id': 'cryptography', + 'title': 'Journey into cryptography', + 'description': 'How have humans protected their secret messages through history? What has changed today?', + }, + 'playlist_mincount': 3, + }] def _real_extract(self, url): m = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/kickstarter.py b/youtube_dl/extractor/kickstarter.py index 961dd1aa6..56a76380c 100644 --- a/youtube_dl/extractor/kickstarter.py +++ b/youtube_dl/extractor/kickstarter.py @@ -8,7 +8,7 @@ from .common import InfoExtractor class KickStarterIE(InfoExtractor): _VALID_URL = r'https?://www\.kickstarter\.com/projects/(?P<id>[^/]*)/.*' - _TEST = { + _TESTS = [{ 'url': 'https://www.kickstarter.com/projects/1404461844/intersection-the-story-of-josh-grant?ref=home_location', 'md5': 'c81addca81327ffa66c642b5d8b08cab', 'info_dict': { @@ -18,22 +18,45 @@ class KickStarterIE(InfoExtractor): 'description': 'A unique motocross documentary that examines the ' 'life and mind of one of sports most elite athletes: Josh Grant.', }, - } + }, { + 'note': 'Embedded video (not using the native kickstarter video service)', + 'url': 'https://www.kickstarter.com/projects/597507018/pebble-e-paper-watch-for-iphone-and-android/posts/659178', + 'playlist': [ + { + 'info_dict': { + 'id': '78704821', + 'ext': 'mp4', + 'uploader_id': 'pebble', + 'uploader': 'Pebble Technology', + 'title': 'Pebble iOS Notifications', + } + } + ], + }] def _real_extract(self, url): m = re.match(self._VALID_URL, url) video_id = m.group('id') webpage = self._download_webpage(url, video_id) - video_url = self._search_regex(r'data-video-url="(.*?)"', - webpage, 'video URL') - video_title = self._html_search_regex(r'<title>(.*?)</title>', - webpage, 'title').rpartition('— Kickstarter')[0].strip() + title = self._html_search_regex( + r'<title>\s*(.*?)(?:\s*— Kickstarter)?\s*</title>', + webpage, 'title') + video_url = self._search_regex( + r'data-video-url="(.*?)"', + webpage, 'video URL', default=None) + if video_url is None: # No native kickstarter, look for embedded videos + return { + '_type': 'url_transparent', + 'ie_key': 'Generic', + 'url': url, + 'title': title, + } return { 'id': video_id, 'url': video_url, - 'title': video_title, + 'title': title, 'description': self._og_search_description(webpage), 'thumbnail': self._og_search_thumbnail(webpage), } diff --git a/youtube_dl/extractor/krasview.py b/youtube_dl/extractor/krasview.py new file mode 100644 index 000000000..6f3d2345b --- /dev/null +++ b/youtube_dl/extractor/krasview.py @@ -0,0 +1,59 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + unescapeHTML, +) + + +class KrasViewIE(InfoExtractor): + IE_DESC = 'Красвью' + _VALID_URL = r'https?://krasview\.ru/video/(?P<id>\d+)' + + _TEST = { + 'url': 'http://krasview.ru/video/512228', + 'md5': '3b91003cf85fc5db277870c8ebd98eae', + 'info_dict': { + 'id': '512228', + 'ext': 'mp4', + 'title': 'Снег, лёд, заносы', + 'description': 'Снято в городе Нягань, в Ханты-Мансийском автономном округе.', + 'duration': 27, + 'thumbnail': 're:^https?://.*\.jpg', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + flashvars = json.loads(self._search_regex( + r'flashvars\s*:\s*({.+?})\s*}\);', webpage, 'flashvars')) + + video_url = flashvars['url'] + title = unescapeHTML(flashvars['title']) + description = unescapeHTML(flashvars.get('subtitle') or self._og_search_description(webpage, default=None)) + thumbnail = flashvars['image'] + duration = int(flashvars['duration']) + filesize = int(flashvars['size']) + width = int_or_none(self._og_search_property('video:width', webpage, 'video width')) + height = int_or_none(self._og_search_property('video:height', webpage, 'video height')) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'filesize': filesize, + 'width': width, + 'height': height, + } diff --git a/youtube_dl/extractor/livestream.py b/youtube_dl/extractor/livestream.py index 2c100d424..516147417 100644 --- a/youtube_dl/extractor/livestream.py +++ b/youtube_dl/extractor/livestream.py @@ -5,18 +5,21 @@ import json from .common import InfoExtractor from ..utils import ( + compat_str, compat_urllib_parse_urlparse, compat_urlparse, - xpath_with_ns, - compat_str, + ExtractorError, + find_xpath_attr, + int_or_none, orderedSet, + xpath_with_ns, ) class LivestreamIE(InfoExtractor): IE_NAME = 'livestream' _VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$' - _TEST = { + _TESTS = [{ 'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370', 'md5': '53274c76ba7754fb0e8d072716f2292b', 'info_dict': { @@ -24,18 +27,88 @@ class LivestreamIE(InfoExtractor): 'ext': 'mp4', 'title': 'Live from Webster Hall NYC', 'upload_date': '20121012', + 'like_count': int, + 'view_count': int, + 'thumbnail': 're:^http://.*\.jpg$' } - } + }, { + 'url': 'http://new.livestream.com/tedx/cityenglish', + 'info_dict': { + 'title': 'TEDCity2.0 (English)', + }, + 'playlist_mincount': 4, + }] + + def _parse_smil(self, video_id, smil_url): + formats = [] + _SWITCH_XPATH = ( + './/{http://www.w3.org/2001/SMIL20/Language}body/' + '{http://www.w3.org/2001/SMIL20/Language}switch') + smil_doc = self._download_xml( + smil_url, video_id, + note='Downloading SMIL information', + errnote='Unable to download SMIL information', + fatal=False) + if smil_doc is False: # Download failed + return formats + title_node = find_xpath_attr( + smil_doc, './/{http://www.w3.org/2001/SMIL20/Language}meta', + 'name', 'title') + if title_node is None: + self.report_warning('Cannot find SMIL id') + switch_node = smil_doc.find(_SWITCH_XPATH) + else: + title_id = title_node.attrib['content'] + switch_node = find_xpath_attr( + smil_doc, _SWITCH_XPATH, 'id', title_id) + if switch_node is None: + raise ExtractorError('Cannot find switch node') + video_nodes = switch_node.findall( + '{http://www.w3.org/2001/SMIL20/Language}video') + + for vn in video_nodes: + tbr = int_or_none(vn.attrib.get('system-bitrate')) + furl = ( + 'http://livestream-f.akamaihd.net/%s?v=3.0.3&fp=WIN%%2014,0,0,145' % + (vn.attrib['src'])) + if 'clipBegin' in vn.attrib: + furl += '&ssek=' + vn.attrib['clipBegin'] + formats.append({ + 'url': furl, + 'format_id': 'smil_%d' % tbr, + 'ext': 'flv', + 'tbr': tbr, + 'preference': -1000, + }) + return formats def _extract_video_info(self, video_data): - video_url = video_data.get('progressive_url_hd') or video_data.get('progressive_url') + video_id = compat_str(video_data['id']) + + FORMAT_KEYS = ( + ('sd', 'progressive_url'), + ('hd', 'progressive_url_hd'), + ) + formats = [{ + 'format_id': format_id, + 'url': video_data[key], + 'quality': i + 1, + } for i, (format_id, key) in enumerate(FORMAT_KEYS) + if video_data.get(key)] + + smil_url = video_data.get('smil_url') + if smil_url: + formats.extend(self._parse_smil(video_id, smil_url)) + self._sort_formats(formats) + return { - 'id': compat_str(video_data['id']), - 'url': video_url, - 'ext': 'mp4', + 'id': video_id, + 'formats': formats, 'title': video_data['caption'], - 'thumbnail': video_data['thumbnail_url'], + 'thumbnail': video_data.get('thumbnail_url'), 'upload_date': video_data['updated_at'].replace('-', '')[:8], + 'like_count': video_data.get('likes', {}).get('total'), + 'view_count': video_data.get('views'), } def _real_extract(self, url): @@ -44,22 +117,37 @@ class LivestreamIE(InfoExtractor): event_name = mobj.group('event_name') webpage = self._download_webpage(url, video_id or event_name) + og_video = self._og_search_video_url( + webpage, 'player url', fatal=False, default=None) + if og_video is not None: + query_str = compat_urllib_parse_urlparse(og_video).query + query = compat_urlparse.parse_qs(query_str) + if 'play_url' in query: + api_url = query['play_url'][0].replace('.smil', '') + info = json.loads(self._download_webpage( + api_url, video_id, 'Downloading video info')) + return self._extract_video_info(info) + + config_json = self._search_regex( + r'window.config = ({.*?});', webpage, 'window config') + info = json.loads(config_json)['event'] + + def is_relevant(vdata, vid): + result = vdata['type'] == 'video' + if video_id is not None: + result = result and compat_str(vdata['data']['id']) == vid + return result + + videos = [self._extract_video_info(video_data['data']) + for video_data in info['feed']['data'] + if is_relevant(video_data, video_id)] if video_id is None: # This is an event page: - config_json = self._search_regex( - r'window.config = ({.*?});', webpage, 'window config') - info = json.loads(config_json)['event'] - videos = [self._extract_video_info(video_data['data']) - for video_data in info['feed']['data'] if video_data['type'] == 'video'] return self.playlist_result(videos, info['id'], info['full_name']) else: - og_video = self._og_search_video_url(webpage, 'player url') - query_str = compat_urllib_parse_urlparse(og_video).query - query = compat_urlparse.parse_qs(query_str) - api_url = query['play_url'][0].replace('.smil', '') - info = json.loads(self._download_webpage( - api_url, video_id, 'Downloading video info')) - return self._extract_video_info(info) + if not videos: + raise ExtractorError('Cannot find video %s' % video_id) + return videos[0] # The original version of Livestream uses a different system @@ -69,7 +157,7 @@ class LivestreamOriginalIE(InfoExtractor): (?P<user>[^/]+)/(?P<type>video|folder) (?:\?.*?Id=|/)(?P<id>.*?)(&|$) ''' - _TEST = { + _TESTS = [{ 'url': 'http://www.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb', 'info_dict': { 'id': 'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb', @@ -80,7 +168,13 @@ class LivestreamOriginalIE(InfoExtractor): # rtmp 'skip_download': True, }, - } + }, { + 'url': 'https://www.livestream.com/newplay/folder?dirId=a07bf706-d0e4-4e75-a747-b021d84f2fd3', + 'info_dict': { + 'id': 'a07bf706-d0e4-4e75-a747-b021d84f2fd3', + }, + 'playlist_mincount': 4, + }] def _extract_video(self, user, video_id): api_url = 'http://x{0}x.api.channel.livestream.com/2.0/clipdetails?extendedInfo=true&id={1}'.format(user, video_id) @@ -103,15 +197,19 @@ class LivestreamOriginalIE(InfoExtractor): def _extract_folder(self, url, folder_id): webpage = self._download_webpage(url, folder_id) - urls = orderedSet(re.findall(r'<a href="(https?://livestre\.am/.*?)"', webpage)) + paths = orderedSet(re.findall( + r'''(?x)(?: + <li\s+class="folder">\s*<a\s+href="| + <a\s+href="(?=https?://livestre\.am/) + )([^"]+)"''', webpage)) return { '_type': 'playlist', 'id': folder_id, 'entries': [{ '_type': 'url', - 'url': video_url, - } for video_url in urls], + 'url': compat_urlparse.urljoin(url, p), + } for p in paths], } def _real_extract(self, url): diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py index 6436c05a3..1a896b536 100644 --- a/youtube_dl/extractor/metacafe.py +++ b/youtube_dl/extractor/metacafe.py @@ -9,6 +9,7 @@ from ..utils import ( compat_urllib_request, determine_ext, ExtractorError, + int_or_none, ) @@ -83,6 +84,21 @@ class MetacafeIE(InfoExtractor): 'skip_download': True, }, }, + # Movieclips.com video + { + 'url': 'http://www.metacafe.com/watch/mv-Wy7ZU/my_week_with_marilyn_do_you_love_me/', + 'info_dict': { + 'id': 'mv-Wy7ZU', + 'ext': 'mp4', + 'title': 'My Week with Marilyn - Do You Love Me?', + 'description': 'From the movie My Week with Marilyn - Colin (Eddie Redmayne) professes his love to Marilyn (Michelle Williams) and gets her to promise to return to set and finish the movie.', + 'uploader': 'movie_trailers', + 'duration': 176, + }, + 'params': { + 'skip_download': 'requires rtmpdump', + } + } ] def report_disclaimer(self): @@ -134,6 +150,7 @@ class MetacafeIE(InfoExtractor): # Extract URL, uploader and title from webpage self.report_extraction(video_id) + video_url = None mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) if mobj is not None: mediaURL = compat_urllib_parse.unquote(mobj.group(1)) @@ -146,16 +163,17 @@ class MetacafeIE(InfoExtractor): else: gdaKey = mobj.group(1) video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) - else: + if video_url is None: mobj = re.search(r'<video src="([^"]+)"', webpage) if mobj: video_url = mobj.group(1) video_ext = 'mp4' - else: - mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) - if mobj is None: - raise ExtractorError('Unable to extract media URL') - vardict = compat_parse_qs(mobj.group(1)) + if video_url is None: + flashvars = self._search_regex( + r' name="flashvars" value="(.*?)"', webpage, 'flashvars', + default=None) + if flashvars: + vardict = compat_parse_qs(flashvars) if 'mediaData' not in vardict: raise ExtractorError('Unable to extract media URL') mobj = re.search( @@ -165,26 +183,68 @@ class MetacafeIE(InfoExtractor): mediaURL = mobj.group('mediaURL').replace('\\/', '/') video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key')) video_ext = determine_ext(video_url) - - video_title = self._html_search_regex(r'(?im)<title>(.*) - Video</title>', webpage, 'title') + if video_url is None: + player_url = self._search_regex( + r"swfobject\.embedSWF\('([^']+)'", + webpage, 'config URL', default=None) + if player_url: + config_url = self._search_regex( + r'config=(.+)$', player_url, 'config URL') + config_doc = self._download_xml( + config_url, video_id, + note='Downloading video config') + smil_url = config_doc.find('.//properties').attrib['smil_file'] + smil_doc = self._download_xml( + smil_url, video_id, + note='Downloading SMIL document') + base_url = smil_doc.find('./head/meta').attrib['base'] + video_url = [] + for vn in smil_doc.findall('.//video'): + br = int(vn.attrib['system-bitrate']) + play_path = vn.attrib['src'] + video_url.append({ + 'format_id': 'smil-%d' % br, + 'url': base_url, + 'play_path': play_path, + 'page_url': url, + 'player_url': player_url, + 'ext': play_path.partition(':')[0], + }) + + if video_url is None: + raise ExtractorError('Unsupported video type') + + video_title = self._html_search_regex( + r'(?im)<title>(.*) - Video</title>', webpage, 'title') description = self._og_search_description(webpage) thumbnail = self._og_search_thumbnail(webpage) video_uploader = self._html_search_regex( r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);', webpage, 'uploader nickname', fatal=False) + duration = int_or_none( + self._html_search_meta('video:duration', webpage)) + + age_limit = ( + 18 + if re.search(r'"contentRating":"restricted"', webpage) + else 0) - if re.search(r'"contentRating":"restricted"', webpage) is not None: - age_limit = 18 + if isinstance(video_url, list): + formats = video_url else: - age_limit = 0 + formats = [{ + 'url': video_url, + 'ext': video_ext, + }] + self._sort_formats(formats) return { 'id': video_id, - 'url': video_url, 'description': description, 'uploader': video_uploader, 'title': video_title, - 'thumbnail':thumbnail, - 'ext': video_ext, + 'thumbnail': thumbnail, 'age_limit': age_limit, + 'formats': formats, + 'duration': duration, } diff --git a/youtube_dl/extractor/ministrygrid.py b/youtube_dl/extractor/ministrygrid.py new file mode 100644 index 000000000..949ad11db --- /dev/null +++ b/youtube_dl/extractor/ministrygrid.py @@ -0,0 +1,57 @@ +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + smuggle_url, +) + + +class MinistryGridIE(InfoExtractor): + _VALID_URL = r'https?://www\.ministrygrid.com/([^/?#]*/)*(?P<id>[^/#?]+)/?(?:$|[?#])' + + _TEST = { + 'url': 'http://www.ministrygrid.com/training-viewer/-/training/t4g-2014-conference/the-gospel-by-numbers-4/the-gospel-by-numbers', + 'md5': '844be0d2a1340422759c2a9101bab017', + 'info_dict': { + 'id': '3453494717001', + 'ext': 'mp4', + 'title': 'The Gospel by Numbers', + 'description': 'Coming soon from T4G 2014!', + 'uploader': 'LifeWay Christian Resources (MG)', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + portlets_json = self._search_regex( + r'Liferay\.Portlet\.list=(\[.+?\])', webpage, 'portlet list') + portlets = json.loads(portlets_json) + pl_id = self._search_regex( + r'<!--\s*p_l_id - ([0-9]+)<br>', webpage, 'p_l_id') + + for i, portlet in enumerate(portlets): + portlet_url = 'http://www.ministrygrid.com/c/portal/render_portlet?p_l_id=%s&p_p_id=%s' % (pl_id, portlet) + portlet_code = self._download_webpage( + portlet_url, video_id, + note='Looking in portlet %s (%d/%d)' % (portlet, i + 1, len(portlets)), + fatal=False) + video_iframe_url = self._search_regex( + r'<iframe.*?src="([^"]+)"', portlet_code, 'video iframe', + default=None) + if video_iframe_url: + surl = smuggle_url( + video_iframe_url, {'force_videoid': video_id}) + return { + '_type': 'url', + 'id': video_id, + 'url': surl, + } + + raise ExtractorError('Could not find video iframe in any portlets') diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py new file mode 100644 index 000000000..979f3d692 --- /dev/null +++ b/youtube_dl/extractor/mitele.py @@ -0,0 +1,60 @@ +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + get_element_by_attribute, + parse_duration, + strip_jsonp, +) + + +class MiTeleIE(InfoExtractor): + IE_NAME = 'mitele.es' + _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<episode>[^/]+)/' + + _TEST = { + 'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/', + 'md5': '6a75fe9d0d3275bead0cb683c616fddb', + 'info_dict': { + 'id': '0fce117d', + 'ext': 'mp4', + 'title': 'Programa 144 - Tor, la web invisible', + 'description': 'md5:3b6fce7eaa41b2d97358726378d9369f', + 'display_id': 'programa-144', + 'duration': 2913, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + episode = mobj.group('episode') + webpage = self._download_webpage(url, episode) + embed_data_json = self._search_regex( + r'MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data', + flags=re.DOTALL + ).replace('\'', '"') + embed_data = json.loads(embed_data_json) + + info_url = embed_data['flashvars']['host'] + info_el = self._download_xml(info_url, episode).find('./video/info') + + video_link = info_el.find('videoUrl/link').text + token_query = compat_urllib_parse.urlencode({'id': video_link}) + token_info = self._download_json( + 'http://token.mitele.es/?' + token_query, episode, + transform_source=strip_jsonp + ) + + return { + 'id': embed_data['videoId'], + 'display_id': episode, + 'title': info_el.find('title').text, + 'url': token_info['tokenizedUrl'], + 'description': get_element_by_attribute('class', 'text', webpage), + 'thumbnail': info_el.find('thumb').text, + 'duration': parse_duration(info_el.find('duration').text), + } diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index 5f64e7bd0..520f27fca 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -6,6 +6,7 @@ from .common import InfoExtractor from ..utils import ( compat_urllib_parse, ExtractorError, + HEADRequest, int_or_none, parse_iso8601, ) @@ -38,7 +39,7 @@ class MixcloudIE(InfoExtractor): try: # We only want to know if the request succeed # don't download the whole file - self._request_webpage(url, None, False) + self._request_webpage(HEADRequest(url), None, False) return url except ExtractorError: url = None diff --git a/youtube_dl/extractor/mlb.py b/youtube_dl/extractor/mlb.py new file mode 100644 index 000000000..bfdb462eb --- /dev/null +++ b/youtube_dl/extractor/mlb.py @@ -0,0 +1,120 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + parse_iso8601, + find_xpath_attr, +) + + +class MLBIE(InfoExtractor): + _VALID_URL = r'https?://m\.mlb\.com/(?:(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v|shared/video/embed/embed\.html\?.*?\bcontent_id=)(?P<id>n?\d+)' + _TESTS = [ + { + 'url': 'http://m.mlb.com/sea/video/topic/51231442/v34698933/nymsea-ackley-robs-a-home-run-with-an-amazing-catch/?c_id=sea', + 'md5': 'ff56a598c2cf411a9a38a69709e97079', + 'info_dict': { + 'id': '34698933', + 'ext': 'mp4', + 'title': "Ackley's spectacular catch", + 'description': 'md5:7f5a981eb4f3cbc8daf2aeffa2215bf0', + 'duration': 66, + 'timestamp': 1405980600, + 'upload_date': '20140721', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, + { + 'url': 'http://m.mlb.com/video/topic/81536970/v34496663/mianym-stanton-practices-for-the-home-run-derby', + 'md5': 'd9c022c10d21f849f49c05ae12a8a7e9', + 'info_dict': { + 'id': '34496663', + 'ext': 'mp4', + 'title': 'Stanton prepares for Derby', + 'description': 'md5:d00ce1e5fd9c9069e9c13ab4faedfa57', + 'duration': 46, + 'timestamp': 1405105800, + 'upload_date': '20140711', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, + { + 'url': 'http://m.mlb.com/video/topic/vtp_hrd_sponsor/v34578115/hrd-cespedes-wins-2014-gillette-home-run-derby', + 'md5': '0e6e73d509321e142409b695eadd541f', + 'info_dict': { + 'id': '34578115', + 'ext': 'mp4', + 'title': 'Cespedes repeats as Derby champ', + 'description': 'md5:08df253ce265d4cf6fb09f581fafad07', + 'duration': 488, + 'timestamp': 1405399936, + 'upload_date': '20140715', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, + { + 'url': 'http://m.mlb.com/video/v34577915/bautista-on-derby-captaining-duties-his-performance', + 'md5': 'b8fd237347b844365d74ea61d4245967', + 'info_dict': { + 'id': '34577915', + 'ext': 'mp4', + 'title': 'Bautista on Home Run Derby', + 'description': 'md5:b80b34031143d0986dddc64a8839f0fb', + 'duration': 52, + 'timestamp': 1405390722, + 'upload_date': '20140715', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, + { + 'url': 'http://m.mlb.com/shared/video/embed/embed.html?content_id=35692085&topic_id=6479266&width=400&height=224&property=mlb', + 'only_matching': True, + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + detail = self._download_xml( + 'http://m.mlb.com/gen/multimedia/detail/%s/%s/%s/%s.xml' + % (video_id[-3], video_id[-2], video_id[-1], video_id), video_id) + + title = detail.find('./headline').text + description = detail.find('./big-blurb').text + duration = parse_duration(detail.find('./duration').text) + timestamp = parse_iso8601(detail.attrib['date'][:-5]) + + thumbnail = find_xpath_attr( + detail, './thumbnailScenarios/thumbnailScenario', 'type', '45').text + + formats = [] + for media_url in detail.findall('./url'): + playback_scenario = media_url.attrib['playback_scenario'] + fmt = { + 'url': media_url.text, + 'format_id': playback_scenario, + } + m = re.search(r'(?P<vbr>\d+)K_(?P<width>\d+)X(?P<height>\d+)', playback_scenario) + if m: + fmt.update({ + 'vbr': int(m.group('vbr')) * 1000, + 'width': int(m.group('width')), + 'height': int(m.group('height')), + }) + formats.append(fmt) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'duration': duration, + 'timestamp': timestamp, + 'formats': formats, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/mofosex.py b/youtube_dl/extractor/mofosex.py index b9430b09b..d658647e6 100644 --- a/youtube_dl/extractor/mofosex.py +++ b/youtube_dl/extractor/mofosex.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import os import re @@ -8,15 +10,17 @@ from ..utils import ( compat_urllib_parse, ) + class MofosexIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>mofosex\.com/videos/(?P<videoid>[0-9]+)/.*?\.html)' + _VALID_URL = r'^https?://(?:www\.)?(?P<url>mofosex\.com/videos/(?P<videoid>[0-9]+)/.*?\.html)' _TEST = { - u'url': u'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html', - u'file': u'5018.mp4', - u'md5': u'1b2eb47ac33cc75d4a80e3026b613c5a', - u'info_dict': { - u"title": u"Japanese Teen Music Video", - u"age_limit": 18, + 'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html', + 'md5': '1b2eb47ac33cc75d4a80e3026b613c5a', + 'info_dict': { + 'id': '5018', + 'ext': 'mp4', + 'title': 'Japanese Teen Music Video', + 'age_limit': 18, } } @@ -29,8 +33,8 @@ class MofosexIE(InfoExtractor): req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) - video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, u'title') - video_url = compat_urllib_parse.unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, u'video_url')) + video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, 'title') + video_url = compat_urllib_parse.unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, 'video_url')) path = compat_urllib_parse_urlparse(video_url).path extension = os.path.splitext(path)[1][1:] format = path.split('/')[5].split('_')[:2] diff --git a/youtube_dl/extractor/mojvideo.py b/youtube_dl/extractor/mojvideo.py new file mode 100644 index 000000000..90b460d65 --- /dev/null +++ b/youtube_dl/extractor/mojvideo.py @@ -0,0 +1,58 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + parse_duration, +) + + +class MojvideoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?mojvideo\.com/video-(?P<display_id>[^/]+)/(?P<id>[a-f0-9]+)' + _TEST = { + 'url': 'http://www.mojvideo.com/video-v-avtu-pred-mano-rdecelaska-alfi-nipic/3d1ed4497707730b2906', + 'md5': 'f7fd662cc8ce2be107b0d4f2c0483ae7', + 'info_dict': { + 'id': '3d1ed4497707730b2906', + 'display_id': 'v-avtu-pred-mano-rdecelaska-alfi-nipic', + 'ext': 'mp4', + 'title': 'V avtu pred mano rdečelaska - Alfi Nipič', + 'thumbnail': 're:^http://.*\.jpg$', + 'duration': 242, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + # XML is malformed + playerapi = self._download_webpage( + 'http://www.mojvideo.com/playerapi.php?v=%s&t=1' % video_id, display_id) + + if '<error>true</error>' in playerapi: + error_desc = self._html_search_regex( + r'<errordesc>([^<]*)</errordesc>', playerapi, 'error description', fatal=False) + raise ExtractorError('%s said: %s' % (self.IE_NAME, error_desc), expected=True) + + title = self._html_search_regex( + r'<title>([^<]+)</title>', playerapi, 'title') + video_url = self._html_search_regex( + r'<file>([^<]+)</file>', playerapi, 'video URL') + thumbnail = self._html_search_regex( + r'<preview>([^<]+)</preview>', playerapi, 'thumbnail', fatal=False) + duration = parse_duration(self._html_search_regex( + r'<duration>([^<]+)</duration>', playerapi, 'duration', fatal=False)) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'duration': duration, + }
\ No newline at end of file diff --git a/youtube_dl/extractor/movieclips.py b/youtube_dl/extractor/movieclips.py new file mode 100644 index 000000000..456807dd1 --- /dev/null +++ b/youtube_dl/extractor/movieclips.py @@ -0,0 +1,78 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_str, + clean_html, +) + + +class MovieClipsIE(InfoExtractor): + _VALID_URL = r'https?://movieclips\.com/(?P<id>[\da-zA-Z]+)(?:-(?P<display_id>[\da-z-]+))?' + _TEST = { + 'url': 'http://movieclips.com/Wy7ZU-my-week-with-marilyn-movie-do-you-love-me/', + 'info_dict': { + 'id': 'Wy7ZU', + 'display_id': 'my-week-with-marilyn-movie-do-you-love-me', + 'ext': 'mp4', + 'title': 'My Week with Marilyn - Do You Love Me?', + 'description': 'md5:e86795bd332fe3cff461e7c8dc542acb', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + 'params': { + # rtmp download + 'skip_download': True, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + show_id = display_id or video_id + + config = self._download_xml( + 'http://config.movieclips.com/player/config/%s' % video_id, + show_id, 'Downloading player config') + + if config.find('./country-region').text == 'false': + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, config.find('./region_alert').text), expected=True) + + properties = config.find('./video/properties') + smil_file = properties.attrib['smil_file'] + + smil = self._download_xml(smil_file, show_id, 'Downloading SMIL') + base_url = smil.find('./head/meta').attrib['base'] + + formats = [] + for video in smil.findall('./body/switch/video'): + vbr = int(video.attrib['system-bitrate']) / 1000 + src = video.attrib['src'] + formats.append({ + 'url': base_url, + 'play_path': src, + 'ext': src.split(':')[0], + 'vbr': vbr, + 'format_id': '%dk' % vbr, + }) + + self._sort_formats(formats) + + title = '%s - %s' % (properties.attrib['clip_movie_title'], properties.attrib['clip_title']) + description = clean_html(compat_str(properties.attrib['clip_description'])) + thumbnail = properties.attrib['image'] + categories = properties.attrib['clip_categories'].split(',') + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'categories': categories, + 'formats': formats, + } diff --git a/youtube_dl/extractor/musicvault.py b/youtube_dl/extractor/musicvault.py new file mode 100644 index 000000000..ebb1eb8e9 --- /dev/null +++ b/youtube_dl/extractor/musicvault.py @@ -0,0 +1,76 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + unified_strdate, +) + + +class MusicVaultIE(InfoExtractor): + _VALID_URL = r'https?://www\.musicvault\.com/(?P<uploader_id>[^/?#]*)/video/(?P<display_id>[^/?#]*)_(?P<id>[0-9]+)\.html' + _TEST = { + 'url': 'http://www.musicvault.com/the-allman-brothers-band/video/straight-from-the-heart_1010863.html', + 'md5': '2cdbb3ae75f7fb3519821507d2fb3c15', + 'info_dict': { + 'id': '1010863', + 'ext': 'mp4', + 'uploader_id': 'the-allman-brothers-band', + 'title': 'Straight from the Heart', + 'duration': 244, + 'uploader': 'The Allman Brothers Band', + 'thumbnail': 're:^https?://.*/thumbnail/.*', + 'upload_date': '19811216', + 'location': 'Capitol Theatre (Passaic, NJ)', + 'description': 'Listen to The Allman Brothers Band perform Straight from the Heart at Capitol Theatre (Passaic, NJ) on Dec 16, 1981', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('display_id') + webpage = self._download_webpage(url, display_id) + + thumbnail = self._search_regex( + r'<meta itemprop="thumbnail" content="([^"]+)"', + webpage, 'thumbnail', fatal=False) + + data_div = self._search_regex( + r'(?s)<div class="data">(.*?)</div>', webpage, 'data fields') + uploader = self._html_search_regex( + r'<h1.*?>(.*?)</h1>', data_div, 'uploader', fatal=False) + title = self._html_search_regex( + r'<h2.*?>(.*?)</h2>', data_div, 'title') + upload_date = unified_strdate(self._html_search_regex( + r'<h3.*?>(.*?)</h3>', data_div, 'uploader', fatal=False)) + location = self._html_search_regex( + r'<h4.*?>(.*?)</h4>', data_div, 'location', fatal=False) + + duration = parse_duration(self._html_search_meta('duration', webpage)) + + VIDEO_URL_TEMPLATE = 'http://cdnapi.kaltura.com/p/%(uid)s/sp/%(wid)s/playManifest/entryId/%(entry_id)s/format/url/protocol/http' + kaltura_id = self._search_regex( + r'<div id="video-detail-player" data-kaltura-id="([^"]+)"', + webpage, 'kaltura ID') + video_url = VIDEO_URL_TEMPLATE % { + 'entry_id': kaltura_id, + 'wid': self._search_regex(r'/wid/_([0-9]+)/', webpage, 'wid'), + 'uid': self._search_regex(r'uiconf_id/([0-9]+)/', webpage, 'uid'), + } + + return { + 'id': mobj.group('id'), + 'url': video_url, + 'ext': 'mp4', + 'display_id': display_id, + 'uploader_id': mobj.group('uploader_id'), + 'thumbnail': thumbnail, + 'description': self._html_search_meta('description', webpage), + 'upload_date': upload_date, + 'location': location, + 'title': title, + 'uploader': uploader, + 'duration': duration, + } diff --git a/youtube_dl/extractor/nba.py b/youtube_dl/extractor/nba.py index 633b42f72..78e650b2d 100644 --- a/youtube_dl/extractor/nba.py +++ b/youtube_dl/extractor/nba.py @@ -3,18 +3,23 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import ( + remove_end, + parse_duration, +) class NBAIE(InfoExtractor): _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video(?P<id>/[^?]*?)(?:/index\.html)?(?:\?.*)?$' _TEST = { 'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html', - 'md5': u'c0edcfc37607344e2ff8f13c378c88a4', + 'md5': 'c0edcfc37607344e2ff8f13c378c88a4', 'info_dict': { 'id': '0021200253-okc-bkn-recap.nba', 'ext': 'mp4', - 'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.', 'title': 'Thunder vs. Nets', + 'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.', + 'duration': 181, }, } @@ -27,13 +32,18 @@ class NBAIE(InfoExtractor): video_url = 'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4' shortened_video_id = video_id.rpartition('/')[2] - title = self._og_search_title(webpage, default=shortened_video_id).replace('NBA.com: ', '') + title = remove_end( + self._og_search_title(webpage, default=shortened_video_id), ' : NBA.com') + + description = self._og_search_description(webpage) + duration = parse_duration( + self._html_search_meta('duration', webpage, 'duration', fatal=False)) - description = self._html_search_regex(r'<meta name="description" (?:content|value)="(.*?)" />', webpage, 'description', fatal=False) return { 'id': shortened_video_id, 'url': video_url, 'title': title, 'description': description, + 'duration': duration, } diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index aa34665d1..d2e4acbad 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -4,7 +4,11 @@ import re import json from .common import InfoExtractor -from ..utils import find_xpath_attr, compat_str +from ..utils import ( + compat_str, + ExtractorError, + find_xpath_attr, +) class NBCIE(InfoExtractor): @@ -85,11 +89,25 @@ class NBCNewsIE(InfoExtractor): flags=re.MULTILINE) bootstrap = json.loads(bootstrap_json) info = bootstrap['results'][0]['video'] - playlist_url = info['fallbackPlaylistUrl'] + '?form=MPXNBCNewsAPI' mpxid = info['mpxId'] - all_videos = self._download_json(playlist_url, title)['videos'] - # The response contains additional videos - info = next(v for v in all_videos if v['mpxId'] == mpxid) + + base_urls = [ + info['fallbackPlaylistUrl'], + info['associatedPlaylistUrl'], + ] + + for base_url in base_urls: + playlist_url = base_url + '?form=MPXNBCNewsAPI' + all_videos = self._download_json(playlist_url, title)['videos'] + + try: + info = next(v for v in all_videos if v['mpxId'] == mpxid) + break + except StopIteration: + continue + + if info is None: + raise ExtractorError('Could not find video in playlists') return { '_type': 'url', diff --git a/youtube_dl/extractor/nhl.py b/youtube_dl/extractor/nhl.py index 2edd806a3..ceda1dcc0 100644 --- a/youtube_dl/extractor/nhl.py +++ b/youtube_dl/extractor/nhl.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re import json @@ -25,8 +27,8 @@ class NHLBaseInfoExtractor(InfoExtractor): 'path': initial_video_url.replace('.mp4', '_sd.mp4'), }) path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data - path_doc = self._download_xml(path_url, video_id, - u'Downloading final video url') + path_doc = self._download_xml( + path_url, video_id, 'Downloading final video url') video_url = path_doc.find('path').text join = compat_urlparse.urljoin @@ -43,17 +45,18 @@ class NHLBaseInfoExtractor(InfoExtractor): class NHLIE(NHLBaseInfoExtractor): - IE_NAME = u'nhl.com' - _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console\?.*?(?<=[?&])id=(?P<id>\d+)' + IE_NAME = 'nhl.com' + _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console\?.*?(?:[?&])id=(?P<id>[0-9]+)' _TEST = { - u'url': u'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614', - u'file': u'453614.mp4', - u'info_dict': { - u'title': u'Quick clip: Weise 4-3 goal vs Flames', - u'description': u'Dale Weise scores his first of the season to put the Canucks up 4-3.', - u'duration': 18, - u'upload_date': u'20131006', + 'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614', + 'info_dict': { + 'id': '453614', + 'ext': 'mp4', + 'title': 'Quick clip: Weise 4-3 goal vs Flames', + 'description': 'Dale Weise scores his first of the season to put the Canucks up 4-3.', + 'duration': 18, + 'upload_date': '20131006', }, } @@ -61,23 +64,23 @@ class NHLIE(NHLBaseInfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') json_url = 'http://video.nhl.com/videocenter/servlets/playlist?ids=%s&format=json' % video_id - info_json = self._download_webpage(json_url, video_id, - u'Downloading info json') - info_json = self._fix_json(info_json) - info = json.loads(info_json)[0] - return self._extract_video(info) + data = self._download_json( + json_url, video_id, transform_source=self._fix_json) + return self._extract_video(data[0]) class NHLVideocenterIE(NHLBaseInfoExtractor): - IE_NAME = u'nhl.com:videocenter' - IE_DESC = u'NHL videocenter category' - _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?.*?catid=(?P<catid>[^&]+))?' - - @classmethod - def suitable(cls, url): - if NHLIE.suitable(url): - return False - return super(NHLVideocenterIE, cls).suitable(url) + IE_NAME = 'nhl.com:videocenter' + IE_DESC = 'NHL videocenter category' + _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?.*?catid=(?P<catid>[0-9]+)(?![&?]id=).*?)?$' + _TEST = { + 'url': 'http://video.canucks.nhl.com/videocenter/console?catid=999', + 'info_dict': { + 'id': '999', + 'title': 'Highlights', + }, + 'playlist_count': 12, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -86,10 +89,10 @@ class NHLVideocenterIE(NHLBaseInfoExtractor): cat_id = self._search_regex( [r'var defaultCatId = "(.+?)";', r'{statusIndex:0,index:0,.*?id:(.*?),'], - webpage, u'category id') + webpage, 'category id') playlist_title = self._html_search_regex( r'tab0"[^>]*?>(.*?)</td>', - webpage, u'playlist title', flags=re.DOTALL).lower().capitalize() + webpage, 'playlist title', flags=re.DOTALL).lower().capitalize() data = compat_urllib_parse.urlencode({ 'cid': cat_id, @@ -104,7 +107,7 @@ class NHLVideocenterIE(NHLBaseInfoExtractor): response = self._fix_json(response) if not response.strip(): self._downloader.report_warning(u'Got an empty reponse, trying ' - u'adding the "newvideos" parameter') + 'adding the "newvideos" parameter') response = self._download_webpage(request_url + '&newvideos=true', playlist_title) response = self._fix_json(response) @@ -114,5 +117,5 @@ class NHLVideocenterIE(NHLBaseInfoExtractor): '_type': 'playlist', 'title': playlist_title, 'id': cat_id, - 'entries': [self._extract_video(i) for i in videos], + 'entries': [self._extract_video(v) for v in videos], } diff --git a/youtube_dl/extractor/nosvideo.py b/youtube_dl/extractor/nosvideo.py new file mode 100644 index 000000000..095965add --- /dev/null +++ b/youtube_dl/extractor/nosvideo.py @@ -0,0 +1,65 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + compat_urllib_request, + xpath_with_ns, +) + +_x = lambda p: xpath_with_ns(p, {'xspf': 'http://xspf.org/ns/0/'}) +_find = lambda el, p: el.find(_x(p)).text.strip() + + +class NosVideoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?nosvideo\.com/' + \ + '(?:embed/|\?v=)(?P<id>[A-Za-z0-9]{12})/?' + _PLAYLIST_URL = 'http://nosvideo.com/xml/{xml_id:s}.xml' + _TEST = { + 'url': 'http://nosvideo.com/?v=drlp6s40kg54', + 'md5': '4b4ac54c6ad5d70ab88f2c2c6ccec71c', + 'info_dict': { + 'id': 'drlp6s40kg54', + 'ext': 'mp4', + 'title': 'big_buck_bunny_480p_surround-fix.avi.mp4', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + fields = { + 'id': video_id, + 'op': 'download1', + 'method_free': 'Continue to Video', + } + post = compat_urllib_parse.urlencode(fields) + req = compat_urllib_request.Request(url, post) + req.add_header('Content-type', 'application/x-www-form-urlencoded') + webpage = self._download_webpage(req, video_id, + 'Downloading download page') + xml_id = self._search_regex(r'php\|([^\|]+)\|', webpage, 'XML ID') + playlist_url = self._PLAYLIST_URL.format(xml_id=xml_id) + playlist = self._download_xml(playlist_url, video_id) + + track = playlist.find(_x('.//xspf:track')) + title = _find(track, './xspf:title') + url = _find(track, './xspf:file') + thumbnail = _find(track, './xspf:image') + + formats = [{ + 'format_id': 'sd', + 'url': url, + }] + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/nowness.py b/youtube_dl/extractor/nowness.py index 1c5e9401f..6b2f3f55a 100644 --- a/youtube_dl/extractor/nowness.py +++ b/youtube_dl/extractor/nowness.py @@ -1,3 +1,4 @@ +# encoding: utf-8 from __future__ import unicode_literals import re @@ -8,19 +9,34 @@ from ..utils import ExtractorError class NownessIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?nowness\.com/[^?#]*?/(?P<id>[0-9]+)/(?P<slug>[^/]+?)(?:$|[?#])' - - _TEST = { - 'url': 'http://www.nowness.com/day/2013/6/27/3131/candor--the-art-of-gesticulation', - 'md5': '068bc0202558c2e391924cb8cc470676', - 'info_dict': { - 'id': '2520295746001', - 'ext': 'mp4', - 'description': 'Candor: The Art of Gesticulation', - 'uploader': 'Nowness', - 'title': 'Candor: The Art of Gesticulation', - } - } + _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/[^?#]*?/(?P<id>[0-9]+)/(?P<slug>[^/]+?)(?:$|[?#])' + + _TESTS = [ + { + 'url': 'http://www.nowness.com/day/2013/6/27/3131/candor--the-art-of-gesticulation', + 'md5': '068bc0202558c2e391924cb8cc470676', + 'info_dict': { + 'id': '2520295746001', + 'ext': 'mp4', + 'title': 'Candor: The Art of Gesticulation', + 'description': 'Candor: The Art of Gesticulation', + 'thumbnail': 're:^https?://.*\.jpg', + 'uploader': 'Nowness', + } + }, + { + 'url': 'http://cn.nowness.com/day/2014/8/7/4069/kasper-bj-rke-ft-jaakko-eino-kalevi--tnr', + 'md5': 'e79cf125e387216f86b2e0a5b5c63aa3', + 'info_dict': { + 'id': '3716354522001', + 'ext': 'mp4', + 'title': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR', + 'description': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR', + 'thumbnail': 're:^https?://.*\.jpg', + 'uploader': 'Nowness', + } + }, + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py index fbcbe1f40..902d62944 100644 --- a/youtube_dl/extractor/npo.py +++ b/youtube_dl/extractor/npo.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor from ..utils import ( unified_strdate, + qualities, ) @@ -17,7 +18,7 @@ class NPOIE(InfoExtractor): 'md5': '4b3f9c429157ec4775f2c9cb7b911016', 'info_dict': { 'id': 'VPWON_1220719', - 'ext': 'mp4', + 'ext': 'm4v', 'title': 'Nieuwsuur', 'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.', 'upload_date': '20140622', @@ -32,31 +33,39 @@ class NPOIE(InfoExtractor): 'http://e.omroep.nl/metadata/aflevering/%s' % video_id, video_id, # We have to remove the javascript callback - transform_source=lambda j: re.sub(r'parseMetadata\((.*?)\);\n//epc', r'\1', j) + transform_source=lambda j: re.sub(r'parseMetadata\((.*?)\);\n//.*$', r'\1', j) ) token_page = self._download_webpage( 'http://ida.omroep.nl/npoplayer/i.js', video_id, note='Downloading token' ) - token = self._search_regex(r'npoplayer.token = "(.+?)"', token_page, 'token') - streams_info = self._download_json( - 'http://ida.omroep.nl/odi/?prid=%s&puboptions=h264_std&adaptive=yes&token=%s' % (video_id, token), - video_id - ) + token = self._search_regex(r'npoplayer\.token = "(.+?)"', token_page, 'token') - stream_info = self._download_json( - streams_info['streams'][0] + '&type=json', - video_id, - 'Downloading stream info' - ) + formats = [] + quality = qualities(['adaptive', 'h264_sb', 'h264_bb', 'h264_std']) + for format_id in metadata['pubopties']: + streams_info = self._download_json( + 'http://ida.omroep.nl/odi/?prid=%s&puboptions=%s&adaptive=yes&token=%s' % (video_id, format_id, token), + video_id, 'Downloading %s streams info' % format_id) + stream_info = self._download_json( + streams_info['streams'][0] + '&type=json', + video_id, 'Downloading %s stream info' % format_id) + if format_id == 'adaptive': + formats.extend(self._extract_m3u8_formats(stream_info['url'], video_id)) + else: + formats.append({ + 'url': stream_info['url'], + 'format_id': format_id, + 'quality': quality(format_id), + }) + self._sort_formats(formats) return { 'id': video_id, 'title': metadata['titel'], - 'ext': 'mp4', - 'url': stream_info['url'], 'description': metadata['info'], 'thumbnail': metadata['images'][-1]['url'], 'upload_date': unified_strdate(metadata['gidsdatum']), + 'formats': formats, } diff --git a/youtube_dl/extractor/nuvid.py b/youtube_dl/extractor/nuvid.py index 280328b78..58ec81f91 100644 --- a/youtube_dl/extractor/nuvid.py +++ b/youtube_dl/extractor/nuvid.py @@ -38,7 +38,7 @@ class NuvidIE(InfoExtractor): webpage = self._download_webpage( request, video_id, 'Downloading %s page' % format_id) video_url = self._html_search_regex( - r'<a href="([^"]+)"\s*>Continue to watch video', webpage, '%s video URL' % format_id, fatal=False) + r'<a\s+href="([^"]+)"\s+class="b_link">', webpage, '%s video URL' % format_id, fatal=False) if not video_url: continue formats.append({ @@ -49,19 +49,24 @@ class NuvidIE(InfoExtractor): webpage = self._download_webpage( 'http://m.nuvid.com/video/%s' % video_id, video_id, 'Downloading video page') title = self._html_search_regex( - r'<div class="title">\s+<h2[^>]*>([^<]+)</h2>', webpage, 'title').strip() - thumbnail = self._html_search_regex( - r'href="(/thumbs/[^"]+)"[^>]*data-link_type="thumbs"', - webpage, 'thumbnail URL', fatal=False) + [r'<span title="([^"]+)">', + r'<div class="thumb-holder video">\s*<h5[^>]*>([^<]+)</h5>'], webpage, 'title').strip() + thumbnails = [ + { + 'url': thumb_url, + } for thumb_url in re.findall(r'<img src="([^"]+)" alt="" />', webpage) + ] + thumbnail = thumbnails[0]['url'] if thumbnails else None duration = parse_duration(self._html_search_regex( - r'Length:\s*<span>(\d{2}:\d{2})</span>',webpage, 'duration', fatal=False)) + r'<i class="fa fa-clock-o"></i>\s*(\d{2}:\d{2})', webpage, 'duration', fatal=False)) upload_date = unified_strdate(self._html_search_regex( - r'Added:\s*<span>(\d{4}-\d{2}-\d{2})</span>', webpage, 'upload date', fatal=False)) + r'<i class="fa fa-user"></i>\s*(\d{4}-\d{2}-\d{2})', webpage, 'upload date', fatal=False)) return { 'id': video_id, 'title': title, - 'thumbnail': 'http://m.nuvid.com%s' % thumbnail, + 'thumbnails': thumbnails, + 'thumbnail': thumbnail, 'duration': duration, 'upload_date': upload_date, 'age_limit': 18, diff --git a/youtube_dl/extractor/oe1.py b/youtube_dl/extractor/oe1.py deleted file mode 100644 index 38971ab4d..000000000 --- a/youtube_dl/extractor/oe1.py +++ /dev/null @@ -1,40 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import calendar -import datetime -import re - -from .common import InfoExtractor - -# audios on oe1.orf.at are only available for 7 days, so we can't -# add tests. - - -class OE1IE(InfoExtractor): - IE_DESC = 'oe1.orf.at' - _VALID_URL = r'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)' - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - show_id = mobj.group('id') - - data = self._download_json( - 'http://oe1.orf.at/programm/%s/konsole' % show_id, - show_id - ) - - timestamp = datetime.datetime.strptime('%s %s' % ( - data['item']['day_label'], - data['item']['time'] - ), '%d.%m.%Y %H:%M') - unix_timestamp = calendar.timegm(timestamp.utctimetuple()) - - return { - 'id': show_id, - 'title': data['item']['title'], - 'url': data['item']['url_stream'], - 'ext': 'mp3', - 'description': data['item'].get('info'), - 'timestamp': unix_timestamp - } diff --git a/youtube_dl/extractor/ooyala.py b/youtube_dl/extractor/ooyala.py index 13f12824c..2044e107e 100644 --- a/youtube_dl/extractor/ooyala.py +++ b/youtube_dl/extractor/ooyala.py @@ -3,23 +3,38 @@ import re import json from .common import InfoExtractor -from ..utils import unescapeHTML +from ..utils import ( + unescapeHTML, + ExtractorError, +) class OoyalaIE(InfoExtractor): _VALID_URL = r'(?:ooyala:|https?://.+?\.ooyala\.com/.*?(?:embedCode|ec)=)(?P<id>.+?)(&|$)' - _TEST = { - # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video - 'url': 'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', - 'md5': '3f5cceb3a7bf461d6c29dc466cf8033c', - 'info_dict': { - 'id': 'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', - 'ext': 'mp4', - 'title': 'Explaining Data Recovery from Hard Drives and SSDs', - 'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.', + _TESTS = [ + { + # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video + 'url': 'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', + 'md5': '3f5cceb3a7bf461d6c29dc466cf8033c', + 'info_dict': { + 'id': 'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', + 'ext': 'mp4', + 'title': 'Explaining Data Recovery from Hard Drives and SSDs', + 'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.', + }, + }, { + # Only available for ipad + 'url': 'http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0', + 'md5': '4b9754921fddb68106e48c142e2a01e6', + 'info_dict': { + 'id': 'x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0', + 'ext': 'mp4', + 'title': 'Simulation Overview - Levels of Simulation', + 'description': '', + }, }, - } + ] @staticmethod def _url_for_embed_code(embed_code): @@ -47,13 +62,30 @@ class OoyalaIE(InfoExtractor): player = self._download_webpage(player_url, embedCode) mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="', player, 'mobile player url') - mobile_player = self._download_webpage(mobile_url, embedCode) - videos_info = self._search_regex( - r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);', - mobile_player, 'info').replace('\\"','"') - videos_more_info = self._search_regex(r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"','"') + # Looks like some videos are only available for particular devices + # (e.g. http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0 + # is only available for ipad) + # Working around with fetching URLs for all the devices found starting with 'unknown' + # until we succeed or eventually fail for each device. + devices = re.findall(r'device\s*=\s*"([^"]+)";', player) + devices.remove('unknown') + devices.insert(0, 'unknown') + for device in devices: + mobile_player = self._download_webpage( + '%s&device=%s' % (mobile_url, device), embedCode, + 'Downloading mobile player JS for %s device' % device) + videos_info = self._search_regex( + r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);', + mobile_player, 'info', fatal=False, default=None) + if videos_info: + break + if not videos_info: + raise ExtractorError('Unable to extract info') + videos_info = videos_info.replace('\\"', '"') + videos_more_info = self._search_regex( + r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"', '"') videos_info = json.loads(videos_info) - videos_more_info =json.loads(videos_more_info) + videos_more_info = json.loads(videos_more_info) if videos_more_info.get('lineup'): videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])] diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index 03421d1d5..011e6be13 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -3,6 +3,8 @@ from __future__ import unicode_literals import json import re +import calendar +import datetime from .common import InfoExtractor from ..utils import ( @@ -12,7 +14,9 @@ from ..utils import ( ) -class ORFIE(InfoExtractor): +class ORFTVthekIE(InfoExtractor): + IE_NAME = 'orf:tvthek' + IE_DESC = 'ORF TVthek' _VALID_URL = r'https?://tvthek\.orf\.at/(?:programs/.+?/episodes|topics/.+?|program/[^/]+)/(?P<id>\d+)' _TEST = { @@ -105,3 +109,73 @@ class ORFIE(InfoExtractor): 'entries': entries, 'id': playlist_id, } + + +# Audios on ORF radio are only available for 7 days, so we can't add tests. + + +class ORFOE1IE(InfoExtractor): + IE_NAME = 'orf:oe1' + IE_DESC = 'Radio Österreich 1' + _VALID_URL = r'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + show_id = mobj.group('id') + + data = self._download_json( + 'http://oe1.orf.at/programm/%s/konsole' % show_id, + show_id + ) + + timestamp = datetime.datetime.strptime('%s %s' % ( + data['item']['day_label'], + data['item']['time'] + ), '%d.%m.%Y %H:%M') + unix_timestamp = calendar.timegm(timestamp.utctimetuple()) + + return { + 'id': show_id, + 'title': data['item']['title'], + 'url': data['item']['url_stream'], + 'ext': 'mp3', + 'description': data['item'].get('info'), + 'timestamp': unix_timestamp + } + + +class ORFFM4IE(InfoExtractor): + IE_DESC = 'orf:fm4' + IE_DESC = 'radio FM4' + _VALID_URL = r'http://fm4\.orf\.at/7tage/?#(?P<date>[0-9]+)/(?P<show>\w+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + show_date = mobj.group('date') + show_id = mobj.group('show') + + data = self._download_json( + 'http://audioapi.orf.at/fm4/json/2.0/broadcasts/%s/4%s' % (show_date, show_id), + show_id + ) + + def extract_entry_dict(info, title, subtitle): + return { + 'id': info['loopStreamId'].replace('.mp3', ''), + 'url': 'http://loopstream01.apa.at/?channel=fm4&id=%s' % info['loopStreamId'], + 'title': title, + 'description': subtitle, + 'duration': (info['end'] - info['start']) / 1000, + 'timestamp': info['start'] / 1000, + 'ext': 'mp3' + } + + entries = [extract_entry_dict(t, data['title'], data['subtitle']) for t in data['streams']] + + return { + '_type': 'playlist', + 'id': show_id, + 'title': data['title'], + 'description': data['subtitle'], + 'entries': entries + }
\ No newline at end of file diff --git a/youtube_dl/extractor/patreon.py b/youtube_dl/extractor/patreon.py new file mode 100644 index 000000000..5429592a7 --- /dev/null +++ b/youtube_dl/extractor/patreon.py @@ -0,0 +1,100 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + js_to_json, +) + + +class PatreonIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?patreon\.com/creation\?hid=(.+)' + _TESTS = [ + { + 'url': 'http://www.patreon.com/creation?hid=743933', + 'md5': 'e25505eec1053a6e6813b8ed369875cc', + 'info_dict': { + 'id': '743933', + 'ext': 'mp3', + 'title': 'Episode 166: David Smalley of Dogma Debate', + 'uploader': 'Cognitive Dissonance Podcast', + 'thumbnail': 're:^https?://.*$', + }, + }, + { + 'url': 'http://www.patreon.com/creation?hid=754133', + 'md5': '3eb09345bf44bf60451b8b0b81759d0a', + 'info_dict': { + 'id': '754133', + 'ext': 'mp3', + 'title': 'CD 167 Extra', + 'uploader': 'Cognitive Dissonance Podcast', + 'thumbnail': 're:^https?://.*$', + }, + }, + ] + + # Currently Patreon exposes download URL via hidden CSS, so login is not + # needed. Keeping this commented for when this inevitably changes. + ''' + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + + login_form = { + 'redirectUrl': 'http://www.patreon.com/', + 'email': username, + 'password': password, + } + + request = compat_urllib_request.Request( + 'https://www.patreon.com/processLogin', + compat_urllib_parse.urlencode(login_form).encode('utf-8') + ) + login_page = self._download_webpage(request, None, note='Logging in as %s' % username) + + if re.search(r'onLoginFailed', login_page): + raise ExtractorError('Unable to login, incorrect username and/or password', expected=True) + + def _real_initialize(self): + self._login() + ''' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group(1) + + webpage = self._download_webpage(url, video_id) + title = self._og_search_title(webpage).strip() + + attach_fn = self._html_search_regex( + r'<div class="attach"><a target="_blank" href="([^"]+)">', + webpage, 'attachment URL', default=None) + if attach_fn is not None: + video_url = 'http://www.patreon.com' + attach_fn + thumbnail = self._og_search_thumbnail(webpage) + uploader = self._html_search_regex( + r'<strong>(.*?)</strong> is creating', webpage, 'uploader') + else: + playlist_js = self._search_regex( + r'(?s)new\s+jPlayerPlaylist\(\s*\{\s*[^}]*},\s*(\[.*?,?\s*\])', + webpage, 'playlist JSON') + playlist_json = js_to_json(playlist_js) + playlist = json.loads(playlist_json) + data = playlist[0] + video_url = self._proto_relative_url(data['mp3']) + thumbnail = self._proto_relative_url(data.get('cover')) + uploader = data.get('artist') + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp3', + 'title': title, + 'uploader': uploader, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index 64cded707..2adfde909 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -20,27 +20,74 @@ class PBSIE(InfoExtractor): ) ''' - _TEST = { - 'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/', - 'md5': 'ce1888486f0908d555a8093cac9a7362', - 'info_dict': { - 'id': '2365006249', - 'ext': 'mp4', - 'title': 'A More Perfect Union', - 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a', - 'duration': 3190, + _TESTS = [ + { + 'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/', + 'md5': 'ce1888486f0908d555a8093cac9a7362', + 'info_dict': { + 'id': '2365006249', + 'ext': 'mp4', + 'title': 'A More Perfect Union', + 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a', + 'duration': 3190, + }, + }, + { + 'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/', + 'md5': '143c98aa54a346738a3d78f54c925321', + 'info_dict': { + 'id': '2365297690', + 'ext': 'mp4', + 'title': 'Losing Iraq', + 'description': 'md5:f5bfbefadf421e8bb8647602011caf8e', + 'duration': 5050, + }, + }, + { + 'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/', + 'md5': 'b19856d7f5351b17a5ab1dc6a64be633', + 'info_dict': { + 'id': '2201174722', + 'ext': 'mp4', + 'title': 'Cyber Schools Gain Popularity, but Quality Questions Persist', + 'description': 'md5:5871c15cba347c1b3d28ac47a73c7c28', + 'duration': 801, + }, }, - } + { + 'url': 'http://www.pbs.org/wnet/gperf/dudamel-conducts-verdi-requiem-hollywood-bowl-full-episode/3374/', + 'md5': 'c62859342be2a0358d6c9eb306595978', + 'info_dict': { + 'id': '2365297708', + 'ext': 'mp4', + 'description': 'md5:68d87ef760660eb564455eb30ca464fe', + 'title': 'Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full', + 'duration': 6559, + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + ] - def _real_extract(self, url): + def _extract_ids(self, url): mobj = re.match(self._VALID_URL, url) presumptive_id = mobj.group('presumptive_id') display_id = presumptive_id if presumptive_id: webpage = self._download_webpage(url, display_id) + + MEDIA_ID_REGEXES = [ + r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed + r'class="coveplayerid">([^<]+)<', # coveplayer + ] + + media_id = self._search_regex( + MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None) + if media_id: + return media_id, presumptive_id + url = self._search_regex( - r'<iframe\s+id=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>', + r'<iframe\s+(?:class|id)=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>', webpage, 'player URL') mobj = re.match(self._VALID_URL, url) @@ -57,6 +104,11 @@ class PBSIE(InfoExtractor): video_id = mobj.group('id') display_id = video_id + return video_id, display_id + + def _real_extract(self, url): + video_id, display_id = self._extract_ids(url) + info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id info = self._download_json(info_url, display_id) diff --git a/youtube_dl/extractor/playfm.py b/youtube_dl/extractor/playfm.py new file mode 100644 index 000000000..72df4d842 --- /dev/null +++ b/youtube_dl/extractor/playfm.py @@ -0,0 +1,82 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + compat_urllib_request, + ExtractorError, + float_or_none, + int_or_none, +) + + +class PlayFMIE(InfoExtractor): + IE_NAME = 'play.fm' + _VALID_URL = r'https?://(?:www\.)?play\.fm/[^?#]*(?P<upload_date>[0-9]{8})(?P<id>[0-9]{6})(?:$|[?#])' + + _TEST = { + 'url': 'http://www.play.fm/recording/leipzigelectronicmusicbatofarparis_fr20140712137220', + 'md5': 'c505f8307825a245d0c7ad1850001f22', + 'info_dict': { + 'id': '137220', + 'ext': 'mp3', + 'title': 'LEIPZIG ELECTRONIC MUSIC @ Batofar (Paris,FR) - 2014-07-12', + 'uploader': 'Sven Tasnadi', + 'uploader_id': 'sventasnadi', + 'duration': 5627.428, + 'upload_date': '20140712', + 'view_count': int, + 'thumbnail': 're:^https?://.*\.jpg$', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + upload_date = mobj.group('upload_date') + + rec_data = compat_urllib_parse.urlencode({'rec_id': video_id}) + req = compat_urllib_request.Request( + 'http://www.play.fm/flexRead/recording', data=rec_data) + req.add_header('Content-Type', 'application/x-www-form-urlencoded') + rec_doc = self._download_xml(req, video_id) + + error_node = rec_doc.find('./error') + if error_node is not None: + raise ExtractorError('An error occured: %s (code %s)' % ( + error_node.text, rec_doc.find('./status').text)) + + recording = rec_doc.find('./recording') + title = recording.find('./title').text + view_count = int_or_none(recording.find('./stats/playcount').text) + duration = float_or_none(recording.find('./duration').text, scale=1000) + thumbnail = recording.find('./image').text + + artist = recording.find('./artists/artist') + uploader = artist.find('./name').text + uploader_id = artist.find('./slug').text + + video_url = '%s//%s/%s/%s/offset/0/sh/%s/rec/%s/jingle/%s/loc/%s' % ( + 'http:', recording.find('./url').text, + recording.find('./_class').text, recording.find('./file_id').text, + rec_doc.find('./uuid').text, video_id, + rec_doc.find('./jingle/file_id').text, + 'http%3A%2F%2Fwww.play.fm%2Fplayer', + ) + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp3', + 'filesize': int_or_none(recording.find('./size').text), + 'title': title, + 'upload_date': upload_date, + 'view_count': view_count, + 'duration': duration, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'uploader_id': uploader_id, + } diff --git a/youtube_dl/extractor/pornotube.py b/youtube_dl/extractor/pornotube.py index 35dc5a9ff..04bd3d979 100644 --- a/youtube_dl/extractor/pornotube.py +++ b/youtube_dl/extractor/pornotube.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -9,15 +11,16 @@ from ..utils import ( class PornotubeIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$' + _VALID_URL = r'https?://(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$' _TEST = { - u'url': u'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing', - u'file': u'1689755.flv', - u'md5': u'374dd6dcedd24234453b295209aa69b6', - u'info_dict': { - u"upload_date": u"20090708", - u"title": u"Marilyn-Monroe-Bathing", - u"age_limit": 18 + 'url': 'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing', + 'md5': '374dd6dcedd24234453b295209aa69b6', + 'info_dict': { + 'id': '1689755', + 'ext': 'flv', + 'upload_date': '20090708', + 'title': 'Marilyn-Monroe-Bathing', + 'age_limit': 18 } } @@ -32,22 +35,22 @@ class PornotubeIE(InfoExtractor): # Get the video URL VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",' - video_url = self._search_regex(VIDEO_URL_RE, webpage, u'video url') + video_url = self._search_regex(VIDEO_URL_RE, webpage, 'video url') video_url = compat_urllib_parse.unquote(video_url) #Get the uploaded date VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by' - upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, u'upload date', fatal=False) - if upload_date: upload_date = unified_strdate(upload_date) + upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, 'upload date', fatal=False) + if upload_date: + upload_date = unified_strdate(upload_date) age_limit = self._rta_search(webpage) - info = {'id': video_id, - 'url': video_url, - 'uploader': None, - 'upload_date': upload_date, - 'title': video_title, - 'ext': 'flv', - 'format': 'flv', - 'age_limit': age_limit} - - return [info] + return { + 'id': video_id, + 'url': video_url, + 'upload_date': upload_date, + 'title': video_title, + 'ext': 'flv', + 'format': 'flv', + 'age_limit': age_limit, + } diff --git a/youtube_dl/extractor/promptfile.py b/youtube_dl/extractor/promptfile.py new file mode 100644 index 000000000..463e85501 --- /dev/null +++ b/youtube_dl/extractor/promptfile.py @@ -0,0 +1,67 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + determine_ext, + compat_urllib_parse, + compat_urllib_request, +) + + +class PromptFileIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P<id>[0-9A-Z\-]+)' + _FILE_NOT_FOUND_REGEX = r'<div.+id="not_found_msg".+>.+</div>[^-]' + _TEST = { + 'url': 'http://www.promptfile.com/l/D21B4746E9-F01462F0FF', + 'md5': 'd1451b6302da7215485837aaea882c4c', + 'info_dict': { + 'id': 'D21B4746E9-F01462F0FF', + 'ext': 'mp4', + 'title': 'Birds.mp4', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + + if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None: + raise ExtractorError('Video %s does not exist' % video_id, + expected=True) + + fields = dict(re.findall(r'''(?x)type="hidden"\s+ + name="(.+?)"\s+ + value="(.*?)" + ''', webpage)) + post = compat_urllib_parse.urlencode(fields) + req = compat_urllib_request.Request(url, post) + req.add_header('Content-type', 'application/x-www-form-urlencoded') + webpage = self._download_webpage( + req, video_id, 'Downloading video page') + + url = self._html_search_regex(r'url:\s*\'([^\']+)\'', webpage, 'URL') + title = self._html_search_regex( + r'<span.+title="([^"]+)">', webpage, 'title') + thumbnail = self._html_search_regex( + r'<div id="player_overlay">.*button>.*?<img src="([^"]+)"', + webpage, 'thumbnail', fatal=False, flags=re.DOTALL) + + formats = [{ + 'format_id': 'sd', + 'url': url, + 'ext': determine_ext(title), + }] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/redtube.py b/youtube_dl/extractor/redtube.py index 4295cf93a..d1e12dd8d 100644 --- a/youtube_dl/extractor/redtube.py +++ b/youtube_dl/extractor/redtube.py @@ -35,9 +35,7 @@ class RedTubeIE(InfoExtractor): r'<h1 class="videoTitle[^"]*">(.+?)</h1>', webpage, u'title') - video_thumbnail = self._html_search_regex( - r'playerInnerHTML.+?<img\s+src="(.+?)"', - webpage, u'thumbnail', fatal=False) + video_thumbnail = self._og_search_thumbnail(webpage) # No self-labeling, but they describe themselves as # "Home of Videos Porno" diff --git a/youtube_dl/extractor/reverbnation.py b/youtube_dl/extractor/reverbnation.py index 49cf427a1..ec7e7df7b 100644 --- a/youtube_dl/extractor/reverbnation.py +++ b/youtube_dl/extractor/reverbnation.py @@ -1,23 +1,23 @@ from __future__ import unicode_literals import re -import time from .common import InfoExtractor -from ..utils import strip_jsonp +from ..utils import str_or_none class ReverbNationIE(InfoExtractor): _VALID_URL = r'^https?://(?:www\.)?reverbnation\.com/.*?/song/(?P<id>\d+).*?$' _TESTS = [{ 'url': 'http://www.reverbnation.com/alkilados/song/16965047-mona-lisa', - 'file': '16965047.mp3', 'md5': '3da12ebca28c67c111a7f8b262d3f7a7', 'info_dict': { + "id": "16965047", + "ext": "mp3", "title": "MONA LISA", "uploader": "ALKILADOS", - "uploader_id": 216429, - "thumbnail": "//gp1.wac.edgecastcdn.net/802892/production_public/Photo/13761700/image/1366002176_AVATAR_MONA_LISA.jpg" + "uploader_id": "216429", + "thumbnail": "re:^https://gp1\.wac\.edgecastcdn\.net/.*?\.jpg$" }, }] @@ -26,10 +26,8 @@ class ReverbNationIE(InfoExtractor): song_id = mobj.group('id') api_res = self._download_json( - 'https://api.reverbnation.com/song/%s?callback=api_response_5&_=%d' - % (song_id, int(time.time() * 1000)), + 'https://api.reverbnation.com/song/%s' % song_id, song_id, - transform_source=strip_jsonp, note='Downloading information of song %s' % song_id ) @@ -38,8 +36,9 @@ class ReverbNationIE(InfoExtractor): 'title': api_res.get('name'), 'url': api_res.get('url'), 'uploader': api_res.get('artist', {}).get('name'), - 'uploader_id': api_res.get('artist', {}).get('id'), - 'thumbnail': api_res.get('image', api_res.get('thumbnail')), + 'uploader_id': str_or_none(api_res.get('artist', {}).get('id')), + 'thumbnail': self._proto_relative_url( + api_res.get('image', api_res.get('thumbnail'))), 'ext': 'mp3', 'vcodec': 'none', } diff --git a/youtube_dl/extractor/rtbf.py b/youtube_dl/extractor/rtbf.py index 205f8a167..dce64e151 100644 --- a/youtube_dl/extractor/rtbf.py +++ b/youtube_dl/extractor/rtbf.py @@ -30,7 +30,7 @@ class RTBFIE(InfoExtractor): page = self._download_webpage('https://www.rtbf.be/video/embed?id=%s' % video_id, video_id) data = json.loads(self._html_search_regex( - r'<div class="js-player-embed" data-video="([^"]+)"', page, 'data video'))['data'] + r'<div class="js-player-embed(?: player-embed)?" data-video="([^"]+)"', page, 'data video'))['data'] video_url = data.get('downloadUrl') or data.get('url') diff --git a/youtube_dl/extractor/rtlnl.py b/youtube_dl/extractor/rtlnl.py new file mode 100644 index 000000000..0ab1eb69c --- /dev/null +++ b/youtube_dl/extractor/rtlnl.py @@ -0,0 +1,67 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import parse_duration + + +class RtlXlIE(InfoExtractor): + IE_NAME = 'rtlxl.nl' + _VALID_URL = r'https?://www\.rtlxl\.nl/#!/[^/]+/(?P<uuid>[^/?]+)' + + _TEST = { + 'url': 'http://www.rtlxl.nl/#!/rtl-nieuws-132237/6e4203a6-0a5e-3596-8424-c599a59e0677', + 'md5': 'cc16baa36a6c169391f0764fa6b16654', + 'info_dict': { + 'id': '6e4203a6-0a5e-3596-8424-c599a59e0677', + 'ext': 'mp4', + 'title': 'RTL Nieuws - Laat', + 'description': 'md5:6b61f66510c8889923b11f2778c72dc5', + 'timestamp': 1408051800, + 'upload_date': '20140814', + 'duration': 576.880, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + uuid = mobj.group('uuid') + + info = self._download_json( + 'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=flash/' % uuid, + uuid) + + material = info['material'][0] + episode_info = info['episodes'][0] + + progname = info['abstracts'][0]['name'] + subtitle = material['title'] or info['episodes'][0]['name'] + + videopath = material['videopath'] + f4m_url = 'http://manifest.us.rtl.nl' + videopath + + formats = self._extract_f4m_formats(f4m_url, uuid) + + video_urlpart = videopath.split('/flash/')[1][:-4] + PG_URL_TEMPLATE = 'http://pg.us.rtl.nl/rtlxl/network/%s/progressive/%s.mp4' + + formats.extend([ + { + 'url': PG_URL_TEMPLATE % ('a2m', video_urlpart), + 'format_id': 'pg-sd', + }, + { + 'url': PG_URL_TEMPLATE % ('a3m', video_urlpart), + 'format_id': 'pg-hd', + } + ]) + + return { + 'id': uuid, + 'title': '%s - %s' % (progname, subtitle), + 'formats': formats, + 'timestamp': material['original_date'], + 'description': episode_info['synopsis'], + 'duration': parse_duration(material.get('duration')), + } diff --git a/youtube_dl/extractor/rtlnow.py b/youtube_dl/extractor/rtlnow.py index 4835ec5ec..a45884b25 100644 --- a/youtube_dl/extractor/rtlnow.py +++ b/youtube_dl/extractor/rtlnow.py @@ -92,16 +92,7 @@ class RTLnowIE(InfoExtractor): }, { 'url': 'http://www.n-tvnow.de/deluxe-alles-was-spass-macht/thema-ua-luxushotel-fuer-vierbeiner.php?container_id=153819&player=1&season=0', - 'info_dict': { - 'id': '153819', - 'ext': 'flv', - 'title': 'Deluxe - Alles was Spaß macht - Thema u.a.: Luxushotel für Vierbeiner', - 'description': 'md5:c3705e1bb32e1a5b2bcd634fc065c631', - 'thumbnail': 'http://autoimg.static-fra.de/ntvnow/383157/1500x1500/image2.jpg', - 'upload_date': '20140221', - 'duration': 2429, - }, - 'skip': 'Only works from Germany', + 'only_matching': True, }, ] diff --git a/youtube_dl/extractor/rtve.py b/youtube_dl/extractor/rtve.py index 77fd08dde..4dd35a47b 100644 --- a/youtube_dl/extractor/rtve.py +++ b/youtube_dl/extractor/rtve.py @@ -1,70 +1,82 @@ # encoding: utf-8 from __future__ import unicode_literals -import re import base64 +import re +import time from .common import InfoExtractor from ..utils import ( struct_unpack, + remove_end, ) +def _decrypt_url(png): + encrypted_data = base64.b64decode(png) + text_index = encrypted_data.find(b'tEXt') + text_chunk = encrypted_data[text_index - 4:] + length = struct_unpack('!I', text_chunk[:4])[0] + # Use bytearray to get integers when iterating in both python 2.x and 3.x + data = bytearray(text_chunk[8:8 + length]) + data = [chr(b) for b in data if b != 0] + hash_index = data.index('#') + alphabet_data = data[:hash_index] + url_data = data[hash_index + 1:] + + alphabet = [] + e = 0 + d = 0 + for l in alphabet_data: + if d == 0: + alphabet.append(l) + d = e = (e + 1) % 4 + else: + d -= 1 + url = '' + f = 0 + e = 3 + b = 1 + for letter in url_data: + if f == 0: + l = int(letter) * 10 + f = 1 + else: + if e == 0: + l += int(letter) + url += alphabet[l] + e = (b + 3) % 4 + f = 0 + b += 1 + else: + e -= 1 + + return url + + + class RTVEALaCartaIE(InfoExtractor): IE_NAME = 'rtve.es:alacarta' IE_DESC = 'RTVE a la carta' _VALID_URL = r'http://www\.rtve\.es/alacarta/videos/[^/]+/[^/]+/(?P<id>\d+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/', - 'md5': '18fcd45965bdd076efdb12cd7f6d7b9e', + 'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43', 'info_dict': { 'id': '2491869', 'ext': 'mp4', 'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia', }, - } - - def _decrypt_url(self, png): - encrypted_data = base64.b64decode(png) - text_index = encrypted_data.find(b'tEXt') - text_chunk = encrypted_data[text_index-4:] - length = struct_unpack('!I', text_chunk[:4])[0] - # Use bytearray to get integers when iterating in both python 2.x and 3.x - data = bytearray(text_chunk[8:8+length]) - data = [chr(b) for b in data if b != 0] - hash_index = data.index('#') - alphabet_data = data[:hash_index] - url_data = data[hash_index+1:] - - alphabet = [] - e = 0 - d = 0 - for l in alphabet_data: - if d == 0: - alphabet.append(l) - d = e = (e + 1) % 4 - else: - d -= 1 - url = '' - f = 0 - e = 3 - b = 1 - for letter in url_data: - if f == 0: - l = int(letter)*10 - f = 1 - else: - if e == 0: - l += int(letter) - url += alphabet[l] - e = (b + 3) % 4 - f = 0 - b += 1 - else: - e -= 1 - - return url + }, { + 'note': 'Live stream', + 'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/', + 'info_dict': { + 'id': '1694255', + 'ext': 'flv', + 'title': 'TODO', + } + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -74,11 +86,57 @@ class RTVEALaCartaIE(InfoExtractor): video_id)['page']['items'][0] png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % video_id png = self._download_webpage(png_url, video_id, 'Downloading url information') - video_url = self._decrypt_url(png) + video_url = _decrypt_url(png) return { 'id': video_id, 'title': info['title'], 'url': video_url, - 'thumbnail': info['image'], + 'thumbnail': info.get('image'), + 'page_url': url, + } + + +class RTVELiveIE(InfoExtractor): + IE_NAME = 'rtve.es:live' + IE_DESC = 'RTVE.es live streams' + _VALID_URL = r'http://www\.rtve\.es/(?:deportes/directo|noticias|television)/(?P<id>[a-zA-Z0-9-]+)' + + _TESTS = [{ + 'url': 'http://www.rtve.es/noticias/directo-la-1/', + 'info_dict': { + 'id': 'directo-la-1', + 'ext': 'flv', + 'title': 're:^La 1 de TVE [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$', + }, + 'params': { + 'skip_download': 'live stream', + } + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + start_time = time.gmtime() + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + player_url = self._search_regex( + r'<param name="movie" value="([^"]+)"/>', webpage, 'player URL') + title = remove_end(self._og_search_title(webpage), ' en directo') + title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time) + + vidplayer_id = self._search_regex( + r' id="vidplayer([0-9]+)"', webpage, 'internal video ID') + png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id + png = self._download_webpage(png_url, video_id, 'Downloading url information') + video_url = _decrypt_url(png) + + return { + 'id': video_id, + 'ext': 'flv', + 'title': title, + 'url': video_url, + 'app': 'rtve-live-live?ovpfv=2.1.2', + 'player_url': player_url, + 'rtmp_live': True, } diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index 357edbbda..0c8790da2 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -74,6 +74,13 @@ class RutubeChannelIE(InfoExtractor): IE_NAME = 'rutube:channel' IE_DESC = 'Rutube channels' _VALID_URL = r'http://rutube\.ru/tags/video/(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://rutube.ru/tags/video/1800/', + 'info_dict': { + 'id': '1800', + }, + 'playlist_mincount': 68, + }] _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json' @@ -101,6 +108,7 @@ class RutubeMovieIE(RutubeChannelIE): IE_NAME = 'rutube:movie' IE_DESC = 'Rutube movies' _VALID_URL = r'http://rutube\.ru/metainfo/tv/(?P<id>\d+)' + _TESTS = [] _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json' _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json' @@ -119,5 +127,12 @@ class RutubePersonIE(RutubeChannelIE): IE_NAME = 'rutube:person' IE_DESC = 'Rutube person videos' _VALID_URL = r'http://rutube\.ru/video/person/(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://rutube.ru/video/person/313878/', + 'info_dict': { + 'id': '313878', + }, + 'playlist_mincount': 37, + }] _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json' diff --git a/youtube_dl/extractor/sapo.py b/youtube_dl/extractor/sapo.py new file mode 100644 index 000000000..172cc1275 --- /dev/null +++ b/youtube_dl/extractor/sapo.py @@ -0,0 +1,119 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + unified_strdate, +) + + +class SapoIE(InfoExtractor): + IE_DESC = 'SAPO Vídeos' + _VALID_URL = r'https?://(?:(?:v2|www)\.)?videos\.sapo\.(?:pt|cv|ao|mz|tl)/(?P<id>[\da-zA-Z]{20})' + + _TESTS = [ + { + 'url': 'http://videos.sapo.pt/UBz95kOtiWYUMTA5Ghfi', + 'md5': '79ee523f6ecb9233ac25075dee0eda83', + 'note': 'SD video', + 'info_dict': { + 'id': 'UBz95kOtiWYUMTA5Ghfi', + 'ext': 'mp4', + 'title': 'Benfica - Marcas na Hitória', + 'description': 'md5:c9082000a128c3fd57bf0299e1367f22', + 'duration': 264, + 'uploader': 'tiago_1988', + 'upload_date': '20080229', + 'categories': ['benfica', 'cabral', 'desporto', 'futebol', 'geovanni', 'hooijdonk', 'joao', 'karel', 'lisboa', 'miccoli'], + }, + }, + { + 'url': 'http://videos.sapo.pt/IyusNAZ791ZdoCY5H5IF', + 'md5': '90a2f283cfb49193fe06e861613a72aa', + 'note': 'HD video', + 'info_dict': { + 'id': 'IyusNAZ791ZdoCY5H5IF', + 'ext': 'mp4', + 'title': 'Codebits VII - Report', + 'description': 'md5:6448d6fd81ce86feac05321f354dbdc8', + 'duration': 144, + 'uploader': 'codebits', + 'upload_date': '20140427', + 'categories': ['codebits', 'codebits2014'], + }, + }, + { + 'url': 'http://v2.videos.sapo.pt/yLqjzPtbTimsn2wWBKHz', + 'md5': 'e5aa7cc0bdc6db9b33df1a48e49a15ac', + 'note': 'v2 video', + 'info_dict': { + 'id': 'yLqjzPtbTimsn2wWBKHz', + 'ext': 'mp4', + 'title': 'Hipnose Condicionativa 4', + 'description': 'md5:ef0481abf8fb4ae6f525088a6dadbc40', + 'duration': 692, + 'uploader': 'sapozen', + 'upload_date': '20090609', + 'categories': ['condicionativa', 'heloisa', 'hipnose', 'miranda', 'sapo', 'zen'], + }, + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + item = self._download_xml( + 'http://rd3.videos.sapo.pt/%s/rss2' % video_id, video_id).find('./channel/item') + + title = item.find('./title').text + description = item.find('./{http://videos.sapo.pt/mrss/}synopse').text + thumbnail = item.find('./{http://search.yahoo.com/mrss/}content').get('url') + duration = parse_duration(item.find('./{http://videos.sapo.pt/mrss/}time').text) + uploader = item.find('./{http://videos.sapo.pt/mrss/}author').text + upload_date = unified_strdate(item.find('./pubDate').text) + view_count = int(item.find('./{http://videos.sapo.pt/mrss/}views').text) + comment_count = int(item.find('./{http://videos.sapo.pt/mrss/}comment_count').text) + tags = item.find('./{http://videos.sapo.pt/mrss/}tags').text + categories = tags.split() if tags else [] + age_limit = 18 if item.find('./{http://videos.sapo.pt/mrss/}m18').text == 'true' else 0 + + video_url = item.find('./{http://videos.sapo.pt/mrss/}videoFile').text + video_size = item.find('./{http://videos.sapo.pt/mrss/}videoSize').text.split('x') + + formats = [{ + 'url': video_url, + 'ext': 'mp4', + 'format_id': 'sd', + 'width': int(video_size[0]), + 'height': int(video_size[1]), + }] + + if item.find('./{http://videos.sapo.pt/mrss/}HD').text == 'true': + formats.append({ + 'url': re.sub(r'/mov/1$', '/mov/39', video_url), + 'ext': 'mp4', + 'format_id': 'hd', + 'width': 1280, + 'height': 720, + }) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'uploader': uploader, + 'upload_date': upload_date, + 'view_count': view_count, + 'comment_count': comment_count, + 'categories': categories, + 'age_limit': age_limit, + 'formats': formats, + } diff --git a/youtube_dl/extractor/savefrom.py b/youtube_dl/extractor/savefrom.py index 198a08c1c..5b7367b94 100644 --- a/youtube_dl/extractor/savefrom.py +++ b/youtube_dl/extractor/savefrom.py @@ -20,7 +20,7 @@ class SaveFromIE(InfoExtractor): 'upload_date': '20120816', 'uploader': 'Howcast', 'uploader_id': 'Howcast', - 'description': 'md5:4f0aac94361a12e1ce57d74f85265175', + 'description': 're:(?s).* Hi, my name is Rene Dreifuss\. And I\'m here to show you some MMA.*', }, 'params': { 'skip_download': True diff --git a/youtube_dl/extractor/sbs.py b/youtube_dl/extractor/sbs.py new file mode 100644 index 000000000..34058fd4b --- /dev/null +++ b/youtube_dl/extractor/sbs.py @@ -0,0 +1,56 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import json +import re +from .common import InfoExtractor +from ..utils import ( + js_to_json, + remove_end, +) + + +class SBSIE(InfoExtractor): + IE_DESC = 'sbs.com.au' + _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/ondemand/video/single/(?P<id>[0-9]+)/' + + _TESTS = [{ + # Original URL is handled by the generic IE which finds the iframe: + # http://www.sbs.com.au/thefeed/blog/2014/08/21/dingo-conservation + 'url': 'http://www.sbs.com.au/ondemand/video/single/320403011771/?source=drupal&vertical=thefeed', + 'md5': '3150cf278965eeabb5b4cea1c963fe0a', + 'info_dict': { + 'id': '320403011771', + 'ext': 'flv', + 'title': 'Dingo Conservation', + 'description': 'Dingoes are on the brink of extinction; most of the animals we think are dingoes are in fact crossbred with wild dogs. This family run a dingo conservation park to prevent their extinction', + 'thumbnail': 're:http://.*\.jpg', + }, + 'add_ies': ['generic'], + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + + release_urls_json = js_to_json(self._search_regex( + r'(?s)playerParams\.releaseUrls\s*=\s*(\{.*?\n\});\n', + webpage, '')) + release_urls = json.loads(release_urls_json) + theplatform_url = ( + release_urls.get('progressive') or release_urls.get('standard')) + + title = remove_end(self._og_search_title(webpage), ' (The Feed)') + description = self._html_search_meta('description', webpage) + thumbnail = self._og_search_thumbnail(webpage) + + return { + '_type': 'url_transparent', + 'id': video_id, + 'url': theplatform_url, + + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py new file mode 100644 index 000000000..badba2ac6 --- /dev/null +++ b/youtube_dl/extractor/shared.py @@ -0,0 +1,57 @@ +from __future__ import unicode_literals + +import re +import base64 + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_urllib_request, + compat_urllib_parse, + int_or_none, +) + + +class SharedIE(InfoExtractor): + _VALID_URL = r'http://shared\.sx/(?P<id>[\da-z]{10})' + + _TEST = { + 'url': 'http://shared.sx/0060718775', + 'md5': '106fefed92a8a2adb8c98e6a0652f49b', + 'info_dict': { + 'id': '0060718775', + 'ext': 'mp4', + 'title': 'Bmp4', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + page = self._download_webpage(url, video_id) + + if re.search(r'>File does not exist<', page) is not None: + raise ExtractorError('Video %s does not exist' % video_id, expected=True) + + download_form = dict(re.findall(r'<input type="hidden" name="([^"]+)" value="([^"]*)"', page)) + + request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(download_form)) + request.add_header('Content-Type', 'application/x-www-form-urlencoded') + + video_page = self._download_webpage(request, video_id, 'Downloading video page') + + video_url = self._html_search_regex(r'data-url="([^"]+)"', video_page, 'video URL') + title = base64.b64decode(self._html_search_meta('full:title', page, 'title')).decode('utf-8') + filesize = int_or_none(self._html_search_meta('full:size', page, 'file size', fatal=False)) + thumbnail = self._html_search_regex( + r'data-poster="([^"]+)"', video_page, 'thumbnail', fatal=False, default=None) + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp4', + 'filesize': filesize, + 'title': title, + 'thumbnail': thumbnail, + }
\ No newline at end of file diff --git a/youtube_dl/extractor/smotri.py b/youtube_dl/extractor/smotri.py index 13e7e71cb..9bd5defa7 100644 --- a/youtube_dl/extractor/smotri.py +++ b/youtube_dl/extractor/smotri.py @@ -267,6 +267,14 @@ class SmotriCommunityIE(InfoExtractor): IE_DESC = 'Smotri.com community videos' IE_NAME = 'smotri:community' _VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)' + _TEST = { + 'url': 'http://smotri.com/community/video/kommuna', + 'info_dict': { + 'id': 'kommuna', + 'title': 'КПРФ', + }, + 'playlist_mincount': 4, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -289,6 +297,14 @@ class SmotriUserIE(InfoExtractor): IE_DESC = 'Smotri.com user videos' IE_NAME = 'smotri:user' _VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)' + _TESTS = [{ + 'url': 'http://smotri.com/user/inspector', + 'info_dict': { + 'id': 'inspector', + 'title': 'Inspector', + }, + 'playlist_mincount': 9, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/snotr.py b/youtube_dl/extractor/snotr.py new file mode 100644 index 000000000..da3b05a8d --- /dev/null +++ b/youtube_dl/extractor/snotr.py @@ -0,0 +1,68 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + float_or_none, + str_to_int, + parse_duration, +) + + +class SnotrIE(InfoExtractor): + _VALID_URL = r'http?://(?:www\.)?snotr\.com/video/(?P<id>\d+)/([\w]+)' + _TESTS = [{ + 'url': 'http://www.snotr.com/video/13708/Drone_flying_through_fireworks', + 'info_dict': { + 'id': '13708', + 'ext': 'flv', + 'title': 'Drone flying through fireworks!', + 'duration': 247, + 'filesize_approx': 98566144, + 'description': 'A drone flying through Fourth of July Fireworks', + } + }, { + 'url': 'http://www.snotr.com/video/530/David_Letteman_-_George_W_Bush_Top_10', + 'info_dict': { + 'id': '530', + 'ext': 'flv', + 'title': 'David Letteman - George W. Bush Top 10', + 'duration': 126, + 'filesize_approx': 8912896, + 'description': 'The top 10 George W. Bush moments, brought to you by David Letterman!', + } + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + title = self._og_search_title(webpage) + + description = self._og_search_description(webpage) + video_url = "http://cdn.videos.snotr.com/%s.flv" % video_id + + view_count = str_to_int(self._html_search_regex( + r'<p>\n<strong>Views:</strong>\n([\d,\.]+)</p>', + webpage, 'view count', fatal=False)) + + duration = parse_duration(self._html_search_regex( + r'<p>\n<strong>Length:</strong>\n\s*([0-9:]+).*?</p>', + webpage, 'duration', fatal=False)) + + filesize_approx = float_or_none(self._html_search_regex( + r'<p>\n<strong>Filesize:</strong>\n\s*([0-9.]+)\s*megabyte</p>', + webpage, 'filesize', fatal=False), invscale=1024 * 1024) + + return { + 'id': video_id, + 'description': description, + 'title': title, + 'url': video_url, + 'view_count': view_count, + 'duration': duration, + 'filesize_approx': filesize_approx, + } diff --git a/youtube_dl/extractor/sockshare.py b/youtube_dl/extractor/sockshare.py new file mode 100644 index 000000000..c663e56d4 --- /dev/null +++ b/youtube_dl/extractor/sockshare.py @@ -0,0 +1,83 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from ..utils import ( + ExtractorError, + compat_urllib_parse, + compat_urllib_request, + determine_ext, +) +import re + +from .common import InfoExtractor + + +class SockshareIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?sockshare\.com/file/(?P<id>[0-9A-Za-z]+)' + _FILE_DELETED_REGEX = r'This file doesn\'t exist, or has been removed\.</div>' + _TEST = { + 'url': 'http://www.sockshare.com/file/437BE28B89D799D7', + 'md5': '9d0bf1cfb6dbeaa8d562f6c97506c5bd', + 'info_dict': { + 'id': '437BE28B89D799D7', + 'title': 'big_buck_bunny_720p_surround.avi', + 'ext': 'avi', + 'thumbnail': 're:^http://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + url = 'http://sockshare.com/file/%s' % video_id + webpage = self._download_webpage(url, video_id) + + if re.search(self._FILE_DELETED_REGEX, webpage) is not None: + raise ExtractorError('Video %s does not exist' % video_id, + expected=True) + + confirm_hash = self._html_search_regex(r'''(?x)<input\s+ + type="hidden"\s+ + value="([^"]*)"\s+ + name="hash" + ''', webpage, 'hash') + + fields = { + "hash": confirm_hash, + "confirm": "Continue as Free User" + } + + post = compat_urllib_parse.urlencode(fields) + req = compat_urllib_request.Request(url, post) + # Apparently, this header is required for confirmation to work. + req.add_header('Host', 'www.sockshare.com') + req.add_header('Content-type', 'application/x-www-form-urlencoded') + + webpage = self._download_webpage( + req, video_id, 'Downloading video page') + + video_url = self._html_search_regex( + r'<a href="([^"]*)".+class="download_file_link"', + webpage, 'file url') + video_url = "http://www.sockshare.com" + video_url + title = self._html_search_regex(( + r'<h1>(.+)<strong>', + r'var name = "([^"]+)";'), + webpage, 'title', default=None) + thumbnail = self._html_search_regex( + r'<img\s+src="([^"]*)".+?name="bg"', + webpage, 'thumbnail') + + formats = [{ + 'format_id': 'sd', + 'url': video_url, + 'ext': determine_ext(title), + }] + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 8a77c1370..b78aed7f0 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -28,7 +28,8 @@ class SoundcloudIE(InfoExtractor): _VALID_URL = r'''(?x)^(?:https?://)? (?:(?:(?:www\.|m\.)?soundcloud\.com/ (?P<uploader>[\w\d-]+)/ - (?!sets/)(?P<title>[\w\d-]+)/? + (?!sets/|likes/?(?:$|[?#])) + (?P<title>[\w\d-]+)/? (?P<token>[^?]+?)?(?:[?].*)?$) |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+)) |(?P<player>(?:w|player|p.)\.soundcloud\.com/player/?.*?url=.*) @@ -82,10 +83,10 @@ class SoundcloudIE(InfoExtractor): # downloadable song { 'url': 'https://soundcloud.com/oddsamples/bus-brakes', - 'md5': 'fee7b8747b09bb755cefd4b853e7249a', + 'md5': '7624f2351f8a3b2e7cd51522496e7631', 'info_dict': { 'id': '128590877', - 'ext': 'wav', + 'ext': 'mp3', 'title': 'Bus Brakes', 'description': 'md5:0170be75dd395c96025d210d261c784e', 'uploader': 'oddsamples', @@ -221,13 +222,16 @@ class SoundcloudIE(InfoExtractor): class SoundcloudSetIE(SoundcloudIE): _VALID_URL = r'https?://(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)' IE_NAME = 'soundcloud:set' - # it's in tests/test_playlists.py - _TESTS = [] + _TESTS = [{ + 'url': 'https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep', + 'info_dict': { + 'title': 'The Royal Concept EP', + }, + 'playlist_mincount': 6, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError('Invalid URL: %s' % url) # extract uploader (which is in the url) uploader = mobj.group(1) @@ -246,20 +250,32 @@ class SoundcloudSetIE(SoundcloudIE): self._downloader.report_error('unable to download video webpage: %s' % compat_str(err['error_message'])) return - self.report_extraction(full_title) - return {'_type': 'playlist', - 'entries': [self._extract_info_dict(track) for track in info['tracks']], - 'id': info['id'], - 'title': info['title'], - } + return { + '_type': 'playlist', + 'entries': [self._extract_info_dict(track) for track in info['tracks']], + 'id': info['id'], + 'title': info['title'], + } class SoundcloudUserIE(SoundcloudIE): _VALID_URL = r'https?://(www\.)?soundcloud\.com/(?P<user>[^/]+)/?((?P<rsrc>tracks|likes)/?)?(\?.*)?$' IE_NAME = 'soundcloud:user' - - # it's in tests/test_playlists.py - _TESTS = [] + _TESTS = [{ + 'url': 'https://soundcloud.com/the-concept-band', + 'info_dict': { + 'id': '9615865', + 'title': 'The Royal Concept', + }, + 'playlist_mincount': 12 + }, { + 'url': 'https://soundcloud.com/the-concept-band/likes', + 'info_dict': { + 'id': '9615865', + 'title': 'The Royal Concept', + }, + 'playlist_mincount': 1, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -301,9 +317,18 @@ class SoundcloudUserIE(SoundcloudIE): class SoundcloudPlaylistIE(SoundcloudIE): _VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P<id>[0-9]+)' IE_NAME = 'soundcloud:playlist' + _TESTS = [ - # it's in tests/test_playlists.py - _TESTS = [] + { + 'url': 'http://api.soundcloud.com/playlists/4110309', + 'info_dict': { + 'id': '4110309', + 'title': 'TILT Brass - Bowery Poetry Club, August \'03 [Non-Site SCR 02]', + 'description': 're:.*?TILT Brass - Bowery Poetry Club', + }, + 'playlist_count': 6, + } + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/sportdeutschland.py b/youtube_dl/extractor/sportdeutschland.py new file mode 100644 index 000000000..185353bef --- /dev/null +++ b/youtube_dl/extractor/sportdeutschland.py @@ -0,0 +1,96 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_request, + parse_iso8601, +) + + +class SportDeutschlandIE(InfoExtractor): + _VALID_URL = r'https?://sportdeutschland\.tv/(?P<sport>[^/?#]+)/(?P<id>[^?#/]+)(?:$|[?#])' + _TESTS = [{ + 'url': 'http://sportdeutschland.tv/badminton/live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen', + 'info_dict': { + 'id': 'live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen', + 'ext': 'mp4', + 'title': 'LIVE: Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen', + 'categories': ['Badminton'], + 'view_count': int, + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 're:^Die Badminton-WM 2014 aus Kopenhagen LIVE', + 'timestamp': int, + 'upload_date': 're:^201408[23][0-9]$', + }, + 'params': { + 'skip_download': 'Live stream', + }, + }, { + 'url': 'http://sportdeutschland.tv/li-ning-badminton-wm-2014/lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs', + 'info_dict': { + 'id': 'lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs', + 'ext': 'mp4', + 'upload_date': '20140825', + 'description': 'md5:60a20536b57cee7d9a4ec005e8687504', + 'timestamp': 1408976060, + 'title': 'Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen: Herren Einzel, Wei Lee vs. Keun Lee', + 'thumbnail': 're:^https?://.*\.jpg$', + 'view_count': int, + 'categories': ['Li-Ning Badminton WM 2014'], + } + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + sport_id = mobj.group('sport') + + api_url = 'http://splink.tv/api/permalinks/%s/%s' % ( + sport_id, video_id) + req = compat_urllib_request.Request(api_url, headers={ + 'Accept': 'application/vnd.vidibus.v2.html+json', + 'Referer': url, + }) + data = self._download_json(req, video_id) + + categories = list(data.get('section', {}).get('tags', {}).values()) + asset = data['asset'] + + formats = [] + smil_url = asset['video'] + if '.smil' in smil_url: + m3u8_url = smil_url.replace('.smil', '.m3u8') + formats.extend( + self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')) + + smil_doc = self._download_xml( + smil_url, video_id, note='Downloading SMIL metadata') + base_url = smil_doc.find('./head/meta').attrib['base'] + formats.extend([{ + 'format_id': 'rmtp', + 'url': base_url, + 'play_path': n.attrib['src'], + 'ext': 'flv', + 'preference': -100, + 'format_note': 'Seems to fail at example stream', + } for n in smil_doc.findall('./body/video')]) + else: + formats.append({'url': smil_url}) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'formats': formats, + 'title': asset['title'], + 'thumbnail': asset.get('image'), + 'description': asset.get('teaser'), + 'categories': categories, + 'view_count': asset.get('views'), + 'rtmp_live': asset.get('live'), + 'timestamp': parse_iso8601(asset.get('date')), + } + diff --git a/youtube_dl/extractor/steam.py b/youtube_dl/extractor/steam.py index af689e2c2..183dcb03c 100644 --- a/youtube_dl/extractor/steam.py +++ b/youtube_dl/extractor/steam.py @@ -53,7 +53,7 @@ class SteamIE(InfoExtractor): 'ext': 'mp4', 'upload_date': '20140329', 'title': 'FRONTIERS - Final Greenlight Trailer', - 'description': 'md5:6df4fe8dd494ae811869672b0767e025', + 'description': 'md5:dc96a773669d0ca1b36c13c1f30250d9', 'uploader': 'AAD Productions', 'uploader_id': 'AtomicAgeDogGames', } diff --git a/youtube_dl/extractor/streamcloud.py b/youtube_dl/extractor/streamcloud.py index 9faf3a5e3..172def221 100644 --- a/youtube_dl/extractor/streamcloud.py +++ b/youtube_dl/extractor/streamcloud.py @@ -1,4 +1,6 @@ # coding: utf-8 +from __future__ import unicode_literals + import re import time @@ -10,18 +12,18 @@ from ..utils import ( class StreamcloudIE(InfoExtractor): - IE_NAME = u'streamcloud.eu' + IE_NAME = 'streamcloud.eu' _VALID_URL = r'https?://streamcloud\.eu/(?P<id>[a-zA-Z0-9_-]+)/(?P<fname>[^#?]*)\.html' _TEST = { - u'url': u'http://streamcloud.eu/skp9j99s4bpz/youtube-dl_test_video_____________-BaW_jenozKc.mp4.html', - u'file': u'skp9j99s4bpz.mp4', - u'md5': u'6bea4c7fa5daaacc2a946b7146286686', - u'info_dict': { - u'title': u'youtube-dl test video \'/\\ ä ↭', - u'duration': 9, + 'url': 'http://streamcloud.eu/skp9j99s4bpz/youtube-dl_test_video_____________-BaW_jenozKc.mp4.html', + 'md5': '6bea4c7fa5daaacc2a946b7146286686', + 'info_dict': { + 'id': 'skp9j99s4bpz', + 'ext': 'mp4', + 'title': 'youtube-dl test video \'/\\ ä ↭', }, - u'skip': u'Only available from the EU' + 'skip': 'Only available from the EU' } def _real_extract(self, url): @@ -46,21 +48,17 @@ class StreamcloudIE(InfoExtractor): req = compat_urllib_request.Request(url, post, headers) webpage = self._download_webpage( - req, video_id, note=u'Downloading video page ...') + req, video_id, note='Downloading video page ...') title = self._html_search_regex( - r'<h1[^>]*>([^<]+)<', webpage, u'title') + r'<h1[^>]*>([^<]+)<', webpage, 'title') video_url = self._search_regex( - r'file:\s*"([^"]+)"', webpage, u'video URL') - duration_str = self._search_regex( - r'duration:\s*"?([0-9]+)"?', webpage, u'duration', fatal=False) - duration = None if duration_str is None else int(duration_str) + r'file:\s*"([^"]+)"', webpage, 'video URL') thumbnail = self._search_regex( - r'image:\s*"([^"]+)"', webpage, u'thumbnail URL', fatal=False) + r'image:\s*"([^"]+)"', webpage, 'thumbnail URL', fatal=False) return { 'id': video_id, 'title': title, 'url': video_url, - 'duration': duration, 'thumbnail': thumbnail, } diff --git a/youtube_dl/extractor/sunporno.py b/youtube_dl/extractor/sunporno.py new file mode 100644 index 000000000..7de3c9dd5 --- /dev/null +++ b/youtube_dl/extractor/sunporno.py @@ -0,0 +1,70 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + int_or_none, + qualities, + determine_ext, +) + + +class SunPornoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?sunporno\.com/videos/(?P<id>\d+)' + _TEST = { + 'url': 'http://www.sunporno.com/videos/807778/', + 'md5': '6457d3c165fd6de062b99ef6c2ff4c86', + 'info_dict': { + 'id': '807778', + 'ext': 'flv', + 'title': 'md5:0a400058e8105d39e35c35e7c5184164', + 'description': 'md5:a31241990e1bd3a64e72ae99afb325fb', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 302, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'title') + description = self._html_search_meta('description', webpage, 'description') + thumbnail = self._html_search_regex( + r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False) + + duration = parse_duration(self._search_regex( + r'<span>Duration: (\d+:\d+)</span>', webpage, 'duration', fatal=False)) + + view_count = int_or_none(self._html_search_regex( + r'<span class="views">(\d+)</span>', webpage, 'view count', fatal=False)) + comment_count = int_or_none(self._html_search_regex( + r'(\d+)</b> Comments?', webpage, 'comment count', fatal=False)) + + formats = [] + quality = qualities(['mp4', 'flv']) + for video_url in re.findall(r'<source src="([^"]+)"', webpage): + video_ext = determine_ext(video_url) + formats.append({ + 'url': video_url, + 'format_id': video_ext, + 'quality': quality(video_ext), + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'view_count': view_count, + 'comment_count': comment_count, + 'formats': formats, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/swrmediathek.py b/youtube_dl/extractor/swrmediathek.py index 6c688c520..5d9d70367 100644 --- a/youtube_dl/extractor/swrmediathek.py +++ b/youtube_dl/extractor/swrmediathek.py @@ -8,7 +8,7 @@ from ..utils import parse_duration class SWRMediathekIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?swrmediathek\.de/player\.htm\?show=(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})' + _VALID_URL = r'https?://(?:www\.)?swrmediathek\.de/(?:content/)?player\.htm\?show=(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})' _TESTS = [{ 'url': 'http://swrmediathek.de/player.htm?show=849790d0-dab8-11e3-a953-0026b975f2e6', @@ -52,6 +52,20 @@ class SWRMediathekIE(InfoExtractor): 'uploader': 'SWR 2', 'uploader_id': '284670', } + }, { + 'url': 'http://swrmediathek.de/content/player.htm?show=52dc7e00-15c5-11e4-84bc-0026b975f2e6', + 'md5': '881531487d0633080a8cc88d31ef896f', + 'info_dict': { + 'id': '52dc7e00-15c5-11e4-84bc-0026b975f2e6', + 'ext': 'mp4', + 'title': 'Familienspaß am Bodensee', + 'description': 'md5:0b591225a32cfde7be1629ed49fe4315', + 'thumbnail': 're:http://.*\.jpg', + 'duration': 1784, + 'upload_date': '20140727', + 'uploader': 'SWR Fernsehen BW', + 'uploader_id': '281130', + } }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/tagesschau.py b/youtube_dl/extractor/tagesschau.py index 25b9864ad..b87047451 100644 --- a/youtube_dl/extractor/tagesschau.py +++ b/youtube_dl/extractor/tagesschau.py @@ -19,16 +19,6 @@ class TagesschauIE(InfoExtractor): 'description': 'md5:69da3c61275b426426d711bde96463ab', 'thumbnail': 're:^http:.*\.jpg$', }, - }, { - 'url': 'http://www.tagesschau.de/multimedia/video/video-5964.html', - 'md5': '66652566900963a3f962333579eeffcf', - 'info_dict': { - 'id': '5964', - 'ext': 'mp4', - 'title': 'Nahost-Konflikt: Israel bombadiert Ziele im Gazastreifen und Westjordanland', - 'description': 'md5:07bfc78c48eec3145ed4805299a1900a', - 'thumbnail': 're:http://.*\.jpg', - }, }] _FORMATS = { diff --git a/youtube_dl/extractor/teachertube.py b/youtube_dl/extractor/teachertube.py index 2c2113b14..8a95fd656 100644 --- a/youtube_dl/extractor/teachertube.py +++ b/youtube_dl/extractor/teachertube.py @@ -62,7 +62,7 @@ class TeacherTubeIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - title = self._html_search_meta('title', webpage, 'title') + title = self._html_search_meta('title', webpage, 'title', fatal=True) TITLE_SUFFIX = ' - TeacherTube' if title.endswith(TITLE_SUFFIX): title = title[:-len(TITLE_SUFFIX)].strip() @@ -101,7 +101,18 @@ class TeacherTubeUserIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(user/profile|collection)/(?P<user>[0-9a-zA-Z]+)/?' - _MEDIA_RE = r'(?s)"sidebar_thumb_time">[0-9:]+</div>.+?<a href="(https?://(?:www\.)?teachertube\.com/(?:video|audio)/[^"]+)">' + _MEDIA_RE = r'''(?sx) + class="?sidebar_thumb_time"?>[0-9:]+</div> + \s* + <a\s+href="(https?://(?:www\.)?teachertube\.com/(?:video|audio)/[^"]+)" + ''' + _TEST = { + 'url': 'http://www.teachertube.com/user/profile/rbhagwati2', + 'info_dict': { + 'id': 'rbhagwati2' + }, + 'playlist_mincount': 179, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -111,14 +122,12 @@ class TeacherTubeUserIE(InfoExtractor): webpage = self._download_webpage(url, user_id) urls.extend(re.findall(self._MEDIA_RE, webpage)) - pages = re.findall(r'/ajax-user/user-videos/%s\?page=([0-9]+)' % user_id, webpage)[1:-1] + pages = re.findall(r'/ajax-user/user-videos/%s\?page=([0-9]+)' % user_id, webpage)[:-1] for p in pages: more = 'http://www.teachertube.com/ajax-user/user-videos/%s?page=%s' % (user_id, p) - webpage = self._download_webpage(more, user_id, 'Downloading page %s/%s' % (p, len(pages) + 1)) - urls.extend(re.findall(self._MEDIA_RE, webpage)) - - entries = [] - for url in urls: - entries.append(self.url_result(url, 'TeacherTube')) + webpage = self._download_webpage(more, user_id, 'Downloading page %s/%s' % (p, len(pages))) + video_urls = re.findall(self._MEDIA_RE, webpage) + urls.extend(video_urls) + entries = [self.url_result(vurl, 'TeacherTube') for vurl in urls] return self.playlist_result(entries, user_id) diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py index f8dd7e955..fa796ce72 100644 --- a/youtube_dl/extractor/teamcoco.py +++ b/youtube_dl/extractor/teamcoco.py @@ -37,7 +37,7 @@ class TeamcocoIE(InfoExtractor): video_id = mobj.group("video_id") if not video_id: video_id = self._html_search_regex( - r'<article class="video" data-id="(\d+?)"', + r'data-node-id="(\d+?)"', webpage, 'video id') data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id diff --git a/youtube_dl/extractor/techtalks.py b/youtube_dl/extractor/techtalks.py index a55f236cb..16e945d8e 100644 --- a/youtube_dl/extractor/techtalks.py +++ b/youtube_dl/extractor/techtalks.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -11,24 +13,30 @@ class TechTalksIE(InfoExtractor): _VALID_URL = r'https?://techtalks\.tv/talks/[^/]*/(?P<id>\d+)/' _TEST = { - u'url': u'http://techtalks.tv/talks/learning-topic-models-going-beyond-svd/57758/', - u'playlist': [ + 'url': 'http://techtalks.tv/talks/learning-topic-models-going-beyond-svd/57758/', + 'info_dict': { + 'id': '57758', + 'title': 'Learning Topic Models --- Going beyond SVD', + }, + 'playlist': [ { - u'file': u'57758.flv', - u'info_dict': { - u'title': u'Learning Topic Models --- Going beyond SVD', + 'info_dict': { + 'id': '57758', + 'ext': 'flv', + 'title': 'Learning Topic Models --- Going beyond SVD', }, }, { - u'file': u'57758-slides.flv', - u'info_dict': { - u'title': u'Learning Topic Models --- Going beyond SVD', + 'info_dict': { + 'id': '57758-slides', + 'ext': 'flv', + 'title': 'Learning Topic Models --- Going beyond SVD', }, }, ], - u'params': { + 'params': { # rtmp download - u'skip_download': True, + 'skip_download': True, }, } @@ -36,30 +44,36 @@ class TechTalksIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) talk_id = mobj.group('id') webpage = self._download_webpage(url, talk_id) - rtmp_url = self._search_regex(r'netConnectionUrl: \'(.*?)\'', webpage, - u'rtmp url') - play_path = self._search_regex(r'href=\'(.*?)\' [^>]*id="flowplayer_presenter"', - webpage, u'presenter play path') + rtmp_url = self._search_regex( + r'netConnectionUrl: \'(.*?)\'', webpage, 'rtmp url') + play_path = self._search_regex( + r'href=\'(.*?)\' [^>]*id="flowplayer_presenter"', + webpage, 'presenter play path') title = clean_html(get_element_by_attribute('class', 'title', webpage)) video_info = { - 'id': talk_id, - 'title': title, - 'url': rtmp_url, - 'play_path': play_path, - 'ext': 'flv', - } + 'id': talk_id, + 'title': title, + 'url': rtmp_url, + 'play_path': play_path, + 'ext': 'flv', + } m_slides = re.search(r'<a class="slides" href=\'(.*?)\'', webpage) if m_slides is None: return video_info else: - return [ - video_info, - # The slides video - { - 'id': talk_id + '-slides', - 'title': title, - 'url': rtmp_url, - 'play_path': m_slides.group(1), - 'ext': 'flv', - }, - ] + return { + '_type': 'playlist', + 'id': talk_id, + 'title': title, + 'entries': [ + video_info, + # The slides video + { + 'id': talk_id + '-slides', + 'title': title, + 'url': rtmp_url, + 'play_path': m_slides.group(1), + 'ext': 'flv', + }, + ], + } diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index bce32a873..1cca47771 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -51,7 +51,6 @@ class TEDIE(SubtitlesInfoExtractor): } }, { 'url': 'http://www.ted.com/talks/gabby_giffords_and_mark_kelly_be_passionate_be_courageous_be_your_best', - 'md5': '49144e345a899b8cb34d315f3b9cfeeb', 'info_dict': { 'id': '1972', 'ext': 'mp4', @@ -59,6 +58,13 @@ class TEDIE(SubtitlesInfoExtractor): 'uploader': 'Gabby Giffords and Mark Kelly', 'description': 'md5:5174aed4d0f16021b704120360f72b92', }, + }, { + 'url': 'http://www.ted.com/playlists/who_are_the_hackers', + 'info_dict': { + 'id': '10', + 'title': 'Who are the hackers?', + }, + 'playlist_mincount': 6, }] _NATIVE_FORMATS = { diff --git a/youtube_dl/extractor/tenplay.py b/youtube_dl/extractor/tenplay.py index 8477840fc..81ba169fb 100644 --- a/youtube_dl/extractor/tenplay.py +++ b/youtube_dl/extractor/tenplay.py @@ -1,8 +1,6 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor diff --git a/youtube_dl/extractor/tnaflix.py b/youtube_dl/extractor/tnaflix.py new file mode 100644 index 000000000..4956f8577 --- /dev/null +++ b/youtube_dl/extractor/tnaflix.py @@ -0,0 +1,84 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + fix_xml_ampersands, +) + + +class TNAFlixIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/(?P<cat_id>[\w-]+)/(?P<display_id>[\w-]+)/video(?P<id>\d+)' + + _TITLE_REGEX = None + _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>' + _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"' + + _TEST = { + 'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878', + 'md5': 'ecf3498417d09216374fc5907f9c6ec0', + 'info_dict': { + 'id': '553878', + 'display_id': 'Carmella-Decesare-striptease', + 'ext': 'mp4', + 'title': 'Carmella Decesare - striptease', + 'description': '', + 'thumbnail': 're:https?://.*\.jpg$', + 'duration': 91, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + title = self._html_search_regex( + self._TITLE_REGEX, webpage, 'title') if self._TITLE_REGEX else self._og_search_title(webpage) + description = self._html_search_regex( + self._DESCRIPTION_REGEX, webpage, 'description', fatal=False, default='') + + age_limit = self._rta_search(webpage) + + duration = self._html_search_meta('duration', webpage, 'duration', default=None) + if duration: + duration = parse_duration(duration[1:]) + + cfg_url = self._html_search_regex( + self._CONFIG_REGEX, webpage, 'flashvars.config') + + cfg_xml = self._download_xml( + cfg_url, display_id, note='Downloading metadata', + transform_source=fix_xml_ampersands) + + thumbnail = cfg_xml.find('./startThumb').text + + formats = [] + for item in cfg_xml.findall('./quality/item'): + video_url = re.sub('speed=\d+', 'speed=', item.find('videoLink').text) + format_id = item.find('res').text + fmt = { + 'url': video_url, + 'format_id': format_id, + } + m = re.search(r'^(\d+)', format_id) + if m: + fmt['height'] = int(m.group(1)) + formats.append(fmt) + self._sort_formats(formats) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'age_limit': age_limit, + 'formats': formats, + } diff --git a/youtube_dl/extractor/toypics.py b/youtube_dl/extractor/toypics.py index 0f389bd93..2756f56d3 100644 --- a/youtube_dl/extractor/toypics.py +++ b/youtube_dl/extractor/toypics.py @@ -42,6 +42,13 @@ class ToypicsIE(InfoExtractor): class ToypicsUserIE(InfoExtractor): IE_DESC = 'Toypics user profile' _VALID_URL = r'http://videos\.toypics\.net/(?P<username>[^/?]+)(?:$|[?#])' + _TEST = { + 'url': 'http://videos.toypics.net/Mikey', + 'info_dict': { + 'id': 'Mikey', + }, + 'playlist_mincount': 19, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/tudou.py b/youtube_dl/extractor/tudou.py index 7a3891b89..dcd823d08 100644 --- a/youtube_dl/extractor/tudou.py +++ b/youtube_dl/extractor/tudou.py @@ -1,5 +1,7 @@ # coding: utf-8 +from __future__ import unicode_literals + import re import json @@ -9,22 +11,29 @@ from .common import InfoExtractor class TudouIE(InfoExtractor): _VALID_URL = r'(?:http://)?(?:www\.)?tudou\.com/(?:listplay|programs|albumplay)/(?:view|(.+?))/(?:([^/]+)|([^/]+))(?:\.html)?' _TESTS = [{ - u'url': u'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html', - u'file': u'159448201.f4v', - u'md5': u'140a49ed444bd22f93330985d8475fcb', - u'info_dict': { - u"title": u"卡马乔国足开大脚长传冲吊集锦" + 'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html', + 'md5': '140a49ed444bd22f93330985d8475fcb', + 'info_dict': { + 'id': '159448201', + 'ext': 'f4v', + 'title': '卡马乔国足开大脚长传冲吊集锦', + 'thumbnail': 're:^https?://.*\.jpg$', + } + }, { + 'url': 'http://www.tudou.com/programs/view/ajX3gyhL0pc/', + 'info_dict': { + 'id': '117049447', + 'ext': 'f4v', + 'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012', + 'thumbnail': 're:^https?://.*\.jpg$', } - }, - { - u'url': u'http://www.tudou.com/albumplay/TenTw_JgiPM/PzsAs5usU9A.html', - u'file': u'todo.mp4', - u'md5': u'todo.mp4', - u'info_dict': { - u'title': u'todo.mp4', + }, { + 'url': 'http://www.tudou.com/albumplay/TenTw_JgiPM/PzsAs5usU9A.html', + 'info_dict': { + 'title': 'todo.mp4', }, - u'add_ie': [u'Youku'], - u'skip': u'Only works from China' + 'add_ie': ['Youku'], + 'skip': 'Only works from China' }] def _url_for_id(self, id, quality = None): @@ -44,20 +53,22 @@ class TudouIE(InfoExtractor): if m and m.group(1): return { '_type': 'url', - 'url': u'youku:' + m.group(1), + 'url': 'youku:' + m.group(1), 'ie_key': 'Youku' } title = self._search_regex( - r",kw:\s*['\"](.+?)[\"']", webpage, u'title') + r",kw:\s*['\"](.+?)[\"']", webpage, 'title') thumbnail_url = self._search_regex( - r",pic:\s*[\"'](.+?)[\"']", webpage, u'thumbnail URL', fatal=False) + r",pic:\s*[\"'](.+?)[\"']", webpage, 'thumbnail URL', fatal=False) segs_json = self._search_regex(r'segs: \'(.*)\'', webpage, 'segments') segments = json.loads(segs_json) # It looks like the keys are the arguments that have to be passed as # the hd field in the request url, we pick the higher - quality = sorted(segments.keys())[-1] + # Also, filter non-number qualities (see issue #3643). + quality = sorted(filter(lambda k: k.isdigit(), segments.keys()), + key=lambda k: int(k))[-1] parts = segments[quality] result = [] len_parts = len(parts) @@ -67,12 +78,13 @@ class TudouIE(InfoExtractor): part_id = part['k'] final_url = self._url_for_id(part_id, quality) ext = (final_url.split('?')[0]).split('.')[-1] - part_info = {'id': part_id, - 'url': final_url, - 'ext': ext, - 'title': title, - 'thumbnail': thumbnail_url, - } + part_info = { + 'id': '%s' % part_id, + 'url': final_url, + 'ext': ext, + 'title': title, + 'thumbnail': thumbnail_url, + } result.append(part_info) return result diff --git a/youtube_dl/extractor/tvigle.py b/youtube_dl/extractor/tvigle.py index 0921cc5f8..dc8697850 100644 --- a/youtube_dl/extractor/tvigle.py +++ b/youtube_dl/extractor/tvigle.py @@ -5,80 +5,82 @@ import re from .common import InfoExtractor from ..utils import ( - unified_strdate, - clean_html, - int_or_none, + float_or_none, + str_to_int, ) class TvigleIE(InfoExtractor): IE_NAME = 'tvigle' IE_DESC = 'Интернет-телевидение Tvigle.ru' - _VALID_URL = r'http://(?:www\.)?tvigle\.ru/category/.+?[\?&]v(?:ideo)?=(?P<id>\d+)' + _VALID_URL = r'http://(?:www\.)?tvigle\.ru/(?:[^/]+/)+(?P<display_id>[^/]+)/$' _TESTS = [ { - 'url': 'http://www.tvigle.ru/category/cinema/1608/?video=503081', - 'md5': '09afba4616666249f087efc6dcf83cb3', + 'url': 'http://www.tvigle.ru/video/brat-2/', + 'md5': '72cb7eab33e54314e1790da402d3c9c3', 'info_dict': { - 'id': '503081', - 'ext': 'flv', + 'id': '5119390', + 'display_id': 'brat-2', + 'ext': 'mp4', 'title': 'Брат 2 ', - 'description': 'md5:f5a42970f50648cee3d7ad740f3ae769', - 'upload_date': '20110919', + 'description': 'md5:5751f4fe345a58e1692585c361294bd8', + 'duration': 7356.369, + 'age_limit': 0, }, }, { - 'url': 'http://www.tvigle.ru/category/men/vysotskiy_vospominaniya02/?flt=196&v=676433', - 'md5': 'e7efe5350dd5011d0de6550b53c3ba7b', + 'url': 'http://www.tvigle.ru/video/vladimir-vysotskii/vedushchii-teleprogrammy-60-minut-ssha-o-vladimire-vysotskom/', + 'md5': 'd9012d7c7c598fe7a11d7fb46dc1f574', 'info_dict': { - 'id': '676433', - 'ext': 'flv', + 'id': '5142516', + 'ext': 'mp4', 'title': 'Ведущий телепрограммы «60 минут» (США) о Владимире Высоцком', 'description': 'md5:027f7dc872948f14c96d19b4178428a4', - 'upload_date': '20121218', + 'duration': 186.080, + 'age_limit': 0, }, }, ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + display_id = mobj.group('display_id') - video_data = self._download_xml( - 'http://www.tvigle.ru/xml/single.php?obj=%s' % video_id, video_id, 'Downloading video XML') + webpage = self._download_webpage(url, display_id) - video = video_data.find('./video') + video_id = self._html_search_regex( + r'<li class="video-preview current_playing" id="(\d+)">', webpage, 'video id') - title = video.get('name') - description = video.get('anons') - if description: - description = clean_html(description) - thumbnail = video_data.get('img') - upload_date = unified_strdate(video.get('date')) - like_count = int_or_none(video.get('vtp')) + video_data = self._download_json( + 'http://cloud.tvigle.ru/api/play/video/%s/' % video_id, display_id) - formats = [] - for num, (format_id, format_note) in enumerate([['low_file', 'SQ'], ['file', 'HQ'], ['hd', 'HD 720']]): - video_url = video.get(format_id) - if not video_url: - continue - formats.append({ - 'url': video_url, - 'format_id': format_id, - 'format_note': format_note, - 'quality': num, - }) + item = video_data['playlist']['items'][0] + + title = item['title'] + description = item['description'] + thumbnail = item['thumbnail'] + duration = float_or_none(item['durationMilliseconds'], 1000) + age_limit = str_to_int(item['ageRestrictions']) + formats = [] + for vcodec, fmts in item['videos'].items(): + for quality, video_url in fmts.items(): + formats.append({ + 'url': video_url, + 'format_id': '%s-%s' % (vcodec, quality), + 'vcodec': vcodec, + 'height': int(quality[:-1]), + }) self._sort_formats(formats) return { 'id': video_id, + 'display_id': display_id, 'title': title, 'description': description, 'thumbnail': thumbnail, - 'upload_date': upload_date, - 'like_count': like_count, - 'age_limit': 18, + 'duration': duration, + 'age_limit': age_limit, 'formats': formats, }
\ No newline at end of file diff --git a/youtube_dl/extractor/tvplay.py b/youtube_dl/extractor/tvplay.py new file mode 100644 index 000000000..a56a7ab5f --- /dev/null +++ b/youtube_dl/extractor/tvplay.py @@ -0,0 +1,85 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + parse_iso8601, + qualities, +) + + +class TVPlayIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?tvplay\.lv/parraides/[^/]+/(?P<id>\d+)' + _TESTS = [ + { + 'url': 'http://www.tvplay.lv/parraides/vinas-melo-labak/418113?autostart=true', + 'info_dict': { + 'id': '418113', + 'ext': 'flv', + 'title': 'Kādi ir īri? - Viņas melo labāk', + 'description': 'Baiba apsmej īrus, kādi tie ir un ko viņi dara.', + 'duration': 25, + 'timestamp': 1406097056, + 'upload_date': '20140723', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + video = self._download_json( + 'http://playapi.mtgx.tv/v1/videos/%s' % video_id, video_id, 'Downloading video JSON') + + if video['is_geo_blocked']: + raise ExtractorError( + 'This content is not available in your country due to copyright reasons', expected=True) + + streams = self._download_json( + 'http://playapi.mtgx.tv/v1/videos/stream/%s' % video_id, video_id, 'Downloading streams JSON') + + quality = qualities(['hls', 'medium', 'high']) + formats = [] + for format_id, video_url in streams['streams'].items(): + if not video_url: + continue + fmt = { + 'format_id': format_id, + 'preference': quality(format_id), + } + if video_url.startswith('rtmp'): + m = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', video_url) + if not m: + continue + fmt.update({ + 'ext': 'flv', + 'url': m.group('url'), + 'app': m.group('app'), + 'play_path': m.group('playpath'), + }) + else: + fmt.update({ + 'url': video_url, + }) + formats.append(fmt) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': video['title'], + 'description': video['description'], + 'duration': video['duration'], + 'timestamp': parse_iso8601(video['created_at']), + 'view_count': video['views']['total'], + 'age_limit': video.get('age_limit', 0), + 'formats': formats, + } diff --git a/youtube_dl/extractor/ubu.py b/youtube_dl/extractor/ubu.py new file mode 100644 index 000000000..0182d67ec --- /dev/null +++ b/youtube_dl/extractor/ubu.py @@ -0,0 +1,56 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import int_or_none + + +class UbuIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?ubu\.com/film/(?P<id>[\da-z_-]+)\.html' + _TEST = { + 'url': 'http://ubu.com/film/her_noise.html', + 'md5': '8edd46ee8aa6b265fb5ed6cf05c36bc9', + 'info_dict': { + 'id': 'her_noise', + 'ext': 'mp4', + 'title': 'Her Noise - The Making Of (2007)', + 'duration': 3600, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex( + r'<title>.+?Film & Video: ([^<]+)</title>', webpage, 'title') + + duration = int_or_none(self._html_search_regex( + r'Duration: (\d+) minutes', webpage, 'duration', fatal=False, default=None)) + if duration: + duration *= 60 + + formats = [] + + FORMAT_REGEXES = [ + ['sq', r"'flashvars'\s*,\s*'file=([^']+)'"], + ['hq', r'href="(http://ubumexico\.centro\.org\.mx/video/[^"]+)"'] + ] + + for format_id, format_regex in FORMAT_REGEXES: + m = re.search(format_regex, webpage) + if m: + formats.append({ + 'url': m.group(1), + 'format_id': format_id, + }) + + return { + 'id': video_id, + 'title': title, + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/unistra.py b/youtube_dl/extractor/unistra.py index 474610eec..f70978299 100644 --- a/youtube_dl/extractor/unistra.py +++ b/youtube_dl/extractor/unistra.py @@ -1,32 +1,66 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor +from ..utils import qualities + class UnistraIE(InfoExtractor): - _VALID_URL = r'http://utv\.unistra\.fr/(?:index|video)\.php\?id_video\=(\d+)' - - _TEST = { - u'url': u'http://utv.unistra.fr/video.php?id_video=154', - u'file': u'154.mp4', - u'md5': u'736f605cfdc96724d55bb543ab3ced24', - u'info_dict': { - u'title': u'M!ss Yella', - u'description': u'md5:104892c71bd48e55d70b902736b81bbf', + _VALID_URL = r'http://utv\.unistra\.fr/(?:index|video)\.php\?id_video\=(?P<id>\d+)' + + _TESTS = [ + { + 'url': 'http://utv.unistra.fr/video.php?id_video=154', + 'md5': '736f605cfdc96724d55bb543ab3ced24', + 'info_dict': { + 'id': '154', + 'ext': 'mp4', + 'title': 'M!ss Yella', + 'description': 'md5:104892c71bd48e55d70b902736b81bbf', + }, }, - } + { + 'url': 'http://utv.unistra.fr/index.php?id_video=437', + 'md5': '1ddddd6cccaae76f622ce29b8779636d', + 'info_dict': { + 'id': '437', + 'ext': 'mp4', + 'title': 'Prix Louise Weiss 2014', + 'description': 'md5:cc3a8735f079f4fb6b0b570fc10c135a', + }, + } + ] def _real_extract(self, url): - id = re.match(self._VALID_URL, url).group(1) - webpage = self._download_webpage(url, id) - file = re.search(r'file: "(.*?)",', webpage).group(1) - title = self._html_search_regex(r'<title>UTV - (.*?)</', webpage, u'title') + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') - video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file + webpage = self._download_webpage(url, video_id) - return {'id': id, - 'title': title, - 'ext': 'mp4', - 'url': video_url, - 'description': self._html_search_regex(r'<meta name="Description" content="(.*?)"', webpage, u'description', flags=re.DOTALL), - 'thumbnail': self._search_regex(r'image: "(.*?)"', webpage, u'thumbnail'), - } + files = set(re.findall(r'file\s*:\s*"([^"]+)"', webpage)) + + quality = qualities(['SD', 'HD']) + formats = [] + for file_path in files: + format_id = 'HD' if file_path.endswith('-HD.mp4') else 'SD' + formats.append({ + 'url': 'http://vod-flash.u-strasbg.fr:8080%s' % file_path, + 'format_id': format_id, + 'quality': quality(format_id) + }) + + title = self._html_search_regex( + r'<title>UTV - (.*?)</', webpage, 'title') + description = self._html_search_regex( + r'<meta name="Description" content="(.*?)"', webpage, 'description', flags=re.DOTALL) + thumbnail = self._search_regex( + r'image: "(.*?)"', webpage, 'thumbnail') + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'formats': formats + } diff --git a/youtube_dl/extractor/ustream.py b/youtube_dl/extractor/ustream.py index 488b10df9..994b60a76 100644 --- a/youtube_dl/extractor/ustream.py +++ b/youtube_dl/extractor/ustream.py @@ -1,6 +1,5 @@ from __future__ import unicode_literals -import json import re from .common import InfoExtractor @@ -68,21 +67,36 @@ class UstreamIE(InfoExtractor): class UstreamChannelIE(InfoExtractor): _VALID_URL = r'https?://www\.ustream\.tv/channel/(?P<slug>.+)' IE_NAME = 'ustream:channel' + _TEST = { + 'url': 'http://www.ustream.tv/channel/channeljapan', + 'info_dict': { + 'id': '10874166', + }, + 'playlist_mincount': 54, + } def _real_extract(self, url): m = re.match(self._VALID_URL, url) - slug = m.group('slug') - webpage = self._download_webpage(url, slug) + display_id = m.group('slug') + webpage = self._download_webpage(url, display_id) channel_id = get_meta_content('ustream:channel_id', webpage) BASE = 'http://www.ustream.tv' next_url = '/ajax/socialstream/videos/%s/1.json' % channel_id video_ids = [] while next_url: - reply = json.loads(self._download_webpage(compat_urlparse.urljoin(BASE, next_url), channel_id)) + reply = self._download_json( + compat_urlparse.urljoin(BASE, next_url), display_id, + note='Downloading video information (next: %d)' % (len(video_ids) + 1)) video_ids.extend(re.findall(r'data-content-id="(\d.*)"', reply['data'])) next_url = reply['nextUrl'] - urls = ['http://www.ustream.tv/recorded/' + vid for vid in video_ids] - url_entries = [self.url_result(eurl, 'Ustream') for eurl in urls] - return self.playlist_result(url_entries, channel_id) + entries = [ + self.url_result('http://www.ustream.tv/recorded/' + vid, 'Ustream') + for vid in video_ids] + return { + '_type': 'playlist', + 'id': channel_id, + 'display_id': display_id, + 'entries': entries, + } diff --git a/youtube_dl/extractor/veehd.py b/youtube_dl/extractor/veehd.py index b1c854a64..77b1f91ce 100644 --- a/youtube_dl/extractor/veehd.py +++ b/youtube_dl/extractor/veehd.py @@ -16,8 +16,9 @@ class VeeHDIE(InfoExtractor): _TEST = { 'url': 'http://veehd.com/video/4686958', - 'file': '4686958.mp4', 'info_dict': { + 'id': '4686958', + 'ext': 'mp4', 'title': 'Time Lapse View from Space ( ISS)', 'uploader_id': 'spotted', 'description': 'md5:f0094c4cf3a72e22bc4e4239ef767ad7', diff --git a/youtube_dl/extractor/vevo.py b/youtube_dl/extractor/vevo.py index eada13ce9..d2ffd1b6b 100644 --- a/youtube_dl/extractor/vevo.py +++ b/youtube_dl/extractor/vevo.py @@ -177,6 +177,7 @@ class VevoIE(InfoExtractor): self._downloader.report_warning( 'Cannot download SMIL information, falling back to JSON ..') + self._sort_formats(formats) timestamp_ms = int(self._search_regex( r'/Date\((\d+)\)/', video_info['launchDate'], 'launch date')) diff --git a/youtube_dl/extractor/vidme.py b/youtube_dl/extractor/vidme.py new file mode 100644 index 000000000..5c89824c1 --- /dev/null +++ b/youtube_dl/extractor/vidme.py @@ -0,0 +1,68 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + float_or_none, + str_to_int, +) + + +class VidmeIE(InfoExtractor): + _VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]+)' + _TEST = { + 'url': 'https://vid.me/QNB', + 'md5': 'f42d05e7149aeaec5c037b17e5d3dc82', + 'info_dict': { + 'id': 'QNB', + 'ext': 'mp4', + 'title': 'Fishing for piranha - the easy way', + 'description': 'source: https://www.facebook.com/photo.php?v=312276045600871', + 'duration': 119.92, + 'timestamp': 1406313244, + 'upload_date': '20140725', + 'thumbnail': 're:^https?://.*\.jpg', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex(r'<source src="([^"]+)"', webpage, 'video URL') + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage, default='') + thumbnail = self._og_search_thumbnail(webpage) + timestamp = int_or_none(self._og_search_property('updated_time', webpage, fatal=False)) + width = int_or_none(self._og_search_property('video:width', webpage, fatal=False)) + height = int_or_none(self._og_search_property('video:height', webpage, fatal=False)) + duration = float_or_none(self._html_search_regex( + r'data-duration="([^"]+)"', webpage, 'duration', fatal=False)) + view_count = str_to_int(self._html_search_regex( + r'<span class="video_views">\s*([\d,\.]+)\s*plays?', webpage, 'view count', fatal=False)) + like_count = str_to_int(self._html_search_regex( + r'class="score js-video-vote-score"[^>]+data-score="([\d,\.\s]+)">', + webpage, 'like count', fatal=False)) + comment_count = str_to_int(self._html_search_regex( + r'class="js-comment-count"[^>]+data-count="([\d,\.\s]+)">', + webpage, 'comment count', fatal=False)) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'width': width, + 'height': height, + 'duration': duration, + 'view_count': view_count, + 'like_count': like_count, + 'comment_count': comment_count, + } diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 255855558..bc01d7fbf 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -57,6 +57,7 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): (?P<proto>(?:https?:)?//)? (?:(?:www|(?P<player>player))\.)? vimeo(?P<pro>pro)?\.com/ + (?!channels/[^/?#]+/?(?:$|[?#])|album/) (?:.*?/)? (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)? (?:videos?/)? @@ -98,7 +99,7 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): 'info_dict': { 'id': '54469442', 'ext': 'mp4', - 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software', + 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012', 'uploader': 'The BLN & Business of Software', 'uploader_id': 'theblnbusinessofsoftware', 'duration': 3610, @@ -122,6 +123,21 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): }, }, { + 'url': 'http://vimeo.com/channels/keypeele/75629013', + 'md5': '2f86a05afe9d7abc0b9126d229bbe15d', + 'note': 'Video is freely available via original URL ' + 'and protected with password when accessed via http://vimeo.com/75629013', + 'info_dict': { + 'id': '75629013', + 'ext': 'mp4', + 'title': 'Key & Peele: Terrorist Interrogation', + 'description': 'md5:8678b246399b070816b12313e8b4eb5c', + 'uploader_id': 'atencio', + 'uploader': 'Peter Atencio', + 'duration': 187, + }, + }, + { 'url': 'http://vimeo.com/76979871', 'md5': '3363dd6ffebe3784d56f4132317fd446', 'note': 'Video with subtitles', @@ -138,15 +154,6 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): }, ] - @classmethod - def suitable(cls, url): - if VimeoChannelIE.suitable(url): - # Otherwise channel urls like http://vimeo.com/channels/31259 would - # match - return False - else: - return super(VimeoIE, cls).suitable(url) - def _verify_video_password(self, url, video_id, webpage): password = self._downloader.params.get('videopassword', None) if password is None: @@ -190,14 +197,14 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): if data is not None: headers = headers.copy() headers.update(data) + if 'Referer' not in headers: + headers['Referer'] = url # Extract ID from URL mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') if mobj.group('pro') or mobj.group('player'): url = 'http://player.vimeo.com/video/' + video_id - else: - url = 'https://vimeo.com/' + video_id # Retrieve video webpage to extract further information request = compat_urllib_request.Request(url, None, headers) @@ -263,7 +270,7 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): if video_thumbnail is None: video_thumbs = config["video"].get("thumbs") if video_thumbs and isinstance(video_thumbs, dict): - _, video_thumbnail = sorted((int(width), t_url) for (width, t_url) in video_thumbs.items())[-1] + _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1] # Extract video description video_description = None @@ -365,9 +372,16 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): class VimeoChannelIE(InfoExtractor): IE_NAME = 'vimeo:channel' - _VALID_URL = r'(?:https?://)?vimeo\.com/channels/(?P<id>[^/]+)/?(\?.*)?$' + _VALID_URL = r'https?://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])' _MORE_PAGES_INDICATOR = r'<a.+?rel="next"' _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"' + _TESTS = [{ + 'url': 'http://vimeo.com/channels/tributes', + 'info_dict': { + 'title': 'Vimeo Tributes', + }, + 'playlist_mincount': 25, + }] def _page_url(self, base_url, pagenum): return '%s/videos/page:%d/' % (base_url, pagenum) @@ -401,14 +415,15 @@ class VimeoChannelIE(InfoExtractor): class VimeoUserIE(VimeoChannelIE): IE_NAME = 'vimeo:user' - _VALID_URL = r'(?:https?://)?vimeo\.com/(?P<name>[^/]+)(?:/videos|[#?]|$)' + _VALID_URL = r'https?://vimeo\.com/(?![0-9]+(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)' _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>' - - @classmethod - def suitable(cls, url): - if VimeoChannelIE.suitable(url) or VimeoIE.suitable(url) or VimeoAlbumIE.suitable(url) or VimeoGroupsIE.suitable(url): - return False - return super(VimeoUserIE, cls).suitable(url) + _TESTS = [{ + 'url': 'http://vimeo.com/nkistudio/videos', + 'info_dict': { + 'title': 'Nki', + }, + 'playlist_mincount': 66, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -418,8 +433,15 @@ class VimeoUserIE(VimeoChannelIE): class VimeoAlbumIE(VimeoChannelIE): IE_NAME = 'vimeo:album' - _VALID_URL = r'(?:https?://)?vimeo\.com/album/(?P<id>\d+)' + _VALID_URL = r'https?://vimeo\.com/album/(?P<id>\d+)' _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>' + _TESTS = [{ + 'url': 'http://vimeo.com/album/2632481', + 'info_dict': { + 'title': 'Staff Favorites: November 2013', + }, + 'playlist_mincount': 13, + }] def _page_url(self, base_url, pagenum): return '%s/page:%d/' % (base_url, pagenum) @@ -433,6 +455,13 @@ class VimeoAlbumIE(VimeoChannelIE): class VimeoGroupsIE(VimeoAlbumIE): IE_NAME = 'vimeo:group' _VALID_URL = r'(?:https?://)?vimeo\.com/groups/(?P<name>[^/]+)' + _TESTS = [{ + 'url': 'http://vimeo.com/groups/rolexawards', + 'info_dict': { + 'title': 'Rolex Awards for Enterprise', + }, + 'playlist_mincount': 73, + }] def _extract_list_title(self, webpage): return self._og_search_title(webpage) @@ -446,8 +475,8 @@ class VimeoGroupsIE(VimeoAlbumIE): class VimeoReviewIE(InfoExtractor): IE_NAME = 'vimeo:review' IE_DESC = 'Review pages on vimeo' - _VALID_URL = r'(?:https?://)?vimeo\.com/[^/]+/review/(?P<id>[^/]+)' - _TEST = { + _VALID_URL = r'https?://vimeo\.com/[^/]+/review/(?P<id>[^/]+)' + _TESTS = [{ 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d', 'file': '75524534.mp4', 'md5': 'c507a72f780cacc12b2248bb4006d253', @@ -455,7 +484,19 @@ class VimeoReviewIE(InfoExtractor): 'title': "DICK HARDWICK 'Comedian'", 'uploader': 'Richard Hardwick', } - } + }, { + 'note': 'video player needs Referer', + 'url': 'http://vimeo.com/user22258446/review/91613211/13f927e053', + 'md5': '6295fdab8f4bf6a002d058b2c6dce276', + 'info_dict': { + 'id': '91613211', + 'ext': 'mp4', + 'title': 'Death by dogma versus assembling agile - Sander Hoogendoorn', + 'uploader': 'DevWeek Events', + 'duration': 2773, + 'thumbnail': 're:^https?://.*\.jpg$', + } + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -470,6 +511,10 @@ class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE): _VALID_URL = r'https?://vimeo\.com/home/watchlater|:vimeowatchlater' _LOGIN_REQUIRED = True _TITLE_RE = r'href="/home/watchlater".*?>(.*?)<' + _TESTS = [{ + 'url': 'http://vimeo.com/home/watchlater', + 'only_matching': True, + }] def _real_initialize(self): self._login() diff --git a/youtube_dl/extractor/vine.py b/youtube_dl/extractor/vine.py index 076c87119..e7754158d 100644 --- a/youtube_dl/extractor/vine.py +++ b/youtube_dl/extractor/vine.py @@ -65,6 +65,13 @@ class VineUserIE(InfoExtractor): IE_NAME = 'vine:user' _VALID_URL = r'(?:https?://)?vine\.co/(?P<user>[^/]+)/?(\?.*)?$' _VINE_BASE_URL = "https://vine.co/" + _TEST = { + 'url': 'https://vine.co/Visa', + 'info_dict': { + 'id': 'Visa', + }, + 'playlist_mincount': 47, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/vodlocker.py b/youtube_dl/extractor/vodlocker.py index 68c59364b..affef6507 100644 --- a/youtube_dl/extractor/vodlocker.py +++ b/youtube_dl/extractor/vodlocker.py @@ -10,7 +10,7 @@ from ..utils import ( class VodlockerIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?vodlocker.com/(?P<id>[0-9a-zA-Z]+)(?:\..*?)?' + _VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?P<id>[0-9a-zA-Z]+)(?:\..*?)?' _TESTS = [{ 'url': 'http://vodlocker.com/e8wvyzz4sl42', @@ -44,7 +44,7 @@ class VodlockerIE(InfoExtractor): req, video_id, 'Downloading video page') title = self._search_regex( - r'id="file_title".*?>\s*(.*?)\s*<span', webpage, 'title') + r'id="file_title".*?>\s*(.*?)\s*<(?:br|span)', webpage, 'title') thumbnail = self._search_regex( r'image:\s*"(http[^\"]+)",', webpage, 'thumbnail') url = self._search_regex( diff --git a/youtube_dl/extractor/vporn.py b/youtube_dl/extractor/vporn.py new file mode 100644 index 000000000..426369c51 --- /dev/null +++ b/youtube_dl/extractor/vporn.py @@ -0,0 +1,99 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + str_to_int, +) + + +class VpornIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?vporn\.com/[^/]+/(?P<display_id>[^/]+)/(?P<id>\d+)' + _TEST = { + 'url': 'http://www.vporn.com/masturbation/violet-on-her-th-birthday/497944/', + 'md5': 'facf37c1b86546fa0208058546842c55', + 'info_dict': { + 'id': '497944', + 'display_id': 'violet-on-her-th-birthday', + 'ext': 'mp4', + 'title': 'Violet on her 19th birthday', + 'description': 'Violet dances in front of the camera which is sure to get you horny.', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': 'kileyGrope', + 'categories': ['Masturbation', 'Teen'], + 'duration': 393, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + title = self._html_search_regex( + r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip() + description = self._html_search_regex( + r'<div class="description_txt">(.*?)</div>', webpage, 'description', fatal=False) + thumbnail = self._html_search_regex( + r'flashvars\.imageUrl\s*=\s*"([^"]+)"', webpage, 'description', fatal=False, default=None) + if thumbnail: + thumbnail = 'http://www.vporn.com' + thumbnail + + uploader = self._html_search_regex( + r'(?s)UPLOADED BY.*?<a href="/user/[^"]+">([^<]+)</a>', + webpage, 'uploader', fatal=False) + + categories = re.findall(r'<a href="/cat/[^"]+">([^<]+)</a>', webpage) + + duration = parse_duration(self._search_regex( + r'duration (\d+ min \d+ sec)', webpage, 'duration', fatal=False)) + + view_count = str_to_int(self._html_search_regex( + r'<span>([\d,\.]+) VIEWS</span>', webpage, 'view count', fatal=False)) + like_count = str_to_int(self._html_search_regex( + r'<span id="like" class="n">([\d,\.]+)</span>', webpage, 'like count', fatal=False)) + dislike_count = str_to_int(self._html_search_regex( + r'<span id="dislike" class="n">([\d,\.]+)</span>', webpage, 'dislike count', fatal=False)) + comment_count = str_to_int(self._html_search_regex( + r'<h4>Comments \(<b>([\d,\.]+)</b>\)</h4>', webpage, 'comment count', fatal=False)) + + formats = [] + + for video in re.findall(r'flashvars\.videoUrl([^=]+?)\s*=\s*"([^"]+)"', webpage): + video_url = video[1] + fmt = { + 'url': video_url, + 'format_id': video[0], + } + m = re.search(r'_(?P<width>\d+)x(?P<height>\d+)_(?P<vbr>\d+)k\.mp4$', video_url) + if m: + fmt.update({ + 'width': int(m.group('width')), + 'height': int(m.group('height')), + 'vbr': int(m.group('vbr')), + }) + formats.append(fmt) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'categories': categories, + 'duration': duration, + 'view_count': view_count, + 'like_count': like_count, + 'dislike_count': dislike_count, + 'comment_count': comment_count, + 'age_limit': 18, + 'formats': formats, + } diff --git a/youtube_dl/extractor/vube.py b/youtube_dl/extractor/vube.py index 7b77865cb..2544c24bd 100644 --- a/youtube_dl/extractor/vube.py +++ b/youtube_dl/extractor/vube.py @@ -3,7 +3,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + int_or_none, + compat_str, +) class VubeIE(InfoExtractor): @@ -20,12 +23,15 @@ class VubeIE(InfoExtractor): 'ext': 'mp4', 'title': 'Chiara Grispo - Price Tag by Jessie J', 'description': 'md5:8ea652a1f36818352428cb5134933313', - 'thumbnail': 'http://frame.thestaticvube.com/snap/228x128/102e7e63057-5ebc-4f5c-4065-6ce4ebde131f.jpg', + 'thumbnail': 're:^http://frame\.thestaticvube\.com/snap/[0-9x]+/102e7e63057-5ebc-4f5c-4065-6ce4ebde131f\.jpg$', 'uploader': 'Chiara.Grispo', - 'uploader_id': '1u3hX0znhP', 'timestamp': 1388743358, 'upload_date': '20140103', - 'duration': 170.56 + 'duration': 170.56, + 'like_count': int, + 'dislike_count': int, + 'comment_count': int, + 'categories': ['pop', 'music', 'cover', 'singing', 'jessie j', 'price tag', 'chiara grispo'], } }, { @@ -36,12 +42,33 @@ class VubeIE(InfoExtractor): 'ext': 'mp4', 'title': 'My 7 year old Sister and I singing "Alive" by Krewella', 'description': 'md5:40bcacb97796339f1690642c21d56f4a', - 'thumbnail': 'http://frame.thestaticvube.com/snap/228x128/102265d5a9f-0f17-4f6b-5753-adf08484ee1e.jpg', + 'thumbnail': 're:^http://frame\.thestaticvube\.com/snap/[0-9x]+/102265d5a9f-0f17-4f6b-5753-adf08484ee1e\.jpg$', 'uploader': 'Seraina', - 'uploader_id': 'XU9VE2BQ2q', 'timestamp': 1396492438, 'upload_date': '20140403', - 'duration': 240.107 + 'duration': 240.107, + 'like_count': int, + 'dislike_count': int, + 'comment_count': int, + 'categories': ['seraina', 'jessica', 'krewella', 'alive'], + } + }, { + 'url': 'http://vube.com/vote/Siren+Gene/0nmsMY5vEq?n=2&t=s', + 'md5': '0584fc13b50f887127d9d1007589d27f', + 'info_dict': { + 'id': '0nmsMY5vEq', + 'ext': 'mp4', + 'title': 'Frozen - Let It Go Cover by Siren Gene', + 'description': 'My rendition of "Let It Go" originally sung by Idina Menzel.', + 'thumbnail': 're:^http://frame\.thestaticvube\.com/snap/[0-9x]+/10283ab622a-86c9-4681-51f2-30d1f65774af\.jpg$', + 'uploader': 'Siren', + 'timestamp': 1395448018, + 'upload_date': '20140322', + 'duration': 221.788, + 'like_count': int, + 'dislike_count': int, + 'comment_count': int, + 'categories': ['let it go', 'cover', 'idina menzel', 'frozen', 'singing', 'disney', 'siren gene'], } } ] @@ -51,39 +78,52 @@ class VubeIE(InfoExtractor): video_id = mobj.group('id') video = self._download_json( - 'http://vube.com/api/v2/video/%s' % video_id, video_id, 'Downloading video JSON') + 'http://vube.com/t-api/v1/video/%s' % video_id, video_id, 'Downloading video JSON') public_id = video['public_id'] - formats = [ - { - 'url': 'http://video.thestaticvube.com/video/%s/%s.mp4' % (fmt['media_resolution_id'], public_id), - 'height': int(fmt['height']), - 'abr': int(fmt['audio_bitrate']), - 'vbr': int(fmt['video_bitrate']), - 'format_id': fmt['media_resolution_id'] - } for fmt in video['mtm'] if fmt['transcoding_status'] == 'processed' - ] + formats = [] + + for media in video['media'].get('video', []) + video['media'].get('audio', []): + if media['transcoding_status'] != 'processed': + continue + fmt = { + 'url': 'http://video.thestaticvube.com/video/%s/%s.mp4' % (media['media_resolution_id'], public_id), + 'abr': int(media['audio_bitrate']), + 'format_id': compat_str(media['media_resolution_id']), + } + vbr = int(media['video_bitrate']) + if vbr: + fmt.update({ + 'vbr': vbr, + 'height': int(media['height']), + }) + formats.append(fmt) self._sort_formats(formats) title = video['title'] description = video.get('description') - thumbnail = video['thumbnail_src'] - if thumbnail.startswith('//'): - thumbnail = 'http:' + thumbnail - uploader = video['user_alias'] - uploader_id = video['user_url_id'] - timestamp = int(video['upload_time']) + thumbnail = self._proto_relative_url(video.get('thumbnail_src'), scheme='http:') + uploader = video.get('user_alias') or video.get('channel') + timestamp = int_or_none(video.get('upload_time')) duration = video['duration'] view_count = video.get('raw_view_count') like_count = video.get('total_likes') - dislike_count= video.get('total_hates') + dislike_count = video.get('total_hates') - comment = self._download_json( - 'http://vube.com/api/video/%s/comment' % video_id, video_id, 'Downloading video comment JSON') + comments = video.get('comments') + comment_count = None + if comments is None: + comment_data = self._download_json( + 'http://vube.com/api/video/%s/comment' % video_id, + video_id, 'Downloading video comment JSON', fatal=False) + if comment_data is not None: + comment_count = int_or_none(comment_data.get('total')) + else: + comment_count = len(comments) - comment_count = int_or_none(comment.get('total')) + categories = [tag['text'] for tag in video['tags']] return { 'id': video_id, @@ -92,11 +132,11 @@ class VubeIE(InfoExtractor): 'description': description, 'thumbnail': thumbnail, 'uploader': uploader, - 'uploader_id': uploader_id, 'timestamp': timestamp, 'duration': duration, 'view_count': view_count, 'like_count': like_count, 'dislike_count': dislike_count, 'comment_count': comment_count, + 'categories': categories, } diff --git a/youtube_dl/extractor/washingtonpost.py b/youtube_dl/extractor/washingtonpost.py index cb8f0887d..88bbbb219 100644 --- a/youtube_dl/extractor/washingtonpost.py +++ b/youtube_dl/extractor/washingtonpost.py @@ -13,6 +13,9 @@ class WashingtonPostIE(InfoExtractor): _VALID_URL = r'^https?://(?:www\.)?washingtonpost\.com/.*?/(?P<id>[^/]+)/(?:$|[?#])' _TEST = { 'url': 'http://www.washingtonpost.com/sf/national/2014/03/22/sinkhole-of-bureaucracy/', + 'info_dict': { + 'title': 'Sinkhole of bureaucracy', + }, 'playlist': [{ 'md5': 'c3f4b4922ffa259243f68e928db2db8c', 'info_dict': { diff --git a/youtube_dl/extractor/wat.py b/youtube_dl/extractor/wat.py index a584e0896..46b4d9133 100644 --- a/youtube_dl/extractor/wat.py +++ b/youtube_dl/extractor/wat.py @@ -2,29 +2,43 @@ from __future__ import unicode_literals import re +import hashlib from .common import InfoExtractor -from ..utils import ( - unified_strdate, -) +from ..utils import unified_strdate class WatIE(InfoExtractor): - _VALID_URL = r'http://www\.wat\.tv/.*-(?P<shortID>.*?)_.*?\.html' + _VALID_URL = r'http://www\.wat\.tv/video/(?P<display_id>.*)-(?P<short_id>.*?)_.*?\.html' IE_NAME = 'wat.tv' - _TEST = { - 'url': 'http://www.wat.tv/video/world-war-philadelphia-vost-6bv55_2fjr7_.html', - 'info_dict': { - 'id': '10631273', - 'ext': 'mp4', - 'title': 'World War Z - Philadelphia VOST', - 'description': 'La menace est partout. Que se passe-t-il à Philadelphia ?\r\nWORLD WAR Z, avec Brad Pitt, au cinéma le 3 juillet.\r\nhttp://www.worldwarz.fr', + _TESTS = [ + { + 'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html', + 'md5': 'ce70e9223945ed26a8056d413ca55dc9', + 'info_dict': { + 'id': '11713067', + 'display_id': 'soupe-figues-l-orange-aux-epices', + 'ext': 'mp4', + 'title': 'Soupe de figues à l\'orange et aux épices', + 'description': 'Retrouvez l\'émission "Petits plats en équilibre", diffusée le 18 août 2014.', + 'upload_date': '20140819', + 'duration': 120, + }, }, - 'params': { - # Sometimes wat serves the whole file with the --test option - 'skip_download': True, + { + 'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html', + 'md5': 'fbc84e4378165278e743956d9c1bf16b', + 'info_dict': { + 'id': '11713075', + 'display_id': 'gregory-lemarchal-voix-ange', + 'ext': 'mp4', + 'title': 'Grégory Lemarchal, une voix d\'ange depuis 10 ans (1/3)', + 'description': 'md5:b7a849cf16a2b733d9cd10c52906dee3', + 'upload_date': '20140816', + 'duration': 2910, + }, }, - } + ] def download_video_info(self, real_id): # 'contentv4' is used in the website, but it also returns the related @@ -36,13 +50,20 @@ class WatIE(InfoExtractor): def real_id_for_chapter(chapter): return chapter['tc_start'].split('-')[0] mobj = re.match(self._VALID_URL, url) - short_id = mobj.group('shortID') - webpage = self._download_webpage(url, short_id) + short_id = mobj.group('short_id') + display_id = mobj.group('display_id') + webpage = self._download_webpage(url, display_id or short_id) real_id = self._search_regex(r'xtpage = ".*-(.*?)";', webpage, 'real id') video_info = self.download_video_info(real_id) + + geo_list = video_info.get('geoList') + country = geo_list[0] if geo_list else '' + chapters = video_info['chapters'] first_chapter = chapters[0] + files = video_info['files'] + first_file = files[0] if real_id_for_chapter(first_chapter) != real_id: self.to_screen('Multipart video detected') @@ -61,12 +82,47 @@ class WatIE(InfoExtractor): upload_date = unified_strdate(first_chapter['date_diffusion']) # Otherwise we can continue and extract just one part, we have to use # the short id for getting the video url + + formats = [{ + 'url': 'http://wat.tv/get/android5/%s.mp4' % real_id, + 'format_id': 'Mobile', + }] + + fmts = [('SD', 'web')] + if first_file.get('hasHD'): + fmts.append(('HD', 'webhd')) + + def compute_token(param): + timestamp = '%08x' % int(self._download_webpage( + 'http://www.wat.tv/servertime', real_id, + 'Downloading server time').split('|')[0]) + magic = '9b673b13fa4682ed14c3cfa5af5310274b514c4133e9b3a81e6e3aba009l2564' + return '%s/%s' % (hashlib.md5((magic + param + timestamp).encode('ascii')).hexdigest(), timestamp) + + for fmt in fmts: + webid = '/%s/%s' % (fmt[1], real_id) + video_url = self._download_webpage( + 'http://www.wat.tv/get%s?token=%s&getURL=1&country=%s' % (webid, compute_token(webid), country), + real_id, + 'Downloding %s video URL' % fmt[0], + 'Failed to download %s video URL' % fmt[0], + False) + if not video_url: + continue + formats.append({ + 'url': video_url, + 'ext': 'mp4', + 'format_id': fmt[0], + }) + return { 'id': real_id, - 'url': 'http://wat.tv/get/android5/%s.mp4' % real_id, + 'display_id': display_id, 'title': first_chapter['title'], 'thumbnail': first_chapter['preview'], 'description': first_chapter['description'], 'view_count': video_info['views'], 'upload_date': upload_date, + 'duration': first_file['duration'], + 'formats': formats, } diff --git a/youtube_dl/extractor/wayofthemaster.py b/youtube_dl/extractor/wayofthemaster.py new file mode 100644 index 000000000..af7bb8b49 --- /dev/null +++ b/youtube_dl/extractor/wayofthemaster.py @@ -0,0 +1,52 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class WayOfTheMasterIE(InfoExtractor): + _VALID_URL = r'https?://www\.wayofthemaster\.com/([^/?#]*/)*(?P<id>[^/?#]+)\.s?html(?:$|[?#])' + + _TEST = { + 'url': 'http://www.wayofthemaster.com/hbks.shtml', + 'md5': '5316b57487ada8480606a93cb3d18d24', + 'info_dict': { + 'id': 'hbks', + 'ext': 'mp4', + 'title': 'Intelligent Design vs. Evolution', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + title = self._search_regex( + r'<img src="images/title_[^"]+".*?alt="([^"]+)"', + webpage, 'title', default=None) + if title is None: + title = self._html_search_regex( + r'<title>(.*?)</title>', webpage, 'page title') + + url_base = self._search_regex( + r'<param\s+name="?movie"?\s+value=".*?/wotm_videoplayer_highlow[0-9]*\.swf\?vid=([^"]+)"', + webpage, 'URL base') + formats = [{ + 'format_id': 'low', + 'quality': 1, + 'url': url_base + '_low.mp4', + }, { + 'format_id': 'high', + 'quality': 2, + 'url': url_base + '_high.mp4', + }] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + } diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py index f741ba540..54d37da61 100644 --- a/youtube_dl/extractor/wdr.py +++ b/youtube_dl/extractor/wdr.py @@ -55,14 +55,14 @@ class WDRIE(InfoExtractor): }, }, { - 'url': 'http://www.funkhauseuropa.de/av/audiosuepersongsoulbossanova100-audioplayer.html', - 'md5': '24e83813e832badb0a8d7d1ef9ef0691', + 'url': 'http://www.funkhauseuropa.de/av/audioflaviacoelhoamaramar100-audioplayer.html', + 'md5': '99a1443ff29af19f6c52cf6f4dc1f4aa', 'info_dict': { - 'id': 'mdb-463528', + 'id': 'mdb-478135', 'ext': 'mp3', - 'title': 'Süpersong: Soul Bossa Nova', + 'title': 'Flavia Coelho: Amar é Amar', 'description': 'md5:7b29e97e10dfb6e265238b32fa35b23a', - 'upload_date': '20140630', + 'upload_date': '20140717', }, }, ] @@ -81,7 +81,7 @@ class WDRIE(InfoExtractor): ] return self.playlist_result(entries, page_id) - flashvars = compat_urlparse.parse_qs( + flashvars = compat_parse_qs( self._html_search_regex(r'<param name="flashvars" value="([^"]+)"', webpage, 'flashvars')) page_id = flashvars['trackerClipId'][0] diff --git a/youtube_dl/extractor/xboxclips.py b/youtube_dl/extractor/xboxclips.py new file mode 100644 index 000000000..a9aa72e73 --- /dev/null +++ b/youtube_dl/extractor/xboxclips.py @@ -0,0 +1,57 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_iso8601, + float_or_none, + int_or_none, +) + + +class XboxClipsIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?xboxclips\.com/video\.php\?.*vid=(?P<id>[\w-]{36})' + _TEST = { + 'url': 'https://xboxclips.com/video.php?uid=2533274823424419&gamertag=Iabdulelah&vid=074a69a9-5faf-46aa-b93b-9909c1720325', + 'md5': 'fbe1ec805e920aeb8eced3c3e657df5d', + 'info_dict': { + 'id': '074a69a9-5faf-46aa-b93b-9909c1720325', + 'ext': 'mp4', + 'title': 'Iabdulelah playing Upload Studio', + 'filesize_approx': 28101836.8, + 'timestamp': 1407388500, + 'upload_date': '20140807', + 'duration': 56, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex( + r'>Link: <a href="([^"]+)">', webpage, 'video URL') + title = self._html_search_regex( + r'<title>XboxClips \| ([^<]+)</title>', webpage, 'title') + timestamp = parse_iso8601(self._html_search_regex( + r'>Recorded: ([^<]+)<', webpage, 'upload date', fatal=False)) + filesize = float_or_none(self._html_search_regex( + r'>Size: ([\d\.]+)MB<', webpage, 'file size', fatal=False), invscale=1024 * 1024) + duration = int_or_none(self._html_search_regex( + r'>Duration: (\d+) Seconds<', webpage, 'duration', fatal=False)) + view_count = int_or_none(self._html_search_regex( + r'>Views: (\d+)<', webpage, 'view count', fatal=False)) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'timestamp': timestamp, + 'filesize_approx': filesize, + 'duration': duration, + 'view_count': view_count, + } diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 5374495f9..00b6d1eba 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -14,7 +14,7 @@ from ..utils import ( class XHamsterIE(InfoExtractor): """Information Extractor for xHamster""" - _VALID_URL = r'http://(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?' + _VALID_URL = r'http://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?' _TESTS = [ { 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html', diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index b293e2665..273d93d9e 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -77,9 +77,17 @@ class XTubeIE(InfoExtractor): 'age_limit': 18, } + class XTubeUserIE(InfoExtractor): IE_DESC = 'XTube user profile' _VALID_URL = r'https?://(?:www\.)?xtube\.com/community/profile\.php\?(.*?)user=(?P<username>[^&#]+)(?:$|[&#])' + _TEST = { + 'url': 'http://www.xtube.com/community/profile.php?user=greenshowers', + 'info_dict': { + 'id': 'greenshowers', + }, + 'playlist_mincount': 155, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index d84be2562..3ab6017cd 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -15,7 +15,7 @@ from ..utils import ( class YahooIE(InfoExtractor): IE_DESC = 'Yahoo screen and movies' - _VALID_URL = r'https?://(?:screen|movies)\.yahoo\.com/.*?-(?P<id>[0-9]+)(?:-[a-z]+)?\.html' + _VALID_URL = r'(?P<url>https?://(?:screen|movies)\.yahoo\.com/.*?-(?P<id>[0-9]+)(?:-[a-z]+)?\.html)' _TESTS = [ { 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', @@ -46,12 +46,23 @@ class YahooIE(InfoExtractor): 'title': 'The World Loves Spider-Man', 'description': '''People all over the world are celebrating the release of \"The Amazing Spider-Man 2.\" We're taking a look at the enthusiastic response Spider-Man has received from viewers all over the world.''', } - } + }, + { + 'url': 'https://screen.yahoo.com/community/community-sizzle-reel-203225340.html?format=embed', + 'md5': '60e8ac193d8fb71997caa8fce54c6460', + 'info_dict': { + 'id': '4fe78544-8d48-39d8-97cd-13f205d9fcdb', + 'ext': 'mp4', + 'title': "Yahoo Saves 'Community'", + 'description': 'md5:4d4145af2fd3de00cbb6c1d664105053', + } + }, ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + url = mobj.group('url') webpage = self._download_webpage(url, video_id) items_json = self._search_regex( @@ -60,7 +71,8 @@ class YahooIE(InfoExtractor): if items_json is None: CONTENT_ID_REGEXES = [ r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"', - r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"' + r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"', + r'"first_videoid"\s*:\s*"([^"]+)"', ] long_id = self._search_regex(CONTENT_ID_REGEXES, webpage, 'content ID') video_id = long_id diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 6123e1256..70f670682 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1,19 +1,15 @@ # coding: utf-8 -import collections -import errno -import io import itertools import json import os.path import re -import struct import traceback -import zlib from .common import InfoExtractor, SearchInfoExtractor from .subtitles import SubtitlesInfoExtractor from ..jsinterp import JSInterpreter +from ..swfinterp import SWFInterpreter from ..utils import ( compat_chr, compat_parse_qs, @@ -23,7 +19,6 @@ from ..utils import ( compat_str, clean_html, - get_cachedir, get_element_by_id, get_element_by_attribute, ExtractorError, @@ -32,13 +27,13 @@ from ..utils import ( unescapeHTML, unified_strdate, orderedSet, - write_json_file, uppercase_escape, ) class YoutubeBaseInfoExtractor(InfoExtractor): """Provide base functions for Youtube extractors""" _LOGIN_URL = 'https://accounts.google.com/ServiceLogin' + _TWOFACTOR_URL = 'https://accounts.google.com/SecondFactor' _LANG_URL = r'https://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' _AGE_URL = 'https://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' _NETRC_MACHINE = 'youtube' @@ -52,12 +47,19 @@ class YoutubeBaseInfoExtractor(InfoExtractor): fatal=False)) def _login(self): + """ + Attempt to log in to YouTube. + True is returned if successful or skipped. + False is returned if login failed. + + If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised. + """ (username, password) = self._get_login_info() # No authentication to be performed if username is None: if self._LOGIN_REQUIRED: raise ExtractorError(u'No login info available, needed for using %s.' % self.IE_NAME, expected=True) - return False + return True login_page = self._download_webpage( self._LOGIN_URL, None, @@ -75,6 +77,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor): u'Email': username, u'GALX': galx, u'Passwd': password, + u'PersistentCookie': u'yes', u'_utf8': u'霱', u'bgresponse': u'js_disabled', @@ -90,6 +93,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor): u'uilel': u'3', u'hl': u'en_US', } + # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode # chokes on unicode login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items()) @@ -101,6 +105,68 @@ class YoutubeBaseInfoExtractor(InfoExtractor): note=u'Logging in', errnote=u'unable to log in', fatal=False) if login_results is False: return False + + if re.search(r'id="errormsg_0_Passwd"', login_results) is not None: + raise ExtractorError(u'Please use your account password and a two-factor code instead of an application-specific password.', expected=True) + + # Two-Factor + # TODO add SMS and phone call support - these require making a request and then prompting the user + + if re.search(r'(?i)<form[^>]* id="gaia_secondfactorform"', login_results) is not None: + tfa_code = self._get_tfa_info() + + if tfa_code is None: + self._downloader.report_warning(u'Two-factor authentication required. Provide it with --twofactor <code>') + self._downloader.report_warning(u'(Note that only TOTP (Google Authenticator App) codes work at this time.)') + return False + + # Unlike the first login form, secTok and timeStmp are both required for the TFA form + + match = re.search(r'id="secTok"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U) + if match is None: + self._downloader.report_warning(u'Failed to get secTok - did the page structure change?') + secTok = match.group(1) + match = re.search(r'id="timeStmp"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U) + if match is None: + self._downloader.report_warning(u'Failed to get timeStmp - did the page structure change?') + timeStmp = match.group(1) + + tfa_form_strs = { + u'continue': u'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', + u'smsToken': u'', + u'smsUserPin': tfa_code, + u'smsVerifyPin': u'Verify', + + u'PersistentCookie': u'yes', + u'checkConnection': u'', + u'checkedDomains': u'youtube', + u'pstMsg': u'1', + u'secTok': secTok, + u'timeStmp': timeStmp, + u'service': u'youtube', + u'hl': u'en_US', + } + tfa_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in tfa_form_strs.items()) + tfa_data = compat_urllib_parse.urlencode(tfa_form).encode('ascii') + + tfa_req = compat_urllib_request.Request(self._TWOFACTOR_URL, tfa_data) + tfa_results = self._download_webpage( + tfa_req, None, + note=u'Submitting TFA code', errnote=u'unable to submit tfa', fatal=False) + + if tfa_results is False: + return False + + if re.search(r'(?i)<form[^>]* id="gaia_secondfactorform"', tfa_results) is not None: + self._downloader.report_warning(u'Two-factor code expired. Please try again, or use a one-use backup code instead.') + return False + if re.search(r'(?i)<form[^>]* id="gaia_loginform"', tfa_results) is not None: + self._downloader.report_warning(u'unable to log in - did the page structure change?') + return False + if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None: + self._downloader.report_warning(u'Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.') + return False + if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None: self._downloader.report_warning(u'unable to log in: bad username or password') return False @@ -227,7 +293,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, # Dash webm audio - '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 48, 'preference': -50}, + '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50}, '172': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50}, # RTMP (unnamed) @@ -246,6 +312,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): u"upload_date": u"20121002", u"description": u"test chars: \"'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .", u"categories": [u'Science & Technology'], + 'like_count': int, + 'dislike_count': int, } }, { @@ -346,28 +414,27 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): """Indicate the download will use the RTMP protocol.""" self.to_screen(u'RTMP download detected') - def _extract_signature_function(self, video_id, player_url, slen): - id_m = re.match(r'.*-(?P<id>[a-zA-Z0-9_-]+)\.(?P<ext>[a-z]+)$', - player_url) + def _signature_cache_id(self, example_sig): + """ Return a string representation of a signature """ + return u'.'.join(compat_str(len(part)) for part in example_sig.split('.')) + + def _extract_signature_function(self, video_id, player_url, example_sig): + id_m = re.match( + r'.*-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.(?P<ext>[a-z]+)$', + player_url) + if not id_m: + raise ExtractorError('Cannot identify player %r' % player_url) player_type = id_m.group('ext') player_id = id_m.group('id') # Read from filesystem cache - func_id = '%s_%s_%d' % (player_type, player_id, slen) + func_id = '%s_%s_%s' % ( + player_type, player_id, self._signature_cache_id(example_sig)) assert os.path.basename(func_id) == func_id - cache_dir = get_cachedir(self._downloader.params) - cache_enabled = cache_dir is not None - if cache_enabled: - cache_fn = os.path.join(os.path.expanduser(cache_dir), - u'youtube-sigfuncs', - func_id + '.json') - try: - with io.open(cache_fn, 'r', encoding='utf-8') as cachef: - cache_spec = json.load(cachef) - return lambda s: u''.join(s[i] for i in cache_spec) - except IOError: - pass # No cache available + cache_spec = self._downloader.cache.load(u'youtube-sigfuncs', func_id) + if cache_spec is not None: + return lambda s: u''.join(s[i] for i in cache_spec) if player_type == 'js': code = self._download_webpage( @@ -385,25 +452,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): else: assert False, 'Invalid player type %r' % player_type - if cache_enabled: - try: - test_string = u''.join(map(compat_chr, range(slen))) - cache_res = res(test_string) - cache_spec = [ord(c) for c in cache_res] - try: - os.makedirs(os.path.dirname(cache_fn)) - except OSError as ose: - if ose.errno != errno.EEXIST: - raise - write_json_file(cache_spec, cache_fn) - except Exception: - tb = traceback.format_exc() - self._downloader.report_warning( - u'Writing cache to %r failed: %s' % (cache_fn, tb)) + if cache_spec is None: + test_string = u''.join(map(compat_chr, range(len(example_sig)))) + cache_res = res(test_string) + cache_spec = [ord(c) for c in cache_res] + self._downloader.cache.store(u'youtube-sigfuncs', func_id, cache_spec) return res - def _print_sig_code(self, func, slen): + def _print_sig_code(self, func, example_sig): def gen_sig_code(idxs): def _genslice(start, end, step): starts = u'' if start == 0 else str(start) @@ -432,11 +489,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): else: yield _genslice(start, i, step) - test_string = u''.join(map(compat_chr, range(slen))) + test_string = u''.join(map(compat_chr, range(len(example_sig)))) cache_res = func(test_string) cache_spec = [ord(c) for c in cache_res] expr_code = u' + '.join(gen_sig_code(cache_spec)) - code = u'if len(s) == %d:\n return %s\n' % (slen, expr_code) + signature_id_tuple = '(%s)' % ( + ', '.join(compat_str(len(p)) for p in example_sig.split('.'))) + code = (u'if tuple(len(p) for p in s.split(\'.\')) == %s:\n' + u' return %s\n') % (signature_id_tuple, expr_code) self.to_screen(u'Extracted signature function:\n' + code) def _parse_sig_js(self, jscode): @@ -449,417 +509,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): return lambda s: initial_function([s]) def _parse_sig_swf(self, file_contents): - if file_contents[1:3] != b'WS': - raise ExtractorError( - u'Not an SWF file; header is %r' % file_contents[:3]) - if file_contents[:1] == b'C': - content = zlib.decompress(file_contents[8:]) - else: - raise NotImplementedError(u'Unsupported compression format %r' % - file_contents[:1]) - - def extract_tags(content): - pos = 0 - while pos < len(content): - header16 = struct.unpack('<H', content[pos:pos+2])[0] - pos += 2 - tag_code = header16 >> 6 - tag_len = header16 & 0x3f - if tag_len == 0x3f: - tag_len = struct.unpack('<I', content[pos:pos+4])[0] - pos += 4 - assert pos+tag_len <= len(content) - yield (tag_code, content[pos:pos+tag_len]) - pos += tag_len - - code_tag = next(tag - for tag_code, tag in extract_tags(content) - if tag_code == 82) - p = code_tag.index(b'\0', 4) + 1 - code_reader = io.BytesIO(code_tag[p:]) - - # Parse ABC (AVM2 ByteCode) - def read_int(reader=None): - if reader is None: - reader = code_reader - res = 0 - shift = 0 - for _ in range(5): - buf = reader.read(1) - assert len(buf) == 1 - b = struct.unpack('<B', buf)[0] - res = res | ((b & 0x7f) << shift) - if b & 0x80 == 0: - break - shift += 7 - return res - - def u30(reader=None): - res = read_int(reader) - assert res & 0xf0000000 == 0 - return res - u32 = read_int - - def s32(reader=None): - v = read_int(reader) - if v & 0x80000000 != 0: - v = - ((v ^ 0xffffffff) + 1) - return v - - def read_string(reader=None): - if reader is None: - reader = code_reader - slen = u30(reader) - resb = reader.read(slen) - assert len(resb) == slen - return resb.decode('utf-8') - - def read_bytes(count, reader=None): - if reader is None: - reader = code_reader - resb = reader.read(count) - assert len(resb) == count - return resb - - def read_byte(reader=None): - resb = read_bytes(1, reader=reader) - res = struct.unpack('<B', resb)[0] - return res - - # minor_version + major_version - read_bytes(2 + 2) - - # Constant pool - int_count = u30() - for _c in range(1, int_count): - s32() - uint_count = u30() - for _c in range(1, uint_count): - u32() - double_count = u30() - read_bytes((double_count-1) * 8) - string_count = u30() - constant_strings = [u''] - for _c in range(1, string_count): - s = read_string() - constant_strings.append(s) - namespace_count = u30() - for _c in range(1, namespace_count): - read_bytes(1) # kind - u30() # name - ns_set_count = u30() - for _c in range(1, ns_set_count): - count = u30() - for _c2 in range(count): - u30() - multiname_count = u30() - MULTINAME_SIZES = { - 0x07: 2, # QName - 0x0d: 2, # QNameA - 0x0f: 1, # RTQName - 0x10: 1, # RTQNameA - 0x11: 0, # RTQNameL - 0x12: 0, # RTQNameLA - 0x09: 2, # Multiname - 0x0e: 2, # MultinameA - 0x1b: 1, # MultinameL - 0x1c: 1, # MultinameLA - } - multinames = [u''] - for _c in range(1, multiname_count): - kind = u30() - assert kind in MULTINAME_SIZES, u'Invalid multiname kind %r' % kind - if kind == 0x07: - u30() # namespace_idx - name_idx = u30() - multinames.append(constant_strings[name_idx]) - else: - multinames.append('[MULTINAME kind: %d]' % kind) - for _c2 in range(MULTINAME_SIZES[kind]): - u30() - - # Methods - method_count = u30() - MethodInfo = collections.namedtuple( - 'MethodInfo', - ['NEED_ARGUMENTS', 'NEED_REST']) - method_infos = [] - for method_id in range(method_count): - param_count = u30() - u30() # return type - for _ in range(param_count): - u30() # param type - u30() # name index (always 0 for youtube) - flags = read_byte() - if flags & 0x08 != 0: - # Options present - option_count = u30() - for c in range(option_count): - u30() # val - read_bytes(1) # kind - if flags & 0x80 != 0: - # Param names present - for _ in range(param_count): - u30() # param name - mi = MethodInfo(flags & 0x01 != 0, flags & 0x04 != 0) - method_infos.append(mi) - - # Metadata - metadata_count = u30() - for _c in range(metadata_count): - u30() # name - item_count = u30() - for _c2 in range(item_count): - u30() # key - u30() # value - - def parse_traits_info(): - trait_name_idx = u30() - kind_full = read_byte() - kind = kind_full & 0x0f - attrs = kind_full >> 4 - methods = {} - if kind in [0x00, 0x06]: # Slot or Const - u30() # Slot id - u30() # type_name_idx - vindex = u30() - if vindex != 0: - read_byte() # vkind - elif kind in [0x01, 0x02, 0x03]: # Method / Getter / Setter - u30() # disp_id - method_idx = u30() - methods[multinames[trait_name_idx]] = method_idx - elif kind == 0x04: # Class - u30() # slot_id - u30() # classi - elif kind == 0x05: # Function - u30() # slot_id - function_idx = u30() - methods[function_idx] = multinames[trait_name_idx] - else: - raise ExtractorError(u'Unsupported trait kind %d' % kind) - - if attrs & 0x4 != 0: # Metadata present - metadata_count = u30() - for _c3 in range(metadata_count): - u30() # metadata index - - return methods - - # Classes + swfi = SWFInterpreter(file_contents) TARGET_CLASSNAME = u'SignatureDecipher' - searched_idx = multinames.index(TARGET_CLASSNAME) - searched_class_id = None - class_count = u30() - for class_id in range(class_count): - name_idx = u30() - if name_idx == searched_idx: - # We found the class we're looking for! - searched_class_id = class_id - u30() # super_name idx - flags = read_byte() - if flags & 0x08 != 0: # Protected namespace is present - u30() # protected_ns_idx - intrf_count = u30() - for _c2 in range(intrf_count): - u30() - u30() # iinit - trait_count = u30() - for _c2 in range(trait_count): - parse_traits_info() - - if searched_class_id is None: - raise ExtractorError(u'Target class %r not found' % - TARGET_CLASSNAME) - - method_names = {} - method_idxs = {} - for class_id in range(class_count): - u30() # cinit - trait_count = u30() - for _c2 in range(trait_count): - trait_methods = parse_traits_info() - if class_id == searched_class_id: - method_names.update(trait_methods.items()) - method_idxs.update(dict( - (idx, name) - for name, idx in trait_methods.items())) - - # Scripts - script_count = u30() - for _c in range(script_count): - u30() # init - trait_count = u30() - for _c2 in range(trait_count): - parse_traits_info() - - # Method bodies - method_body_count = u30() - Method = collections.namedtuple('Method', ['code', 'local_count']) - methods = {} - for _c in range(method_body_count): - method_idx = u30() - u30() # max_stack - local_count = u30() - u30() # init_scope_depth - u30() # max_scope_depth - code_length = u30() - code = read_bytes(code_length) - if method_idx in method_idxs: - m = Method(code, local_count) - methods[method_idxs[method_idx]] = m - exception_count = u30() - for _c2 in range(exception_count): - u30() # from - u30() # to - u30() # target - u30() # exc_type - u30() # var_name - trait_count = u30() - for _c2 in range(trait_count): - parse_traits_info() - - assert p + code_reader.tell() == len(code_tag) - assert len(methods) == len(method_idxs) - - method_pyfunctions = {} - - def extract_function(func_name): - if func_name in method_pyfunctions: - return method_pyfunctions[func_name] - if func_name not in methods: - raise ExtractorError(u'Cannot find function %r' % func_name) - m = methods[func_name] - - def resfunc(args): - registers = ['(this)'] + list(args) + [None] * m.local_count - stack = [] - coder = io.BytesIO(m.code) - while True: - opcode = struct.unpack('!B', coder.read(1))[0] - if opcode == 36: # pushbyte - v = struct.unpack('!B', coder.read(1))[0] - stack.append(v) - elif opcode == 44: # pushstring - idx = u30(coder) - stack.append(constant_strings[idx]) - elif opcode == 48: # pushscope - # We don't implement the scope register, so we'll just - # ignore the popped value - stack.pop() - elif opcode == 70: # callproperty - index = u30(coder) - mname = multinames[index] - arg_count = u30(coder) - args = list(reversed( - [stack.pop() for _ in range(arg_count)])) - obj = stack.pop() - if mname == u'split': - assert len(args) == 1 - assert isinstance(args[0], compat_str) - assert isinstance(obj, compat_str) - if args[0] == u'': - res = list(obj) - else: - res = obj.split(args[0]) - stack.append(res) - elif mname == u'slice': - assert len(args) == 1 - assert isinstance(args[0], int) - assert isinstance(obj, list) - res = obj[args[0]:] - stack.append(res) - elif mname == u'join': - assert len(args) == 1 - assert isinstance(args[0], compat_str) - assert isinstance(obj, list) - res = args[0].join(obj) - stack.append(res) - elif mname in method_pyfunctions: - stack.append(method_pyfunctions[mname](args)) - else: - raise NotImplementedError( - u'Unsupported property %r on %r' - % (mname, obj)) - elif opcode == 72: # returnvalue - res = stack.pop() - return res - elif opcode == 79: # callpropvoid - index = u30(coder) - mname = multinames[index] - arg_count = u30(coder) - args = list(reversed( - [stack.pop() for _ in range(arg_count)])) - obj = stack.pop() - if mname == u'reverse': - assert isinstance(obj, list) - obj.reverse() - else: - raise NotImplementedError( - u'Unsupported (void) property %r on %r' - % (mname, obj)) - elif opcode == 93: # findpropstrict - index = u30(coder) - mname = multinames[index] - res = extract_function(mname) - stack.append(res) - elif opcode == 97: # setproperty - index = u30(coder) - value = stack.pop() - idx = stack.pop() - obj = stack.pop() - assert isinstance(obj, list) - assert isinstance(idx, int) - obj[idx] = value - elif opcode == 98: # getlocal - index = u30(coder) - stack.append(registers[index]) - elif opcode == 99: # setlocal - index = u30(coder) - value = stack.pop() - registers[index] = value - elif opcode == 102: # getproperty - index = u30(coder) - pname = multinames[index] - if pname == u'length': - obj = stack.pop() - assert isinstance(obj, list) - stack.append(len(obj)) - else: # Assume attribute access - idx = stack.pop() - assert isinstance(idx, int) - obj = stack.pop() - assert isinstance(obj, list) - stack.append(obj[idx]) - elif opcode == 128: # coerce - u30(coder) - elif opcode == 133: # coerce_s - assert isinstance(stack[-1], (type(None), compat_str)) - elif opcode == 164: # modulo - value2 = stack.pop() - value1 = stack.pop() - res = value1 % value2 - stack.append(res) - elif opcode == 208: # getlocal_0 - stack.append(registers[0]) - elif opcode == 209: # getlocal_1 - stack.append(registers[1]) - elif opcode == 210: # getlocal_2 - stack.append(registers[2]) - elif opcode == 211: # getlocal_3 - stack.append(registers[3]) - elif opcode == 214: # setlocal_2 - registers[2] = stack.pop() - elif opcode == 215: # setlocal_3 - registers[3] = stack.pop() - else: - raise NotImplementedError( - u'Unsupported opcode %d' % opcode) - - method_pyfunctions[func_name] = resfunc - return resfunc - - initial_function = extract_function(u'decipher') + searched_class = swfi.extract_class(TARGET_CLASSNAME) + initial_function = swfi.extract_function(searched_class, u'decipher') return lambda s: initial_function([s]) def _decrypt_signature(self, s, video_id, player_url, age_gate=False): @@ -871,20 +524,20 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): if player_url.startswith(u'//'): player_url = u'https:' + player_url try: - player_id = (player_url, len(s)) + player_id = (player_url, self._signature_cache_id(s)) if player_id not in self._player_cache: func = self._extract_signature_function( - video_id, player_url, len(s) + video_id, player_url, s ) self._player_cache[player_id] = func func = self._player_cache[player_id] if self._downloader.params.get('youtube_print_sig_code'): - self._print_sig_code(func, len(s)) + self._print_sig_code(func, s) return func(s) except Exception as e: tb = traceback.format_exc() raise ExtractorError( - u'Automatic signature extraction failed: ' + tb, cause=e) + u'Signature extraction failed: ' + tb, cause=e) def _get_available_subtitles(self, video_id, webpage): try: @@ -899,6 +552,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): sub_lang_list = {} for l in lang_list: lang = l[1] + if lang in sub_lang_list: + continue params = compat_urllib_parse.urlencode({ 'lang': lang, 'v': video_id, @@ -1014,14 +669,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): age_gate = True # We simulate the access to the video from www.youtube.com/v/{video_id} # this can be viewed without login into Youtube - data = compat_urllib_parse.urlencode({'video_id': video_id, - 'el': 'player_embedded', - 'gl': 'US', - 'hl': 'en', - 'eurl': 'https://youtube.googleapis.com/v/' + video_id, - 'asv': 3, - 'sts':'1588', - }) + data = compat_urllib_parse.urlencode({ + 'video_id': video_id, + 'eurl': 'https://youtube.googleapis.com/v/' + video_id, + 'sts': self._search_regex( + r'"sts"\s*:\s*(\d+)', video_webpage, 'sts'), + }) video_info_url = proto + '://www.youtube.com/get_video_info?' + data video_info_webpage = self._download_webpage(video_info_url, video_id, note=False, @@ -1103,7 +756,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) upload_date = unified_strdate(upload_date) - m_cat_container = get_element_by_id("eow-category", video_webpage) + m_cat_container = self._search_regex( + r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>', + video_webpage, 'categories', fatal=False) if m_cat_container: category = self._html_search_regex( r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category', @@ -1132,15 +787,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): else: video_description = u'' - def _extract_count(klass): + def _extract_count(count_name): count = self._search_regex( - r'class="%s">([\d,]+)</span>' % re.escape(klass), - video_webpage, klass, default=None) + r'id="watch-%s"[^>]*>.*?([\d,]+)\s*</span>' % re.escape(count_name), + video_webpage, count_name, default=None) if count is not None: return int(count.replace(',', '')) return None - like_count = _extract_count(u'likes-count') - dislike_count = _extract_count(u'dislikes-count') + like_count = _extract_count(u'like') + dislike_count = _extract_count(u'dislike') # subtitles video_subtitles = self.extract_subtitles(video_id, video_webpage) @@ -1214,43 +869,54 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): url_map = {} for url_data_str in encoded_url_map.split(','): url_data = compat_parse_qs(url_data_str) - if 'itag' in url_data and 'url' in url_data: - url = url_data['url'][0] - if 'sig' in url_data: - url += '&signature=' + url_data['sig'][0] - elif 's' in url_data: - encrypted_sig = url_data['s'][0] - if self._downloader.params.get('verbose'): - if age_gate: - if player_url is None: - player_version = 'unknown' - else: - player_version = self._search_regex( - r'-(.+)\.swf$', player_url, - u'flash player', fatal=False) + if 'itag' not in url_data or 'url' not in url_data: + continue + format_id = url_data['itag'][0] + url = url_data['url'][0] + + if 'sig' in url_data: + url += '&signature=' + url_data['sig'][0] + elif 's' in url_data: + encrypted_sig = url_data['s'][0] + + if not age_gate: + jsplayer_url_json = self._search_regex( + r'"assets":.+?"js":\s*("[^"]+")', + video_webpage, u'JS player URL') + player_url = json.loads(jsplayer_url_json) + if player_url is None: + player_url_json = self._search_regex( + r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")', + video_webpage, u'age gate player URL') + player_url = json.loads(player_url_json) + + if self._downloader.params.get('verbose'): + if player_url is None: + player_version = 'unknown' + player_desc = 'unknown' + else: + if player_url.endswith('swf'): + player_version = self._search_regex( + r'-(.+?)(?:/watch_as3)?\.swf$', player_url, + u'flash player', fatal=False) player_desc = 'flash player %s' % player_version else: player_version = self._search_regex( - r'html5player-(.+?)\.js', video_webpage, + r'html5player-([^/]+?)(?:/html5player)?\.js', + player_url, 'html5 player', fatal=False) player_desc = u'html5 player %s' % player_version - parts_sizes = u'.'.join(compat_str(len(part)) for part in encrypted_sig.split('.')) - self.to_screen(u'encrypted signature length %d (%s), itag %s, %s' % - (len(encrypted_sig), parts_sizes, url_data['itag'][0], player_desc)) - - if not age_gate: - jsplayer_url_json = self._search_regex( - r'"assets":.+?"js":\s*("[^"]+")', - video_webpage, u'JS player URL') - player_url = json.loads(jsplayer_url_json) - - signature = self._decrypt_signature( - encrypted_sig, video_id, player_url, age_gate) - url += '&signature=' + signature - if 'ratebypass' not in url: - url += '&ratebypass=yes' - url_map[url_data['itag'][0]] = url + parts_sizes = self._signature_cache_id(encrypted_sig) + self.to_screen(u'{%s} signature length %s, %s' % + (format_id, parts_sizes, player_desc)) + + signature = self._decrypt_signature( + encrypted_sig, video_id, player_url, age_gate) + url += '&signature=' + signature + if 'ratebypass' not in url: + url += '&ratebypass=yes' + url_map[format_id] = url formats = _map_to_format_list(url_map) elif video_info.get('hlsvp'): manifest_url = video_info['hlsvp'][0] @@ -1359,21 +1025,26 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): self._login() def _ids_to_results(self, ids): - return [self.url_result(vid_id, 'Youtube', video_id=vid_id) - for vid_id in ids] + return [ + self.url_result(vid_id, 'Youtube', video_id=vid_id) + for vid_id in ids] def _extract_mix(self, playlist_id): # The mixes are generated from a a single video # the id of the playlist is just 'RD' + video_id url = 'https://youtube.com/watch?v=%s&list=%s' % (playlist_id[-11:], playlist_id) - webpage = self._download_webpage(url, playlist_id, u'Downloading Youtube mix') + webpage = self._download_webpage( + url, playlist_id, u'Downloading Youtube mix') search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage) - title_span = (search_title('playlist-title') or - search_title('title long-title') or search_title('title')) + title_span = ( + search_title('playlist-title') or + search_title('title long-title') or + search_title('title')) title = clean_html(title_span) - video_re = r'''(?x)data-video-username=".*?".*? - href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id) - ids = orderedSet(re.findall(video_re, webpage, flags=re.DOTALL)) + ids = orderedSet(re.findall( + r'''(?xs)data-video-username=".*?".*? + href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id), + webpage)) url_results = self._ids_to_results(ids) return self.playlist_result(url_results, playlist_id, title) @@ -1466,6 +1137,7 @@ class YoutubeTopListIE(YoutubePlaylistIE): msg = u'Downloading Youtube mix' if i > 0: msg += ', retry #%d' % i + webpage = self._download_webpage(url, title, msg) ids = orderedSet(re.findall(video_re, webpage)) if ids: @@ -1738,12 +1410,6 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): paging = mobj.group('paging') return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE) -class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): - IE_DESC = u'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)' - _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?' - _FEED_NAME = 'subscriptions' - _PLAYLIST_TITLE = u'Youtube Subscriptions' - class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): IE_DESC = u'YouTube.com recommended videos, "ytrec" keyword (requires authentication)' _VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?' @@ -1776,6 +1442,43 @@ class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): return self.url_result(playlist_id, 'YoutubePlaylist') +class YoutubeSubscriptionsIE(YoutubePlaylistIE): + IE_NAME = u'youtube:subscriptions' + IE_DESC = u'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)' + _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?' + + def _real_extract(self, url): + title = u'Youtube Subscriptions' + page = self._download_webpage('https://www.youtube.com/feed/subscriptions', title) + + # The extraction process is the same as for playlists, but the regex + # for the video ids doesn't contain an index + ids = [] + more_widget_html = content_html = page + + for page_num in itertools.count(1): + matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html) + new_ids = orderedSet(matches) + ids.extend(new_ids) + + mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) + if not mobj: + break + + more = self._download_json( + 'https://youtube.com/%s' % mobj.group('more'), title, + 'Downloading page #%s' % page_num, + transform_source=uppercase_escape) + content_html = more['content_html'] + more_widget_html = more['load_more_widget_html'] + + return { + '_type': 'playlist', + 'title': title, + 'entries': self._ids_to_results(ids), + } + + class YoutubeTruncatedURLIE(InfoExtractor): IE_NAME = 'youtube:truncated_url' IE_DESC = False # Do not list diff --git a/youtube_dl/jsinterp.py b/youtube_dl/jsinterp.py index ae5bca2e6..c40cd376d 100644 --- a/youtube_dl/jsinterp.py +++ b/youtube_dl/jsinterp.py @@ -1,5 +1,6 @@ from __future__ import unicode_literals +import json import re from .utils import ( @@ -40,8 +41,9 @@ class JSInterpreter(object): assign = lambda v: v expr = stmt[len('return '):] else: - raise ExtractorError( - 'Cannot determine left side of statement in %r' % stmt) + # Try interpreting it as an expression + expr = stmt + assign = lambda v: v v = self.interpret_expression(expr, local_vars, allow_recursion) return assign(v) @@ -53,35 +55,63 @@ class JSInterpreter(object): if expr.isalpha(): return local_vars[expr] - m = re.match(r'^(?P<in>[a-z]+)\.(?P<member>.*)$', expr) + try: + return json.loads(expr) + except ValueError: + pass + + m = re.match( + r'^(?P<var>[a-zA-Z0-9_]+)\.(?P<member>[^(]+)(?:\(+(?P<args>[^()]*)\))?$', + expr) if m: + variable = m.group('var') member = m.group('member') - variable = m.group('in') + arg_str = m.group('args') - if variable not in local_vars: + if variable in local_vars: + obj = local_vars[variable] + else: if variable not in self._objects: self._objects[variable] = self.extract_object(variable) obj = self._objects[variable] - key, args = member.split('(', 1) - args = args.strip(')') - argvals = [int(v) if v.isdigit() else local_vars[v] - for v in args.split(',')] - return obj[key](argvals) - - val = local_vars[variable] - if member == 'split("")': - return list(val) - if member == 'join("")': - return ''.join(val) - if member == 'length': - return len(val) - if member == 'reverse()': - return val[::-1] - slice_m = re.match(r'slice\((?P<idx>.*)\)', member) - if slice_m: - idx = self.interpret_expression( - slice_m.group('idx'), local_vars, allow_recursion - 1) - return val[idx:] + + if arg_str is None: + # Member access + if member == 'length': + return len(obj) + return obj[member] + + assert expr.endswith(')') + # Function call + if arg_str == '': + argvals = tuple() + else: + argvals = tuple([ + self.interpret_expression(v, local_vars, allow_recursion) + for v in arg_str.split(',')]) + + if member == 'split': + assert argvals == ('',) + return list(obj) + if member == 'join': + assert len(argvals) == 1 + return argvals[0].join(obj) + if member == 'reverse': + assert len(argvals) == 0 + obj.reverse() + return obj + if member == 'slice': + assert len(argvals) == 1 + return obj[argvals[0]:] + if member == 'splice': + assert isinstance(obj, list) + index, howMany = argvals + res = [] + for i in range(index, min(index + howMany, len(obj))): + res.append(obj.pop(index)) + return res + + return obj[member](argvals) m = re.match( r'^(?P<in>[a-z]+)\[(?P<idx>.+)\]$', expr) @@ -103,10 +133,11 @@ class JSInterpreter(object): r'^(?P<func>[a-zA-Z$]+)\((?P<args>[a-z0-9,]+)\)$', expr) if m: fname = m.group('func') + argvals = tuple([ + int(v) if v.isdigit() else local_vars[v] + for v in m.group('args').split(',')]) if fname not in self._functions: self._functions[fname] = self.extract_function(fname) - argvals = [int(v) if v.isdigit() else local_vars[v] - for v in m.group('args').split(',')] return self._functions[fname](argvals) raise ExtractorError('Unsupported JS expression %r' % expr) @@ -114,13 +145,13 @@ class JSInterpreter(object): obj = {} obj_m = re.search( (r'(?:var\s+)?%s\s*=\s*\{' % re.escape(objname)) + - r'\s*(?P<fields>([a-zA-Z$]+\s*:\s*function\(.*?\)\s*\{.*?\})*)' + + r'\s*(?P<fields>([a-zA-Z$0-9]+\s*:\s*function\(.*?\)\s*\{.*?\})*)' + r'\}\s*;', self.code) fields = obj_m.group('fields') # Currently, it only supports function definitions fields_m = re.finditer( - r'(?P<key>[a-zA-Z$]+)\s*:\s*function' + r'(?P<key>[a-zA-Z$0-9]+)\s*:\s*function' r'\((?P<args>[a-z,]+)\){(?P<code>[^}]+)}', fields) for f in fields_m: diff --git a/youtube_dl/postprocessor/__init__.py b/youtube_dl/postprocessor/__init__.py index 08e6ddd00..15aa0daa9 100644 --- a/youtube_dl/postprocessor/__init__.py +++ b/youtube_dl/postprocessor/__init__.py @@ -9,6 +9,7 @@ from .ffmpeg import ( FFmpegEmbedSubtitlePP, ) from .xattrpp import XAttrMetadataPP +from .execafterdownload import ExecAfterDownloadPP __all__ = [ 'AtomicParsleyPP', @@ -19,4 +20,5 @@ __all__ = [ 'FFmpegExtractAudioPP', 'FFmpegEmbedSubtitlePP', 'XAttrMetadataPP', + 'ExecAfterDownloadPP', ] diff --git a/youtube_dl/postprocessor/execafterdownload.py b/youtube_dl/postprocessor/execafterdownload.py new file mode 100644 index 000000000..08419a3d4 --- /dev/null +++ b/youtube_dl/postprocessor/execafterdownload.py @@ -0,0 +1,31 @@ +from __future__ import unicode_literals + +import subprocess + +from .common import PostProcessor +from ..utils import ( + shlex_quote, + PostProcessingError, +) + + +class ExecAfterDownloadPP(PostProcessor): + def __init__(self, downloader=None, verboseOutput=None, exec_cmd=None): + self.verboseOutput = verboseOutput + self.exec_cmd = exec_cmd + + def run(self, information): + cmd = self.exec_cmd + if not '{}' in cmd: + cmd += ' {}' + + cmd = cmd.replace('{}', shlex_quote(information['filepath'])) + + self._downloader.to_screen("[exec] Executing command: %s" % cmd) + retCode = subprocess.call(cmd, shell=True) + if retCode != 0: + raise PostProcessingError( + 'Command returned error code %d' % retCode) + + return None, information # by default, keep file and do nothing + diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 45328ed43..8c5f7c43b 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -18,14 +18,15 @@ from ..utils import ( ) - class FFmpegPostProcessorError(PostProcessingError): pass + class FFmpegPostProcessor(PostProcessor): - def __init__(self,downloader=None): + def __init__(self, downloader=None, deletetempfiles=False): PostProcessor.__init__(self, downloader) self._exes = self.detect_executables() + self._deletetempfiles = deletetempfiles @staticmethod def detect_executables(): @@ -60,6 +61,9 @@ class FFmpegPostProcessor(PostProcessor): stderr = stderr.decode('utf-8', 'replace') msg = stderr.strip().split('\n')[-1] raise FFmpegPostProcessorError(msg) + if self._deletetempfiles: + for ipath in input_paths: + os.remove(ipath) def run_ffmpeg(self, path, out_path, opts): self.run_ffmpeg_multiple_files([path], out_path, opts) diff --git a/youtube_dl/swfinterp.py b/youtube_dl/swfinterp.py new file mode 100644 index 000000000..b63c65b20 --- /dev/null +++ b/youtube_dl/swfinterp.py @@ -0,0 +1,609 @@ +from __future__ import unicode_literals + +import collections +import io +import zlib + +from .utils import ( + compat_str, + ExtractorError, + struct_unpack, +) + + +def _extract_tags(file_contents): + if file_contents[1:3] != b'WS': + raise ExtractorError( + 'Not an SWF file; header is %r' % file_contents[:3]) + if file_contents[:1] == b'C': + content = zlib.decompress(file_contents[8:]) + else: + raise NotImplementedError( + 'Unsupported compression format %r' % + file_contents[:1]) + + # Determine number of bits in framesize rectangle + framesize_nbits = struct_unpack('!B', content[:1])[0] >> 3 + framesize_len = (5 + 4 * framesize_nbits + 7) // 8 + + pos = framesize_len + 2 + 2 + while pos < len(content): + header16 = struct_unpack('<H', content[pos:pos + 2])[0] + pos += 2 + tag_code = header16 >> 6 + tag_len = header16 & 0x3f + if tag_len == 0x3f: + tag_len = struct_unpack('<I', content[pos:pos + 4])[0] + pos += 4 + assert pos + tag_len <= len(content), \ + ('Tag %d ends at %d+%d - that\'s longer than the file (%d)' + % (tag_code, pos, tag_len, len(content))) + yield (tag_code, content[pos:pos + tag_len]) + pos += tag_len + + +class _AVMClass_Object(object): + def __init__(self, avm_class): + self.avm_class = avm_class + + def __repr__(self): + return '%s#%x' % (self.avm_class.name, id(self)) + + +class _ScopeDict(dict): + def __init__(self, avm_class): + super(_ScopeDict, self).__init__() + self.avm_class = avm_class + + def __repr__(self): + return '%s__Scope(%s)' % ( + self.avm_class.name, + super(_ScopeDict, self).__repr__()) + + +class _AVMClass(object): + def __init__(self, name_idx, name): + self.name_idx = name_idx + self.name = name + self.method_names = {} + self.method_idxs = {} + self.methods = {} + self.method_pyfunctions = {} + + self.variables = _ScopeDict(self) + + def make_object(self): + return _AVMClass_Object(self) + + def __repr__(self): + return '_AVMClass(%s)' % (self.name) + + def register_methods(self, methods): + self.method_names.update(methods.items()) + self.method_idxs.update(dict( + (idx, name) + for name, idx in methods.items())) + + +class _Multiname(object): + def __init__(self, kind): + self.kind = kind + + def __repr__(self): + return '[MULTINAME kind: 0x%x]' % self.kind + + +def _read_int(reader): + res = 0 + shift = 0 + for _ in range(5): + buf = reader.read(1) + assert len(buf) == 1 + b = struct_unpack('<B', buf)[0] + res = res | ((b & 0x7f) << shift) + if b & 0x80 == 0: + break + shift += 7 + return res + + +def _u30(reader): + res = _read_int(reader) + assert res & 0xf0000000 == 0 + return res +_u32 = _read_int + + +def _s32(reader): + v = _read_int(reader) + if v & 0x80000000 != 0: + v = - ((v ^ 0xffffffff) + 1) + return v + + +def _s24(reader): + bs = reader.read(3) + assert len(bs) == 3 + last_byte = b'\xff' if (ord(bs[2:3]) >= 0x80) else b'\x00' + return struct_unpack('<i', bs + last_byte)[0] + + +def _read_string(reader): + slen = _u30(reader) + resb = reader.read(slen) + assert len(resb) == slen + return resb.decode('utf-8') + + +def _read_bytes(count, reader): + assert count >= 0 + resb = reader.read(count) + assert len(resb) == count + return resb + + +def _read_byte(reader): + resb = _read_bytes(1, reader=reader) + res = struct_unpack('<B', resb)[0] + return res + + +class SWFInterpreter(object): + def __init__(self, file_contents): + code_tag = next(tag + for tag_code, tag in _extract_tags(file_contents) + if tag_code == 82) + p = code_tag.index(b'\0', 4) + 1 + code_reader = io.BytesIO(code_tag[p:]) + + # Parse ABC (AVM2 ByteCode) + + # Define a couple convenience methods + u30 = lambda *args: _u30(*args, reader=code_reader) + s32 = lambda *args: _s32(*args, reader=code_reader) + u32 = lambda *args: _u32(*args, reader=code_reader) + read_bytes = lambda *args: _read_bytes(*args, reader=code_reader) + read_byte = lambda *args: _read_byte(*args, reader=code_reader) + + # minor_version + major_version + read_bytes(2 + 2) + + # Constant pool + int_count = u30() + for _c in range(1, int_count): + s32() + uint_count = u30() + for _c in range(1, uint_count): + u32() + double_count = u30() + read_bytes(max(0, (double_count - 1)) * 8) + string_count = u30() + self.constant_strings = [''] + for _c in range(1, string_count): + s = _read_string(code_reader) + self.constant_strings.append(s) + namespace_count = u30() + for _c in range(1, namespace_count): + read_bytes(1) # kind + u30() # name + ns_set_count = u30() + for _c in range(1, ns_set_count): + count = u30() + for _c2 in range(count): + u30() + multiname_count = u30() + MULTINAME_SIZES = { + 0x07: 2, # QName + 0x0d: 2, # QNameA + 0x0f: 1, # RTQName + 0x10: 1, # RTQNameA + 0x11: 0, # RTQNameL + 0x12: 0, # RTQNameLA + 0x09: 2, # Multiname + 0x0e: 2, # MultinameA + 0x1b: 1, # MultinameL + 0x1c: 1, # MultinameLA + } + self.multinames = [''] + for _c in range(1, multiname_count): + kind = u30() + assert kind in MULTINAME_SIZES, 'Invalid multiname kind %r' % kind + if kind == 0x07: + u30() # namespace_idx + name_idx = u30() + self.multinames.append(self.constant_strings[name_idx]) + else: + self.multinames.append(_Multiname(kind)) + for _c2 in range(MULTINAME_SIZES[kind]): + u30() + + # Methods + method_count = u30() + MethodInfo = collections.namedtuple( + 'MethodInfo', + ['NEED_ARGUMENTS', 'NEED_REST']) + method_infos = [] + for method_id in range(method_count): + param_count = u30() + u30() # return type + for _ in range(param_count): + u30() # param type + u30() # name index (always 0 for youtube) + flags = read_byte() + if flags & 0x08 != 0: + # Options present + option_count = u30() + for c in range(option_count): + u30() # val + read_bytes(1) # kind + if flags & 0x80 != 0: + # Param names present + for _ in range(param_count): + u30() # param name + mi = MethodInfo(flags & 0x01 != 0, flags & 0x04 != 0) + method_infos.append(mi) + + # Metadata + metadata_count = u30() + for _c in range(metadata_count): + u30() # name + item_count = u30() + for _c2 in range(item_count): + u30() # key + u30() # value + + def parse_traits_info(): + trait_name_idx = u30() + kind_full = read_byte() + kind = kind_full & 0x0f + attrs = kind_full >> 4 + methods = {} + if kind in [0x00, 0x06]: # Slot or Const + u30() # Slot id + u30() # type_name_idx + vindex = u30() + if vindex != 0: + read_byte() # vkind + elif kind in [0x01, 0x02, 0x03]: # Method / Getter / Setter + u30() # disp_id + method_idx = u30() + methods[self.multinames[trait_name_idx]] = method_idx + elif kind == 0x04: # Class + u30() # slot_id + u30() # classi + elif kind == 0x05: # Function + u30() # slot_id + function_idx = u30() + methods[function_idx] = self.multinames[trait_name_idx] + else: + raise ExtractorError('Unsupported trait kind %d' % kind) + + if attrs & 0x4 != 0: # Metadata present + metadata_count = u30() + for _c3 in range(metadata_count): + u30() # metadata index + + return methods + + # Classes + class_count = u30() + classes = [] + for class_id in range(class_count): + name_idx = u30() + + cname = self.multinames[name_idx] + avm_class = _AVMClass(name_idx, cname) + classes.append(avm_class) + + u30() # super_name idx + flags = read_byte() + if flags & 0x08 != 0: # Protected namespace is present + u30() # protected_ns_idx + intrf_count = u30() + for _c2 in range(intrf_count): + u30() + u30() # iinit + trait_count = u30() + for _c2 in range(trait_count): + trait_methods = parse_traits_info() + avm_class.register_methods(trait_methods) + + assert len(classes) == class_count + self._classes_by_name = dict((c.name, c) for c in classes) + + for avm_class in classes: + u30() # cinit + trait_count = u30() + for _c2 in range(trait_count): + trait_methods = parse_traits_info() + avm_class.register_methods(trait_methods) + + # Scripts + script_count = u30() + for _c in range(script_count): + u30() # init + trait_count = u30() + for _c2 in range(trait_count): + parse_traits_info() + + # Method bodies + method_body_count = u30() + Method = collections.namedtuple('Method', ['code', 'local_count']) + for _c in range(method_body_count): + method_idx = u30() + u30() # max_stack + local_count = u30() + u30() # init_scope_depth + u30() # max_scope_depth + code_length = u30() + code = read_bytes(code_length) + for avm_class in classes: + if method_idx in avm_class.method_idxs: + m = Method(code, local_count) + avm_class.methods[avm_class.method_idxs[method_idx]] = m + exception_count = u30() + for _c2 in range(exception_count): + u30() # from + u30() # to + u30() # target + u30() # exc_type + u30() # var_name + trait_count = u30() + for _c2 in range(trait_count): + parse_traits_info() + + assert p + code_reader.tell() == len(code_tag) + + def extract_class(self, class_name): + try: + return self._classes_by_name[class_name] + except KeyError: + raise ExtractorError('Class %r not found' % class_name) + + def extract_function(self, avm_class, func_name): + if func_name in avm_class.method_pyfunctions: + return avm_class.method_pyfunctions[func_name] + if func_name in self._classes_by_name: + return self._classes_by_name[func_name].make_object() + if func_name not in avm_class.methods: + raise ExtractorError('Cannot find function %s.%s' % ( + avm_class.name, func_name)) + m = avm_class.methods[func_name] + + def resfunc(args): + # Helper functions + coder = io.BytesIO(m.code) + s24 = lambda: _s24(coder) + u30 = lambda: _u30(coder) + + registers = [avm_class.variables] + list(args) + [None] * m.local_count + stack = [] + scopes = collections.deque([ + self._classes_by_name, avm_class.variables]) + while True: + opcode = _read_byte(coder) + if opcode == 17: # iftrue + offset = s24() + value = stack.pop() + if value: + coder.seek(coder.tell() + offset) + elif opcode == 18: # iffalse + offset = s24() + value = stack.pop() + if not value: + coder.seek(coder.tell() + offset) + elif opcode == 36: # pushbyte + v = _read_byte(coder) + stack.append(v) + elif opcode == 42: # dup + value = stack[-1] + stack.append(value) + elif opcode == 44: # pushstring + idx = u30() + stack.append(self.constant_strings[idx]) + elif opcode == 48: # pushscope + new_scope = stack.pop() + scopes.append(new_scope) + elif opcode == 66: # construct + arg_count = u30() + args = list(reversed( + [stack.pop() for _ in range(arg_count)])) + obj = stack.pop() + res = obj.avm_class.make_object() + stack.append(res) + elif opcode == 70: # callproperty + index = u30() + mname = self.multinames[index] + arg_count = u30() + args = list(reversed( + [stack.pop() for _ in range(arg_count)])) + obj = stack.pop() + + if isinstance(obj, _AVMClass_Object): + func = self.extract_function(obj.avm_class, mname) + res = func(args) + stack.append(res) + continue + elif isinstance(obj, _ScopeDict): + if mname in obj.avm_class.method_names: + func = self.extract_function(obj.avm_class, mname) + res = func(args) + else: + res = obj[mname] + stack.append(res) + continue + elif isinstance(obj, compat_str): + if mname == 'split': + assert len(args) == 1 + assert isinstance(args[0], compat_str) + if args[0] == '': + res = list(obj) + else: + res = obj.split(args[0]) + stack.append(res) + continue + elif isinstance(obj, list): + if mname == 'slice': + assert len(args) == 1 + assert isinstance(args[0], int) + res = obj[args[0]:] + stack.append(res) + continue + elif mname == 'join': + assert len(args) == 1 + assert isinstance(args[0], compat_str) + res = args[0].join(obj) + stack.append(res) + continue + raise NotImplementedError( + 'Unsupported property %r on %r' + % (mname, obj)) + elif opcode == 72: # returnvalue + res = stack.pop() + return res + elif opcode == 74: # constructproperty + index = u30() + arg_count = u30() + args = list(reversed( + [stack.pop() for _ in range(arg_count)])) + obj = stack.pop() + + mname = self.multinames[index] + assert isinstance(obj, _AVMClass) + + # We do not actually call the constructor for now; + # we just pretend it does nothing + stack.append(obj.make_object()) + elif opcode == 79: # callpropvoid + index = u30() + mname = self.multinames[index] + arg_count = u30() + args = list(reversed( + [stack.pop() for _ in range(arg_count)])) + obj = stack.pop() + if mname == 'reverse': + assert isinstance(obj, list) + obj.reverse() + else: + raise NotImplementedError( + 'Unsupported (void) property %r on %r' + % (mname, obj)) + elif opcode == 86: # newarray + arg_count = u30() + arr = [] + for i in range(arg_count): + arr.append(stack.pop()) + arr = arr[::-1] + stack.append(arr) + elif opcode == 93: # findpropstrict + index = u30() + mname = self.multinames[index] + for s in reversed(scopes): + if mname in s: + res = s + break + else: + res = scopes[0] + stack.append(res[mname]) + elif opcode == 94: # findproperty + index = u30() + mname = self.multinames[index] + for s in reversed(scopes): + if mname in s: + res = s + break + else: + res = avm_class.variables + stack.append(res) + elif opcode == 96: # getlex + index = u30() + mname = self.multinames[index] + for s in reversed(scopes): + if mname in s: + scope = s + break + else: + scope = avm_class.variables + # I cannot find where static variables are initialized + # so let's just return None + res = scope.get(mname) + stack.append(res) + elif opcode == 97: # setproperty + index = u30() + value = stack.pop() + idx = self.multinames[index] + if isinstance(idx, _Multiname): + idx = stack.pop() + obj = stack.pop() + obj[idx] = value + elif opcode == 98: # getlocal + index = u30() + stack.append(registers[index]) + elif opcode == 99: # setlocal + index = u30() + value = stack.pop() + registers[index] = value + elif opcode == 102: # getproperty + index = u30() + pname = self.multinames[index] + if pname == 'length': + obj = stack.pop() + assert isinstance(obj, list) + stack.append(len(obj)) + else: # Assume attribute access + idx = stack.pop() + assert isinstance(idx, int) + obj = stack.pop() + assert isinstance(obj, list) + stack.append(obj[idx]) + elif opcode == 115: # convert_ + value = stack.pop() + intvalue = int(value) + stack.append(intvalue) + elif opcode == 128: # coerce + u30() + elif opcode == 133: # coerce_s + assert isinstance(stack[-1], (type(None), compat_str)) + elif opcode == 160: # add + value2 = stack.pop() + value1 = stack.pop() + res = value1 + value2 + stack.append(res) + elif opcode == 161: # subtract + value2 = stack.pop() + value1 = stack.pop() + res = value1 - value2 + stack.append(res) + elif opcode == 164: # modulo + value2 = stack.pop() + value1 = stack.pop() + res = value1 % value2 + stack.append(res) + elif opcode == 175: # greaterequals + value2 = stack.pop() + value1 = stack.pop() + result = value1 >= value2 + stack.append(result) + elif opcode == 208: # getlocal_0 + stack.append(registers[0]) + elif opcode == 209: # getlocal_1 + stack.append(registers[1]) + elif opcode == 210: # getlocal_2 + stack.append(registers[2]) + elif opcode == 211: # getlocal_3 + stack.append(registers[3]) + elif opcode == 212: # setlocal_0 + registers[0] = stack.pop() + elif opcode == 213: # setlocal_1 + registers[1] = stack.pop() + elif opcode == 214: # setlocal_2 + registers[2] = stack.pop() + elif opcode == 215: # setlocal_3 + registers[3] = stack.pop() + else: + raise NotImplementedError( + 'Unsupported opcode %d' % opcode) + + avm_class.method_pyfunctions[func_name] = resfunc + return resfunc + diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 64a9618ca..0bc410e91 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -24,6 +24,7 @@ import socket import struct import subprocess import sys +import tempfile import traceback import xml.etree.ElementTree import zlib @@ -91,11 +92,9 @@ except ImportError: compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w') try: - from urllib.parse import parse_qs as compat_parse_qs -except ImportError: # Python 2 - # HACK: The following is the correct parse_qs implementation from cpython 3's stdlib. - # Python 2's version is apparently totally broken - def _unquote(string, encoding='utf-8', errors='replace'): + from urllib.parse import unquote as compat_urllib_parse_unquote +except ImportError: + def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'): if string == '': return string res = string.split('%') @@ -130,6 +129,13 @@ except ImportError: # Python 2 string += pct_sequence.decode(encoding, errors) return string + +try: + from urllib.parse import parse_qs as compat_parse_qs +except ImportError: # Python 2 + # HACK: The following is the correct parse_qs implementation from cpython 3's stdlib. + # Python 2's version is apparently totally broken + def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False, encoding='utf-8', errors='replace'): qs, _coerce_result = qs, unicode @@ -149,10 +155,12 @@ except ImportError: # Python 2 continue if len(nv[1]) or keep_blank_values: name = nv[0].replace('+', ' ') - name = _unquote(name, encoding=encoding, errors=errors) + name = compat_urllib_parse_unquote( + name, encoding=encoding, errors=errors) name = _coerce_result(name) value = nv[1].replace('+', ' ') - value = _unquote(value, encoding=encoding, errors=errors) + value = compat_urllib_parse_unquote( + value, encoding=encoding, errors=errors) value = _coerce_result(value) r.append((name, value)) return r @@ -184,6 +192,13 @@ try: except ImportError: # Python 2.6 from xml.parsers.expat import ExpatError as compat_xml_parse_error +try: + from shlex import quote as shlex_quote +except ImportError: # Python < 3.3 + def shlex_quote(s): + return "'" + s.replace("'", "'\"'\"'") + "'" + + def compat_ord(c): if type(c) is int: return c else: return ord(c) @@ -221,22 +236,46 @@ else: assert type(s) == type(u'') print(s) -# In Python 2.x, json.dump expects a bytestream. -# In Python 3.x, it writes to a character stream -if sys.version_info < (3,0): - def write_json_file(obj, fn): - with open(fn, 'wb') as f: - json.dump(obj, f) -else: - def write_json_file(obj, fn): - with open(fn, 'w', encoding='utf-8') as f: - json.dump(obj, f) -if sys.version_info >= (2,7): +def write_json_file(obj, fn): + """ Encode obj as JSON and write it to fn, atomically """ + + args = { + 'suffix': '.tmp', + 'prefix': os.path.basename(fn) + '.', + 'dir': os.path.dirname(fn), + 'delete': False, + } + + # In Python 2.x, json.dump expects a bytestream. + # In Python 3.x, it writes to a character stream + if sys.version_info < (3, 0): + args['mode'] = 'wb' + else: + args.update({ + 'mode': 'w', + 'encoding': 'utf-8', + }) + + tf = tempfile.NamedTemporaryFile(**args) + + try: + with tf: + json.dump(obj, tf) + os.rename(tf.name, fn) + except: + try: + os.remove(tf.name) + except OSError: + pass + raise + + +if sys.version_info >= (2, 7): def find_xpath_attr(node, xpath, key, val): """ Find the xpath xpath[@key=val] """ - assert re.match(r'^[a-zA-Z]+$', key) - assert re.match(r'^[a-zA-Z0-9@\s:._]*$', val) + assert re.match(r'^[a-zA-Z-]+$', key) + assert re.match(r'^[a-zA-Z0-9@\s:._-]*$', val) expr = xpath + u"[@%s='%s']" % (key, val) return node.find(expr) else: @@ -259,30 +298,6 @@ def xpath_with_ns(path, ns_map): replaced.append('{%s}%s' % (ns_map[ns], tag)) return '/'.join(replaced) -def htmlentity_transform(matchobj): - """Transforms an HTML entity to a character. - - This function receives a match object and is intended to be used with - the re.sub() function. - """ - entity = matchobj.group(1) - - # Known non-numeric HTML entity - if entity in compat_html_entities.name2codepoint: - return compat_chr(compat_html_entities.name2codepoint[entity]) - - mobj = re.match(u'(?u)#(x?\\d+)', entity) - if mobj is not None: - numstr = mobj.group(1) - if numstr.startswith(u'x'): - base = 16 - numstr = u'0%s' % numstr - else: - base = 10 - return compat_chr(int(numstr, base)) - - # Unknown entity in name, return its literal representation - return (u'&%s;' % entity) compat_html_parser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix class BaseHTMLParser(compat_html_parser.HTMLParser): @@ -504,13 +519,33 @@ def orderedSet(iterable): return res +def _htmlentity_transform(entity): + """Transforms an HTML entity to a character.""" + # Known non-numeric HTML entity + if entity in compat_html_entities.name2codepoint: + return compat_chr(compat_html_entities.name2codepoint[entity]) + + mobj = re.match(r'#(x?[0-9]+)', entity) + if mobj is not None: + numstr = mobj.group(1) + if numstr.startswith(u'x'): + base = 16 + numstr = u'0%s' % numstr + else: + base = 10 + return compat_chr(int(numstr, base)) + + # Unknown entity in name, return its literal representation + return (u'&%s;' % entity) + + def unescapeHTML(s): if s is None: return None assert type(s) == compat_str - result = re.sub(r'(?u)&(.+?);', htmlentity_transform, s) - return result + return re.sub( + r'&([^;]+);', lambda m: _htmlentity_transform(m.group(1)), s) def encodeFilename(s, for_subprocess=False): @@ -727,10 +762,9 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler): return ret def http_request(self, req): - for h,v in std_headers.items(): - if h in req.headers: - del req.headers[h] - req.add_header(h, v) + for h, v in std_headers.items(): + if h not in req.headers: + req.add_header(h, v) if 'Youtubedl-no-compression' in req.headers: if 'Accept-encoding' in req.headers: del req.headers['Accept-encoding'] @@ -820,8 +854,10 @@ def unified_strdate(date_str): '%b %dnd %Y %I:%M%p', '%b %dth %Y %I:%M%p', '%Y-%m-%d', + '%Y/%m/%d', '%d.%m.%Y', '%d/%m/%Y', + '%d/%m/%y', '%Y/%m/%d %H:%M:%S', '%Y-%m-%d %H:%M:%S', '%d.%m.%Y %H:%M', @@ -845,6 +881,8 @@ def unified_strdate(date_str): return upload_date def determine_ext(url, default_ext=u'unknown_video'): + if url is None: + return default_ext guess = url.partition(u'?')[0].rpartition(u'.')[2] if re.match(r'^[A-Za-z0-9]+$', guess): return guess @@ -1038,12 +1076,6 @@ def intlist_to_bytes(xs): return bytes(xs) -def get_cachedir(params={}): - cache_root = os.environ.get('XDG_CACHE_HOME', - os.path.expanduser('~/.cache')) - return params.get('cachedir', os.path.join(cache_root, 'youtube-dl')) - - # Cross-platform file locking if sys.platform == 'win32': import ctypes.wintypes @@ -1103,10 +1135,10 @@ else: import fcntl def _lock_file(f, exclusive): - fcntl.lockf(f, fcntl.LOCK_EX if exclusive else fcntl.LOCK_SH) + fcntl.flock(f, fcntl.LOCK_EX if exclusive else fcntl.LOCK_SH) def _unlock_file(f): - fcntl.lockf(f, fcntl.LOCK_UN) + fcntl.flock(f, fcntl.LOCK_UN) class locked_file(object): @@ -1193,11 +1225,6 @@ def format_bytes(bytes): return u'%.2f%s' % (converted, suffix) -def str_to_int(int_str): - int_str = re.sub(r'[,\.]', u'', int_str) - return int(int_str) - - def get_term_width(): columns = os.environ.get('COLUMNS', None) if columns: @@ -1255,6 +1282,12 @@ def remove_start(s, start): return s +def remove_end(s, end): + if s.endswith(end): + return s[:-len(end)] + return s + + def url_basename(url): path = compat_urlparse.urlparse(url).path return path.strip(u'/').split(u'/')[-1] @@ -1265,23 +1298,39 @@ class HEADRequest(compat_urllib_request.Request): return "HEAD" -def int_or_none(v, scale=1, default=None, get_attr=None): +def int_or_none(v, scale=1, default=None, get_attr=None, invscale=1): if get_attr: if v is not None: v = getattr(v, get_attr, None) - return default if v is None else (int(v) // scale) + if v == '': + v = None + return default if v is None else (int(v) * invscale // scale) + + +def str_or_none(v, default=None): + return default if v is None else compat_str(v) + +def str_to_int(int_str): + """ A more relaxed version of int_or_none """ + if int_str is None: + return None + int_str = re.sub(r'[,\.\+]', u'', int_str) + return int(int_str) -def float_or_none(v, scale=1, default=None): - return default if v is None else (float(v) / scale) + +def float_or_none(v, scale=1, invscale=1, default=None): + return default if v is None else (float(v) * invscale / scale) def parse_duration(s): if s is None: return None + s = s.strip() + m = re.match( - r'(?:(?:(?P<hours>[0-9]+)[:h])?(?P<mins>[0-9]+)[:m])?(?P<secs>[0-9]+)s?(?::[0-9]+)?$', s) + r'(?i)(?:(?:(?P<hours>[0-9]+)\s*(?:[:h]|hours?)\s*)?(?P<mins>[0-9]+)\s*(?:[:m]|mins?|minutes?)\s*)?(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*(?:s|secs?|seconds?)?$', s) if not m: return None res = int(m.group('secs')) @@ -1289,6 +1338,8 @@ def parse_duration(s): res += int(m.group('mins')) * 60 if m.group('hours'): res += int(m.group('hours')) * 60 * 60 + if m.group('ms'): + res += float(m.group('ms')) return res @@ -1399,6 +1450,12 @@ def urlencode_postdata(*args, **kargs): return compat_urllib_parse.urlencode(*args, **kargs).encode('ascii') +try: + etree_iter = xml.etree.ElementTree.Element.iter +except AttributeError: # Python <=2.6 + etree_iter = lambda n: n.findall('.//*') + + def parse_xml(s): class TreeBuilder(xml.etree.ElementTree.TreeBuilder): def doctype(self, name, pubid, system): @@ -1406,7 +1463,14 @@ def parse_xml(s): parser = xml.etree.ElementTree.XMLParser(target=TreeBuilder()) kwargs = {'parser': parser} if sys.version_info >= (2, 7) else {} - return xml.etree.ElementTree.XML(s.encode('utf-8'), **kwargs) + tree = xml.etree.ElementTree.XML(s.encode('utf-8'), **kwargs) + # Fix up XML parser in Python 2.x + if sys.version_info < (3, 0): + for n in etree_iter(tree): + if n.text is not None: + if not isinstance(n.text, compat_str): + n.text = n.text.decode('utf-8') + return tree if sys.version_info < (3, 0) and sys.platform == 'win32': @@ -1431,6 +1495,34 @@ def strip_jsonp(code): return re.sub(r'(?s)^[a-zA-Z0-9_]+\s*\(\s*(.*)\);?\s*?\s*$', r'\1', code) +def js_to_json(code): + def fix_kv(m): + key = m.group(2) + if key.startswith("'"): + assert key.endswith("'") + assert '"' not in key + key = '"%s"' % key[1:-1] + elif not key.startswith('"'): + key = '"%s"' % key + + value = m.group(4) + if value.startswith("'"): + assert value.endswith("'") + assert '"' not in value + value = '"%s"' % value[1:-1] + + return m.group(1) + key + m.group(3) + value + + res = re.sub(r'''(?x) + ([{,]\s*) + ("[^"]*"|\'[^\']*\'|[a-z0-9A-Z]+) + (:\s*) + ([0-9.]+|true|false|"[^"]*"|\'[^\']*\'|\[|\{) + ''', fix_kv, code) + res = re.sub(r',(\s*\])', lambda m: m.group(1), res) + return res + + def qualities(quality_ids): """ Get a numeric quality value out of a list of possible values """ def q(qid): diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 4d606c3d2..ecc2e0f53 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,2 +1,2 @@ -__version__ = '2014.07.15' +__version__ = '2014.09.06' |