aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--AUTHORS1
-rw-r--r--README.md5
-rw-r--r--youtube_dl/extractor/__init__.py2
-rw-r--r--youtube_dl/extractor/common.py29
-rw-r--r--youtube_dl/extractor/esri.py74
-rw-r--r--youtube_dl/extractor/lynda.py10
-rw-r--r--youtube_dl/extractor/moniker.py18
-rw-r--r--youtube_dl/extractor/shahid.py107
-rw-r--r--youtube_dl/extractor/youtube.py53
9 files changed, 248 insertions, 51 deletions
diff --git a/AUTHORS b/AUTHORS
index ded9e87d2..d1693224e 100644
--- a/AUTHORS
+++ b/AUTHORS
@@ -139,3 +139,4 @@ slangangular
Behrouz Abbasi
ngld
nyuszika7h
+Shaun Walbridge
diff --git a/README.md b/README.md
index 15baf75ce..542a7c26a 100644
--- a/README.md
+++ b/README.md
@@ -272,6 +272,7 @@ The `-o` option allows users to indicate a template for the output file names. T
- `autonumber`: The sequence will be replaced by a five-digit number that will be increased with each download, starting at zero.
- `playlist`: The name or the id of the playlist that contains the video.
- `playlist_index`: The index of the video in the playlist, a five-digit number.
+ - `format_id`: The sequence will be replaced by the format code specified by `--format`.
The current default template is `%(title)s-%(id)s.%(ext)s`.
@@ -544,7 +545,7 @@ If you want to add support for a new site, you can follow this quick list (assum
```
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. 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.
+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 and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L62-L200). Add tests and code for as many as you want.
8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8).
9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
@@ -572,7 +573,7 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl:
ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
```
-Most likely, you'll want to use various options. For a list of what can be done, have a look at [youtube_dl/YoutubeDL.py](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L69). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
+Most likely, you'll want to use various options. For a list of what can be done, have a look at [youtube_dl/YoutubeDL.py](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L117-L265). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
Here's a more complete example of a program that outputs only errors (and a short message after the download is finished), and downloads/converts the video to an mp3 file:
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 5307240f8..fa9acc923 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -158,6 +158,7 @@ from .eporner import EpornerIE
from .eroprofile import EroProfileIE
from .escapist import EscapistIE
from .espn import ESPNIE
+from .esri import EsriVideoIE
from .everyonesmixtape import EveryonesMixtapeIE
from .exfm import ExfmIE
from .expotv import ExpoTVIE
@@ -523,6 +524,7 @@ from .senateisvp import SenateISVPIE
from .servingsys import ServingSysIE
from .sexu import SexuIE
from .sexykarma import SexyKarmaIE
+from .shahid import ShahidIE
from .shared import SharedIE
from .sharesix import ShareSixIE
from .sina import SinaIE
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index 5982055be..65835d257 100644
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -15,6 +15,7 @@ import xml.etree.ElementTree
from ..compat import (
compat_cookiejar,
compat_cookies,
+ compat_getpass,
compat_HTTPError,
compat_http_client,
compat_urllib_error,
@@ -610,7 +611,7 @@ class InfoExtractor(object):
return (username, password)
- def _get_tfa_info(self):
+ def _get_tfa_info(self, note='two-factor verification code'):
"""
Get the two-factor authentication info
TODO - asking the user will be required for sms/phone verify
@@ -624,7 +625,7 @@ class InfoExtractor(object):
if downloader_params.get('twofactor', None) is not None:
return downloader_params['twofactor']
- return None
+ return compat_getpass('Type %s and press [Return]: ' % note)
# Helper functions for extracting OpenGraph info
@staticmethod
@@ -640,7 +641,7 @@ class InfoExtractor(object):
@staticmethod
def _meta_regex(prop):
return r'''(?isx)<meta
- (?=[^>]+(?:itemprop|name|property|id)=(["\']?)%s\1)
+ (?=[^>]+(?:itemprop|name|property|id|http-equiv)=(["\']?)%s\1)
[^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(prop)
def _og_search_property(self, prop, html, name=None, **kargs):
@@ -724,16 +725,18 @@ class InfoExtractor(object):
@staticmethod
def _hidden_inputs(html):
- return dict([
- (input.group('name'), input.group('value')) for input in re.finditer(
- r'''(?x)
- <input\s+
- type=(?P<q_hidden>["\'])hidden(?P=q_hidden)\s+
- name=(?P<q_name>["\'])(?P<name>.+?)(?P=q_name)\s+
- (?:id=(?P<q_id>["\']).+?(?P=q_id)\s+)?
- value=(?P<q_value>["\'])(?P<value>.*?)(?P=q_value)
- ''', html)
- ])
+ hidden_inputs = {}
+ for input in re.findall(r'<input([^>]+)>', html):
+ if not re.search(r'type=(["\'])hidden\1', input):
+ continue
+ name = re.search(r'name=(["\'])(?P<value>.+?)\1', input)
+ if not name:
+ continue
+ value = re.search(r'value=(["\'])(?P<value>.*?)\1', input)
+ if not value:
+ continue
+ hidden_inputs[name.group('value')] = value.group('value')
+ return hidden_inputs
def _form_hidden_inputs(self, form_id, html):
form = self._search_regex(
diff --git a/youtube_dl/extractor/esri.py b/youtube_dl/extractor/esri.py
new file mode 100644
index 000000000..bf5d2019f
--- /dev/null
+++ b/youtube_dl/extractor/esri.py
@@ -0,0 +1,74 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_urlparse
+from ..utils import (
+ int_or_none,
+ parse_filesize,
+ unified_strdate,
+)
+
+
+class EsriVideoIE(InfoExtractor):
+ _VALID_URL = r'https?://video\.esri\.com/watch/(?P<id>[0-9]+)'
+ _TEST = {
+ 'url': 'https://video.esri.com/watch/1124/arcgis-online-_dash_-developing-applications',
+ 'md5': 'd4aaf1408b221f1b38227a9bbaeb95bc',
+ 'info_dict': {
+ 'id': '1124',
+ 'ext': 'mp4',
+ 'title': 'ArcGIS Online - Developing Applications',
+ 'description': 'Jeremy Bartley demonstrates how to develop applications with ArcGIS Online.',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 185,
+ 'upload_date': '20120419',
+ }
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ formats = []
+ for width, height, content in re.findall(
+ r'(?s)<li><strong>(\d+)x(\d+):</strong>(.+?)</li>', webpage):
+ for video_url, ext, filesize in re.findall(
+ r'<a[^>]+href="([^"]+)">([^<]+)&nbsp;\(([^<]+)\)</a>', content):
+ formats.append({
+ 'url': compat_urlparse.urljoin(url, video_url),
+ 'ext': ext.lower(),
+ 'format_id': '%s-%s' % (ext.lower(), height),
+ 'width': int(width),
+ 'height': int(height),
+ 'filesize_approx': parse_filesize(filesize),
+ })
+ self._sort_formats(formats)
+
+ title = self._html_search_meta('title', webpage, 'title')
+ description = self._html_search_meta(
+ 'description', webpage, 'description', fatal=False)
+
+ thumbnail = self._html_search_meta('thumbnail', webpage, 'thumbnail', fatal=False)
+ if thumbnail:
+ thumbnail = re.sub(r'_[st]\.jpg$', '_x.jpg', thumbnail)
+
+ duration = int_or_none(self._search_regex(
+ [r'var\s+videoSeconds\s*=\s*(\d+)', r"'duration'\s*:\s*(\d+)"],
+ webpage, 'duration', fatal=False))
+
+ upload_date = unified_strdate(self._html_search_meta(
+ 'last-modified', webpage, 'upload date', fatal=None))
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ 'upload_date': upload_date,
+ 'formats': formats
+ }
diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py
index deead220a..5b9157ed4 100644
--- a/youtube_dl/extractor/lynda.py
+++ b/youtube_dl/extractor/lynda.py
@@ -11,6 +11,7 @@ from ..compat import (
)
from ..utils import (
ExtractorError,
+ clean_html,
int_or_none,
)
@@ -70,6 +71,15 @@ class LyndaBaseIE(InfoExtractor):
'Confirming log in and log out from another device')
if all(not re.search(p, login_page) for p in ('isLoggedIn\s*:\s*true', r'logout\.aspx', r'>Log out<')):
+ if 'login error' in login_page:
+ mobj = re.search(
+ r'(?s)<h1[^>]+class="topmost">(?P<title>[^<]+)</h1>\s*<div>(?P<description>.+?)</div>',
+ login_page)
+ if mobj:
+ raise ExtractorError(
+ 'lynda returned error: %s - %s'
+ % (mobj.group('title'), clean_html(mobj.group('description'))),
+ expected=True)
raise ExtractorError('Unable to log in')
diff --git a/youtube_dl/extractor/moniker.py b/youtube_dl/extractor/moniker.py
index 88dcd4f73..69e4bcd1a 100644
--- a/youtube_dl/extractor/moniker.py
+++ b/youtube_dl/extractor/moniker.py
@@ -9,7 +9,10 @@ from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
-from ..utils import ExtractorError
+from ..utils import (
+ ExtractorError,
+ remove_start,
+)
class MonikerIE(InfoExtractor):
@@ -25,6 +28,14 @@ class MonikerIE(InfoExtractor):
'title': 'youtube-dl test video',
},
}, {
+ 'url': 'http://allmyvideos.net/embed-jih3nce3x6wn',
+ 'md5': '710883dee1bfc370ecf9fa6a89307c88',
+ 'info_dict': {
+ 'id': 'jih3nce3x6wn',
+ 'ext': 'mp4',
+ 'title': 'youtube-dl test video',
+ },
+ }, {
'url': 'http://vidspot.net/l2ngsmhs8ci5',
'md5': '710883dee1bfc370ecf9fa6a89307c88',
'info_dict': {
@@ -38,7 +49,10 @@ class MonikerIE(InfoExtractor):
}]
def _real_extract(self, url):
- video_id = self._match_id(url)
+ orig_video_id = self._match_id(url)
+ video_id = remove_start(orig_video_id, 'embed-')
+ url = url.replace(orig_video_id, video_id)
+ assert re.match(self._VALID_URL, url) is not None
orig_webpage = self._download_webpage(url, video_id)
if '>File Not Found<' in orig_webpage:
diff --git a/youtube_dl/extractor/shahid.py b/youtube_dl/extractor/shahid.py
new file mode 100644
index 000000000..6e9903d5e
--- /dev/null
+++ b/youtube_dl/extractor/shahid.py
@@ -0,0 +1,107 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse
+from ..utils import (
+ ExtractorError,
+ int_or_none,
+ parse_iso8601,
+)
+
+
+class ShahidIE(InfoExtractor):
+ _VALID_URL = r'https?://shahid\.mbc\.net/ar/episode/(?P<id>\d+)/?'
+ _TESTS = [{
+ 'url': 'https://shahid.mbc.net/ar/episode/90574/%D8%A7%D9%84%D9%85%D9%84%D9%83-%D8%B9%D8%A8%D8%AF%D8%A7%D9%84%D9%84%D9%87-%D8%A7%D9%84%D8%A5%D9%86%D8%B3%D8%A7%D9%86-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-3.html',
+ 'info_dict': {
+ 'id': '90574',
+ 'ext': 'm3u8',
+ 'title': 'الملك عبدالله الإنسان الموسم 1 كليب 3',
+ 'description': 'الفيلم الوثائقي - الملك عبد الله الإنسان',
+ 'duration': 2972,
+ 'timestamp': 1422057420,
+ 'upload_date': '20150123',
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ }
+ }, {
+ # shahid plus subscriber only
+ 'url': 'https://shahid.mbc.net/ar/episode/90511/%D9%85%D8%B1%D8%A7%D9%8A%D8%A7-2011-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1.html',
+ 'only_matching': True
+ }]
+
+ def _handle_error(self, response):
+ if not isinstance(response, dict):
+ return
+ error = response.get('error')
+ if error:
+ raise ExtractorError(
+ '%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())),
+ expected=True)
+
+ def _download_json(self, url, video_id, note='Downloading JSON metadata'):
+ response = super(ShahidIE, self)._download_json(url, video_id, note)['data']
+ self._handle_error(response)
+ return response
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ api_vars = {
+ 'id': video_id,
+ 'type': 'player',
+ 'url': 'http://api.shahid.net/api/v1_1',
+ 'playerType': 'episode',
+ }
+
+ flashvars = self._search_regex(
+ r'var\s+flashvars\s*=\s*({[^}]+})', webpage, 'flashvars', default=None)
+ if flashvars:
+ for key in api_vars.keys():
+ value = self._search_regex(
+ r'\b%s\s*:\s*(?P<q>["\'])(?P<value>.+?)(?P=q)' % key,
+ flashvars, 'type', default=None, group='value')
+ if value:
+ api_vars[key] = value
+
+ player = self._download_json(
+ 'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-%s.type-%s.html'
+ % (video_id, api_vars['type']), video_id, 'Downloading player JSON')
+
+ formats = self._extract_m3u8_formats(player['url'], video_id, 'mp4')
+
+ video = self._download_json(
+ '%s/%s/%s?%s' % (
+ api_vars['url'], api_vars['playerType'], api_vars['id'],
+ compat_urllib_parse.urlencode({
+ 'apiKey': 'sh@hid0nlin3',
+ 'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
+ }).encode('utf-8')),
+ video_id, 'Downloading video JSON')
+
+ video = video[api_vars['playerType']]
+
+ title = video['title']
+ description = video.get('description')
+ thumbnail = video.get('thumbnailUrl')
+ duration = int_or_none(video.get('duration'))
+ timestamp = parse_iso8601(video.get('referenceDate'))
+ categories = [
+ category['name']
+ for category in video.get('genres', []) if 'name' in category]
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ 'timestamp': timestamp,
+ 'categories': categories,
+ 'formats': formats,
+ }
diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index facd837ad..887c46d95 100644
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -33,6 +33,7 @@ from ..utils import (
int_or_none,
orderedSet,
parse_duration,
+ remove_start,
smuggle_url,
str_to_int,
unescapeHTML,
@@ -46,7 +47,7 @@ from ..utils import (
class YoutubeBaseInfoExtractor(InfoExtractor):
"""Provide base functions for Youtube extractors"""
_LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
- _TWOFACTOR_URL = 'https://accounts.google.com/SecondFactor'
+ _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
_NETRC_MACHINE = 'youtube'
# If True it will raise an error if no login info is provided
_LOGIN_REQUIRED = False
@@ -128,40 +129,24 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
# 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 re.search(r'(?i)<form[^>]* id="challenge"', login_results) is not None:
+ tfa_code = self._get_tfa_info('2-step verification code')
- if tfa_code is None:
- self._downloader.report_warning('Two-factor authentication required. Provide it with --twofactor <code>')
- self._downloader.report_warning('(Note that only TOTP (Google Authenticator App) codes work at this time.)')
+ if not tfa_code:
+ self._downloader.report_warning(
+ 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
+ '(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('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('Failed to get timeStmp - did the page structure change?')
- timeStmp = match.group(1)
-
- tfa_form_strs = {
- 'continue': 'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1',
- 'smsToken': '',
- 'smsUserPin': tfa_code,
- 'smsVerifyPin': 'Verify',
-
- 'PersistentCookie': 'yes',
- 'checkConnection': '',
- 'checkedDomains': 'youtube',
- 'pstMsg': '1',
- 'secTok': secTok,
- 'timeStmp': timeStmp,
- 'service': 'youtube',
- 'hl': 'en_US',
- }
+ tfa_code = remove_start(tfa_code, 'G-')
+
+ tfa_form_strs = self._form_hidden_inputs('challenge', login_results)
+
+ tfa_form_strs.update({
+ 'Pin': tfa_code,
+ 'TrustDevice': 'on',
+ })
+
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')
@@ -173,8 +158,8 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
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('Two-factor code expired. Please try again, or use a one-use backup code instead.')
+ if re.search(r'(?i)<form[^>]* id="challenge"', tfa_results) is not None:
+ self._downloader.report_warning('Two-factor code expired or invalid. 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('unable to log in - did the page structure change?')