X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fgeneric.py;h=d224aa8e18471787bc00a515836b39fd558bac1f;hb=9e1a5b845586a0a5431fb72467142046d8571e6f;hp=2bfa20606cd7846b0d15e8c441de3fce2a8982f6;hpb=8fb7ff25c5056ed0f23f35129bb0d6eba5dd6555;p=youtube-dl diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 2bfa20606..d224aa8e1 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -7,11 +7,12 @@ import re from .common import InfoExtractor from .youtube import YoutubeIE -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urlparse, compat_xml_parse_error, - +) +from ..utils import ( determine_ext, ExtractorError, float_or_none, @@ -28,6 +29,7 @@ from .brightcove import BrightcoveIE from .ooyala import OoyalaIE from .rutv import RUTVIE from .smotri import SmotriIE +from .condenast import CondeNastIE class GenericIE(InfoExtractor): @@ -98,6 +100,22 @@ class GenericIE(InfoExtractor): 'uploader': 'Championat', }, }, + { + # https://github.com/rg3/youtube-dl/issues/3541 + 'add_ie': ['Brightcove'], + 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1', + 'info_dict': { + 'id': '3866516442001', + 'ext': 'mp4', + 'title': 'Leer mij vrouwen kennen: Aflevering 1', + 'description': 'Leer mij vrouwen kennen: Aflevering 1', + 'uploader': 'SBS Broadcasting', + }, + 'skip': 'Restricted to Netherlands', + 'params': { + 'skip_download': True, # m3u8 download + }, + }, # Direct link to a video { 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4', @@ -155,7 +173,6 @@ class GenericIE(InfoExtractor): # funnyordie embed { 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns', - 'md5': '7cf780be104d40fea7bae52eed4a470e', 'info_dict': { 'id': '18e820ec3f', 'ext': 'mp4', @@ -180,13 +197,13 @@ class GenericIE(InfoExtractor): # Embedded TED video { 'url': 'http://en.support.wordpress.com/videos/ted-talks/', - 'md5': 'deeeabcc1085eb2ba205474e7235a3d5', + 'md5': '65fdff94098e4a607385a60c5177c638', 'info_dict': { - 'id': '981', + 'id': '1969', 'ext': 'mp4', - 'title': 'My web playroom', - 'uploader': 'Ze Frank', - 'description': 'md5:ddb2a40ecd6b6a147e400e535874947b', + 'title': 'Hidden miracles of the natural world', + 'uploader': 'Louie Schwartzberg', + 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9', } }, # Embeded Ustream video @@ -226,21 +243,6 @@ 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', - }, - }, # Condé Nast embed { 'url': 'http://www.wired.com/2014/04/honda-asimo/', @@ -295,13 +297,13 @@ class GenericIE(InfoExtractor): { 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM', 'info_dict': { - 'id': 'jpSGZsgga_I', + 'id': '4vAffPZIT44', 'ext': 'mp4', - 'title': 'Asphalt 8: Airborne - Launch Trailer', + 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!', 'uploader': 'Gameloft', 'uploader_id': 'gameloft', - 'upload_date': '20130821', - 'description': 'md5:87bd95f13d8be3e7da87a5f2c443106a', + 'upload_date': '20140828', + 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4', }, 'params': { 'skip_download': True, @@ -340,7 +342,7 @@ class GenericIE(InfoExtractor): 'ext': 'mp4', 'age_limit': 18, 'uploader': 'www.handjobhub.com', - 'title': 'Busty Blonde Siri Tit Fuck While Wank at Handjob Hub', + 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com', } }, # RSS feed @@ -382,14 +384,69 @@ class GenericIE(InfoExtractor): 'thumbnail': 're:^https?://.*\.jpg$', }, }, + # Wistia embed + { + 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson', + 'md5': '8788b683c777a5cf25621eaf286d0c23', + 'info_dict': { + 'id': '1cfaf6b7ea', + 'ext': 'mov', + 'title': 'md5:51364a8d3d009997ba99656004b5e20d', + 'duration': 643.0, + 'filesize': 182808282, + 'uploader': 'education-portal.com', + }, + }, + { + 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz', + 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4', + 'info_dict': { + 'id': 'uxjb0lwrcz', + 'ext': 'mp4', + 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks', + 'duration': 1715.0, + 'uploader': 'thoughtworks.wistia.com', + }, + }, + # Direct download with broken HEAD + { + 'url': 'http://ai-radio.org:8000/radio.opus', + 'info_dict': { + 'id': 'radio', + 'ext': 'opus', + 'title': 'radio', + }, + 'params': { + 'skip_download': True, # infinite live stream + }, + 'expected_warnings': [ + r'501.*Not Implemented' + ], + }, + # Soundcloud embed + { + 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/', + 'info_dict': { + 'id': '174391317', + 'ext': 'mp3', + 'description': 'md5:ff867d6b555488ad3c52572bb33d432c', + 'uploader': 'Sophos Security', + 'title': 'Chet Chat 171 - Oct 29, 2014', + 'upload_date': '20141029', + } + }, + # Livestream embed + { + 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast', + 'info_dict': { + 'id': '67864563', + 'ext': 'flv', + 'upload_date': '20141112', + 'title': 'Rosetta #CometLanding webcast HL 10', + } + }, ] - def report_download_webpage(self, video_id): - """Report webpage download.""" - if not self._downloader.params.get('test', False): - self._downloader.report_warning('Falling back on generic information extractor.') - super(GenericIE, self).report_download_webpage(video_id) - def report_following_redirect(self, new_url): """Report information extraction.""" self._downloader.to_screen('[redirect] Following redirect to %s' % new_url) @@ -484,11 +541,13 @@ class GenericIE(InfoExtractor): 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube' ) % (url, url), expected=True) else: - assert ':' in default_search + if ':' not in default_search: + default_search += ':' return self.url_result(default_search + url) url, smuggled_data = unsmuggle_url(url) force_videoid = None + is_intentional = smuggled_data and smuggled_data.get('to_generic') if smuggled_data and 'force_videoid' in smuggled_data: force_videoid = smuggled_data['force_videoid'] video_id = force_videoid @@ -498,14 +557,14 @@ class GenericIE(InfoExtractor): self.to_screen('%s: Requesting header' % video_id) head_req = HEADRequest(url) - response = self._request_webpage( + head_response = self._request_webpage( head_req, video_id, note=False, errnote='Could not send HEAD request to %s' % url, fatal=False) - if response is not False: + if head_response is not False: # Check for redirect - new_url = response.geturl() + new_url = head_response.geturl() if url != new_url: self.report_following_redirect(new_url) if force_videoid: @@ -513,31 +572,36 @@ class GenericIE(InfoExtractor): new_url, {'force_videoid': force_videoid}) return self.url_result(new_url) - # Check for direct link to a video - content_type = response.headers.get('Content-Type', '') - m = re.match(r'^(?Paudio|video|application(?=/ogg$))/(?P.+)$', content_type) - if m: - upload_date = response.headers.get('Last-Modified') - if upload_date: - upload_date = unified_strdate(upload_date) - return { - 'id': video_id, - 'title': os.path.splitext(url_basename(url))[0], - 'formats': [{ - 'format_id': m.group('format_id'), - 'url': url, - 'vcodec': 'none' if m.group('type') == 'audio' else None - }], - 'upload_date': upload_date, - } + full_response = None + if head_response is False: + full_response = self._request_webpage(url, video_id) + head_response = full_response + + # Check for direct link to a video + content_type = head_response.headers.get('Content-Type', '') + m = re.match(r'^(?Paudio|video|application(?=/ogg$))/(?P.+)$', content_type) + if m: + upload_date = unified_strdate( + head_response.headers.get('Last-Modified')) + return { + 'id': video_id, + 'title': os.path.splitext(url_basename(url))[0], + 'direct': True, + 'formats': [{ + 'format_id': m.group('format_id'), + 'url': url, + 'vcodec': 'none' if m.group('type') == 'audio' else None + }], + 'upload_date': upload_date, + } - try: - webpage = self._download_webpage(url, video_id) - except ValueError: - # since this is the last-resort InfoExtractor, if - # this error is thrown, it'll be thrown here - raise ExtractorError('Failed to download URL: %s' % url) + if not self._downloader.params.get('test', False) and not is_intentional: + self._downloader.report_warning('Falling back on generic information extractor.') + if full_response: + webpage = self._webpage_read_content(full_response, url, video_id) + else: + webpage = self._download_webpage(url, video_id) self.report_extraction(video_id) # Is it an RSS feed? @@ -584,7 +648,9 @@ class GenericIE(InfoExtractor): # Helper method def _playlist_from_matches(matches, getter, ie=None): - urlrs = orderedSet(self.url_result(getter(m), ie) for m in matches) + urlrs = orderedSet( + self.url_result(self._proto_relative_url(getter(m)), ie) + for m in matches) return self.playlist_result( urlrs, playlist_id=video_id, playlist_title=video_title) @@ -611,13 +677,13 @@ class GenericIE(InfoExtractor): if mobj: player_url = unescapeHTML(mobj.group('url')) surl = smuggle_url(player_url, {'Referer': url}) - return self.url_result(surl, 'Vimeo') + return self.url_result(surl) # Look for embedded (swf embed) Vimeo player mobj = re.search( - r']+?src="(https?://(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage) + r']+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage) if mobj: - return self.url_result(mobj.group(1), 'Vimeo') + return self.url_result(mobj.group(1)) # Look for embedded YouTube player matches = re.findall(r'''(?x) @@ -625,15 +691,16 @@ class GenericIE(InfoExtractor): ]+?src=| data-video-url=| ]+?src=| - embedSWF\(?:\s* + embedSWF\(?:\s*| + new\s+SWFObject\( ) (["\']) (?P(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/ - (?:embed|v)/.+?) + (?:embed|v|p)/.+?) \1''', webpage) if matches: return _playlist_from_matches( - matches, lambda m: unescapeHTML(m[1]), ie='Youtube') + matches, lambda m: unescapeHTML(m[1])) # Look for embedded Dailymotion player matches = re.findall( @@ -642,23 +709,46 @@ class GenericIE(InfoExtractor): return _playlist_from_matches( matches, lambda m: unescapeHTML(m[1])) + # Look for embedded Dailymotion playlist player (#3822) + m = re.search( + r']+?src=(["\'])(?P(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage) + if m: + playlists = re.findall( + r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url'))) + if playlists: + return _playlist_from_matches( + playlists, lambda p: '//dailymotion.com/playlist/%s' % p) + # Look for embedded Wistia player match = re.search( - r']+?src=(["\'])(?P(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage) + r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage) if match: + embed_url = self._proto_relative_url( + unescapeHTML(match.group('url'))) return { '_type': 'url_transparent', - 'url': unescapeHTML(match.group('url')), + 'url': embed_url, 'ie_key': 'Wistia', 'uploader': video_uploader, 'title': video_title, 'id': video_id, } + match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P[^"\']+)', webpage) + if match: + return { + '_type': 'url_transparent', + 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')), + 'ie_key': 'Wistia', + 'uploader': video_uploader, + 'title': video_title, + 'id': match.group('id') + } + # Look for embedded blip.tv player mobj = re.search(r']*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage) if mobj: - return self.url_result('http://blip.tv/a/a-'+mobj.group(1), 'BlipTV') + return self.url_result('http://blip.tv/a/a-' + mobj.group(1), 'BlipTV') mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage) if mobj: return self.url_result(mobj.group(1), 'BlipTV') @@ -694,7 +784,7 @@ class GenericIE(InfoExtractor): # Look for Ooyala videos mobj = (re.search(r'player.ooyala.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P[^"&]+)', webpage) or - re.search(r'OO.Player.create\([\'"].*?[\'"],\s*[\'"](?P.{32})[\'"]', webpage)) + re.search(r'OO.Player.create\([\'"].*?[\'"],\s*[\'"](?P.{32})[\'"]', webpage)) if mobj is not None: return OoyalaIE._build_url_result(mobj.group('ec')) @@ -788,7 +878,7 @@ class GenericIE(InfoExtractor): # Look for embeded soundcloud player mobj = re.search( - r'