diff options
Diffstat (limited to 'youtube_dl')
72 files changed, 2275 insertions, 789 deletions
diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index ae0ec49f8..d4dd05d8c 100644..100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -8,6 +8,7 @@ import datetime import errno import io import json +import locale import os import platform import re @@ -159,6 +160,7 @@ class YoutubeDL(object): include_ads: Download ads as well 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. The following parameters are not used by YoutubeDL itself, they are used by the FileDownloader: @@ -284,6 +286,9 @@ class YoutubeDL(object): """Print message to stdout if not in quiet mode.""" return self.to_stdout(message, skip_eol, check_quiet=True) + def _write_string(self, s, out=None): + write_string(s, out=out, encoding=self.params.get('encoding')) + def to_stdout(self, message, skip_eol=False, check_quiet=False): """Print message to stdout if not in quiet mode.""" if self.params.get('logger'): @@ -293,7 +298,7 @@ class YoutubeDL(object): terminator = ['\n', ''][skip_eol] output = message + terminator - write_string(output, self._screen_file) + self._write_string(output, self._screen_file) def to_stderr(self, message): """Print message to stderr.""" @@ -303,7 +308,7 @@ class YoutubeDL(object): else: message = self._bidi_workaround(message) output = message + '\n' - write_string(output, self._err_file) + self._write_string(output, self._err_file) def to_console_title(self, message): if not self.params.get('consoletitle', False): @@ -313,21 +318,21 @@ class YoutubeDL(object): # already of type unicode() ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) elif 'TERM' in os.environ: - write_string('\033]0;%s\007' % message, self._screen_file) + self._write_string('\033]0;%s\007' % message, self._screen_file) def save_console_title(self): if not self.params.get('consoletitle', False): return if 'TERM' in os.environ: # Save the title on stack - write_string('\033[22;0t', self._screen_file) + self._write_string('\033[22;0t', self._screen_file) def restore_console_title(self): if not self.params.get('consoletitle', False): return if 'TERM' in os.environ: # Restore the title from stack - write_string('\033[23;0t', self._screen_file) + self._write_string('\033[23;0t', self._screen_file) def __enter__(self): self.save_console_title() @@ -700,6 +705,11 @@ class YoutubeDL(object): def process_video_result(self, info_dict, download=True): assert info_dict.get('_type', 'video') == 'video' + if 'id' not in info_dict: + raise ExtractorError('Missing "id" field in extractor result') + if 'title' not in info_dict: + raise ExtractorError('Missing "title" field in extractor result') + if 'playlist' not in info_dict: # It isn't part of a playlist info_dict['playlist'] = None @@ -731,6 +741,9 @@ class YoutubeDL(object): # We check that all the formats have the format and format_id fields for i, format in enumerate(formats): + if 'url' not in format: + raise ExtractorError('Missing "url" key in result (index %d)' % i) + if format.get('format_id') is None: format['format_id'] = compat_str(i) if format.get('format') is None: @@ -741,7 +754,7 @@ class YoutubeDL(object): ) # Automatically determine file extension if missing if 'ext' not in format: - format['ext'] = determine_ext(format['url']) + format['ext'] = determine_ext(format['url']).lower() format_limit = self.params.get('format_limit', None) if format_limit: @@ -866,7 +879,7 @@ class YoutubeDL(object): try: dn = os.path.dirname(encodeFilename(filename)) - if dn != '' and not os.path.exists(dn): + if dn and not os.path.exists(dn): os.makedirs(dn) except (OSError, IOError) as err: self.report_error('unable to create directory ' + compat_str(err)) @@ -923,7 +936,7 @@ class YoutubeDL(object): with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile: subfile.write(sub) except (OSError, IOError): - self.report_error('Cannot write subtitles file ' + descfn) + self.report_error('Cannot write subtitles file ' + sub_filename) return if self.params.get('writeinfojson', False): @@ -1200,7 +1213,17 @@ class YoutubeDL(object): def print_debug_header(self): if not self.params.get('verbose'): return - write_string('[debug] youtube-dl version ' + __version__ + '\n') + + write_string( + '[debug] Encodings: locale %s, fs %s, out %s, pref %s\n' % ( + locale.getpreferredencoding(), + sys.getfilesystemencoding(), + sys.stdout.encoding, + self.get_encoding()), + encoding=None + ) + + self._write_string('[debug] youtube-dl version ' + __version__ + '\n') try: sp = subprocess.Popen( ['git', 'rev-parse', '--short', 'HEAD'], @@ -1209,20 +1232,20 @@ class YoutubeDL(object): out, err = sp.communicate() out = out.decode().strip() if re.match('[0-9a-f]+', out): - write_string('[debug] Git HEAD: ' + out + '\n') + self._write_string('[debug] Git HEAD: ' + out + '\n') except: try: sys.exc_clear() except: pass - write_string('[debug] Python version %s - %s' % + self._write_string('[debug] Python version %s - %s' % (platform.python_version(), platform_name()) + '\n') proxy_map = {} for handler in self._opener.handlers: if hasattr(handler, 'proxies'): proxy_map.update(handler.proxies) - write_string('[debug] Proxy map: ' + compat_str(proxy_map) + '\n') + self._write_string('[debug] Proxy map: ' + compat_str(proxy_map) + '\n') def _setup_opener(self): timeout_val = self.params.get('socket_timeout') @@ -1264,3 +1287,19 @@ class YoutubeDL(object): # (See https://github.com/rg3/youtube-dl/issues/1309 for details) opener.addheaders = [] self._opener = opener + + def encode(self, s): + if isinstance(s, bytes): + return s # Already encoded + + try: + return s.encode(self.get_encoding()) + except UnicodeEncodeError as err: + err.reason = err.reason + '. Check your system encoding configuration or use the --encoding option.' + raise + + def get_encoding(self): + encoding = self.params.get('encoding') + if encoding is None: + encoding = preferredencoding() + return encoding diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 4f4ec3871..42ef13786 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -51,6 +51,8 @@ __authors__ = ( 'David Wagner', 'Juan C. Olivares', 'Mattias Harrysson', + 'phaer', + 'Sainyam Kapoor', ) __license__ = 'Public Domain' @@ -243,7 +245,7 @@ def parseOpts(overrideArguments=None): 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', action='store_true', dest='prefer_insecure', + '--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', @@ -257,13 +259,17 @@ def parseOpts(overrideArguments=None): 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". By default (with value "auto") youtube-dl guesses.') + 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". By default (with value "auto") youtube-dl guesses.') 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', @@ -397,7 +403,7 @@ def parseOpts(overrideArguments=None): help='simulate, quiet but print output format', default=False) verbosity.add_option('-j', '--dump-json', action='store_true', dest='dumpjson', - help='simulate, quiet but print JSON information', default=False) + help='simulate, quiet but print JSON information. See --output for a description of available keys.', default=False) verbosity.add_option('--newline', action='store_true', dest='progress_with_newline', help='output progress bar as new lines', default=False) verbosity.add_option('--no-progress', @@ -543,8 +549,6 @@ def parseOpts(overrideArguments=None): write_string(u'[debug] System config: ' + repr(_hide_login_info(systemConf)) + '\n') write_string(u'[debug] User config: ' + repr(_hide_login_info(userConf)) + '\n') write_string(u'[debug] Command-line args: ' + repr(_hide_login_info(commandLineConf)) + '\n') - write_string(u'[debug] Encodings: locale %r, fs %r, out %r, pref: %r\n' % - (locale.getpreferredencoding(), sys.getfilesystemencoding(), sys.stdout.encoding, preferredencoding())) return parser, opts, args @@ -678,7 +682,7 @@ def _real_main(argv=None): date = DateRange.day(opts.date) else: date = DateRange(opts.dateafter, opts.datebefore) - if opts.default_search not in ('auto', None) and ':' not in opts.default_search: + if opts.default_search not in ('auto', 'auto_warning', 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 @@ -789,6 +793,7 @@ def _real_main(argv=None): 'include_ads': opts.include_ads, 'default_search': opts.default_search, 'youtube_include_dash_manifest': opts.youtube_include_dash_manifest, + 'encoding': opts.encoding, } with YoutubeDL(ydl_opts) as ydl: diff --git a/youtube_dl/downloader/common.py b/youtube_dl/downloader/common.py index 5a068aa8b..917f3450e 100644 --- a/youtube_dl/downloader/common.py +++ b/youtube_dl/downloader/common.py @@ -4,9 +4,10 @@ import sys import time from ..utils import ( + compat_str, encodeFilename, - timeconvert, format_bytes, + timeconvert, ) @@ -173,7 +174,7 @@ class FileDownloader(object): return os.rename(encodeFilename(old_filename), encodeFilename(new_filename)) except (IOError, OSError) as err: - self.report_error(u'unable to rename file: %s' % str(err)) + self.report_error(u'unable to rename file: %s' % compat_str(err)) def try_utime(self, filename, last_modified_hdr): """Try to set the last-modified time of the given file.""" diff --git a/youtube_dl/downloader/f4m.py b/youtube_dl/downloader/f4m.py index 4e6abfe10..e6be6ae6c 100644 --- a/youtube_dl/downloader/f4m.py +++ b/youtube_dl/downloader/f4m.py @@ -297,6 +297,7 @@ class F4mFD(FileDownloader): break frags_filenames.append(frag_filename) + dest_stream.close() self.report_finish(format_bytes(state['downloaded_bytes']), time.time() - start) self.try_rename(tmpfilename, filename) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 685fc749d..3a91e1a46 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -32,6 +32,7 @@ from .canal13cl import Canal13clIE from .canalplus import CanalplusIE from .canalc2 import Canalc2IE from .cbs import CBSIE +from .cbsnews import CBSNewsIE from .ceskatelevize import CeskaTelevizeIE from .channel9 import Channel9IE from .chilloutzone import ChilloutzoneIE @@ -40,6 +41,7 @@ from .clipfish import ClipfishIE from .cliphunter import CliphunterIE from .clipsyndicate import ClipsyndicateIE from .cmt import CMTIE +from .cnet import CNETIE from .cnn import ( CNNIE, CNNBlogsIE, @@ -61,6 +63,7 @@ from .dotsub import DotsubIE from .dreisat import DreiSatIE from .defense import DefenseGouvFrIE from .discovery import DiscoveryIE +from .divxstage import DivxStageIE from .dropbox import DropboxIE from .ebaumsworld import EbaumsWorldIE from .ehow import EHowIE @@ -83,6 +86,7 @@ from .fktv import ( ) from .flickr import FlickrIE from .fourtube import FourTubeIE +from .franceculture import FranceCultureIE from .franceinter import FranceInterIE from .francetv import ( PluzzIE, @@ -152,10 +156,14 @@ from .mixcloud import MixcloudIE from .mpora import MporaIE from .mofosex import MofosexIE from .mooshare import MooshareIE +from .morningstar import MorningstarIE +from .motorsport import MotorsportIE +from .movshare import MovShareIE from .mtv import ( MTVIE, MTVIggyIE, ) +from .musicplayon import MusicPlayOnIE from .muzu import MuzuTVIE from .myspace import MySpaceIE from .myspass import MySpassIE @@ -177,6 +185,8 @@ from .normalboots import NormalbootsIE from .novamov import NovaMovIE from .nowness import NownessIE from .nowvideo import NowVideoIE +from .ntv import NTVIE +from .oe1 import OE1IE from .ooyala import OoyalaIE from .orf import ORFIE from .parliamentliveuk import ParliamentLiveUKIE @@ -198,6 +208,7 @@ from .rottentomatoes import RottenTomatoesIE from .roxwel import RoxwelIE from .rtlnow import RTLnowIE from .rts import RTSIE +from .rtve import RTVEALaCartaIE from .rutube import ( RutubeIE, RutubeChannelIE, @@ -256,6 +267,7 @@ from .udemy import ( UdemyCourseIE ) from .unistra import UnistraIE +from .urort import UrortIE from .ustream import UstreamIE, UstreamChannelIE from .vbox7 import Vbox7IE from .veehd import VeeHDIE @@ -268,6 +280,7 @@ from .videodetective import VideoDetectiveIE from .videolecturesnet import VideoLecturesNetIE from .videofyme import VideofyMeIE from .videopremium import VideoPremiumIE +from .videoweed import VideoWeedIE from .vimeo import ( VimeoIE, VimeoChannelIE, @@ -282,7 +295,10 @@ from .vk import VKIE from .vube import VubeIE from .washingtonpost import WashingtonPostIE from .wat import WatIE -from .wdr import WDRIE +from .wdr import ( + WDRIE, + WDRMausIE, +) from .weibo import WeiboIE from .wimp import WimpIE from .wistia import WistiaIE diff --git a/youtube_dl/extractor/appletrailers.py b/youtube_dl/extractor/appletrailers.py index 922cede05..dc8657b67 100644 --- a/youtube_dl/extractor/appletrailers.py +++ b/youtube_dl/extractor/appletrailers.py @@ -6,7 +6,6 @@ import json from .common import InfoExtractor from ..utils import ( compat_urlparse, - determine_ext, ) @@ -16,9 +15,10 @@ class AppleTrailersIE(InfoExtractor): "url": "http://trailers.apple.com/trailers/wb/manofsteel/", "playlist": [ { - "file": "manofsteel-trailer4.mov", "md5": "d97a8e575432dbcb81b7c3acb741f8a8", "info_dict": { + "id": "manofsteel-trailer4", + "ext": "mov", "duration": 111, "title": "Trailer 4", "upload_date": "20130523", @@ -26,9 +26,10 @@ class AppleTrailersIE(InfoExtractor): }, }, { - "file": "manofsteel-trailer3.mov", "md5": "b8017b7131b721fb4e8d6f49e1df908c", "info_dict": { + "id": "manofsteel-trailer3", + "ext": "mov", "duration": 182, "title": "Trailer 3", "upload_date": "20130417", @@ -36,9 +37,10 @@ class AppleTrailersIE(InfoExtractor): }, }, { - "file": "manofsteel-trailer.mov", "md5": "d0f1e1150989b9924679b441f3404d48", "info_dict": { + "id": "manofsteel-trailer", + "ext": "mov", "duration": 148, "title": "Trailer", "upload_date": "20121212", @@ -46,15 +48,16 @@ class AppleTrailersIE(InfoExtractor): }, }, { - "file": "manofsteel-teaser.mov", "md5": "5fe08795b943eb2e757fa95cb6def1cb", "info_dict": { + "id": "manofsteel-teaser", + "ext": "mov", "duration": 93, "title": "Teaser", "upload_date": "20120721", "uploader_id": "wb", }, - } + }, ] } @@ -65,16 +68,16 @@ class AppleTrailersIE(InfoExtractor): movie = mobj.group('movie') uploader_id = mobj.group('company') - playlist_url = compat_urlparse.urljoin(url, u'includes/playlists/itunes.inc') + playlist_url = compat_urlparse.urljoin(url, 'includes/playlists/itunes.inc') def fix_html(s): - s = re.sub(r'(?s)<script[^<]*?>.*?</script>', u'', s) + s = re.sub(r'(?s)<script[^<]*?>.*?</script>', '', s) s = re.sub(r'<img ([^<]*?)>', r'<img \1/>', s) # The ' in the onClick attributes are not escaped, it couldn't be parsed # like: http://trailers.apple.com/trailers/wb/gravity/ def _clean_json(m): - return u'iTunes.playURL(%s);' % m.group(1).replace('\'', ''') + return 'iTunes.playURL(%s);' % m.group(1).replace('\'', ''') s = re.sub(self._JSON_RE, _clean_json, s) - s = u'<html>' + s + u'</html>' + s = '<html>' + s + u'</html>' return s doc = self._download_xml(playlist_url, movie, transform_source=fix_html) @@ -82,7 +85,7 @@ class AppleTrailersIE(InfoExtractor): for li in doc.findall('./div/ul/li'): on_click = li.find('.//a').attrib['onClick'] trailer_info_json = self._search_regex(self._JSON_RE, - on_click, u'trailer info') + on_click, 'trailer info') trailer_info = json.loads(trailer_info_json) title = trailer_info['title'] video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower() @@ -98,8 +101,7 @@ class AppleTrailersIE(InfoExtractor): first_url = trailer_info['url'] trailer_id = first_url.split('/')[-1].rpartition('_')[0].lower() settings_json_url = compat_urlparse.urljoin(url, 'includes/settings/%s.json' % trailer_id) - settings_json = self._download_webpage(settings_json_url, trailer_id, u'Downloading settings json') - settings = json.loads(settings_json) + settings = self._download_json(settings_json_url, trailer_id, 'Downloading settings json') formats = [] for format in settings['metadata']['sizes']: @@ -107,7 +109,6 @@ class AppleTrailersIE(InfoExtractor): format_url = re.sub(r'_(\d*p.mov)', r'_h\1', format['src']) formats.append({ 'url': format_url, - 'ext': determine_ext(format_url), 'format': format['type'], 'width': format['width'], 'height': int(format['height']), diff --git a/youtube_dl/extractor/bloomberg.py b/youtube_dl/extractor/bloomberg.py index 2415ce403..25fb79e14 100644 --- a/youtube_dl/extractor/bloomberg.py +++ b/youtube_dl/extractor/bloomberg.py @@ -1,22 +1,21 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor -from .ooyala import OoyalaIE class BloombergIE(InfoExtractor): _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<name>.+?)\.html' _TEST = { - u'url': u'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html', - u'file': u'12bzhqZTqQHmmlA8I-i0NpzJgcG5NNYX.mp4', - u'info_dict': { - u'title': u'Shah\'s Presentation on Foreign-Exchange Strategies', - u'description': u'md5:abc86e5236f9f0e4866c59ad36736686', - }, - u'params': { - # Requires ffmpeg (m3u8 manifest) - u'skip_download': True, + 'url': 'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html', + 'md5': '7bf08858ff7c203c870e8a6190e221e5', + 'info_dict': { + 'id': 'qurhIVlJSB6hzkVi229d8g', + 'ext': 'flv', + 'title': 'Shah\'s Presentation on Foreign-Exchange Strategies', + 'description': 'md5:0681e0d30dcdfc6abf34594961d8ea88', }, } @@ -24,7 +23,16 @@ class BloombergIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) name = mobj.group('name') webpage = self._download_webpage(url, name) - embed_code = self._search_regex( - r'<source src="https?://[^/]+/[^/]+/[^/]+/([^/]+)', webpage, - 'embed code') - return OoyalaIE._build_url_result(embed_code) + f4m_url = self._search_regex( + r'<source src="(https?://[^"]+\.f4m.*?)"', webpage, + 'f4m url') + title = re.sub(': Video$', '', self._og_search_title(webpage)) + + return { + 'id': name.split('-')[-1], + 'title': title, + 'url': f4m_url, + 'ext': 'flv', + 'description': self._og_search_description(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + } diff --git a/youtube_dl/extractor/br.py b/youtube_dl/extractor/br.py index 7cc159e20..b5b56ff00 100644 --- a/youtube_dl/extractor/br.py +++ b/youtube_dl/extractor/br.py @@ -4,39 +4,72 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ExtractorError +from ..utils import ( + ExtractorError, + int_or_none, +) class BRIE(InfoExtractor): - IE_DESC = "Bayerischer Rundfunk Mediathek" - _VALID_URL = r"^https?://(?:www\.)?br\.de/mediathek/video/(?:sendungen/)?(?:[a-z0-9\-/]+/)?(?P<id>[a-z0-9\-]+)\.html$" - _BASE_URL = "http://www.br.de" + IE_DESC = 'Bayerischer Rundfunk Mediathek' + _VALID_URL = r'https?://(?:www\.)?br\.de/(?:[a-z0-9\-]+/)+(?P<id>[a-z0-9\-]+)\.html' + _BASE_URL = 'http://www.br.de' _TESTS = [ { - "url": "http://www.br.de/mediathek/video/anselm-gruen-114.html", - "md5": "c4f83cf0f023ba5875aba0bf46860df2", - "info_dict": { - "id": "2c8d81c5-6fb7-4a74-88d4-e768e5856532", - "ext": "mp4", - "title": "Feiern und Verzichten", - "description": "Anselm Grün: Feiern und Verzichten", - "uploader": "BR/Birgit Baier", - "upload_date": "20140301" + 'url': 'http://www.br.de/mediathek/video/anselm-gruen-114.html', + 'md5': 'c4f83cf0f023ba5875aba0bf46860df2', + 'info_dict': { + 'id': '2c8d81c5-6fb7-4a74-88d4-e768e5856532', + 'ext': 'mp4', + 'title': 'Feiern und Verzichten', + 'description': 'Anselm Grün: Feiern und Verzichten', + 'uploader': 'BR/Birgit Baier', + 'upload_date': '20140301', } }, { - "url": "http://www.br.de/mediathek/video/sendungen/unter-unserem-himmel/unter-unserem-himmel-alpen-ueber-den-pass-100.html", - "md5": "ab451b09d861dbed7d7cc9ab0be19ebe", - "info_dict": { - "id": "2c060e69-3a27-4e13-b0f0-668fac17d812", - "ext": "mp4", - "title": "Über den Pass", - "description": "Die Eroberung der Alpen: Über den Pass", - "uploader": None, - "upload_date": None + 'url': 'http://www.br.de/mediathek/video/sendungen/unter-unserem-himmel/unter-unserem-himmel-alpen-ueber-den-pass-100.html', + 'md5': 'ab451b09d861dbed7d7cc9ab0be19ebe', + 'info_dict': { + 'id': '2c060e69-3a27-4e13-b0f0-668fac17d812', + 'ext': 'mp4', + 'title': 'Über den Pass', + 'description': 'Die Eroberung der Alpen: Über den Pass', } - } + }, + { + 'url': 'http://www.br.de/nachrichten/schaeuble-haushaltsentwurf-bundestag-100.html', + 'md5': '3db0df1a9a9cd9fa0c70e6ea8aa8e820', + 'info_dict': { + 'id': 'c6aae3de-2cf9-43f2-957f-f17fef9afaab', + 'ext': 'aac', + 'title': '"Keine neuen Schulden im nächsten Jahr"', + 'description': 'Haushaltsentwurf: "Keine neuen Schulden im nächsten Jahr"', + } + }, + { + 'url': 'http://www.br.de/radio/bayern1/service/team/videos/team-video-erdelt100.html', + 'md5': 'dbab0aef2e047060ea7a21fc1ce1078a', + 'info_dict': { + 'id': '6ba73750-d405-45d3-861d-1ce8c524e059', + 'ext': 'mp4', + 'title': 'Umweltbewusster Häuslebauer', + 'description': 'Uwe Erdelt: Umweltbewusster Häuslebauer', + } + }, + { + 'url': 'http://www.br.de/fernsehen/br-alpha/sendungen/kant-fuer-anfaenger/kritik-der-reinen-vernunft/kant-kritik-01-metaphysik100.html', + 'md5': '23bca295f1650d698f94fc570977dae3', + 'info_dict': { + 'id': 'd982c9ce-8648-4753-b358-98abb8aec43d', + 'ext': 'mp4', + 'title': 'Folge 1 - Metaphysik', + 'description': 'Kant für Anfänger: Folge 1 - Metaphysik', + 'uploader': 'Eva Maria Steimle', + 'upload_date': '20140117', + } + }, ] def _real_extract(self, url): @@ -44,56 +77,63 @@ class BRIE(InfoExtractor): display_id = mobj.group('id') page = self._download_webpage(url, display_id) xml_url = self._search_regex( - r"return BRavFramework\.register\(BRavFramework\('avPlayer_(?:[a-f0-9-]{36})'\)\.setup\({dataURL:'(/mediathek/video/[a-z0-9/~_.-]+)'}\)\);", page, "XMLURL") + r"return BRavFramework\.register\(BRavFramework\('avPlayer_(?:[a-f0-9-]{36})'\)\.setup\({dataURL:'(/(?:[a-z0-9\-]+/)+[a-z0-9/~_.-]+)'}\)\);", page, 'XMLURL') xml = self._download_xml(self._BASE_URL + xml_url, None) - videos = [] - for xml_video in xml.findall("video"): - video = { - "id": xml_video.get("externalId"), - "title": xml_video.find("title").text, - "formats": self._extract_formats(xml_video.find("assets")), - "thumbnails": self._extract_thumbnails(xml_video.find("teaserImage/variants")), - "description": " ".join(xml_video.find("shareTitle").text.splitlines()), - "webpage_url": xml_video.find("permalink").text + medias = [] + + for xml_media in xml.findall('video') + xml.findall('audio'): + media = { + 'id': xml_media.get('externalId'), + 'title': xml_media.find('title').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()), + 'webpage_url': xml_media.find('permalink').text } - if xml_video.find("author").text: - video["uploader"] = xml_video.find("author").text - if xml_video.find("broadcastDate").text: - video["upload_date"] = "".join(reversed(xml_video.find("broadcastDate").text.split("."))) - videos.append(video) + if xml_media.find('author').text: + media['uploader'] = xml_media.find('author').text + if xml_media.find('broadcastDate').text: + media['upload_date'] = ''.join(reversed(xml_media.find('broadcastDate').text.split('.'))) + medias.append(media) - if len(videos) > 1: + if len(medias) > 1: self._downloader.report_warning( - 'found multiple videos; please ' + 'found multiple medias; please ' 'report this with the video URL to http://yt-dl.org/bug') - if not videos: - raise ExtractorError('No video entries found') - return videos[0] + if not medias: + raise ExtractorError('No media entries found') + return medias[0] def _extract_formats(self, assets): + + def text_or_none(asset, tag): + elem = asset.find(tag) + return None if elem is None else elem.text + formats = [{ - "url": asset.find("downloadUrl").text, - "ext": asset.find("mediaType").text, - "format_id": asset.get("type"), - "width": int(asset.find("frameWidth").text), - "height": int(asset.find("frameHeight").text), - "tbr": int(asset.find("bitrateVideo").text), - "abr": int(asset.find("bitrateAudio").text), - "vcodec": asset.find("codecVideo").text, - "container": asset.find("mediaType").text, - "filesize": int(asset.find("size").text), - } for asset in assets.findall("asset") - if asset.find("downloadUrl") is not None] + 'url': text_or_none(asset, 'downloadUrl'), + 'ext': text_or_none(asset, 'mediaType'), + 'format_id': asset.get('type'), + 'width': int_or_none(text_or_none(asset, 'frameWidth')), + 'height': int_or_none(text_or_none(asset, 'frameHeight')), + 'tbr': int_or_none(text_or_none(asset, 'bitrateVideo')), + 'abr': int_or_none(text_or_none(asset, 'bitrateAudio')), + 'vcodec': text_or_none(asset, 'codecVideo'), + 'acodec': text_or_none(asset, 'codecAudio'), + 'container': text_or_none(asset, 'mediaType'), + 'filesize': int_or_none(text_or_none(asset, 'size')), + } for asset in assets.findall('asset') + if asset.find('downloadUrl') is not None] self._sort_formats(formats) return formats def _extract_thumbnails(self, variants): thumbnails = [{ - "url": self._BASE_URL + variant.find("url").text, - "width": int(variant.find("width").text), - "height": int(variant.find("height").text), - } for variant in variants.findall("variant")] - thumbnails.sort(key=lambda x: x["width"] * x["height"], reverse=True) + 'url': self._BASE_URL + variant.find('url').text, + 'width': int_or_none(variant.find('width').text), + 'height': int_or_none(variant.find('height').text), + } for variant in variants.findall('variant')] + thumbnails.sort(key=lambda x: x['width'] * x['height'], reverse=True) return thumbnails diff --git a/youtube_dl/extractor/breakcom.py b/youtube_dl/extractor/breakcom.py index 85635d1cc..1bfc9f35b 100644 --- a/youtube_dl/extractor/breakcom.py +++ b/youtube_dl/extractor/breakcom.py @@ -27,9 +27,10 @@ class BreakIE(InfoExtractor): webpage, 'info json', flags=re.DOTALL) info = json.loads(info_json) video_url = info['videoUri'] - m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', video_url) - if m_youtube is not None: - return self.url_result(m_youtube.group(1), 'Youtube') + youtube_id = info.get('youtubeId') + if youtube_id: + return self.url_result(youtube_id, 'Youtube') + final_url = video_url + '?' + info['AuthToken'] return { 'id': video_id, diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 83eec84d3..3c02c297a 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -87,7 +87,7 @@ class BrightcoveIE(InfoExtractor): object_str = object_str.replace('<--', '<!--') object_str = fix_xml_ampersands(object_str) - object_doc = xml.etree.ElementTree.fromstring(object_str) + object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8')) fv_el = find_xpath_attr(object_doc, './param', 'name', 'flashVars') if fv_el is not None: @@ -140,7 +140,11 @@ class BrightcoveIE(InfoExtractor): url_m = re.search(r'<meta\s+property="og:video"\s+content="(http://c.brightcove.com/[^"]+)"', webpage) if url_m: - return [unescapeHTML(url_m.group(1))] + 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: + return [url] matches = re.findall( r'''(?sx)<object diff --git a/youtube_dl/extractor/byutv.py b/youtube_dl/extractor/byutv.py index 91c6398f5..cf19b7b0c 100644 --- a/youtube_dl/extractor/byutv.py +++ b/youtube_dl/extractor/byutv.py @@ -4,9 +4,7 @@ import json import re from .common import InfoExtractor -from ..utils import ( - ExtractorError, -) +from ..utils import ExtractorError class BYUtvIE(InfoExtractor): @@ -16,7 +14,7 @@ class BYUtvIE(InfoExtractor): 'info_dict': { 'id': 'granite-flats-talking', 'ext': 'mp4', - 'description': 'md5:1a7ae3e153359b7cc355ef3963441e5f', + 'description': 'md5:4e9a7ce60f209a33eca0ac65b4918e1c', 'title': 'Talking', 'thumbnail': 're:^https?://.*promo.*' }, diff --git a/youtube_dl/extractor/c56.py b/youtube_dl/extractor/c56.py index 690bc7c25..cb96c3876 100644 --- a/youtube_dl/extractor/c56.py +++ b/youtube_dl/extractor/c56.py @@ -2,39 +2,46 @@ from __future__ import unicode_literals import re -import json from .common import InfoExtractor class C56IE(InfoExtractor): - _VALID_URL = r'https?://((www|player)\.)?56\.com/(.+?/)?(v_|(play_album.+-))(?P<textid>.+?)\.(html|swf)' + _VALID_URL = r'https?://(?:(?:www|player)\.)?56\.com/(?:.+?/)?(?:v_|(?:play_album.+-))(?P<textid>.+?)\.(?:html|swf)' IE_NAME = '56.com' _TEST = { 'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html', - 'file': '93440716.flv', 'md5': 'e59995ac63d0457783ea05f93f12a866', 'info_dict': { + 'id': '93440716', + 'ext': 'flv', 'title': '网事知多少 第32期：车怒', + 'duration': 283.813, }, } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE) text_id = mobj.group('textid') - info_page = self._download_webpage('http://vxml.56.com/json/%s/' % text_id, - text_id, 'Downloading video info') - info = json.loads(info_page)['info'] - formats = [{ - 'format_id': f['type'], - 'filesize': int(f['filesize']), - 'url': f['url'] - } for f in info['rfiles']] + + page = self._download_json( + 'http://vxml.56.com/json/%s/' % text_id, text_id, 'Downloading video info') + + info = page['info'] + + formats = [ + { + 'format_id': f['type'], + 'filesize': int(f['filesize']), + 'url': f['url'] + } for f in info['rfiles'] + ] self._sort_formats(formats) return { 'id': info['vid'], 'title': info['Subject'], + 'duration': int(info['duration']) / 1000.0, 'formats': formats, 'thumbnail': info.get('bimg') or info.get('img'), } diff --git a/youtube_dl/extractor/canalplus.py b/youtube_dl/extractor/canalplus.py index 7cdcd8399..49dfd881e 100644 --- a/youtube_dl/extractor/canalplus.py +++ b/youtube_dl/extractor/canalplus.py @@ -28,7 +28,7 @@ class CanalplusIE(InfoExtractor): video_id = mobj.groupdict().get('id') if video_id is None: webpage = self._download_webpage(url, mobj.group('path')) - video_id = self._search_regex(r'videoId = "(\d+)";', webpage, u'video id') + video_id = self._search_regex(r'<canal:player videoId="(\d+)"', webpage, u'video id') info_url = self._VIDEO_INFO_TEMPLATE % video_id doc = self._download_xml(info_url,video_id, u'Downloading video info') diff --git a/youtube_dl/extractor/cbsnews.py b/youtube_dl/extractor/cbsnews.py new file mode 100644 index 000000000..0bce7937f --- /dev/null +++ b/youtube_dl/extractor/cbsnews.py @@ -0,0 +1,87 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor + + +class CBSNewsIE(InfoExtractor): + IE_DESC = 'CBS News' + _VALID_URL = r'http://(?:www\.)?cbsnews\.com/(?:[^/]+/)+(?P<id>[\da-z_-]+)' + + _TESTS = [ + { + 'url': 'http://www.cbsnews.com/news/tesla-and-spacex-elon-musks-industrial-empire/', + 'info_dict': { + 'id': 'tesla-and-spacex-elon-musks-industrial-empire', + 'ext': 'flv', + 'title': 'Tesla and SpaceX: Elon Musk\'s industrial empire', + 'thumbnail': 'http://beta.img.cbsnews.com/i/2014/03/30/60147937-2f53-4565-ad64-1bdd6eb64679/60-0330-pelley-640x360.jpg', + 'duration': 791, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/', + 'info_dict': { + 'id': 'fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack', + 'ext': 'flv', + 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack', + 'thumbnail': 'http://cbsnews2.cbsistatic.com/hub/i/r/2014/04/04/0c9fbc66-576b-41ca-8069-02d122060dd2/thumbnail/140x90/6dad7a502f88875ceac38202984b6d58/en-0404-werner-replace-640x360.jpg', + 'duration': 205, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + ] + + 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_info = json.loads(self._html_search_regex( + r'(?:<ul class="media-list items" id="media-related-items"><li data-video-info|<div id="cbsNewsVideoPlayer" data-video-player-options)=\'({.+?})\'', + webpage, 'video JSON info')) + + item = video_info['item'] if 'item' in video_info else video_info + title = item.get('articleTitle') or item.get('hed') + duration = item.get('duration') + thumbnail = item.get('mediaImage') or item.get('thumbnail') + + formats = [] + for format_id in ['RtmpMobileLow', 'RtmpMobileHigh', 'Hls', 'RtmpDesktop']: + uri = item.get('media' + format_id + 'URI') + if not uri: + continue + fmt = { + 'url': uri, + 'format_id': format_id, + } + if uri.startswith('rtmp'): + fmt.update({ + 'app': 'ondemand?auth=cbs', + 'play_path': 'mp4:' + uri.split('<break>')[-1], + 'player_url': 'http://www.cbsnews.com/[[IMPORT]]/vidtech.cbsinteractive.com/player/3_3_0/CBSI_PLAYER_HD.swf', + 'page_url': 'http://www.cbsnews.com', + 'ext': 'flv', + }) + elif uri.endswith('.m3u8'): + fmt['ext'] = 'mp4' + formats.append(fmt) + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'duration': duration, + 'formats': formats, + }
\ No newline at end of file diff --git a/youtube_dl/extractor/clipsyndicate.py b/youtube_dl/extractor/clipsyndicate.py index 9ab6a4ab6..02a1667fa 100644 --- a/youtube_dl/extractor/clipsyndicate.py +++ b/youtube_dl/extractor/clipsyndicate.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -11,13 +13,14 @@ class ClipsyndicateIE(InfoExtractor): _VALID_URL = r'http://www\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)' _TEST = { - u'url': u'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe', - u'md5': u'4d7d549451bad625e0ff3d7bd56d776c', - u'info_dict': { - u'id': u'4629301', - u'ext': u'mp4', - u'title': u'Brick Briscoe', - u'duration': 612, + 'url': 'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe', + 'md5': '4d7d549451bad625e0ff3d7bd56d776c', + 'info_dict': { + 'id': '4629301', + 'ext': 'mp4', + 'title': 'Brick Briscoe', + 'duration': 612, + 'thumbnail': 're:^https?://.+\.jpg', }, } @@ -26,13 +29,13 @@ class ClipsyndicateIE(InfoExtractor): video_id = mobj.group('id') js_player = self._download_webpage( 'http://eplayer.clipsyndicate.com/embed/player.js?va_id=%s' % video_id, - video_id, u'Downlaoding player') + video_id, 'Downlaoding player') # it includes a required token - flvars = self._search_regex(r'flvars: "(.*?)"', js_player, u'flvars') + flvars = self._search_regex(r'flvars: "(.*?)"', js_player, 'flvars') pdoc = self._download_xml( 'http://eplayer.clipsyndicate.com/osmf/playlist?%s' % flvars, - video_id, u'Downloading video info', + video_id, 'Downloading video info', transform_source=fix_xml_ampersands) track_doc = pdoc.find('trackList/track') diff --git a/youtube_dl/extractor/cnet.py b/youtube_dl/extractor/cnet.py new file mode 100644 index 000000000..f5ab443d2 --- /dev/null +++ b/youtube_dl/extractor/cnet.py @@ -0,0 +1,75 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + int_or_none, +) + + +class CNETIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/' + _TEST = { + 'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/', + 'md5': '041233212a0d06b179c87cbcca1577b8', + 'info_dict': { + 'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60', + 'ext': 'mp4', + 'title': 'Hands-on with Microsoft Windows 8.1 Update', + 'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.', + 'thumbnail': 're:^http://.*/flmswindows8.jpg$', + 'uploader_id': 'sarah.mitroff@cbsinteractive.com', + 'uploader': 'Sarah Mitroff', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('id') + + webpage = self._download_webpage(url, display_id) + data_json = self._html_search_regex( + r"<div class=\"cnetVideoPlayer\" data-cnet-video-options='([^']+)'", + webpage, 'data json') + data = json.loads(data_json) + vdata = data['video'] + if not vdata: + vdata = data['videos'][0] + if not vdata: + raise ExtractorError('Cannot find video data') + + video_id = vdata['id'] + title = vdata['headline'] + description = vdata.get('dek') + thumbnail = vdata.get('image', {}).get('path') + author = vdata.get('author') + if author: + uploader = '%s %s' % (author['firstName'], author['lastName']) + uploader_id = author.get('email') + else: + uploader = None + uploader_id = None + + formats = [{ + 'format_id': '%s-%s-%s' % ( + f['type'], f['format'], + int_or_none(f.get('bitrate'), 1000, default='')), + 'url': f['uri'], + 'tbr': int_or_none(f.get('bitrate'), 1000), + } for f in vdata['files']['data']] + self._sort_formats(formats) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'formats': formats, + 'description': description, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py index 483ae5761..6e3a316c6 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -8,7 +8,7 @@ from ..utils import ( compat_str, compat_urllib_parse, ExtractorError, - int_or_none, + float_or_none, unified_strdate, ) @@ -21,7 +21,7 @@ class ComedyCentralIE(MTVServicesInfoExtractor): _TEST = { 'url': 'http://www.comedycentral.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother', - 'md5': '4167875aae411f903b751a21f357f1ee', + 'md5': 'c4f48e9eda1b16dd10add0744344b6d8', 'info_dict': { 'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354', 'ext': 'mp4', @@ -41,13 +41,15 @@ class ComedyCentralShowsIE(InfoExtractor): _VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport) |https?://(:www\.)? (?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/ - (full-episodes/(?P<episode>.*)| + ((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)| (?P<clip> - (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?)) - |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))| + (?:(?:guests/[^/]+|videos|video-playlists|special-editions)/[^/]+/(?P<videotitle>[^/?#]+)) + |(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?)) + |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)) + )| (?P<interview> - extended-interviews/(?P<interID>[0-9]+)/playlist_tds_extended_(?P<interview_title>.*?)/.*?))) - $''' + extended-interviews/(?P<interID>[0-9a-z]+)/(?:playlist_tds_extended_)?(?P<interview_title>.*?)(/.*?)?))) + (?:[?#].*|$)''' _TEST = { 'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart', 'md5': '4e2f5cb088a83cd8cdb7756132f9739d', @@ -57,7 +59,7 @@ class ComedyCentralShowsIE(InfoExtractor): 'upload_date': '20121213', 'description': 'Kristen Stewart learns to let loose in "On the Road."', 'uploader': 'thedailyshow', - 'title': 'thedailyshow-kristen-stewart part 1', + 'title': 'thedailyshow kristen-stewart part 1', } } @@ -102,7 +104,9 @@ class ComedyCentralShowsIE(InfoExtractor): assert mobj is not None if mobj.group('clip'): - if mobj.group('showname') == 'thedailyshow': + if mobj.group('videotitle'): + epTitle = mobj.group('videotitle') + elif mobj.group('showname') == 'thedailyshow': epTitle = mobj.group('tdstitle') else: epTitle = mobj.group('cntitle') @@ -134,7 +138,7 @@ class ComedyCentralShowsIE(InfoExtractor): # a URL prefix; so extract the alternate reference # and then add the URL prefix manually. - altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage) + altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video|playlist).*?:.*?)"', webpage) if len(altMovieParams) == 0: raise ExtractorError('unable to find Flash URL in webpage ' + url) else: @@ -159,9 +163,9 @@ class ComedyCentralShowsIE(InfoExtractor): thumbnail = itemEl.find('.//{http://search.yahoo.com/mrss/}thumbnail').attrib.get('url') content = itemEl.find('.//{http://search.yahoo.com/mrss/}content') - duration = int_or_none(content.attrib.get('duration')) + duration = float_or_none(content.attrib.get('duration')) mediagen_url = content.attrib['url'] - guid = itemEl.find('.//guid').text.rpartition(':')[-1] + guid = itemEl.find('./guid').text.rpartition(':')[-1] cdoc = self._download_xml( mediagen_url, epTitle, diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 78f238f84..9653d44eb 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -251,7 +251,21 @@ class InfoExtractor(object): with open(filename, 'wb') as outf: outf.write(webpage_bytes) - content = webpage_bytes.decode(encoding, 'replace') + try: + content = webpage_bytes.decode(encoding, 'replace') + 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.' + blocked_iframe = self._html_search_regex( + r'<iframe src="([^"]+)"', content, + u'Websense information URL', default=None) + if blocked_iframe: + msg += u' Visit %s for more details' % blocked_iframe + raise ExtractorError(msg, expected=True) + return (content, urlh) def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True): diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index 2a8eda9ef..b6552c542 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -4,6 +4,7 @@ import re from .common import InfoExtractor from ..utils import ( + int_or_none, unescapeHTML, find_xpath_attr, ) @@ -54,18 +55,29 @@ class CSpanIE(InfoExtractor): info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id data = self._download_json(info_url, video_id) - url = unescapeHTML(data['video']['files'][0]['path']['#text']) - - doc = self._download_xml('http://www.c-span.org/common/services/flashXml.php?programid=' + video_id, + doc = self._download_xml( + 'http://www.c-span.org/common/services/flashXml.php?programid=' + video_id, video_id) - def find_string(s): - return find_xpath_attr(doc, './/string', 'name', s).text + title = find_xpath_attr(doc, './/string', 'name', 'title').text + thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text + + files = data['video']['files'] + + entries = [{ + 'id': '%s_%d' % (video_id, partnum + 1), + 'title': ( + title if len(files) == 1 else + '%s part %d' % (title, partnum + 1)), + 'url': unescapeHTML(f['path']['#text']), + 'description': description, + 'thumbnail': thumbnail, + 'duration': int_or_none(f.get('length', {}).get('#text')), + } for partnum, f in enumerate(files)] return { + '_type': 'playlist', + 'entries': entries, + 'title': title, 'id': video_id, - 'title': find_string('title'), - 'url': url, - 'description': description, - 'thumbnail': find_string('poster'), } diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 10b97d8ca..bae1c7754 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -8,7 +8,6 @@ from .subtitles import SubtitlesInfoExtractor from ..utils import ( compat_urllib_request, compat_str, - get_element_by_attribute, get_element_by_id, orderedSet, str_to_int, @@ -180,7 +179,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): IE_NAME = u'dailymotion:playlist' _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/' - _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/playlist/.+?".*?>.*?</a>.*?</div>' + _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"' _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s' def _extract_entries(self, id): @@ -190,10 +189,9 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): webpage = self._download_webpage(request, id, u'Downloading page %s' % pagenum) - playlist_el = get_element_by_attribute(u'class', u'row video_list', webpage) - video_ids.extend(re.findall(r'data-id="(.+?)"', playlist_el)) + video_ids.extend(re.findall(r'data-id="(.+?)"', webpage)) - if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None: + if re.search(self._MORE_PAGES_INDICATOR, webpage) is None: break return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion') for video_id in orderedSet(video_ids)] @@ -203,17 +201,17 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): playlist_id = mobj.group('id') webpage = self._download_webpage(url, playlist_id) - return {'_type': 'playlist', - 'id': playlist_id, - 'title': get_element_by_id(u'playlist_name', webpage), - 'entries': self._extract_entries(playlist_id), - } + return { + '_type': 'playlist', + 'id': playlist_id, + 'title': self._og_search_title(webpage), + 'entries': self._extract_entries(playlist_id), + } class DailymotionUserIE(DailymotionPlaylistIE): IE_NAME = u'dailymotion:user' - _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)' - _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/user/.+?".*?>.*?</a>.*?</div>' + _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)' _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s' def _real_extract(self, url): diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py index 885944c5e..2ae6ecc12 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -10,9 +10,10 @@ class DiscoveryIE(InfoExtractor): _VALID_URL = r'http://dsc\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?' _TEST = { 'url': 'http://dsc.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm', - 'file': '614784.mp4', 'md5': 'e12614f9ee303a6ccef415cb0793eba2', 'info_dict': { + 'id': '614784', + 'ext': 'mp4', 'title': 'MythBusters: Mission Impossible Outtakes', 'description': ('Watch Jamie Hyneman and Adam Savage practice being' ' each other -- to the point of confusing Jamie\'s dog -- and ' @@ -34,7 +35,7 @@ class DiscoveryIE(InfoExtractor): formats = [] for f in info['mp4']: formats.append( - {'url': f['src'], r'ext': r'mp4', 'tbr': int(f['bitrate'][:-1])}) + {'url': f['src'], 'ext': 'mp4', 'tbr': int(f['bitrate'][:-1])}) return { 'id': info['contentId'], diff --git a/youtube_dl/extractor/divxstage.py b/youtube_dl/extractor/divxstage.py new file mode 100644 index 000000000..4ca3f37a2 --- /dev/null +++ b/youtube_dl/extractor/divxstage.py @@ -0,0 +1,27 @@ +from __future__ import unicode_literals + +from .novamov import NovaMovIE + + +class DivxStageIE(NovaMovIE): + IE_NAME = 'divxstage' + IE_DESC = 'DivxStage' + + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'divxstage\.(?:eu|net|ch|co|at|ag)'} + + _HOST = 'www.divxstage.eu' + + _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' + _TITLE_REGEX = r'<div class="video_det">\s*<strong>([^<]+)</strong>' + _DESCRIPTION_REGEX = r'<div class="video_det">\s*<strong>[^<]+</strong>\s*<p>([^<]+)</p>' + + _TEST = { + 'url': 'http://www.divxstage.eu/video/57f238e2e5e01', + 'md5': '63969f6eb26533a1968c4d325be63e72', + 'info_dict': { + 'id': '57f238e2e5e01', + 'ext': 'flv', + 'title': 'youtubedl test video', + 'description': 'This is a test video for youtubedl.', + } + }
\ No newline at end of file diff --git a/youtube_dl/extractor/ehow.py b/youtube_dl/extractor/ehow.py index 2bb77aec6..f8f49a013 100644 --- a/youtube_dl/extractor/ehow.py +++ b/youtube_dl/extractor/ehow.py @@ -1,23 +1,25 @@ +from __future__ import unicode_literals + import re from ..utils import ( compat_urllib_parse, - determine_ext ) from .common import InfoExtractor class EHowIE(InfoExtractor): - IE_NAME = u'eHow' - _VALID_URL = r'(?:https?://)?(?:www\.)?ehow\.com/[^/_?]*_(?P<id>[0-9]+)' + IE_NAME = 'eHow' + _VALID_URL = r'https?://(?:www\.)?ehow\.com/[^/_?]*_(?P<id>[0-9]+)' _TEST = { - u'url': u'http://www.ehow.com/video_12245069_hardwood-flooring-basics.html', - u'file': u'12245069.flv', - u'md5': u'9809b4e3f115ae2088440bcb4efbf371', - u'info_dict': { - u"title": u"Hardwood Flooring Basics", - u"description": u"Hardwood flooring may be time consuming, but its ultimately a pretty straightforward concept. Learn about hardwood flooring basics with help from a hardware flooring business owner in this free video...", - u"uploader": u"Erick Nathan" + 'url': 'http://www.ehow.com/video_12245069_hardwood-flooring-basics.html', + 'md5': '9809b4e3f115ae2088440bcb4efbf371', + 'info_dict': { + 'id': '12245069', + 'ext': 'flv', + 'title': 'Hardwood Flooring Basics', + 'description': 'Hardwood flooring may be time consuming, but its ultimately a pretty straightforward concept. Learn about hardwood flooring basics with help from a hardware flooring business owner in this free video...', + 'uploader': 'Erick Nathan', } } @@ -26,21 +28,16 @@ class EHowIE(InfoExtractor): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) video_url = self._search_regex(r'(?:file|source)=(http[^\'"&]*)', - webpage, u'video URL') - final_url = compat_urllib_parse.unquote(video_url) - uploader = self._search_regex(r'<meta name="uploader" content="(.+?)" />', - webpage, u'uploader') + webpage, 'video URL') + final_url = compat_urllib_parse.unquote(video_url) + uploader = self._html_search_meta('uploader', webpage) title = self._og_search_title(webpage).replace(' | eHow', '') - ext = determine_ext(final_url) return { - '_type': 'video', - 'id': video_id, - 'url': final_url, - 'ext': ext, - 'title': title, - 'thumbnail': self._og_search_thumbnail(webpage), + 'id': video_id, + 'url': final_url, + 'title': title, + 'thumbnail': self._og_search_thumbnail(webpage), 'description': self._og_search_description(webpage), - 'uploader': uploader, + 'uploader': uploader, } - diff --git a/youtube_dl/extractor/firstpost.py b/youtube_dl/extractor/firstpost.py index 7e3d1afd2..eccd8dde9 100644 --- a/youtube_dl/extractor/firstpost.py +++ b/youtube_dl/extractor/firstpost.py @@ -6,7 +6,6 @@ from .common import InfoExtractor class FirstpostIE(InfoExtractor): - IE_NAME = 'Firstpost.com' _VALID_URL = r'http://(?:www\.)?firstpost\.com/[^/]+/.*-(?P<id>[0-9]+)\.html' _TEST = { @@ -16,7 +15,6 @@ class FirstpostIE(InfoExtractor): 'id': '1025403', 'ext': 'mp4', 'title': 'India to launch indigenous aircraft carrier INS Vikrant today', - 'description': 'Its flight deck is over twice the size of a football field, its power unit can light up the entire Kochi city and the cabling is enough to cover the distance between here to Delhi.', } } @@ -24,15 +22,26 @@ class FirstpostIE(InfoExtractor): 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'<div.*?name="div_video".*?flashvars="([^"]+)">', - webpage, 'video URL') + data = self._download_xml( + 'http://www.firstpost.com/getvideoxml-%s.xml' % video_id, video_id, + 'Downloading video XML') + + item = data.find('./playlist/item') + thumbnail = item.find('./image').text + title = item.find('./title').text + + formats = [ + { + 'url': details.find('./file').text, + 'format_id': details.find('./label').text.strip(), + 'width': int(details.find('./width').text.strip()), + 'height': int(details.find('./height').text.strip()), + } for details in item.findall('./source/file_details') if details.find('./file').text + ] return { 'id': video_id, - 'url': video_url, - 'title': self._og_search_title(webpage), - 'description': self._og_search_description(webpage), - 'thumbnail': self._og_search_thumbnail(webpage), + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, } diff --git a/youtube_dl/extractor/franceculture.py b/youtube_dl/extractor/franceculture.py new file mode 100644 index 000000000..898e0dda7 --- /dev/null +++ b/youtube_dl/extractor/franceculture.py @@ -0,0 +1,77 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + compat_parse_qs, + compat_urlparse, +) + + +class FranceCultureIE(InfoExtractor): + _VALID_URL = r'(?P<baseurl>http://(?:www\.)?franceculture\.fr/)player/reecouter\?play=(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://www.franceculture.fr/player/reecouter?play=4795174', + 'info_dict': { + 'id': '4795174', + 'ext': 'mp3', + 'title': 'Rendez-vous au pays des geeks', + 'vcodec': 'none', + 'uploader': 'Colette Fellous', + 'upload_date': '20140301', + 'duration': 3601, + 'thumbnail': r're:^http://www\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$', + 'description': 'Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche des « geeks », une enquête menée aux Etats-Unis dans la S ...', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + baseurl = mobj.group('baseurl') + + webpage = self._download_webpage(url, video_id) + params_code = self._search_regex( + r"<param name='movie' value='/sites/all/modules/rf/rf_player/swf/loader.swf\?([^']+)' />", + webpage, 'parameter code') + params = compat_parse_qs(params_code) + video_url = compat_urlparse.urljoin(baseurl, params['urlAOD'][0]) + + title = self._html_search_regex( + r'<h1 class="title[^"]+">(.+?)</h1>', webpage, 'title') + uploader = self._html_search_regex( + r'(?s)<div id="emission".*?<span class="author">(.*?)</span>', + webpage, 'uploader', fatal=False) + thumbnail_part = self._html_search_regex( + r'(?s)<div id="emission".*?<img src="([^"]+)"', webpage, + 'thumbnail', fatal=False) + if thumbnail_part is None: + thumbnail = None + else: + thumbnail = compat_urlparse.urljoin(baseurl, thumbnail_part) + description = self._html_search_regex( + r'(?s)<p class="desc">(.*?)</p>', webpage, 'description') + + info = json.loads(params['infoData'][0])[0] + duration = info.get('media_length') + upload_date_candidate = info.get('media_section5') + upload_date = ( + upload_date_candidate + if (upload_date_candidate is not None and + re.match(r'[0-9]{8}$', upload_date_candidate)) + else None) + + return { + 'id': video_id, + 'url': video_url, + 'vcodec': 'none' if video_url.lower().endswith('.mp3') else None, + 'duration': duration, + 'uploader': uploader, + 'upload_date': upload_date, + 'title': title, + 'thumbnail': thumbnail, + 'description': description, + } diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index e7ee31877..cf245d9cd 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -25,6 +25,7 @@ from ..utils import ( from .brightcove import BrightcoveIE from .ooyala import OoyalaIE from .rutv import RUTVIE +from .smotri import SmotriIE class GenericIE(InfoExtractor): @@ -81,6 +82,17 @@ class GenericIE(InfoExtractor): }, 'add_ie': ['Brightcove'], }, + { + 'url': 'http://www.championat.com/video/football/v/87/87499.html', + 'md5': 'fb973ecf6e4a78a67453647444222983', + 'info_dict': { + 'id': '3414141473001', + 'ext': 'mp4', + 'title': 'Видео. Удаление Дзагоева (ЦСКА)', + 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"', + 'uploader': 'Championat', + }, + }, # Direct link to a video { 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4', @@ -102,20 +114,6 @@ class GenericIE(InfoExtractor): 'title': '2cc213299525360.mov', # that's what we get }, }, - # second style of embedded ooyala videos - { - 'url': 'http://www.smh.com.au/tv/business/show/financial-review-sunday/behind-the-scenes-financial-review-sunday--4350201.html', - 'info_dict': { - 'id': '13djJjYjptA1XpPx8r9kuzPyj3UZH0Uk', - 'ext': 'mp4', - 'title': 'Behind-the-scenes: Financial Review Sunday ', - 'description': 'Step inside Channel Nine studios for an exclusive tour of its upcoming financial business show.', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - }, # google redirect { 'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE', @@ -186,6 +184,17 @@ class GenericIE(InfoExtractor): 'description': 'md5:ddb2a40ecd6b6a147e400e535874947b', } }, + # Embeded Ustream video + { + 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm', + 'md5': '27b99cdb639c9b12a79bca876a073417', + 'info_dict': { + 'id': '45734260', + 'ext': 'flv', + 'uploader': 'AU SPA: The NSA and Privacy', + 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman' + } + }, # nowvideo embed hidden behind percent encoding { 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/', @@ -212,6 +221,21 @@ class GenericIE(InfoExtractor): 'skip_download': 'Requires rtmpdump' } }, + # smotri embed + { + 'url': 'http://rbctv.rbc.ru/archive/news/562949990879132.shtml', + 'md5': 'ec40048448e9284c9a1de77bb188108b', + 'info_dict': { + 'id': 'v27008541fad', + 'ext': 'mp4', + 'title': 'Крым и Севастополь вошли в состав России', + 'description': 'md5:fae01b61f68984c7bd2fa741e11c3175', + 'duration': 900, + 'upload_date': '20140318', + 'uploader': 'rbctv_2012_4', + 'uploader_id': 'rbctv_2012_4', + }, + }, ] def report_download_webpage(self, video_id): @@ -300,13 +324,16 @@ class GenericIE(InfoExtractor): if not parsed_url.scheme: default_search = self._downloader.params.get('default_search') if default_search is None: - default_search = 'auto' + default_search = 'auto_warning' - if default_search == 'auto': + if default_search in ('auto', 'auto_warning'): if '/' in url: self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http') return self.url_result('http://' + url) else: + if default_search == 'auto_warning': + self._downloader.report_warning( + 'Falling back to youtube search for %s . Set --default-search to "auto" to suppress this warning.' % url) return self.url_result('ytsearch:' + url) else: assert ':' in default_search @@ -484,17 +511,18 @@ class GenericIE(InfoExtractor): if mobj is not None: return self.url_result(mobj.group(1), 'Mpora') - # Look for embedded NovaMov player + # Look for embedded NovaMov-based player mobj = re.search( - r'<iframe[^>]+?src=(["\'])(?P<url>http://(?:(?:embed|www)\.)?novamov\.com/embed\.php.+?)\1', webpage) + r'''(?x)<iframe[^>]+?src=(["\']) + (?P<url>http://(?:(?:embed|www)\.)? + (?:novamov\.com| + nowvideo\.(?:ch|sx|eu|at|ag|co)| + videoweed\.(?:es|com)| + movshare\.(?:net|sx|ag)| + divxstage\.(?:eu|net|ch|co|at|ag)) + /embed\.php.+?)\1''', webpage) if mobj is not None: - return self.url_result(mobj.group('url'), 'NovaMov') - - # Look for embedded NowVideo player - mobj = re.search( - r'<iframe[^>]+?src=(["\'])(?P<url>http://(?:(?:embed|www)\.)?nowvideo\.(?:ch|sx|eu)/embed\.php.+?)\1', webpage) - if mobj is not None: - return self.url_result(mobj.group('url'), 'NowVideo') + return self.url_result(mobj.group('url')) # Look for embedded Facebook player mobj = re.search( @@ -540,6 +568,12 @@ class GenericIE(InfoExtractor): if mobj is not None: return self.url_result(mobj.group('url'), 'TED') + # Look for embedded Ustream videos + mobj = re.search( + r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'Ustream') + # Look for embedded arte.tv player mobj = re.search( r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"', @@ -547,6 +581,11 @@ class GenericIE(InfoExtractor): if mobj is not None: return self.url_result(mobj.group('url'), 'ArteTVEmbed') + # Look for embedded smotri.com player + smotri_url = SmotriIE._extract_url(webpage) + if smotri_url: + return self.url_result(smotri_url, 'Smotri') + # Start with something easy: JW Player in SWFObject mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) if mobj is None: diff --git a/youtube_dl/extractor/huffpost.py b/youtube_dl/extractor/huffpost.py index 0d1ea6802..94e7cf790 100644 --- a/youtube_dl/extractor/huffpost.py +++ b/youtube_dl/extractor/huffpost.py @@ -21,9 +21,10 @@ class HuffPostIE(InfoExtractor): _TEST = { 'url': 'http://live.huffingtonpost.com/r/segment/legalese-it/52dd3e4b02a7602131000677', - 'file': '52dd3e4b02a7602131000677.mp4', 'md5': '55f5e8981c1c80a64706a44b74833de8', 'info_dict': { + 'id': '52dd3e4b02a7602131000677', + 'ext': 'mp4', 'title': 'Legalese It! with @MikeSacksHP', 'description': 'This week on Legalese It, Mike talks to David Bosco about his new book on the ICC, "Rough Justice," he also discusses the Virginia AG\'s historic stance on gay marriage, the execution of Edgar Tamayo, the ICC\'s delay of Kenya\'s President and more. ', 'duration': 1549, diff --git a/youtube_dl/extractor/ign.py b/youtube_dl/extractor/ign.py index 381af91e4..cfeaa4146 100644 --- a/youtube_dl/extractor/ign.py +++ b/youtube_dl/extractor/ign.py @@ -1,10 +1,8 @@ +from __future__ import unicode_literals + import re -import json from .common import InfoExtractor -from ..utils import ( - determine_ext, -) class IGNIE(InfoExtractor): @@ -14,52 +12,57 @@ class IGNIE(InfoExtractor): """ _VALID_URL = r'https?://.+?\.ign\.com/(?P<type>videos|show_videos|articles|(?:[^/]*/feature))(/.+)?/(?P<name_or_id>.+)' - IE_NAME = u'ign.com' + IE_NAME = 'ign.com' _CONFIG_URL_TEMPLATE = 'http://www.ign.com/videos/configs/id/%s.config' - _DESCRIPTION_RE = [r'<span class="page-object-description">(.+?)</span>', - r'id="my_show_video">.*?<p>(.*?)</p>', - ] + _DESCRIPTION_RE = [ + r'<span class="page-object-description">(.+?)</span>', + r'id="my_show_video">.*?<p>(.*?)</p>', + ] _TESTS = [ { - u'url': u'http://www.ign.com/videos/2013/06/05/the-last-of-us-review', - u'file': u'8f862beef863986b2785559b9e1aa599.mp4', - u'md5': u'eac8bdc1890980122c3b66f14bdd02e9', - u'info_dict': { - u'title': u'The Last of Us Review', - u'description': u'md5:c8946d4260a4d43a00d5ae8ed998870c', + 'url': 'http://www.ign.com/videos/2013/06/05/the-last-of-us-review', + 'md5': 'eac8bdc1890980122c3b66f14bdd02e9', + 'info_dict': { + 'id': '8f862beef863986b2785559b9e1aa599', + 'ext': 'mp4', + 'title': 'The Last of Us Review', + 'description': 'md5:c8946d4260a4d43a00d5ae8ed998870c', } }, { - u'url': u'http://me.ign.com/en/feature/15775/100-little-things-in-gta-5-that-will-blow-your-mind', - u'playlist': [ + 'url': 'http://me.ign.com/en/feature/15775/100-little-things-in-gta-5-that-will-blow-your-mind', + 'playlist': [ { - u'file': u'5ebbd138523268b93c9141af17bec937.mp4', - u'info_dict': { - u'title': u'GTA 5 Video Review', - u'description': u'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.', + 'info_dict': { + 'id': '5ebbd138523268b93c9141af17bec937', + 'ext': 'mp4', + 'title': 'GTA 5 Video Review', + 'description': 'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.', }, }, { - u'file': u'638672ee848ae4ff108df2a296418ee2.mp4', - u'info_dict': { - u'title': u'26 Twisted Moments from GTA 5 in Slow Motion', - u'description': u'The twisted beauty of GTA 5 in stunning slow motion.', + 'info_dict': { + 'id': '638672ee848ae4ff108df2a296418ee2', + 'ext': 'mp4', + 'title': '26 Twisted Moments from GTA 5 in Slow Motion', + 'description': 'The twisted beauty of GTA 5 in stunning slow motion.', }, }, ], - u'params': { - u'skip_download': True, + 'params': { + 'skip_download': True, }, }, ] def _find_video_id(self, webpage): - res_id = [r'data-video-id="(.+?)"', - r'<object id="vid_(.+?)"', - r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"', - ] + res_id = [ + r'data-video-id="(.+?)"', + r'<object id="vid_(.+?)"', + r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"', + ] return self._search_regex(res_id, webpage, 'video id') def _real_extract(self, url): @@ -68,7 +71,7 @@ class IGNIE(InfoExtractor): 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, u'video url') + video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, 'video url') return self.url_result(video_url, ie='IGN') elif page_type != 'video': multiple_urls = re.findall( @@ -80,41 +83,37 @@ class IGNIE(InfoExtractor): video_id = self._find_video_id(webpage) result = self._get_video_info(video_id) description = self._html_search_regex(self._DESCRIPTION_RE, - webpage, 'video description', - flags=re.DOTALL) + webpage, 'video description', flags=re.DOTALL) result['description'] = description return result def _get_video_info(self, video_id): config_url = self._CONFIG_URL_TEMPLATE % video_id - config = json.loads(self._download_webpage(config_url, video_id, - u'Downloading video info')) + config = self._download_json(config_url, video_id) media = config['playlist']['media'] - video_url = media['url'] - return {'id': media['metadata']['videoId'], - 'url': video_url, - 'ext': determine_ext(video_url), - 'title': media['metadata']['title'], - 'thumbnail': media['poster'][0]['url'].replace('{size}', 'grande'), - } + return { + 'id': media['metadata']['videoId'], + 'url': media['url'], + 'title': media['metadata']['title'], + 'thumbnail': media['poster'][0]['url'].replace('{size}', 'grande'), + } class OneUPIE(IGNIE): - """Extractor for 1up.com, it uses the ign videos system.""" - _VALID_URL = r'https?://gamevideos\.1up\.com/(?P<type>video)/id/(?P<name_or_id>.+)' IE_NAME = '1up.com' _DESCRIPTION_RE = r'<div id="vid_summary">(.+?)</div>' _TEST = { - u'url': u'http://gamevideos.1up.com/video/id/34976', - u'file': u'34976.mp4', - u'md5': u'68a54ce4ebc772e4b71e3123d413163d', - u'info_dict': { - u'title': u'Sniper Elite V2 - Trailer', - u'description': u'md5:5d289b722f5a6d940ca3136e9dae89cf', + 'url': 'http://gamevideos.1up.com/video/id/34976', + 'md5': '68a54ce4ebc772e4b71e3123d413163d', + 'info_dict': { + 'id': '34976', + 'ext': 'mp4', + 'title': 'Sniper Elite V2 - Trailer', + 'description': 'md5:5d289b722f5a6d940ca3136e9dae89cf', } } @@ -123,7 +122,6 @@ class OneUPIE(IGNIE): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - id = mobj.group('name_or_id') result = super(OneUPIE, self)._real_extract(url) - result['id'] = id + result['id'] = mobj.group('name_or_id') return result diff --git a/youtube_dl/extractor/justintv.py b/youtube_dl/extractor/justintv.py index e9bde0c18..7083db12e 100644 --- a/youtube_dl/extractor/justintv.py +++ b/youtube_dl/extractor/justintv.py @@ -1,9 +1,12 @@ +from __future__ import unicode_literals + import json import os import re from .common import InfoExtractor from ..utils import ( + compat_str, ExtractorError, formatSeconds, ) @@ -24,34 +27,31 @@ class JustinTVIE(InfoExtractor): /?(?:\#.*)?$ """ _JUSTIN_PAGE_LIMIT = 100 - IE_NAME = u'justin.tv' + IE_NAME = 'justin.tv' + IE_DESC = 'justin.tv and twitch.tv' _TEST = { - u'url': u'http://www.twitch.tv/thegamedevhub/b/296128360', - u'file': u'296128360.flv', - u'md5': u'ecaa8a790c22a40770901460af191c9a', - u'info_dict': { - u"upload_date": u"20110927", - u"uploader_id": 25114803, - u"uploader": u"thegamedevhub", - u"title": u"Beginner Series - Scripting With Python Pt.1" + 'url': 'http://www.twitch.tv/thegamedevhub/b/296128360', + 'md5': 'ecaa8a790c22a40770901460af191c9a', + 'info_dict': { + 'id': '296128360', + 'ext': 'flv', + 'upload_date': '20110927', + 'uploader_id': 25114803, + 'uploader': 'thegamedevhub', + 'title': 'Beginner Series - Scripting With Python Pt.1' } } - def report_download_page(self, channel, offset): - """Report attempt to download a single page of videos.""" - self.to_screen(u'%s: Downloading video information from %d to %d' % - (channel, offset, offset + self._JUSTIN_PAGE_LIMIT)) - # Return count of items, list of *valid* items def _parse_page(self, url, video_id): info_json = self._download_webpage(url, video_id, - u'Downloading video info JSON', - u'unable to download video info JSON') + 'Downloading video info JSON', + 'unable to download video info JSON') response = json.loads(info_json) if type(response) != list: error_text = response.get('error', 'unknown error') - raise ExtractorError(u'Justin.tv API: %s' % error_text) + raise ExtractorError('Justin.tv API: %s' % error_text) info = [] for clip in response: video_url = clip['video_file_url'] @@ -62,7 +62,7 @@ class JustinTVIE(InfoExtractor): video_id = clip['id'] video_title = clip.get('title', video_id) info.append({ - 'id': video_id, + 'id': compat_str(video_id), 'url': video_url, 'title': video_title, 'uploader': clip.get('channel_name', video_uploader_id), @@ -74,8 +74,6 @@ class JustinTVIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'invalid URL: %s' % url) api_base = 'http://api.justin.tv' paged = False @@ -89,40 +87,41 @@ class JustinTVIE(InfoExtractor): webpage = self._download_webpage(url, chapter_id) m = re.search(r'PP\.archive_id = "([0-9]+)";', webpage) if not m: - raise ExtractorError(u'Cannot find archive of a chapter') + raise ExtractorError('Cannot find archive of a chapter') archive_id = m.group(1) api = api_base + '/broadcast/by_chapter/%s.xml' % chapter_id - doc = self._download_xml(api, chapter_id, - note=u'Downloading chapter information', - errnote=u'Chapter information download failed') + doc = self._download_xml( + api, chapter_id, + note='Downloading chapter information', + errnote='Chapter information download failed') for a in doc.findall('.//archive'): if archive_id == a.find('./id').text: break else: - raise ExtractorError(u'Could not find chapter in chapter information') + raise ExtractorError('Could not find chapter in chapter information') video_url = a.find('./video_file_url').text - video_ext = video_url.rpartition('.')[2] or u'flv' + video_ext = video_url.rpartition('.')[2] or 'flv' - chapter_api_url = u'https://api.twitch.tv/kraken/videos/c' + chapter_id - chapter_info_json = self._download_webpage(chapter_api_url, u'c' + chapter_id, - note='Downloading chapter metadata', - errnote='Download of chapter metadata failed') - chapter_info = json.loads(chapter_info_json) + chapter_api_url = 'https://api.twitch.tv/kraken/videos/c' + chapter_id + chapter_info = self._download_json( + chapter_api_url, 'c' + chapter_id, + note='Downloading chapter metadata', + errnote='Download of chapter metadata failed') bracket_start = int(doc.find('.//bracket_start').text) bracket_end = int(doc.find('.//bracket_end').text) # TODO determine start (and probably fix up file) # youtube-dl -v http://www.twitch.tv/firmbelief/c/1757457 - #video_url += u'?start=' + TODO:start_timestamp + #video_url += '?start=' + TODO:start_timestamp # bracket_start is 13290, but we want 51670615 - self._downloader.report_warning(u'Chapter detected, but we can just download the whole file. ' - u'Chapter starts at %s and ends at %s' % (formatSeconds(bracket_start), formatSeconds(bracket_end))) + self._downloader.report_warning('Chapter detected, but we can just download the whole file. ' + 'Chapter starts at %s and ends at %s' % (formatSeconds(bracket_start), formatSeconds(bracket_end))) info = { - 'id': u'c' + chapter_id, + 'id': 'c' + chapter_id, 'url': video_url, 'ext': video_ext, 'title': chapter_info['title'], @@ -131,14 +130,12 @@ class JustinTVIE(InfoExtractor): 'uploader': chapter_info['channel']['display_name'], 'uploader_id': chapter_info['channel']['name'], } - return [info] + return info else: video_id = mobj.group('videoid') api = api_base + '/broadcast/by_archive/%s.json' % video_id - self.report_extraction(video_id) - - info = [] + entries = [] offset = 0 limit = self._JUSTIN_PAGE_LIMIT while True: @@ -146,8 +143,12 @@ class JustinTVIE(InfoExtractor): self.report_download_page(video_id, offset) page_url = api + ('?offset=%d&limit=%d' % (offset, limit)) page_count, page_info = self._parse_page(page_url, video_id) - info.extend(page_info) + entries.extend(page_info) if not paged or page_count != limit: break offset += limit - return info + return { + '_type': 'playlist', + 'id': video_id, + 'entries': entries, + } diff --git a/youtube_dl/extractor/keezmovies.py b/youtube_dl/extractor/keezmovies.py index 29658a7d6..75b63cffb 100644 --- a/youtube_dl/extractor/keezmovies.py +++ b/youtube_dl/extractor/keezmovies.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import os import re @@ -11,22 +13,22 @@ from ..aes import ( aes_decrypt_text ) + class KeezMoviesIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>keezmovies\.com/video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)' + _VALID_URL = r'^https?://(?:www\.)?keezmovies\.com/video/.+?(?P<videoid>[0-9]+)(?:[/?&]|$)' _TEST = { - u'url': u'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711', - u'file': u'1214711.mp4', - u'md5': u'6e297b7e789329923fcf83abb67c9289', - u'info_dict': { - u"title": u"Petite Asian Lady Mai Playing In Bathtub", - u"age_limit": 18, + 'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711', + 'file': '1214711.mp4', + 'md5': '6e297b7e789329923fcf83abb67c9289', + 'info_dict': { + 'title': 'Petite Asian Lady Mai Playing In Bathtub', + 'age_limit': 18, } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('videoid') - url = 'http://www.' + mobj.group('url') req = compat_urllib_request.Request(url) req.add_header('Cookie', 'age_verified=1') @@ -38,10 +40,10 @@ class KeezMoviesIE(InfoExtractor): embedded_url = mobj.group(1) return self.url_result(embedded_url) - video_title = self._html_search_regex(r'<h1 [^>]*>([^<]+)', webpage, u'title') - video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&', webpage, u'video_url')) - if webpage.find('encrypted=true')!=-1: - password = self._html_search_regex(r'video_title=(.+?)&', webpage, u'password') + video_title = self._html_search_regex(r'<h1 [^>]*>([^<]+)', webpage, 'title') + video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&', webpage, 'video_url')) + if 'encrypted=true' in webpage: + password = self._html_search_regex(r'video_title=(.+?)&', webpage, 'password') video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8') path = compat_urllib_parse_urlparse(video_url).path extension = os.path.splitext(path)[1][1:] diff --git a/youtube_dl/extractor/kickstarter.py b/youtube_dl/extractor/kickstarter.py index 50bc883ef..961dd1aa6 100644 --- a/youtube_dl/extractor/kickstarter.py +++ b/youtube_dl/extractor/kickstarter.py @@ -1,37 +1,39 @@ +# encoding: utf-8 +from __future__ import unicode_literals + import re from .common import InfoExtractor class KickStarterIE(InfoExtractor): - _VALID_URL = r'https?://www\.kickstarter\.com/projects/(?P<id>\d*)/.*' + _VALID_URL = r'https?://www\.kickstarter\.com/projects/(?P<id>[^/]*)/.*' _TEST = { - u"url": u"https://www.kickstarter.com/projects/1404461844/intersection-the-story-of-josh-grant?ref=home_location", - u"file": u"1404461844.mp4", - u"md5": u"c81addca81327ffa66c642b5d8b08cab", - u"info_dict": { - u"title": u"Intersection: The Story of Josh Grant by Kyle Cowling", + 'url': 'https://www.kickstarter.com/projects/1404461844/intersection-the-story-of-josh-grant?ref=home_location', + 'md5': 'c81addca81327ffa66c642b5d8b08cab', + 'info_dict': { + 'id': '1404461844', + 'ext': 'mp4', + 'title': 'Intersection: The Story of Josh Grant by Kyle Cowling', + 'description': 'A unique motocross documentary that examines the ' + 'life and mind of one of sports most elite athletes: Josh Grant.', }, } def _real_extract(self, url): m = re.match(self._VALID_URL, url) video_id = m.group('id') - webpage_src = self._download_webpage(url, video_id) + webpage = self._download_webpage(url, video_id) - video_url = self._search_regex(r'data-video="(.*?)">', - webpage_src, u'video URL') - if 'mp4' in video_url: - ext = 'mp4' - else: - ext = 'flv' - video_title = self._html_search_regex(r"<title>(.*?)</title>", - webpage_src, u'title').rpartition(u'\u2014 Kickstarter')[0].strip() + 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() - results = [{ - 'id': video_id, - 'url': video_url, - 'title': video_title, - 'ext': ext, - }] - return results + return { + 'id': video_id, + 'url': video_url, + 'title': video_title, + 'description': self._og_search_description(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + } diff --git a/youtube_dl/extractor/metacritic.py b/youtube_dl/extractor/metacritic.py index 465ac4916..07f072924 100644 --- a/youtube_dl/extractor/metacritic.py +++ b/youtube_dl/extractor/metacritic.py @@ -13,8 +13,9 @@ class MetacriticIE(InfoExtractor): _TEST = { 'url': 'http://www.metacritic.com/game/playstation-4/infamous-second-son/trailers/3698222', - 'file': '3698222.mp4', 'info_dict': { + 'id': '3698222', + 'ext': 'mp4', 'title': 'inFamous: Second Son - inSide Sucker Punch: Smoke & Mirrors', 'description': 'Take a peak behind-the-scenes to see how Sucker Punch brings smoke into the universe of inFAMOUS Second Son on the PS4.', 'duration': 221, diff --git a/youtube_dl/extractor/mooshare.py b/youtube_dl/extractor/mooshare.py index f1875add5..7d21ea18f 100644 --- a/youtube_dl/extractor/mooshare.py +++ b/youtube_dl/extractor/mooshare.py @@ -14,7 +14,7 @@ from ..utils import ( class MooshareIE(InfoExtractor): IE_NAME = 'mooshare' IE_DESC = 'Mooshare.biz' - _VALID_URL = r'http://mooshare\.biz/(?P<id>[\da-z]{12})' + _VALID_URL = r'http://(?:www\.)?mooshare\.biz/(?P<id>[\da-z]{12})' _TESTS = [ { diff --git a/youtube_dl/extractor/morningstar.py b/youtube_dl/extractor/morningstar.py new file mode 100644 index 000000000..320d27bdd --- /dev/null +++ b/youtube_dl/extractor/morningstar.py @@ -0,0 +1,47 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class MorningstarIE(InfoExtractor): + IE_DESC = 'morningstar.com' + _VALID_URL = r'https?://(?:www\.)?morningstar\.com/[cC]over/video[cC]enter\.aspx\?id=(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://www.morningstar.com/cover/videocenter.aspx?id=615869', + 'md5': '6c0acface7a787aadc8391e4bbf7b0f5', + 'info_dict': { + 'id': '615869', + 'ext': 'mp4', + 'title': 'Get Ahead of the Curve on 2013 Taxes', + 'description': "Vanguard's Joel Dickson on managing higher tax rates for high-income earners and fund capital-gain distributions in 2013.", + 'thumbnail': r're:^https?://.*m(?:orning)?star\.com/.+thumb\.jpg$' + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + title = self._html_search_regex( + r'<h1 id="titleLink">(.*?)</h1>', webpage, 'title') + video_url = self._html_search_regex( + r'<input type="hidden" id="hidVideoUrl" value="([^"]+)"', + webpage, 'video URL') + thumbnail = self._html_search_regex( + r'<input type="hidden" id="hidSnapshot" value="([^"]+)"', + webpage, 'thumbnail', fatal=False) + description = self._html_search_regex( + r'<div id="mstarDeck".*?>(.*?)</div>', + webpage, 'description', fatal=False) + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'thumbnail': thumbnail, + 'description': description, + } diff --git a/youtube_dl/extractor/motorsport.py b/youtube_dl/extractor/motorsport.py new file mode 100644 index 000000000..7c0ec6a12 --- /dev/null +++ b/youtube_dl/extractor/motorsport.py @@ -0,0 +1,63 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import hashlib +import json +import re +import time + +from .common import InfoExtractor +from ..utils import ( + compat_parse_qs, + compat_str, + int_or_none, +) + + +class MotorsportIE(InfoExtractor): + IE_DESC = 'motorsport.com' + _VALID_URL = r'http://www\.motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/(?:$|[?#])' + _TEST = { + 'url': 'http://www.motorsport.com/f1/video/main-gallery/red-bull-racing-2014-rules-explained/', + 'md5': '5592cb7c5005d9b2c163df5ac3dc04e4', + 'info_dict': { + 'id': '7063', + 'ext': 'mp4', + 'title': 'Red Bull Racing: 2014 Rules Explained', + 'duration': 207, + 'description': 'A new clip from Red Bull sees Daniel Ricciardo and Sebastian Vettel explain the 2014 Formula One regulations – which are arguably the most complex the sport has ever seen.', + 'uploader': 'rainiere', + 'thumbnail': r're:^http://.*motorsport\.com/.+\.jpg$' + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('id') + + webpage = self._download_webpage(url, display_id) + flashvars_code = self._html_search_regex( + r'<embed id="player".*?flashvars="([^"]+)"', webpage, 'flashvars') + flashvars = compat_parse_qs(flashvars_code) + params = json.loads(flashvars['parameters'][0]) + + e = compat_str(int(time.time()) + 24 * 60 * 60) + base_video_url = params['location'] + '?e=' + e + s = 'h3hg713fh32' + h = hashlib.md5((s + base_video_url).encode('utf-8')).hexdigest() + video_url = base_video_url + '&h=' + h + + uploader = self._html_search_regex( + r'(?s)<span class="label">Video by: </span>(.*?)</a>', webpage, + 'uploader', fatal=False) + + return { + 'id': params['video_id'], + 'display_id': display_id, + 'title': params['title'], + 'url': video_url, + 'description': params.get('description'), + 'thumbnail': params.get('main_thumb'), + 'duration': int_or_none(params.get('duration')), + 'uploader': uploader, + } diff --git a/youtube_dl/extractor/movshare.py b/youtube_dl/extractor/movshare.py new file mode 100644 index 000000000..4191cf7a0 --- /dev/null +++ b/youtube_dl/extractor/movshare.py @@ -0,0 +1,27 @@ +from __future__ import unicode_literals + +from .novamov import NovaMovIE + + +class MovShareIE(NovaMovIE): + IE_NAME = 'movshare' + IE_DESC = 'MovShare' + + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'movshare\.(?:net|sx|ag)'} + + _HOST = 'www.movshare.net' + + _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' + _TITLE_REGEX = r'<strong>Title:</strong> ([^<]+)</p>' + _DESCRIPTION_REGEX = r'<strong>Description:</strong> ([^<]+)</p>' + + _TEST = { + 'url': 'http://www.movshare.net/video/559e28be54d96', + 'md5': 'abd31a2132947262c50429e1d16c1bfd', + 'info_dict': { + 'id': '559e28be54d96', + 'ext': 'flv', + 'title': 'dissapeared image', + 'description': 'optical illusion dissapeared image magic illusion', + } + }
\ No newline at end of file diff --git a/youtube_dl/extractor/mpora.py b/youtube_dl/extractor/mpora.py index 6a8e2cc44..39d6feb98 100644 --- a/youtube_dl/extractor/mpora.py +++ b/youtube_dl/extractor/mpora.py @@ -4,9 +4,7 @@ import json import re from .common import InfoExtractor -from ..utils import ( - int_or_none, -) +from ..utils import int_or_none class MporaIE(InfoExtractor): @@ -20,7 +18,7 @@ class MporaIE(InfoExtractor): 'info_dict': { 'title': 'Katy Curd - Winter in the Forest', 'duration': 416, - 'uploader': 'petenewman', + 'uploader': 'Peter Newman Media', }, } diff --git a/youtube_dl/extractor/musicplayon.py b/youtube_dl/extractor/musicplayon.py new file mode 100644 index 000000000..42d7a82a5 --- /dev/null +++ b/youtube_dl/extractor/musicplayon.py @@ -0,0 +1,75 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import int_or_none + + +class MusicPlayOnIE(InfoExtractor): + _VALID_URL = r'https?://(?:.+?\.)?musicplayon\.com/play(?:-touch)?\?(?:v|pl=100&play)=(?P<id>\d+)' + + _TEST = { + 'url': 'http://en.musicplayon.com/play?v=433377', + 'info_dict': { + 'id': '433377', + 'ext': 'mp4', + 'title': 'Rick Ross - Interview On Chelsea Lately (2014)', + 'description': 'Rick Ross Interview On Chelsea Lately', + 'duration': 342, + 'uploader': 'ultrafish', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + page = self._download_webpage(url, video_id) + + title = self._og_search_title(page) + description = self._og_search_description(page) + thumbnail = self._og_search_thumbnail(page) + duration = self._html_search_meta('video:duration', page, 'duration', fatal=False) + view_count = self._og_search_property('count', page, fatal=False) + uploader = self._html_search_regex( + r'<div>by <a href="[^"]+" class="purple">([^<]+)</a></div>', page, 'uploader', fatal=False) + + formats = [ + { + 'url': 'http://media0-eu-nl.musicplayon.com/stream-mobile?id=%s&type=.mp4' % video_id, + 'ext': 'mp4', + } + ] + + manifest = self._download_webpage( + 'http://en.musicplayon.com/manifest.m3u8?v=%s' % video_id, video_id, 'Downloading manifest') + + for entry in manifest.split('#')[1:]: + if entry.startswith('EXT-X-STREAM-INF:'): + meta, url, _ = entry.split('\n') + params = dict(param.split('=') for param in meta.split(',')[1:]) + formats.append({ + 'url': url, + 'ext': 'mp4', + 'tbr': int(params['BANDWIDTH']), + 'width': int(params['RESOLUTION'].split('x')[1]), + 'height': int(params['RESOLUTION'].split('x')[-1]), + 'format_note': params['NAME'].replace('"', '').strip(), + }) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'duration': int_or_none(duration), + 'view_count': int_or_none(view_count), + 'formats': formats, + }
\ No newline at end of file diff --git a/youtube_dl/extractor/nba.py b/youtube_dl/extractor/nba.py index 7e421610e..633b42f72 100644 --- a/youtube_dl/extractor/nba.py +++ b/youtube_dl/extractor/nba.py @@ -6,12 +6,13 @@ from .common import InfoExtractor class NBAIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*?)(?:/index\.html)?(?:\?.*)?$' + _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', - 'file': u'0021200253-okc-bkn-recap.nba.mp4', 'md5': u'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', }, @@ -19,7 +20,7 @@ class NBAIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) + video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) @@ -33,7 +34,6 @@ class NBAIE(InfoExtractor): return { 'id': shortened_video_id, 'url': video_url, - 'ext': 'mp4', 'title': title, 'description': description, } diff --git a/youtube_dl/extractor/niconico.py b/youtube_dl/extractor/niconico.py index 46774317c..517a72561 100644 --- a/youtube_dl/extractor/niconico.py +++ b/youtube_dl/extractor/niconico.py @@ -1,12 +1,10 @@ # encoding: utf-8 +from __future__ import unicode_literals import re -import socket from .common import InfoExtractor from ..utils import ( - compat_http_client, - compat_urllib_error, compat_urllib_parse, compat_urllib_request, compat_urlparse, @@ -18,57 +16,54 @@ from ..utils import ( class NiconicoIE(InfoExtractor): - IE_NAME = u'niconico' - IE_DESC = u'ニコニコ動画' + IE_NAME = 'niconico' + IE_DESC = 'ニコニコ動画' _TEST = { - u'url': u'http://www.nicovideo.jp/watch/sm22312215', - u'file': u'sm22312215.mp4', - u'md5': u'd1a75c0823e2f629128c43e1212760f9', - u'info_dict': { - u'title': u'Big Buck Bunny', - u'uploader': u'takuya0301', - u'uploader_id': u'2698420', - u'upload_date': u'20131123', - u'description': u'(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org', + 'url': 'http://www.nicovideo.jp/watch/sm22312215', + 'md5': 'd1a75c0823e2f629128c43e1212760f9', + 'info_dict': { + 'id': 'sm22312215', + 'ext': 'mp4', + 'title': 'Big Buck Bunny', + 'uploader': 'takuya0301', + 'uploader_id': '2698420', + 'upload_date': '20131123', + 'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org', }, - u'params': { - u'username': u'ydl.niconico@gmail.com', - u'password': u'youtube-dl', + 'params': { + 'username': 'ydl.niconico@gmail.com', + 'password': 'youtube-dl', }, } _VALID_URL = r'^https?://(?:www\.|secure\.)?nicovideo\.jp/watch/([a-z][a-z][0-9]+)(?:.*)$' _NETRC_MACHINE = 'niconico' - # If True it will raise an error if no login info is provided - _LOGIN_REQUIRED = True def _real_initialize(self): self._login() def _login(self): (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 + # Login is required + raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) # Log in login_form_strs = { - u'mail': username, - u'password': password, + 'mail': username, + 'password': password, } # 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()) + login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items()) login_data = compat_urllib_parse.urlencode(login_form).encode('utf-8') request = compat_urllib_request.Request( - u'https://secure.nicovideo.jp/secure/login', login_data) + 'https://secure.nicovideo.jp/secure/login', login_data) login_results = self._download_webpage( - request, u'', note=u'Logging in', errnote=u'Unable to log in') + request, None, note='Logging in', errnote='Unable to log in') if re.search(r'(?i)<h1 class="mb8p4">Log in error</h1>', login_results) is not None: - self._downloader.report_warning(u'unable to log in: bad username or password') + self._downloader.report_warning('unable to log in: bad username or password') return False return True @@ -82,12 +77,12 @@ class NiconicoIE(InfoExtractor): video_info = self._download_xml( 'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id, - note=u'Downloading video info page') + note='Downloading video info page') # Get flv info flv_info_webpage = self._download_webpage( - u'http://flapi.nicovideo.jp/api/getflv?v=' + video_id, - video_id, u'Downloading flv info') + 'http://flapi.nicovideo.jp/api/getflv?v=' + video_id, + video_id, 'Downloading flv info') video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0] # Start extracting information @@ -106,22 +101,22 @@ class NiconicoIE(InfoExtractor): url = 'http://seiga.nicovideo.jp/api/user/info?id=' + video_uploader_id try: user_info = self._download_xml( - url, video_id, note=u'Downloading user information') + url, video_id, note='Downloading user information') video_uploader = user_info.find('.//nickname').text - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.report_warning(u'Unable to download user info webpage: %s' % compat_str(err)) + except ExtractorError as err: + self._downloader.report_warning('Unable to download user info webpage: %s' % compat_str(err)) return { - 'id': video_id, - 'url': video_real_url, - 'title': video_title, - 'ext': video_extension, - 'format': video_format, - 'thumbnail': video_thumbnail, + 'id': video_id, + 'url': video_real_url, + 'title': video_title, + 'ext': video_extension, + 'format': video_format, + 'thumbnail': video_thumbnail, 'description': video_description, - 'uploader': video_uploader, + 'uploader': video_uploader, 'upload_date': video_upload_date, 'uploader_id': video_uploader_id, - 'view_count': video_view_count, + 'view_count': video_view_count, 'webpage_url': video_webpage_url, } diff --git a/youtube_dl/extractor/ninegag.py b/youtube_dl/extractor/ninegag.py index b8c892cce..3352b8330 100644 --- a/youtube_dl/extractor/ninegag.py +++ b/youtube_dl/extractor/ninegag.py @@ -7,9 +7,14 @@ from .common import InfoExtractor class NineGagIE(InfoExtractor): IE_NAME = '9gag' - _VALID_URL = r'^https?://(?:www\.)?9gag\.tv/v/(?P<id>[0-9]+)' + _VALID_URL = r'''(?x)^https?://(?:www\.)?9gag\.tv/ + (?: + v/(?P<numid>[0-9]+)| + p/(?P<id>[a-zA-Z0-9]+)/(?P<display_id>[^?#/]+) + ) + ''' - _TEST = { + _TESTS = [{ "url": "http://9gag.tv/v/1912", "info_dict": { "id": "1912", @@ -20,17 +25,33 @@ class NineGagIE(InfoExtractor): "thumbnail": "re:^https?://", }, 'add_ie': ['Youtube'] - } + }, + { + 'url': 'http://9gag.tv/p/KklwM/alternate-banned-opening-scene-of-gravity?ref=fsidebar', + 'info_dict': { + 'id': 'KklwM', + 'ext': 'mp4', + 'display_id': 'alternate-banned-opening-scene-of-gravity', + "description": "While Gravity was a pretty awesome movie already, YouTuber Krishna Shenoi came up with a way to improve upon it, introducing a much better solution to Sandra Bullock's seemingly endless tumble in space. The ending is priceless.", + 'title': "Banned Opening Scene Of \"Gravity\" That Changes The Whole Movie", + }, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = mobj.group('numid') or mobj.group('id') + display_id = mobj.group('display_id') or video_id - webpage = self._download_webpage(url, video_id) + webpage = self._download_webpage(url, display_id) youtube_id = self._html_search_regex( r'(?s)id="jsid-video-post-container".*?data-external-id="([^"]+)"', webpage, 'video ID') + title = self._html_search_regex( + r'(?s)id="jsid-video-post-container".*?data-title="([^"]+)"', + webpage, 'title', default=None) + if not title: + title = self._og_search_title(webpage) description = self._html_search_regex( r'(?s)<div class="video-caption">.*?<p>(.*?)</p>', webpage, 'description', fatal=False) @@ -46,7 +67,8 @@ class NineGagIE(InfoExtractor): 'url': youtube_id, 'ie_key': 'Youtube', 'id': video_id, - 'title': self._og_search_title(webpage), + 'display_id': display_id, + 'title': title, 'description': description, 'view_count': view_count, 'thumbnail': self._og_search_thumbnail(webpage), diff --git a/youtube_dl/extractor/novamov.py b/youtube_dl/extractor/novamov.py index fd310e219..2e7ab1e4f 100644 --- a/youtube_dl/extractor/novamov.py +++ b/youtube_dl/extractor/novamov.py @@ -13,7 +13,8 @@ class NovaMovIE(InfoExtractor): IE_NAME = 'novamov' IE_DESC = 'NovaMov' - _VALID_URL = r'http://(?:(?:www\.)?%(host)s/video/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<videoid>[a-z\d]{13})' % {'host': 'novamov\.com'} + _VALID_URL_TEMPLATE = r'http://(?:(?:www\.)?%(host)s/(?:file|video)/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<id>[a-z\d]{13})' + _VALID_URL = _VALID_URL_TEMPLATE % {'host': 'novamov\.com'} _HOST = 'www.novamov.com' @@ -36,18 +37,17 @@ class NovaMovIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') + video_id = mobj.group('id') page = self._download_webpage( 'http://%s/video/%s' % (self._HOST, video_id), video_id, 'Downloading video page') if re.search(self._FILE_DELETED_REGEX, page) is not None: - raise ExtractorError(u'Video %s does not exist' % video_id, expected=True) + raise ExtractorError('Video %s does not exist' % video_id, expected=True) filekey = self._search_regex(self._FILEKEY_REGEX, page, 'filekey') title = self._html_search_regex(self._TITLE_REGEX, page, 'title', fatal=False) - description = self._html_search_regex(self._DESCRIPTION_REGEX, page, 'description', default='', fatal=False) api_response = self._download_webpage( diff --git a/youtube_dl/extractor/nowvideo.py b/youtube_dl/extractor/nowvideo.py index dd665874d..bfba18418 100644 --- a/youtube_dl/extractor/nowvideo.py +++ b/youtube_dl/extractor/nowvideo.py @@ -7,7 +7,7 @@ class NowVideoIE(NovaMovIE): IE_NAME = 'nowvideo' IE_DESC = 'NowVideo' - _VALID_URL = r'http://(?:(?:www\.)?%(host)s/video/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<videoid>[a-z\d]{13})' % {'host': 'nowvideo\.(?:ch|sx|eu)'} + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:ch|sx|eu|at|ag|co)'} _HOST = 'www.nowvideo.ch' diff --git a/youtube_dl/extractor/ntv.py b/youtube_dl/extractor/ntv.py new file mode 100644 index 000000000..dfbcb792c --- /dev/null +++ b/youtube_dl/extractor/ntv.py @@ -0,0 +1,157 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + unescapeHTML +) + + +class NTVIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?ntv\.ru/(?P<id>.+)' + + _TESTS = [ + { + 'url': 'http://www.ntv.ru/novosti/863142/', + 'info_dict': { + 'id': '746000', + 'ext': 'flv', + 'title': 'Командующий Черноморским флотом провел переговоры в штабе ВМС Украины', + 'description': 'Командующий Черноморским флотом провел переговоры в штабе ВМС Украины', + 'duration': 136, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.ntv.ru/video/novosti/750370/', + 'info_dict': { + 'id': '750370', + 'ext': 'flv', + 'title': 'Родные пассажиров пропавшего Boeing не верят в трагический исход', + 'description': 'Родные пассажиров пропавшего Boeing не верят в трагический исход', + 'duration': 172, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.ntv.ru/peredacha/segodnya/m23700/o232416', + 'info_dict': { + 'id': '747480', + 'ext': 'flv', + 'title': '«Сегодня». 21 марта 2014 года. 16:00 ', + 'description': '«Сегодня». 21 марта 2014 года. 16:00 ', + 'duration': 1496, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.ntv.ru/kino/Koma_film', + 'info_dict': { + 'id': '758100', + 'ext': 'flv', + 'title': 'Остросюжетный фильм «Кома»', + 'description': 'Остросюжетный фильм «Кома»', + 'duration': 5592, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.ntv.ru/serial/Delo_vrachey/m31760/o233916/', + 'info_dict': { + 'id': '751482', + 'ext': 'flv', + 'title': '«Дело врачей»: «Деревце жизни»', + 'description': '«Дело врачей»: «Деревце жизни»', + 'duration': 2590, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + ] + + _VIDEO_ID_REGEXES = [ + r'<meta property="og:url" content="http://www\.ntv\.ru/video/(\d+)', + r'<video embed=[^>]+><id>(\d+)</id>', + r'<video restriction[^>]+><key>(\d+)</key>' + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + page = self._download_webpage(url, video_id, 'Downloading page') + + for pattern in self._VIDEO_ID_REGEXES: + mobj = re.search(pattern, page) + if mobj: + break + + if not mobj: + raise ExtractorError('No media links available for %s' % video_id) + + video_id = mobj.group(1) + + player = self._download_xml('http://www.ntv.ru/vi%s/' % video_id, video_id, 'Downloading video XML') + title = unescapeHTML(player.find('./data/title').text) + description = unescapeHTML(player.find('./data/description').text) + + video = player.find('./data/video') + video_id = video.find('./id').text + thumbnail = video.find('./splash').text + duration = int(video.find('./totaltime').text) + view_count = int(video.find('./views').text) + puid22 = video.find('./puid22').text + + apps = { + '4': 'video1', + '7': 'video2', + } + + app = apps[puid22] if puid22 in apps else apps['4'] + + formats = [] + for format_id in ['', 'hi', 'webm']: + file = video.find('./%sfile' % format_id) + if file is None: + continue + size = video.find('./%ssize' % format_id) + formats.append({ + 'url': 'rtmp://media.ntv.ru/%s' % app, + 'app': app, + 'play_path': file.text, + 'rtmp_conn': 'B:1', + 'player_url': 'http://www.ntv.ru/swf/vps1.swf?update=20131128', + 'page_url': 'http://www.ntv.ru', + 'flash_ver': 'LNX 11,2,202,341', + 'rtmp_live': True, + 'ext': 'flv', + 'filesize': int(size.text), + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'view_count': view_count, + 'formats': formats, + }
\ No newline at end of file diff --git a/youtube_dl/extractor/oe1.py b/youtube_dl/extractor/oe1.py new file mode 100644 index 000000000..38971ab4d --- /dev/null +++ b/youtube_dl/extractor/oe1.py @@ -0,0 +1,40 @@ +# 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/pornhd.py b/youtube_dl/extractor/pornhd.py index 58f9c690e..718fe9aba 100644 --- a/youtube_dl/extractor/pornhd.py +++ b/youtube_dl/extractor/pornhd.py @@ -1,44 +1,81 @@ from __future__ import unicode_literals import re +import json from .common import InfoExtractor -from ..utils import compat_urllib_parse +from ..utils import int_or_none class PornHdIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<video_id>[0-9]+)/(?P<video_title>.+)' + _VALID_URL = r'http://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)' _TEST = { 'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video', - 'file': '1962.flv', - 'md5': '35272469887dca97abd30abecc6cdf75', + 'md5': '956b8ca569f7f4d8ec563e2c41598441', 'info_dict': { - "title": "sierra-day-gets-his-cum-all-over-herself-hd-porn-video", - "age_limit": 18, + 'id': '1962', + 'ext': 'mp4', + 'title': 'Sierra loves doing laundry', + 'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294', + 'age_limit': 18, } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('video_id') - video_title = mobj.group('video_title') + video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - next_url = self._html_search_regex( - r'&hd=(http.+?)&', webpage, 'video URL') - next_url = compat_urllib_parse.unquote(next_url) + title = self._og_search_title(webpage) + TITLE_SUFFIX = ' porn HD Video | PornHD.com ' + if title.endswith(TITLE_SUFFIX): + title = title[:-len(TITLE_SUFFIX)] + + description = self._html_search_regex( + r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False) + view_count = int_or_none(self._html_search_regex( + r'(\d+) views </span>', webpage, 'view count', fatal=False)) + + formats = [ + { + 'url': format_url, + 'ext': format.lower(), + 'format_id': '%s-%s' % (format.lower(), quality.lower()), + 'quality': 1 if quality.lower() == 'high' else 0, + } for format, quality, format_url in re.findall( + r'var __video([\da-zA-Z]+?)(Low|High)StreamUrl = \'(http://.+?)\?noProxy=1\'', webpage) + ] + + mobj = re.search(r'flashVars = (?P<flashvars>{.+?});', webpage) + if mobj: + flashvars = json.loads(mobj.group('flashvars')) + formats.extend([ + { + 'url': flashvars['hashlink'].replace('?noProxy=1', ''), + 'ext': 'flv', + 'format_id': 'flv-low', + 'quality': 0, + }, + { + 'url': flashvars['hd'].replace('?noProxy=1', ''), + 'ext': 'flv', + 'format_id': 'flv-high', + 'quality': 1, + } + ]) + thumbnail = flashvars['urlWallpaper'] + else: + thumbnail = self._og_search_thumbnail(webpage) - video_url = self._download_webpage( - next_url, video_id, note='Retrieving video URL', - errnote='Could not retrieve video URL') - age_limit = 18 + self._sort_formats(formats) return { 'id': video_id, - 'url': video_url, - 'ext': 'flv', - 'title': video_title, - 'age_limit': age_limit, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'view_count': view_count, + 'formats': formats, + 'age_limit': 18, } diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py index 3f585bebf..1e84b175f 100644 --- a/youtube_dl/extractor/prosiebensat1.py +++ b/youtube_dl/extractor/prosiebensat1.py @@ -160,6 +160,7 @@ class ProSiebenSat1IE(InfoExtractor): _CLIPID_REGEXES = [ r'"clip_id"\s*:\s+"(\d+)"', r'clipid: "(\d+)"', + r'clipId=(\d+)', ] _TITLE_REGEXES = [ r'<h2 class="subtitle" itemprop="name">\s*(.+?)</h2>', diff --git a/youtube_dl/extractor/pyvideo.py b/youtube_dl/extractor/pyvideo.py index 33054591b..0bc0859b4 100644 --- a/youtube_dl/extractor/pyvideo.py +++ b/youtube_dl/extractor/pyvideo.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re import os @@ -5,45 +7,51 @@ from .common import InfoExtractor class PyvideoIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?pyvideo\.org/video/(?P<id>\d+)/(.*)' - _TESTS = [{ - u'url': u'http://pyvideo.org/video/1737/become-a-logging-expert-in-30-minutes', - u'file': u'24_4WWkSmNo.mp4', - u'md5': u'de317418c8bc76b1fd8633e4f32acbc6', - u'info_dict': { - u"title": u"Become a logging expert in 30 minutes", - u"description": u"md5:9665350d466c67fb5b1598de379021f7", - u"upload_date": u"20130320", - u"uploader": u"NextDayVideo", - u"uploader_id": u"NextDayVideo", + _VALID_URL = r'http://(?:www\.)?pyvideo\.org/video/(?P<id>\d+)/(.*)' + + _TESTS = [ + { + 'url': 'http://pyvideo.org/video/1737/become-a-logging-expert-in-30-minutes', + 'md5': 'de317418c8bc76b1fd8633e4f32acbc6', + 'info_dict': { + 'id': '24_4WWkSmNo', + 'ext': 'mp4', + 'title': 'Become a logging expert in 30 minutes', + 'description': 'md5:9665350d466c67fb5b1598de379021f7', + 'upload_date': '20130320', + 'uploader': 'NextDayVideo', + 'uploader_id': 'NextDayVideo', + }, + 'add_ie': ['Youtube'], }, - u'add_ie': ['Youtube'], - }, - { - u'url': u'http://pyvideo.org/video/2542/gloriajw-spotifywitherikbernhardsson182m4v', - u'md5': u'5fe1c7e0a8aa5570330784c847ff6d12', - u'info_dict': { - u'id': u'2542', - u'ext': u'm4v', - u'title': u'Gloriajw-SpotifyWithErikBernhardsson182', + { + 'url': 'http://pyvideo.org/video/2542/gloriajw-spotifywitherikbernhardsson182m4v', + 'md5': '5fe1c7e0a8aa5570330784c847ff6d12', + 'info_dict': { + 'id': '2542', + 'ext': 'm4v', + 'title': 'Gloriajw-SpotifyWithErikBernhardsson182', + }, }, - }, ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) - m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', webpage) + m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', webpage) if m_youtube is not None: return self.url_result(m_youtube.group(1), 'Youtube') - title = self._html_search_regex(r'<div class="section">.*?<h3>([^>]+?)</h3>', - webpage, u'title', flags=re.DOTALL) - video_url = self._search_regex([r'<source src="(.*?)"', - r'<dt>Download</dt>.*?<a href="(.+?)"'], - webpage, u'video url', flags=re.DOTALL) + title = self._html_search_regex( + r'<div class="section">.*?<h3(?:\s+class="[^"]*")?>([^>]+?)</h3>', + webpage, 'title', flags=re.DOTALL) + video_url = self._search_regex( + [r'<source src="(.*?)"', r'<dt>Download</dt>.*?<a href="(.+?)"'], + webpage, 'video url', flags=re.DOTALL) + return { 'id': video_id, 'title': os.path.splitext(title)[0], diff --git a/youtube_dl/extractor/ro220.py b/youtube_dl/extractor/ro220.py index 4678f62df..a6ad59465 100644 --- a/youtube_dl/extractor/ro220.py +++ b/youtube_dl/extractor/ro220.py @@ -18,7 +18,7 @@ class Ro220IE(InfoExtractor): 'md5': '03af18b73a07b4088753930db7a34add', 'info_dict': { "title": "Luati-le Banii sez 4 ep 1", - "description": "Iata-ne reveniti dupa o binemeritata vacanta. Va astept si pe Facebook cu pareri si comentarii.", + "description": "re:^Iata-ne reveniti dupa o binemeritata vacanta\. +Va astept si pe Facebook cu pareri si comentarii.$", } } diff --git a/youtube_dl/extractor/roxwel.py b/youtube_dl/extractor/roxwel.py index d339e6cb5..41638c1d0 100644 --- a/youtube_dl/extractor/roxwel.py +++ b/youtube_dl/extractor/roxwel.py @@ -1,5 +1,6 @@ +from __future__ import unicode_literals + import re -import json from .common import InfoExtractor from ..utils import unified_strdate, determine_ext @@ -9,41 +10,44 @@ class RoxwelIE(InfoExtractor): _VALID_URL = r'https?://www\.roxwel\.com/player/(?P<filename>.+?)(\.|\?|$)' _TEST = { - u'url': u'http://www.roxwel.com/player/passionpittakeawalklive.html', - u'file': u'passionpittakeawalklive.flv', - u'md5': u'd9dea8360a1e7d485d2206db7fe13035', - u'info_dict': { - u'title': u'Take A Walk (live)', - u'uploader': u'Passion Pit', - u'description': u'Passion Pit performs "Take A Walk\" live at The Backyard in Austin, Texas. ', + 'url': 'http://www.roxwel.com/player/passionpittakeawalklive.html', + 'info_dict': { + 'id': 'passionpittakeawalklive', + 'ext': 'flv', + 'title': 'Take A Walk (live)', + 'uploader': 'Passion Pit', + 'uploader_id': 'passionpit', + 'upload_date': '20120928', + 'description': 'Passion Pit performs "Take A Walk\" live at The Backyard in Austin, Texas. ', }, - u'skip': u'Requires rtmpdump', + 'params': { + # rtmp download + 'skip_download': True, + } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) filename = mobj.group('filename') info_url = 'http://www.roxwel.com/api/videos/%s' % filename - info_page = self._download_webpage(info_url, filename, - u'Downloading video info') + info = self._download_json(info_url, filename) - self.report_extraction(filename) - info = json.loads(info_page) rtmp_rates = sorted([int(r.replace('flv_', '')) for r in info['media_rates'] if r.startswith('flv_')]) best_rate = rtmp_rates[-1] url_page_url = 'http://roxwel.com/pl_one_time.php?filename=%s&quality=%s' % (filename, best_rate) - rtmp_url = self._download_webpage(url_page_url, filename, u'Downloading video url') + rtmp_url = self._download_webpage(url_page_url, filename, 'Downloading video url') ext = determine_ext(rtmp_url) if ext == 'f4v': rtmp_url = rtmp_url.replace(filename, 'mp4:%s' % filename) - return {'id': filename, - 'title': info['title'], - 'url': rtmp_url, - 'ext': 'flv', - 'description': info['description'], - 'thumbnail': info.get('player_image_url') or info.get('image_url_large'), - 'uploader': info['artist'], - 'uploader_id': info['artistname'], - 'upload_date': unified_strdate(info['dbdate']), - } + return { + 'id': filename, + 'title': info['title'], + 'url': rtmp_url, + 'ext': 'flv', + 'description': info['description'], + 'thumbnail': info.get('player_image_url') or info.get('image_url_large'), + 'uploader': info['artist'], + 'uploader_id': info['artistname'], + 'upload_date': unified_strdate(info['dbdate']), + } diff --git a/youtube_dl/extractor/rts.py b/youtube_dl/extractor/rts.py index bcdfbdd56..e8199b114 100644 --- a/youtube_dl/extractor/rts.py +++ b/youtube_dl/extractor/rts.py @@ -9,46 +9,136 @@ from ..utils import ( parse_duration, parse_iso8601, unescapeHTML, + compat_str, ) class RTSIE(InfoExtractor): IE_DESC = 'RTS.ch' - _VALID_URL = r'^https?://(?:www\.)?rts\.ch/archives/tv/[^/]+/(?P<id>[0-9]+)-.*?\.html' - - _TEST = { - 'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html', - 'md5': '753b877968ad8afaeddccc374d4256a5', - 'info_dict': { - 'id': '3449373', - 'ext': 'mp4', - 'duration': 1488, - 'title': 'Les Enfants Terribles', - 'description': 'France Pommier et sa soeur Luce Feral, les deux filles de ce groupe de 5.', - 'uploader': 'Divers', - 'upload_date': '19680921', - 'timestamp': -40280400, - 'thumbnail': 're:^https?://.*\.image' + _VALID_URL = r'^https?://(?:www\.)?rts\.ch/(?:[^/]+/){2,}(?P<id>[0-9]+)-.*?\.html' + + _TESTS = [ + { + 'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html', + 'md5': '753b877968ad8afaeddccc374d4256a5', + 'info_dict': { + 'id': '3449373', + 'ext': 'mp4', + 'duration': 1488, + 'title': 'Les Enfants Terribles', + 'description': 'France Pommier et sa soeur Luce Feral, les deux filles de ce groupe de 5.', + 'uploader': 'Divers', + 'upload_date': '19680921', + 'timestamp': -40280400, + 'thumbnail': 're:^https?://.*\.image' + }, + }, + { + 'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html', + 'md5': 'c148457a27bdc9e5b1ffe081a7a8337b', + 'info_dict': { + 'id': '5624067', + 'ext': 'mp4', + 'duration': 3720, + 'title': 'Les yeux dans les cieux - Mon homard au Canada', + 'description': 'md5:d22ee46f5cc5bac0912e5a0c6d44a9f7', + 'uploader': 'Passe-moi les jumelles', + 'upload_date': '20140404', + 'timestamp': 1396635300, + 'thumbnail': 're:^https?://.*\.image' + }, + }, + { + 'url': 'http://www.rts.ch/video/sport/hockey/5745975-1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski.html', + 'md5': 'b4326fecd3eb64a458ba73c73e91299d', + 'info_dict': { + 'id': '5745975', + 'ext': 'mp4', + 'duration': 48, + 'title': '1/2, Kloten - Fribourg (5-2): second but pour Gottéron par Kwiatowski', + 'description': 'Hockey - Playoff', + 'uploader': 'Hockey', + 'upload_date': '20140403', + 'timestamp': 1396556882, + 'thumbnail': 're:^https?://.*\.image' + }, + 'skip': 'Blocked outside Switzerland', }, - } + { + 'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html', + 'md5': '9bb06503773c07ce83d3cbd793cebb91', + 'info_dict': { + 'id': '5745356', + 'ext': 'mp4', + 'duration': 33, + 'title': 'Londres cachée par un épais smog', + 'description': 'Un important voile de smog recouvre Londres depuis mercredi, provoqué par la pollution et du sable du Sahara.', + 'uploader': 'Le Journal en continu', + 'upload_date': '20140403', + 'timestamp': 1396537322, + 'thumbnail': 're:^https?://.*\.image' + }, + }, + { + 'url': 'http://www.rts.ch/audio/couleur3/programmes/la-belle-video-de-stephane-laurenceau/5706148-urban-hippie-de-damien-krisl-03-04-2014.html', + 'md5': 'dd8ef6a22dff163d063e2a52bc8adcae', + 'info_dict': { + 'id': '5706148', + 'ext': 'mp3', + 'duration': 123, + 'title': '"Urban Hippie", de Damien Krisl', + 'description': 'Des Hippies super glam.', + 'upload_date': '20140403', + 'timestamp': 1396551600, + }, + }, + ] def _real_extract(self, url): m = re.match(self._VALID_URL, url) video_id = m.group('id') - all_info = self._download_json( - 'http://www.rts.ch/a/%s.html?f=json/article' % video_id, video_id) - info = all_info['video']['JSONinfo'] + def download_json(internal_id): + return self._download_json( + 'http://www.rts.ch/a/%s.html?f=json/article' % internal_id, + video_id) + + all_info = download_json(video_id) + + # video_id extracted out of URL is not always a real id + if 'video' not in all_info and 'audio' not in all_info: + page = self._download_webpage(url, video_id) + internal_id = self._html_search_regex( + r'<(?:video|audio) data-id="([0-9]+)"', page, + 'internal video id') + all_info = download_json(internal_id) + + info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio'] upload_timestamp = parse_iso8601(info.get('broadcast_date')) - duration = parse_duration(info.get('duration')) + duration = info.get('duration') or info.get('cutout') or info.get('cutduration') + if isinstance(duration, compat_str): + duration = parse_duration(duration) + view_count = info.get('plays') thumbnail = unescapeHTML(info.get('preview_image_url')) + + def extract_bitrate(url): + return int_or_none(self._search_regex( + r'-([0-9]+)k\.', url, 'bitrate', default=None)) + formats = [{ 'format_id': fid, 'url': furl, - 'tbr': int_or_none(self._search_regex( - r'-([0-9]+)k\.', furl, 'bitrate', default=None)), + 'tbr': extract_bitrate(furl), } for fid, furl in info['streams'].items()] + + if 'media' in info: + formats.extend([{ + 'format_id': '%s-%sk' % (media['ext'], media['rate']), + 'url': 'http://download-video.rts.ch/%s' % media['url'], + 'tbr': media['rate'] or extract_bitrate(media['url']), + } for media in info['media'] if media.get('rate')]) + self._sort_formats(formats) return { @@ -57,6 +147,7 @@ class RTSIE(InfoExtractor): 'title': info['title'], 'description': info.get('intro'), 'duration': duration, + 'view_count': view_count, 'uploader': info.get('programName'), 'timestamp': upload_timestamp, 'thumbnail': thumbnail, diff --git a/youtube_dl/extractor/rtve.py b/youtube_dl/extractor/rtve.py new file mode 100644 index 000000000..77fd08dde --- /dev/null +++ b/youtube_dl/extractor/rtve.py @@ -0,0 +1,84 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re +import base64 + +from .common import InfoExtractor +from ..utils import ( + struct_unpack, +) + + +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 = { + 'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/', + 'md5': '18fcd45965bdd076efdb12cd7f6d7b9e', + '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 + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + info = self._download_json( + 'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id, + 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) + + return { + 'id': video_id, + 'title': info['title'], + 'url': video_url, + 'thumbnail': info['image'], + } diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index 4922dd764..f1ce66433 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -2,7 +2,6 @@ from __future__ import unicode_literals import re -import json import itertools from .common import InfoExtractor @@ -20,8 +19,9 @@ class RutubeIE(InfoExtractor): _TEST = { 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/', - 'file': '3eac3b4561676c17df9132a9a1e62e3e.mp4', 'info_dict': { + 'id': '3eac3b4561676c17df9132a9a1e62e3e', + 'ext': 'mp4', 'title': 'Раненный кенгуру забежал в аптеку', 'description': 'http://www.ntdtv.ru ', 'duration': 80, @@ -38,15 +38,15 @@ class RutubeIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - - api_response = self._download_webpage('http://rutube.ru/api/video/%s/?format=json' % video_id, - video_id, 'Downloading video JSON') - video = json.loads(api_response) - - api_response = self._download_webpage('http://rutube.ru/api/play/trackinfo/%s/?format=json' % video_id, - video_id, 'Downloading trackinfo JSON') - trackinfo = json.loads(api_response) - + + video = self._download_json( + 'http://rutube.ru/api/video/%s/?format=json' % video_id, + video_id, 'Downloading video JSON') + + trackinfo = self._download_json( + 'http://rutube.ru/api/play/trackinfo/%s/?format=json' % video_id, + video_id, 'Downloading trackinfo JSON') + # Some videos don't have the author field author = trackinfo.get('author') or {} m3u8_url = trackinfo['video_balancer'].get('m3u8') @@ -79,10 +79,9 @@ class RutubeChannelIE(InfoExtractor): def _extract_videos(self, channel_id, channel_title=None): entries = [] for pagenum in itertools.count(1): - api_response = self._download_webpage( + page = self._download_json( self._PAGE_TEMPLATE % (channel_id, pagenum), channel_id, 'Downloading page %s' % pagenum) - page = json.loads(api_response) results = page['results'] if not results: break @@ -108,10 +107,9 @@ class RutubeMovieIE(RutubeChannelIE): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) movie_id = mobj.group('id') - api_response = self._download_webpage( + movie = self._download_json( self._MOVIE_TEMPLATE % movie_id, movie_id, 'Downloading movie JSON') - movie = json.loads(api_response) movie_name = movie['name'] return self._extract_videos(movie_id, movie_name) diff --git a/youtube_dl/extractor/slideshare.py b/youtube_dl/extractor/slideshare.py index 9c62825cc..53c3c9220 100644 --- a/youtube_dl/extractor/slideshare.py +++ b/youtube_dl/extractor/slideshare.py @@ -39,7 +39,8 @@ class SlideshareIE(InfoExtractor): ext = info['jsplayer']['video_extension'] video_url = compat_urlparse.urljoin(bucket, doc + '-SD.' + ext) description = self._html_search_regex( - r'<p class="description.*?"[^>]*>(.*?)</p>', webpage, 'description') + r'<p\s+(?:style="[^"]*"\s+)?class="description.*?"[^>]*>(.*?)</p>', webpage, + 'description', fatal=False) return { '_type': 'video', diff --git a/youtube_dl/extractor/smotri.py b/youtube_dl/extractor/smotri.py index 540c55703..13e7e71cb 100644 --- a/youtube_dl/extractor/smotri.py +++ b/youtube_dl/extractor/smotri.py @@ -13,22 +13,24 @@ from ..utils import ( compat_urllib_request, ExtractorError, url_basename, + int_or_none, ) class SmotriIE(InfoExtractor): IE_DESC = 'Smotri.com' IE_NAME = 'smotri' - _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/video/view/\?id=(?P<videoid>v(?P<realvideoid>[0-9]+)[a-z0-9]{4}))' + _VALID_URL = r'^https?://(?:www\.)?(?:smotri\.com/video/view/\?id=|pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=)(?P<videoid>v(?P<realvideoid>[0-9]+)[a-z0-9]{4})' _NETRC_MACHINE = 'smotri' _TESTS = [ # real video id 2610366 { 'url': 'http://smotri.com/video/view/?id=v261036632ab', - 'file': 'v261036632ab.mp4', 'md5': '2a7b08249e6f5636557579c368040eb9', 'info_dict': { + 'id': 'v261036632ab', + 'ext': 'mp4', 'title': 'катастрофа с камер видеонаблюдения', 'uploader': 'rbc2008', 'uploader_id': 'rbc08', @@ -40,9 +42,10 @@ class SmotriIE(InfoExtractor): # real video id 57591 { 'url': 'http://smotri.com/video/view/?id=v57591cb20', - 'file': 'v57591cb20.flv', 'md5': '830266dfc21f077eac5afd1883091bcd', 'info_dict': { + 'id': 'v57591cb20', + 'ext': 'flv', 'title': 'test', 'uploader': 'Support Photofile@photofile', 'uploader_id': 'support-photofile', @@ -54,9 +57,10 @@ class SmotriIE(InfoExtractor): # video-password { 'url': 'http://smotri.com/video/view/?id=v1390466a13c', - 'file': 'v1390466a13c.mp4', 'md5': 'f6331cef33cad65a0815ee482a54440b', 'info_dict': { + 'id': 'v1390466a13c', + 'ext': 'mp4', 'title': 'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1', 'uploader': 'timoxa40', 'uploader_id': 'timoxa40', @@ -71,9 +75,10 @@ class SmotriIE(InfoExtractor): # age limit + video-password { 'url': 'http://smotri.com/video/view/?id=v15408898bcf', - 'file': 'v15408898bcf.flv', 'md5': '91e909c9f0521adf5ee86fbe073aad70', 'info_dict': { + 'id': 'v15408898bcf', + 'ext': 'flv', 'title': 'этот ролик не покажут по ТВ', 'uploader': 'zzxxx', 'uploader_id': 'ueggb', @@ -85,7 +90,22 @@ class SmotriIE(InfoExtractor): 'params': { 'videopassword': '333' } - } + }, + # swf player + { + 'url': 'http://pics.smotri.com/scrubber_custom8.swf?file=v9188090500', + 'md5': '4d47034979d9390d14acdf59c4935bc2', + 'info_dict': { + 'id': 'v9188090500', + 'ext': 'mp4', + 'title': 'Shakira - Don\'t Bother', + 'uploader': 'HannahL', + 'uploader_id': 'lisaha95', + 'upload_date': '20090331', + 'description': 'Shakira - Don\'t Bother, видео Shakira - Don\'t Bother', + 'thumbnail': 'http://frame8.loadup.ru/44/0b/918809.7.3.jpg', + }, + }, ] _SUCCESS = 0 @@ -93,6 +113,21 @@ class SmotriIE(InfoExtractor): _PASSWORD_DETECTED = 2 _VIDEO_NOT_FOUND = 3 + @classmethod + def _extract_url(cls, webpage): + mobj = re.search( + r'<embed[^>]src=(["\'])(?P<url>http://pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=v.+?\1)', + webpage) + if mobj is not None: + return mobj.group('url') + + mobj = re.search( + r'''(?x)<div\s+class="video_file">http://smotri\.com/video/download/file/[^<]+</div>\s* + <div\s+class="video_image">[^<]+</div>\s* + <div\s+class="video_id">(?P<id>[^<]+)</div>''', webpage) + if mobj is not None: + return 'http://smotri.com/video/view/?id=%s' % mobj.group('id') + def _search_meta(self, name, html, display_name=None): if display_name is None: display_name = name @@ -134,7 +169,7 @@ class SmotriIE(InfoExtractor): # Video JSON does not provide enough meta data # We will extract some from the video web page instead - video_page_url = 'http://' + mobj.group('url') + video_page_url = 'http://smotri.com/video/view/?id=%s' % video_id video_page = self._download_webpage(video_page_url, video_id, 'Downloading video page') # Warning if video is unavailable @@ -222,7 +257,7 @@ class SmotriIE(InfoExtractor): 'upload_date': video_upload_date, 'uploader_id': video_uploader_id, 'duration': video_duration, - 'view_count': video_view_count, + 'view_count': int_or_none(video_view_count), 'age_limit': 18 if adult_content else 0, 'video_page_url': video_page_url } diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py index 9dcffead0..dcdadd120 100644 --- a/youtube_dl/extractor/teamcoco.py +++ b/youtube_dl/extractor/teamcoco.py @@ -9,8 +9,18 @@ from ..utils import ( class TeamcocoIE(InfoExtractor): - _VALID_URL = r'http://teamcoco\.com/video/(?P<url_title>.*)' - _TEST = { + _VALID_URL = r'http://teamcoco\.com/video/(?P<video_id>[0-9]+)?/?(?P<display_id>.*)' + _TESTS = [ + { + 'url': 'http://teamcoco.com/video/80187/conan-becomes-a-mary-kay-beauty-consultant', + 'file': '80187.mp4', + 'md5': '3f7746aa0dc86de18df7539903d399ea', + 'info_dict': { + 'title': 'Conan Becomes A Mary Kay Beauty Consultant', + 'description': 'Mary Kay is perhaps the most trusted name in female beauty, so of course Conan is a natural choice to sell their products.' + } + }, + { 'url': 'http://teamcoco.com/video/louis-ck-interview-george-w-bush', 'file': '19705.mp4', 'md5': 'cde9ba0fa3506f5f017ce11ead928f9a', @@ -19,22 +29,23 @@ class TeamcocoIE(InfoExtractor): "title": "Louis C.K. Interview Pt. 1 11/3/11" } } + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError('Invalid URL: %s' % url) - url_title = mobj.group('url_title') - webpage = self._download_webpage(url, url_title) - - video_id = self._html_search_regex( - r'<article class="video" data-id="(\d+?)"', - webpage, 'video id') - self.report_extraction(video_id) + display_id = mobj.group('display_id') + webpage = self._download_webpage(url, display_id) + + video_id = mobj.group("video_id") + if not video_id: + video_id = self._html_search_regex( + r'<article class="video" data-id="(\d+?)"', + webpage, 'video id') data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id - data = self._download_xml(data_url, video_id, 'Downloading data webpage') + data = self._download_xml( + data_url, display_id, 'Downloading data webpage') qualities = ['500k', '480p', '1000k', '720p', '1080p'] formats = [] @@ -69,6 +80,7 @@ class TeamcocoIE(InfoExtractor): return { 'id': video_id, + 'display_id': display_id, 'formats': formats, 'title': self._og_search_title(webpage), 'thumbnail': self._og_search_thumbnail(webpage), diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index ad1a46c33..be7a0f866 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -18,12 +18,14 @@ class TEDIE(SubtitlesInfoExtractor): (?P<type_playlist>playlists(?:/\d+)?) # We have a playlist | ((?P<type_talk>talks)) # We have a simple talk + | + (?P<type_watch>watch)/[^/]+/[^/]+ ) (/lang/(.*?))? # The url may contain the language - /(?P<name>\w+) # Here goes the name and then ".html" + /(?P<name>[\w-]+) # Here goes the name and then ".html" .*)$ ''' - _TEST = { + _TESTS = [{ 'url': 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html', 'md5': '4ea1dada91e4174b53dac2bb8ace429d', 'info_dict': { @@ -35,13 +37,24 @@ class TEDIE(SubtitlesInfoExtractor): 'consciousness, but that half the time our brains are ' 'actively fooling us.'), 'uploader': 'Dan Dennett', + 'width': 854, } - } + }, { + 'url': 'http://www.ted.com/watch/ted-institute/ted-bcg/vishal-sikka-the-beauty-and-power-of-algorithms', + 'md5': '226f4fb9c62380d11b7995efa4c87994', + 'info_dict': { + 'id': 'vishal-sikka-the-beauty-and-power-of-algorithms', + 'ext': 'mp4', + 'title': 'Vishal Sikka: The beauty and power of algorithms', + 'thumbnail': 're:^https?://.+\.jpg', + 'description': 'Adaptive, intelligent, and consistent, algorithms are emerging as the ultimate app for everything from matching consumers to products to assessing medical diagnoses. Vishal Sikka shares his appreciation for the algorithm, charting both its inherent beauty and its growing power.', + } + }] - _FORMATS_PREFERENCE = { - 'low': 1, - 'medium': 2, - 'high': 3, + _NATIVE_FORMATS = { + 'low': {'preference': 1, 'width': 320, 'height': 180}, + 'medium': {'preference': 2, 'width': 512, 'height': 288}, + 'high': {'preference': 3, 'width': 854, 'height': 480}, } def _extract_info(self, webpage): @@ -57,6 +70,8 @@ class TEDIE(SubtitlesInfoExtractor): name = m.group('name') if m.group('type_talk'): return self._talk_info(url, name) + elif m.group('type_watch'): + return self._watch_info(url, name) else: return self._playlist_videos_info(url, name) @@ -84,12 +99,14 @@ class TEDIE(SubtitlesInfoExtractor): talk_info = self._extract_info(webpage)['talks'][0] formats = [{ - 'ext': 'mp4', 'url': format_url, 'format_id': format_id, 'format': format_id, - 'preference': self._FORMATS_PREFERENCE.get(format_id, -1), } for (format_id, format_url) in talk_info['nativeDownloads'].items()] + for f in formats: + finfo = self._NATIVE_FORMATS.get(f['format_id']) + if finfo: + f.update(finfo) self._sort_formats(formats) video_id = compat_str(talk_info['id']) @@ -123,3 +140,26 @@ class TEDIE(SubtitlesInfoExtractor): else: self._downloader.report_warning(u'video doesn\'t have subtitles') return {} + + def _watch_info(self, url, name): + webpage = self._download_webpage(url, name) + + config_json = self._html_search_regex( + r"data-config='([^']+)", webpage, 'config') + config = json.loads(config_json) + video_url = config['video']['url'] + thumbnail = config.get('image', {}).get('url') + + title = self._html_search_regex( + r"(?s)<h1(?:\s+class='[^']+')?>(.+?)</h1>", webpage, 'title') + description = self._html_search_regex( + r'(?s)<h4 class="[^"]+" id="h3--about-this-talk">.*?</h4>(.*?)</div>', + webpage, 'description', fatal=False) + + return { + 'id': name, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'description': description, + } diff --git a/youtube_dl/extractor/tf1.py b/youtube_dl/extractor/tf1.py index 2c5c88be8..fdae17b1b 100644 --- a/youtube_dl/extractor/tf1.py +++ b/youtube_dl/extractor/tf1.py @@ -1,33 +1,37 @@ # coding: utf-8 +from __future__ import unicode_literals -import json import re from .common import InfoExtractor + class TF1IE(InfoExtractor): """TF1 uses the wat.tv player.""" - _VALID_URL = r'http://videos\.tf1\.fr/.*-(.*?)\.html' + _VALID_URL = r'http://videos\.tf1\.fr/.*-(?P<id>.*?)\.html' _TEST = { - u'url': u'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html', - u'file': u'10635995.mp4', - u'md5': u'2e378cc28b9957607d5e88f274e637d8', - u'info_dict': { - u'title': u'Citroën Grand C4 Picasso 2013 : présentation officielle', - u'description': u'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.', + 'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html', + 'info_dict': { + 'id': '10635995', + 'ext': 'mp4', + 'title': 'Citroën Grand C4 Picasso 2013 : présentation officielle', + 'description': 'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.', + }, + 'params': { + # Sometimes wat serves the whole file with the --test option + 'skip_download': True, }, - u'skip': u'Sometimes wat serves the whole file with the --test option', } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - id = mobj.group(1) - webpage = self._download_webpage(url, id) - embed_url = self._html_search_regex(r'"(https://www.wat.tv/embedframe/.*?)"', - webpage, 'embed url') - embed_page = self._download_webpage(embed_url, id, u'Downloading embed player page') + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + embed_url = self._html_search_regex( + r'"(https://www.wat.tv/embedframe/.*?)"', webpage, 'embed url') + embed_page = self._download_webpage(embed_url, video_id, + 'Downloading embed player page') wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id') - wat_info = self._download_webpage('http://www.wat.tv/interface/contentv3/%s' % wat_id, id, u'Downloading Wat info') - wat_info = json.loads(wat_info)['media'] - wat_url = wat_info['url'] - return self.url_result(wat_url, 'Wat') + wat_info = self._download_json( + 'http://www.wat.tv/interface/contentv3/%s' % wat_id, video_id) + return self.url_result(wat_info['media']['url'], 'Wat') diff --git a/youtube_dl/extractor/urort.py b/youtube_dl/extractor/urort.py new file mode 100644 index 000000000..5d06fcc9e --- /dev/null +++ b/youtube_dl/extractor/urort.py @@ -0,0 +1,61 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + unified_strdate, +) + + +class UrortIE(InfoExtractor): + IE_DESC = 'NRK P3 Urørt' + _VALID_URL = r'https?://(?:www\.)?urort\.p3\.no/#!/Band/(?P<id>[^/]+)$' + + _TEST = { + 'url': 'https://urort.p3.no/#!/Band/Gerilja', + 'md5': '5ed31a924be8a05e47812678a86e127b', + 'info_dict': { + 'id': '33124-4', + 'ext': 'mp3', + 'title': 'The Bomb', + 'thumbnail': 're:^https?://.+\.jpg', + 'like_count': int, + 'uploader': 'Gerilja', + 'uploader_id': 'Gerilja', + 'upload_date': '20100323', + }, + 'params': { + 'matchtitle': '^The Bomb$', # To test, we want just one video + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + playlist_id = mobj.group('id') + + fstr = compat_urllib_parse.quote("InternalBandUrl eq '%s'" % playlist_id) + json_url = 'http://urort.p3.no/breeze/urort/TrackDtos?$filter=' + fstr + songs = self._download_json(json_url, playlist_id) + print(songs[0]) + + entries = [{ + 'id': '%d-%s' % (s['BandId'], s['$id']), + 'title': s['Title'], + 'url': s['TrackUrl'], + 'ext': 'mp3', + 'uploader_id': playlist_id, + 'uploader': s.get('BandName', playlist_id), + 'like_count': s.get('LikeCount'), + 'thumbnail': 'http://urort.p3.no/cloud/images/%s' % s['Image'], + 'upload_date': unified_strdate(s.get('Released')), + } for s in songs] + + return { + '_type': 'playlist', + 'id': playlist_id, + 'title': playlist_id, + 'entries': entries, + } diff --git a/youtube_dl/extractor/ustream.py b/youtube_dl/extractor/ustream.py index 7fa2b9e15..e4bb3b949 100644 --- a/youtube_dl/extractor/ustream.py +++ b/youtube_dl/extractor/ustream.py @@ -11,7 +11,7 @@ from ..utils import ( class UstreamIE(InfoExtractor): - _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P<videoID>\d+)' + _VALID_URL = r'https?://www\.ustream\.tv/(?P<type>recorded|embed)/(?P<videoID>\d+)' IE_NAME = 'ustream' _TEST = { 'url': 'http://www.ustream.tv/recorded/20274954', @@ -25,6 +25,13 @@ class UstreamIE(InfoExtractor): def _real_extract(self, url): m = re.match(self._VALID_URL, url) + if m.group('type') == 'embed': + video_id = m.group('videoID') + webpage = self._download_webpage(url, video_id) + desktop_video_id = self._html_search_regex(r'ContentVideoIds=\["([^"]*?)"\]', webpage, 'desktop_video_id') + desktop_url = 'http://www.ustream.tv/recorded/' + desktop_video_id + return self.url_result(desktop_url, 'Ustream') + video_id = m.group('videoID') video_url = 'http://tcdn.ustream.tv/video/%s' % video_id diff --git a/youtube_dl/extractor/videoweed.py b/youtube_dl/extractor/videoweed.py new file mode 100644 index 000000000..4a08ddd43 --- /dev/null +++ b/youtube_dl/extractor/videoweed.py @@ -0,0 +1,26 @@ +from __future__ import unicode_literals + +from .novamov import NovaMovIE + + +class VideoWeedIE(NovaMovIE): + IE_NAME = 'videoweed' + IE_DESC = 'VideoWeed' + + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'videoweed\.(?:es|com)'} + + _HOST = 'www.videoweed.es' + + _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' + _TITLE_REGEX = r'<h1 class="text_shadow">([^<]+)</h1>' + + _TEST = { + 'url': 'http://www.videoweed.es/file/b42178afbea14', + 'md5': 'abd31a2132947262c50429e1d16c1bfd', + 'info_dict': { + 'id': 'b42178afbea14', + 'ext': 'flv', + 'title': 'optical illusion dissapeared image magic illusion', + 'description': '' + }, + }
\ No newline at end of file diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index 3b3bec92f..8b1432fec 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -16,7 +16,7 @@ from ..utils import ( class VKIE(InfoExtractor): IE_NAME = 'vk.com' - _VALID_URL = r'https?://vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>\d+).*?\bid=(?P<id>\d+)|(?:videos.*?\?.*?z=)?video(?P<videoid>.*?)(?:\?|%2F|$))' + _VALID_URL = r'https?://vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:videos.*?\?.*?z=)?video(?P<videoid>.*?)(?:\?|%2F|$))' _NETRC_MACHINE = 'vk' _TESTS = [ diff --git a/youtube_dl/extractor/wat.py b/youtube_dl/extractor/wat.py index 4fab6c6e8..a584e0896 100644 --- a/youtube_dl/extractor/wat.py +++ b/youtube_dl/extractor/wat.py @@ -1,37 +1,37 @@ # coding: utf-8 +from __future__ import unicode_literals -import json import re from .common import InfoExtractor - 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/.*-(?P<shortID>.*?)_.*?\.html' IE_NAME = 'wat.tv' _TEST = { - u'url': u'http://www.wat.tv/video/world-war-philadelphia-vost-6bv55_2fjr7_.html', - u'file': u'10631273.mp4', - u'md5': u'd8b2231e1e333acd12aad94b80937e19', - u'info_dict': { - u'title': u'World War Z - Philadelphia VOST', - u'description': u'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', + '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', + }, + 'params': { + # Sometimes wat serves the whole file with the --test option + 'skip_download': True, }, - u'skip': u'Sometimes wat serves the whole file with the --test option', } - + def download_video_info(self, real_id): # 'contentv4' is used in the website, but it also returns the related # videos, we don't need them - info = self._download_webpage('http://www.wat.tv/interface/contentv3/' + real_id, real_id, 'Downloading video info') - info = json.loads(info) + info = self._download_json('http://www.wat.tv/interface/contentv3/' + real_id, real_id) return info['media'] - def _real_extract(self, url): def real_id_for_chapter(chapter): return chapter['tc_start'].split('-')[0] @@ -56,17 +56,17 @@ class WatIE(InfoExtractor): entries = [self.url_result(chapter_url) for chapter_url in chapter_urls] return self.playlist_result(entries, real_id, video_info['title']) + upload_date = None + if 'date_diffusion' in first_chapter: + 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 - info = {'id': real_id, - 'url': 'http://wat.tv/get/android5/%s.mp4' % real_id, - 'ext': 'mp4', - 'title': first_chapter['title'], - 'thumbnail': first_chapter['preview'], - 'description': first_chapter['description'], - 'view_count': video_info['views'], - } - if 'date_diffusion' in first_chapter: - info['upload_date'] = unified_strdate(first_chapter['date_diffusion']) - - return info + return { + 'id': real_id, + 'url': 'http://wat.tv/get/android5/%s.mp4' % real_id, + 'title': first_chapter['title'], + 'thumbnail': first_chapter['preview'], + 'description': first_chapter['description'], + 'view_count': video_info['views'], + 'upload_date': upload_date, + } diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py index 500b9146f..63691aa67 100644 --- a/youtube_dl/extractor/wdr.py +++ b/youtube_dl/extractor/wdr.py @@ -4,9 +4,10 @@ import re from .common import InfoExtractor from ..utils import ( - unified_strdate, + compat_parse_qs, compat_urlparse, determine_ext, + unified_strdate, ) @@ -111,4 +112,85 @@ class WDRIE(InfoExtractor): 'description': description, 'thumbnail': thumbnail, 'upload_date': upload_date, - }
\ No newline at end of file + } + + +class WDRMausIE(InfoExtractor): + _VALID_URL = 'http://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P<id>[^/?#]+)(?:/index\.php5|(?<!index)\.php5|/(?:$|[?#]))' + IE_DESC = 'Sendung mit der Maus' + _TESTS = [{ + 'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5', + 'info_dict': { + 'id': 'aktuelle-sendung', + 'ext': 'mp4', + 'thumbnail': 're:^http://.+\.jpg', + 'upload_date': 're:^[0-9]{8}$', + 'title': 're:^[0-9.]{10} - Aktuelle Sendung$', + } + }, { + 'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/40_jahre_maus.php5', + 'md5': '3b1227ca3ed28d73ec5737c65743b2a3', + 'info_dict': { + 'id': '40_jahre_maus', + 'ext': 'mp4', + 'thumbnail': 're:^http://.+\.jpg', + 'upload_date': '20131007', + 'title': '12.03.2011 - 40 Jahre Maus', + } + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + param_code = self._html_search_regex( + r'<a href="\?startVideo=1&([^"]+)"', webpage, 'parameters') + + title_date = self._search_regex( + r'<div class="sendedatum"><p>Sendedatum:\s*([0-9\.]+)</p>', + webpage, 'air date') + title_str = self._html_search_regex( + r'<h1>(.*?)</h1>', webpage, 'title') + title = '%s - %s' % (title_date, title_str) + upload_date = unified_strdate( + self._html_search_meta('dc.date', webpage)) + + fields = compat_parse_qs(param_code) + video_url = fields['firstVideo'][0] + thumbnail = compat_urlparse.urljoin(url, fields['startPicture'][0]) + + formats = [{ + 'format_id': 'rtmp', + 'url': video_url, + }] + + jscode = self._download_webpage( + 'http://www.wdrmaus.de/codebase/js/extended-medien.min.js', + video_id, fatal=False, + note='Downloading URL translation table', + errnote='Could not download URL translation table') + if jscode: + for m in re.finditer( + r"stream:\s*'dslSrc=(?P<stream>[^']+)',\s*download:\s*'(?P<dl>[^']+)'\s*\}", + jscode): + if video_url.startswith(m.group('stream')): + http_url = video_url.replace( + m.group('stream'), m.group('dl')) + formats.append({ + 'format_id': 'http', + 'url': http_url, + }) + break + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + } + +# TODO test _1
\ No newline at end of file diff --git a/youtube_dl/extractor/weibo.py b/youtube_dl/extractor/weibo.py index fa784ab99..b24297a40 100644 --- a/youtube_dl/extractor/weibo.py +++ b/youtube_dl/extractor/weibo.py @@ -1,10 +1,11 @@ # coding: utf-8 +from __future__ import unicode_literals import re -import json from .common import InfoExtractor + class WeiboIE(InfoExtractor): """ The videos in Weibo come from different sites, this IE just finds the link @@ -13,16 +14,16 @@ class WeiboIE(InfoExtractor): _VALID_URL = r'https?://video\.weibo\.com/v/weishipin/t_(?P<id>.+?)\.htm' _TEST = { - u'add_ie': ['Sina'], - u'url': u'http://video.weibo.com/v/weishipin/t_zjUw2kZ.htm', - u'file': u'98322879.flv', - u'info_dict': { - u'title': u'魔声耳机最新广告“All Eyes On Us”', + 'url': 'http://video.weibo.com/v/weishipin/t_zjUw2kZ.htm', + 'info_dict': { + 'id': '98322879', + 'ext': 'flv', + 'title': '魔声耳机最新广告“All Eyes On Us”', }, - u'note': u'Sina video', - u'params': { - u'skip_download': True, + 'params': { + 'skip_download': True, }, + 'add_ie': ['Sina'], } # Additional example videos from different sites @@ -33,17 +34,16 @@ class WeiboIE(InfoExtractor): mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE) video_id = mobj.group('id') info_url = 'http://video.weibo.com/?s=v&a=play_list&format=json&mix_video_id=t_%s' % video_id - info_page = self._download_webpage(info_url, video_id) - info = json.loads(info_page) + info = self._download_json(info_url, video_id) videos_urls = map(lambda v: v['play_page_url'], info['result']['data']) - #Prefer sina video since they have thumbnails - videos_urls = sorted(videos_urls, key=lambda u: u'video.sina.com' in u) + # Prefer sina video since they have thumbnails + videos_urls = sorted(videos_urls, key=lambda u: 'video.sina.com' in u) player_url = videos_urls[-1] - m_sina = re.match(r'https?://video.sina.com.cn/v/b/(\d+)-\d+.html', player_url) + m_sina = re.match(r'https?://video\.sina\.com\.cn/v/b/(\d+)-\d+\.html', + player_url) if m_sina is not None: self.to_screen('Sina video detected') sina_id = m_sina.group(1) player_url = 'http://you.video.sina.com.cn/swf/quotePlayer.swf?vid=%s' % sina_id return self.url_result(player_url) - diff --git a/youtube_dl/extractor/wimp.py b/youtube_dl/extractor/wimp.py index 79fd53e0c..c27dda944 100644 --- a/youtube_dl/extractor/wimp.py +++ b/youtube_dl/extractor/wimp.py @@ -3,11 +3,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from .youtube import YoutubeIE class WimpIE(InfoExtractor): _VALID_URL = r'http://(?:www\.)?wimp\.com/([^/]+)/' - _TEST = { + _TESTS = [{ 'url': 'http://www.wimp.com/maruexhausted/', 'md5': 'f1acced123ecb28d9bb79f2479f2b6a1', 'info_dict': { @@ -16,7 +17,20 @@ class WimpIE(InfoExtractor): 'title': 'Maru is exhausted.', 'description': 'md5:57e099e857c0a4ea312542b684a869b8', } - } + }, { + # youtube video + 'url': 'http://www.wimp.com/clowncar/', + 'info_dict': { + 'id': 'cG4CEr2aiSg', + 'ext': 'mp4', + 'title': 'Basset hound clown car...incredible!', + 'description': 'md5:8d228485e0719898c017203f900b3a35', + 'uploader': 'Gretchen Hoey', + 'uploader_id': 'gretchenandjeff1', + 'upload_date': '20140303', + }, + 'add_ie': ['Youtube'], + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -24,6 +38,13 @@ class WimpIE(InfoExtractor): webpage = self._download_webpage(url, video_id) video_url = self._search_regex( r's1\.addVariable\("file",\s*"([^"]+)"\);', webpage, 'video URL') + if YoutubeIE.suitable(video_url): + self.to_screen('Found YouTube video') + return { + '_type': 'url', + 'url': video_url, + 'ie_key': YoutubeIE.ie_key(), + } return { 'id': video_id, @@ -31,4 +52,4 @@ class WimpIE(InfoExtractor): 'title': self._og_search_title(webpage), 'thumbnail': self._og_search_thumbnail(webpage), 'description': self._og_search_description(webpage), - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index d92d14f71..e2cf1ae56 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -15,22 +15,24 @@ from ..utils import ( class YahooIE(InfoExtractor): IE_DESC = 'Yahoo screen' - _VALID_URL = r'http://screen\.yahoo\.com/.*?-(?P<id>\d*?)\.html' + _VALID_URL = r'https?://screen\.yahoo\.com/.*?-(?P<id>[0-9]+)(?:-[a-z]+)?\.html' _TESTS = [ { 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', - 'file': '214727115.mp4', 'md5': '4962b075c08be8690a922ee026d05e69', 'info_dict': { + 'id': '214727115', + 'ext': 'mp4', 'title': 'Julian Smith & Travis Legg Watch Julian Smith', 'description': 'Julian and Travis watch Julian Smith', }, }, { 'url': 'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html', - 'file': '103000935.mp4', 'md5': 'd6e6fc6e1313c608f316ddad7b82b306', 'info_dict': { + 'id': '103000935', + 'ext': 'mp4', 'title': 'Codefellas - The Cougar Lies with Spanish Moss', 'description': 'Agent Topple\'s mustache does its dirty work, and Nicole brokers a deal for peace. But why is the NSA collecting millions of Instagram brunch photos? And if your waffles have nothing to hide, what are they so worried about?', }, @@ -60,10 +62,9 @@ class YahooIE(InfoExtractor): 'env': 'prod', 'format': 'json', }) - query_result_json = self._download_webpage( + query_result = self._download_json( 'http://video.query.yahoo.com/v1/public/yql?' + data, video_id, 'Downloading video info') - query_result = json.loads(query_result_json) info = query_result['query']['results']['mediaObj'][0] meta = info['meta'] @@ -86,7 +87,6 @@ class YahooIE(InfoExtractor): else: format_url = compat_urlparse.urljoin(host, path) format_info['url'] = format_url - formats.append(format_info) self._sort_formats(formats) @@ -134,27 +134,25 @@ class YahooSearchIE(SearchInfoExtractor): def _get_n_results(self, query, n): """Get a specified number of results for a query""" - - res = { - '_type': 'playlist', - 'id': query, - 'entries': [] - } - for pagenum in itertools.count(0): + entries = [] + for pagenum in itertools.count(0): result_url = 'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30) - webpage = self._download_webpage(result_url, query, - note='Downloading results page '+str(pagenum+1)) - info = json.loads(webpage) + info = self._download_json(result_url, query, + note='Downloading results page '+str(pagenum+1)) m = info['m'] results = info['results'] for (i, r) in enumerate(results): - if (pagenum * 30) +i >= n: + if (pagenum * 30) + i >= n: break mobj = re.search(r'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r) e = self.url_result('http://' + mobj.group('url'), 'Yahoo') - res['entries'].append(e) - if (pagenum * 30 +i >= n) or (m['last'] >= (m['total'] -1)): + entries.append(e) + if (pagenum * 30 + i >= n) or (m['last'] >= (m['total'] - 1)): break - return res + return { + '_type': 'playlist', + 'id': query, + 'entries': entries, + } diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 3a3a5a39e..334a61833 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -7,13 +7,13 @@ import itertools import json import os.path import re -import string import struct import traceback import zlib from .common import InfoExtractor, SearchInfoExtractor from .subtitles import SubtitlesInfoExtractor +from ..jsinterp import JSInterpreter from ..utils import ( compat_chr, compat_parse_qs, @@ -438,113 +438,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): def _parse_sig_js(self, jscode): funcname = self._search_regex( r'signature=([a-zA-Z]+)', jscode, - u'Initial JS player signature function name') - - functions = {} - - def argidx(varname): - return string.lowercase.index(varname) - - def interpret_statement(stmt, local_vars, allow_recursion=20): - if allow_recursion < 0: - raise ExtractorError(u'Recursion limit reached') - - if stmt.startswith(u'var '): - stmt = stmt[len(u'var '):] - ass_m = re.match(r'^(?P<out>[a-z]+)(?:\[(?P<index>[^\]]+)\])?' + - r'=(?P<expr>.*)$', stmt) - if ass_m: - if ass_m.groupdict().get('index'): - def assign(val): - lvar = local_vars[ass_m.group('out')] - idx = interpret_expression(ass_m.group('index'), - local_vars, allow_recursion) - assert isinstance(idx, int) - lvar[idx] = val - return val - expr = ass_m.group('expr') - else: - def assign(val): - local_vars[ass_m.group('out')] = val - return val - expr = ass_m.group('expr') - elif stmt.startswith(u'return '): - assign = lambda v: v - expr = stmt[len(u'return '):] - else: - raise ExtractorError( - u'Cannot determine left side of statement in %r' % stmt) - - v = interpret_expression(expr, local_vars, allow_recursion) - return assign(v) - - def interpret_expression(expr, local_vars, allow_recursion): - if expr.isdigit(): - return int(expr) - - if expr.isalpha(): - return local_vars[expr] - - m = re.match(r'^(?P<in>[a-z]+)\.(?P<member>.*)$', expr) - if m: - member = m.group('member') - val = local_vars[m.group('in')] - if member == 'split("")': - return list(val) - if member == 'join("")': - return u''.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 = interpret_expression( - slice_m.group('idx'), local_vars, allow_recursion-1) - return val[idx:] - - m = re.match( - r'^(?P<in>[a-z]+)\[(?P<idx>.+)\]$', expr) - if m: - val = local_vars[m.group('in')] - idx = interpret_expression(m.group('idx'), local_vars, - allow_recursion-1) - return val[idx] - - m = re.match(r'^(?P<a>.+?)(?P<op>[%])(?P<b>.+?)$', expr) - if m: - a = interpret_expression(m.group('a'), - local_vars, allow_recursion) - b = interpret_expression(m.group('b'), - local_vars, allow_recursion) - return a % b - - m = re.match( - r'^(?P<func>[a-zA-Z$]+)\((?P<args>[a-z0-9,]+)\)$', expr) - if m: - fname = m.group('func') - if fname not in functions: - functions[fname] = extract_function(fname) - argvals = [int(v) if v.isdigit() else local_vars[v] - for v in m.group('args').split(',')] - return functions[fname](argvals) - raise ExtractorError(u'Unsupported JS expression %r' % expr) - - def extract_function(funcname): - func_m = re.search( - r'function ' + re.escape(funcname) + - r'\((?P<args>[a-z,]+)\){(?P<code>[^}]+)}', - jscode) - argnames = func_m.group('args').split(',') - - def resf(args): - local_vars = dict(zip(argnames, args)) - for stmt in func_m.group('code').split(';'): - res = interpret_statement(stmt, local_vars) - return res - return resf - - initial_function = extract_function(funcname) + u'Initial JS player signature function name') + + jsi = JSInterpreter(jscode) + initial_function = jsi.extract_function(funcname) return lambda s: initial_function([s]) def _parse_sig_swf(self, file_contents): @@ -1549,12 +1446,15 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): break more = self._download_json( - 'https://youtube.com/%s' % mobj.group('more'), playlist_id, 'Downloading page #%s' % page_num) + 'https://youtube.com/%s' % mobj.group('more'), playlist_id, + 'Downloading page #%s' % page_num, + transform_source=uppercase_escape) content_html = more['content_html'] more_widget_html = more['load_more_widget_html'] playlist_title = self._html_search_regex( - r'<h1 class="pl-header-title">\s*(.*?)\s*</h1>', page, u'title') + r'(?s)<h1 class="pl-header-title[^"]*">\s*(.*?)\s*</h1>', + page, u'title') url_results = self._ids_to_results(ids) return self.playlist_result(url_results, playlist_id, playlist_title) @@ -1712,7 +1612,7 @@ class YoutubeUserIE(InfoExtractor): class YoutubeSearchIE(SearchInfoExtractor): IE_DESC = u'YouTube.com searches' - _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc' + _API_URL = u'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc' _MAX_RESULTS = 1000 IE_NAME = u'youtube:search' _SEARCH_KEY = 'ytsearch' @@ -1723,9 +1623,12 @@ class YoutubeSearchIE(SearchInfoExtractor): video_ids = [] pagenum = 0 limit = n + PAGE_SIZE = 50 - while (50 * pagenum) < limit: - result_url = self._API_URL % (compat_urllib_parse.quote_plus(query), (50*pagenum)+1) + while (PAGE_SIZE * pagenum) < limit: + result_url = self._API_URL % ( + compat_urllib_parse.quote_plus(query.encode('utf-8')), + (PAGE_SIZE * pagenum) + 1) data_json = self._download_webpage( result_url, video_id=u'query "%s"' % query, note=u'Downloading page %s' % (pagenum + 1), @@ -1836,11 +1739,10 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): feed_entries = [] paging = 0 for i in itertools.count(1): - info = self._download_webpage(self._FEED_TEMPLATE % paging, + info = self._download_json(self._FEED_TEMPLATE % paging, u'%s feed' % self._FEED_NAME, u'Downloading page %s' % i) - info = json.loads(info) - feed_html = info['feed_html'] + feed_html = info.get('feed_html') or info.get('content_html') m_ids = re.finditer(r'"/watch\?v=(.*?)["&]', feed_html) ids = orderedSet(m.group(1) for m in m_ids) feed_entries.extend( @@ -1852,7 +1754,7 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): 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)' + 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' diff --git a/youtube_dl/jsinterp.py b/youtube_dl/jsinterp.py new file mode 100644 index 000000000..449482d3c --- /dev/null +++ b/youtube_dl/jsinterp.py @@ -0,0 +1,116 @@ +from __future__ import unicode_literals + +import re + +from .utils import ( + ExtractorError, +) + + +class JSInterpreter(object): + def __init__(self, code): + self.code = code + self._functions = {} + + def interpret_statement(self, stmt, local_vars, allow_recursion=20): + if allow_recursion < 0: + raise ExtractorError('Recursion limit reached') + + if stmt.startswith('var '): + stmt = stmt[len('var '):] + ass_m = re.match(r'^(?P<out>[a-z]+)(?:\[(?P<index>[^\]]+)\])?' + + r'=(?P<expr>.*)$', stmt) + if ass_m: + if ass_m.groupdict().get('index'): + def assign(val): + lvar = local_vars[ass_m.group('out')] + idx = self.interpret_expression( + ass_m.group('index'), local_vars, allow_recursion) + assert isinstance(idx, int) + lvar[idx] = val + return val + expr = ass_m.group('expr') + else: + def assign(val): + local_vars[ass_m.group('out')] = val + return val + expr = ass_m.group('expr') + elif stmt.startswith('return '): + assign = lambda v: v + expr = stmt[len('return '):] + else: + raise ExtractorError( + 'Cannot determine left side of statement in %r' % stmt) + + v = self.interpret_expression(expr, local_vars, allow_recursion) + return assign(v) + + def interpret_expression(self, expr, local_vars, allow_recursion): + if expr.isdigit(): + return int(expr) + + if expr.isalpha(): + return local_vars[expr] + + m = re.match(r'^(?P<in>[a-z]+)\.(?P<member>.*)$', expr) + if m: + member = m.group('member') + val = local_vars[m.group('in')] + if member == 'split("")': + return list(val) + if member == 'join("")': + return u''.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:] + + m = re.match( + r'^(?P<in>[a-z]+)\[(?P<idx>.+)\]$', expr) + if m: + val = local_vars[m.group('in')] + idx = self.interpret_expression( + m.group('idx'), local_vars, allow_recursion - 1) + return val[idx] + + m = re.match(r'^(?P<a>.+?)(?P<op>[%])(?P<b>.+?)$', expr) + if m: + a = self.interpret_expression( + m.group('a'), local_vars, allow_recursion) + b = self.interpret_expression( + m.group('b'), local_vars, allow_recursion) + return a % b + + m = re.match( + r'^(?P<func>[a-zA-Z$]+)\((?P<args>[a-z0-9,]+)\)$', expr) + if m: + fname = m.group('func') + 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) + + def extract_function(self, funcname): + func_m = re.search( + (r'(?:function %s|%s\s*=\s*function)' % ( + re.escape(funcname), re.escape(funcname))) + + r'\((?P<args>[a-z,]+)\){(?P<code>[^}]+)}', + self.code) + if func_m is None: + raise ExtractorError('Could not find JS function %r' % funcname) + argnames = func_m.group('args').split(',') + + def resf(args): + local_vars = dict(zip(argnames, args)) + for stmt in func_m.group('code').split(';'): + res = self.interpret_statement(stmt, local_vars) + return res + return resf + diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index d5b71b96f..602e370f4 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -54,7 +54,7 @@ class FFmpegPostProcessor(PostProcessor): if self._downloader.params.get('verbose', False): self._downloader.to_screen(u'[debug] ffmpeg command line: %s' % shell_quote(cmd)) p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE) - stdout,stderr = p.communicate() + stdout, stderr = p.communicate() if p.returncode != 0: stderr = stderr.decode('utf-8', 'replace') msg = stderr.strip().split('\n')[-1] diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 29c9b1a4c..9c9320934 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -2,6 +2,7 @@ # -*- coding: utf-8 -*- import calendar +import codecs import contextlib import ctypes import datetime @@ -539,7 +540,6 @@ def encodeFilename(s, for_subprocess=False): encoding = 'utf-8' return s.encode(encoding, 'ignore') - def decodeOption(optval): if optval is None: return optval @@ -910,25 +910,84 @@ def platform_name(): return res -def write_string(s, out=None): +def _windows_write_string(s, out): + """ Returns True if the string was written using special methods, + False if it has yet to be written out.""" + # Adapted from http://stackoverflow.com/a/3259271/35070 + + import ctypes + import ctypes.wintypes + + WIN_OUTPUT_IDS = { + 1: -11, + 2: -12, + } + + def ucs2_len(s): + return sum((2 if ord(c) > 0xffff else 1) for c in s) + + fileno = out.fileno() + if fileno not in WIN_OUTPUT_IDS: + return False + + GetStdHandle = ctypes.WINFUNCTYPE( + ctypes.wintypes.HANDLE, ctypes.wintypes.DWORD)( + ("GetStdHandle", ctypes.windll.kernel32)) + h = GetStdHandle(WIN_OUTPUT_IDS[fileno]) + + WriteConsoleW = ctypes.WINFUNCTYPE( + ctypes.wintypes.BOOL, ctypes.wintypes.HANDLE, ctypes.wintypes.LPWSTR, + ctypes.wintypes.DWORD, ctypes.POINTER(ctypes.wintypes.DWORD), + ctypes.wintypes.LPVOID)(("WriteConsoleW", ctypes.windll.kernel32)) + written = ctypes.wintypes.DWORD(0) + + GetFileType = ctypes.WINFUNCTYPE(ctypes.wintypes.DWORD, ctypes.wintypes.DWORD)(("GetFileType", ctypes.windll.kernel32)) + FILE_TYPE_CHAR = 0x0002 + FILE_TYPE_REMOTE = 0x8000 + GetConsoleMode = ctypes.WINFUNCTYPE( + ctypes.wintypes.BOOL, ctypes.wintypes.HANDLE, + ctypes.POINTER(ctypes.wintypes.DWORD))( + ("GetConsoleMode", ctypes.windll.kernel32)) + INVALID_HANDLE_VALUE = ctypes.wintypes.DWORD(-1).value + + def not_a_console(handle): + if handle == INVALID_HANDLE_VALUE or handle is None: + return True + return ((GetFileType(handle) & ~FILE_TYPE_REMOTE) != FILE_TYPE_CHAR + or GetConsoleMode(handle, ctypes.byref(ctypes.wintypes.DWORD())) == 0) + + if not_a_console(h): + return False + + remaining = ucs2_len(s) + while remaining > 0: + ret = WriteConsoleW( + h, s, min(remaining, 1024), ctypes.byref(written), None) + if ret == 0: + raise OSError('Failed to write string') + remaining -= written.value + return True + + +def write_string(s, out=None, encoding=None): if out is None: out = sys.stderr assert type(s) == compat_str + if sys.platform == 'win32' and encoding is None and hasattr(out, 'fileno'): + if _windows_write_string(s, out): + return + if ('b' in getattr(out, 'mode', '') or sys.version_info[0] < 3): # Python 2 lies about mode of sys.stderr - s = s.encode(preferredencoding(), 'ignore') - try: + byt = s.encode(encoding or preferredencoding(), 'ignore') + out.write(byt) + elif hasattr(out, 'buffer'): + enc = encoding or getattr(out, 'encoding', None) or preferredencoding() + byt = s.encode(enc, 'ignore') + out.buffer.write(byt) + else: out.write(s) - except UnicodeEncodeError: - # In Windows shells, this can fail even when the codec is just charmap!? - # See https://wiki.python.org/moin/PrintFails#Issue - if sys.platform == 'win32' and hasattr(out, 'encoding'): - s = s.encode(out.encoding, 'ignore').decode(out.encoding) - out.write(s) - else: - raise - out.flush() @@ -1177,8 +1236,12 @@ class HEADRequest(compat_urllib_request.Request): return "HEAD" -def int_or_none(v, scale=1): - return v if v is None else (int(v) // scale) +def int_or_none(v, scale=1, default=None): + return default if v is None else (int(v) // scale) + + +def float_or_none(v, scale=1, default=None): + return default if v is None else (float(v) / scale) def parse_duration(s): @@ -1260,9 +1323,11 @@ class PagedList(object): def uppercase_escape(s): + unicode_escape = codecs.getdecoder('unicode_escape') return re.sub( - r'\\U([0-9a-fA-F]{8})', - lambda m: compat_chr(int(m.group(1), base=16)), s) + r'\\U[0-9a-fA-F]{8}', + lambda m: unicode_escape(m.group(0))[0], + s) try: struct.pack(u'!I', 0) diff --git a/youtube_dl/version.py b/youtube_dl/version.py index b569d52f5..541bc2f96 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,2 +1,2 @@ -__version__ = '2014.03.25.1' +__version__ = '2014.04.11.2' |