diff options
Diffstat (limited to 'youtube_dl/extractor')
58 files changed, 1428 insertions, 481 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 037654a23..9502d07a4 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -23,7 +23,10 @@ from .alphaporno import AlphaPornoIE from .animeondemand import AnimeOnDemandIE from .anitube import AnitubeIE from .anysex import AnySexIE -from .aol import AolIE +from .aol import ( + AolIE, + AolFeaturesIE, +) from .allocine import AllocineIE from .aparat import AparatIE from .appleconnect import AppleConnectIE @@ -51,6 +54,7 @@ from .arte import ( from .atresplayer import AtresPlayerIE from .atttechchannel import ATTTechChannelIE from .audimedia import AudiMediaIE +from .audioboom import AudioBoomIE from .audiomack import AudiomackIE, AudiomackAlbumIE from .azubu import AzubuIE, AzubuLiveIE from .baidu import BaiduVideoIE @@ -185,6 +189,10 @@ from .dumpert import DumpertIE from .defense import DefenseGouvFrIE from .discovery import DiscoveryIE from .dropbox import DropboxIE +from .dw import ( + DWIE, + DWArticleIE, +) from .eagleplatform import EaglePlatformIE from .ebaumsworld import EbaumsWorldIE from .echomsk import EchoMskIE @@ -209,10 +217,7 @@ from .everyonesmixtape import EveryonesMixtapeIE from .exfm import ExfmIE from .expotv import ExpoTVIE from .extremetube import ExtremeTubeIE -from .facebook import ( - FacebookIE, - FacebookPostIE, -) +from .facebook import FacebookIE from .faz import FazIE from .fc2 import FC2IE from .fczenit import FczenitIE @@ -340,6 +345,7 @@ from .konserthusetplay import KonserthusetPlayIE from .kontrtube import KontrTubeIE from .krasview import KrasViewIE from .ku6 import Ku6IE +from .kusi import KUSIIE from .kuwo import ( KuwoIE, KuwoAlbumIE, @@ -383,6 +389,7 @@ from .lynda import ( from .m6 import M6IE from .macgamestore import MacGameStoreIE from .mailru import MailRuIE +from .makerschannel import MakersChannelIE from .makertv import MakerTVIE from .malemotion import MalemotionIE from .matchtv import MatchTVIE @@ -392,6 +399,7 @@ from .metacritic import MetacriticIE from .mgoon import MgoonIE from .minhateca import MinhatecaIE from .ministrygrid import MinistryGridIE +from .minoto import MinotoIE from .miomio import MioMioIE from .mit import TechTVMITIE, MITIE, OCWMITIE from .mitele import MiTeleIE @@ -590,6 +598,7 @@ from .regiotv import RegioTVIE from .restudy import RestudyIE from .reverbnation import ReverbNationIE from .revision3 import Revision3IE +from .rice import RICEIE from .ringtv import RingTVIE from .ro220 import Ro220IE from .rottentomatoes import RottenTomatoesIE @@ -728,6 +737,7 @@ from .theplatform import ( ThePlatformFeedIE, ) from .thesixtyone import TheSixtyOneIE +from .thestar import TheStarIE from .thisamericanlife import ThisAmericanLifeIE from .thisav import ThisAVIE from .tinypic import TinyPicIE @@ -774,6 +784,7 @@ from .tv2 import ( TV2IE, TV2ArticleIE, ) +from .tv3 import TV3IE from .tv4 import TV4IE from .tvc import ( TVCIE, @@ -813,6 +824,7 @@ from .udn import UDNEmbedIE from .digiteka import DigitekaIE from .unistra import UnistraIE from .urort import UrortIE +from .usatoday import USATodayIE from .ustream import UstreamIE, UstreamChannelIE from .ustudio import UstudioIE from .varzesh3 import Varzesh3IE @@ -828,7 +840,10 @@ from .vgtv import ( VGTVIE, ) from .vh1 import VH1IE -from .vice import ViceIE +from .vice import ( + ViceIE, + ViceShowIE, +) from .viddler import ViddlerIE from .videodetective import VideoDetectiveIE from .videofyme import VideofyMeIE @@ -855,6 +870,7 @@ from .vimeo import ( VimeoChannelIE, VimeoGroupsIE, VimeoLikesIE, + VimeoOndemandIE, VimeoReviewIE, VimeoUserIE, VimeoWatchLaterIE, diff --git a/youtube_dl/extractor/aljazeera.py b/youtube_dl/extractor/aljazeera.py index 5b2c0dc9a..cddcaa489 100644 --- a/youtube_dl/extractor/aljazeera.py +++ b/youtube_dl/extractor/aljazeera.py @@ -13,24 +13,18 @@ class AlJazeeraIE(InfoExtractor): 'ext': 'mp4', 'title': 'The Slum - Episode 1: Deliverance', 'description': 'As a birth attendant advocating for family planning, Remy is on the frontline of Tondo\'s battle with overcrowding.', - 'uploader': 'Al Jazeera English', + 'uploader_id': '665003303001', + 'timestamp': 1411116829, + 'upload_date': '20140919', }, - 'add_ie': ['BrightcoveLegacy'], + 'add_ie': ['BrightcoveNew'], 'skip': 'Not accessible from Travis CI server', } + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/665003303001/default_default/index.html?videoId=%s' def _real_extract(self, url): program_name = self._match_id(url) webpage = self._download_webpage(url, program_name) brightcove_id = self._search_regex( r'RenderPagesVideo\(\'(.+?)\'', webpage, 'brightcove id') - - return { - '_type': 'url', - 'url': ( - 'brightcove:' - 'playerKey=AQ~~%2CAAAAmtVJIFk~%2CTVGOQ5ZTwJbeMWnq5d_H4MOM57xfzApc' - '&%40videoPlayer={0}'.format(brightcove_id) - ), - 'ie_key': 'BrightcoveLegacy', - } + return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id) diff --git a/youtube_dl/extractor/aol.py b/youtube_dl/extractor/aol.py index b51eafc45..b761b2cc4 100644 --- a/youtube_dl/extractor/aol.py +++ b/youtube_dl/extractor/aol.py @@ -1,24 +1,11 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor class AolIE(InfoExtractor): IE_NAME = 'on.aol.com' - _VALID_URL = r'''(?x) - (?: - aol-video:| - http://on\.aol\.com/ - (?: - video/.*-| - playlist/(?P<playlist_display_id>[^/?#]+?)-(?P<playlist_id>[0-9]+)[?#].*_videoid= - ) - ) - (?P<id>[0-9]+) - (?:$|\?) - ''' + _VALID_URL = r'(?:aol-video:|http://on\.aol\.com/video/.*-)(?P<id>[0-9]+)(?:$|\?)' _TESTS = [{ 'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img', @@ -29,42 +16,31 @@ class AolIE(InfoExtractor): 'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam', }, 'add_ie': ['FiveMin'], - }, { - 'url': 'http://on.aol.com/playlist/brace-yourself---todays-weirdest-news-152147?icid=OnHomepageC4_Omg_Img#_videoid=518184316', - 'info_dict': { - 'id': '152147', - 'title': 'Brace Yourself - Today\'s Weirdest News', - }, - 'playlist_mincount': 10, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - playlist_id = mobj.group('playlist_id') - if not playlist_id or self._downloader.params.get('noplaylist'): - return self.url_result('5min:%s' % video_id) + video_id = self._match_id(url) + return self.url_result('5min:%s' % video_id) - self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) - webpage = self._download_webpage(url, playlist_id) - title = self._html_search_regex( - r'<h1 class="video-title[^"]*">(.+?)</h1>', webpage, 'title') - playlist_html = self._search_regex( - r"(?s)<ul\s+class='video-related[^']*'>(.*?)</ul>", webpage, - 'playlist HTML') - entries = [{ - '_type': 'url', - 'url': 'aol-video:%s' % m.group('id'), - 'ie_key': 'Aol', - } for m in re.finditer( - r"<a\s+href='.*videoid=(?P<id>[0-9]+)'\s+class='video-thumb'>", - playlist_html)] +class AolFeaturesIE(InfoExtractor): + IE_NAME = 'features.aol.com' + _VALID_URL = r'http://features\.aol\.com/video/(?P<id>[^/?#]+)' - return { - '_type': 'playlist', - 'id': playlist_id, - 'display_id': mobj.group('playlist_display_id'), - 'title': title, - 'entries': entries, - } + _TESTS = [{ + 'url': 'http://features.aol.com/video/behind-secret-second-careers-late-night-talk-show-hosts', + 'md5': '7db483bb0c09c85e241f84a34238cc75', + 'info_dict': { + 'id': '519507715', + 'ext': 'mp4', + 'title': 'What To Watch - February 17, 2016', + }, + 'add_ie': ['FiveMin'], + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + return self.url_result(self._search_regex( + r'<script type="text/javascript" src="(https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js[^"]+)"', + webpage, '5min embed url'), 'FiveMin') diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index efde7e207..3e119e21b 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -121,15 +121,18 @@ class ArteTVPlus7IE(InfoExtractor): json_url = compat_parse_qs( compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0] if json_url: - return self._extract_from_json_url(json_url, video_id, lang) - # Differend kind of embed URL (e.g. + title = self._search_regex( + r'<h3[^>]+title=(["\'])(?P<title>.+?)\1', + webpage, 'title', default=None, group='title') + return self._extract_from_json_url(json_url, video_id, lang, title=title) + # Different kind of embed URL (e.g. # http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium) embed_url = self._search_regex( r'<iframe[^>]+src=(["\'])(?P<url>.+?)\1', webpage, 'embed url', group='url') return self.url_result(embed_url) - def _extract_from_json_url(self, json_url, video_id, lang): + def _extract_from_json_url(self, json_url, video_id, lang, title=None): info = self._download_json(json_url, video_id) player_info = info['videoJsonPlayer'] @@ -137,7 +140,7 @@ class ArteTVPlus7IE(InfoExtractor): if not upload_date_str: upload_date_str = (player_info.get('VRA') or player_info.get('VDA') or '').split(' ')[0] - title = player_info['VTI'].strip() + title = (player_info.get('VTI') or title or player_info['VID']).strip() subtitle = player_info.get('VSU', '').strip() if subtitle: title += ' - %s' % subtitle diff --git a/youtube_dl/extractor/audimedia.py b/youtube_dl/extractor/audimedia.py index 3b2effa15..aa6925623 100644 --- a/youtube_dl/extractor/audimedia.py +++ b/youtube_dl/extractor/audimedia.py @@ -10,9 +10,9 @@ from ..utils import ( class AudiMediaIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?audimedia\.tv/(?:en|de)/vid/(?P<id>[^/?#]+)' + _VALID_URL = r'https?://(?:www\.)?audi-mediacenter\.com/(?:en|de)/audimediatv/(?P<id>[^/?#]+)' _TEST = { - 'url': 'https://audimedia.tv/en/vid/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test', + 'url': 'https://www.audi-mediacenter.com/en/audimediatv/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test-1467', 'md5': '79a8b71c46d49042609795ab59779b66', 'info_dict': { 'id': '1565', @@ -32,7 +32,10 @@ class AudiMediaIE(InfoExtractor): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) - raw_payload = self._search_regex(r'<script[^>]+class="amtv-embed"[^>]+id="([^"]+)"', webpage, 'raw payload') + raw_payload = self._search_regex([ + r'class="amtv-embed"[^>]+id="([^"]+)"', + r'class=\\"amtv-embed\\"[^>]+id=\\"([^"]+)\\"', + ], webpage, 'raw payload') _, stage_mode, video_id, lang = raw_payload.split('-') # TODO: handle s and e stage_mode (live streams and ended live streams) @@ -59,13 +62,19 @@ class AudiMediaIE(InfoExtractor): video_version_url = video_version.get('download_url') or video_version.get('stream_url') if not video_version_url: continue - formats.append({ + f = { 'url': video_version_url, 'width': int_or_none(video_version.get('width')), 'height': int_or_none(video_version.get('height')), 'abr': int_or_none(video_version.get('audio_bitrate')), 'vbr': int_or_none(video_version.get('video_bitrate')), - }) + } + bitrate = self._search_regex(r'(\d+)k', video_version_url, 'bitrate', default=None) + if bitrate: + f.update({ + 'format_id': 'http-%s' % bitrate, + }) + formats.append(f) self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/audioboom.py b/youtube_dl/extractor/audioboom.py new file mode 100644 index 000000000..2ec2d7092 --- /dev/null +++ b/youtube_dl/extractor/audioboom.py @@ -0,0 +1,66 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import float_or_none + + +class AudioBoomIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?audioboom\.com/boos/(?P<id>[0-9]+)' + _TEST = { + 'url': 'https://audioboom.com/boos/4279833-3-09-2016-czaban-hour-3?t=0', + 'md5': '63a8d73a055c6ed0f1e51921a10a5a76', + 'info_dict': { + 'id': '4279833', + 'ext': 'mp3', + 'title': '3/09/2016 Czaban Hour 3', + 'description': 'Guest: Nate Davis - NFL free agency, Guest: Stan Gans', + 'duration': 2245.72, + 'uploader': 'Steve Czaban', + 'uploader_url': 're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + clip = None + + clip_store = self._parse_json( + self._search_regex( + r'data-new-clip-store=(["\'])(?P<json>{.*?"clipId"\s*:\s*%s.*?})\1' % video_id, + webpage, 'clip store', default='{}', group='json'), + video_id, fatal=False) + if clip_store: + clips = clip_store.get('clips') + if clips and isinstance(clips, list) and isinstance(clips[0], dict): + clip = clips[0] + + def from_clip(field): + if clip: + clip.get(field) + + audio_url = from_clip('clipURLPriorToLoading') or self._og_search_property( + 'audio', webpage, 'audio url') + title = from_clip('title') or self._og_search_title(webpage) + description = from_clip('description') or self._og_search_description(webpage) + + duration = float_or_none(from_clip('duration') or self._html_search_meta( + 'weibo:audio:duration', webpage)) + + uploader = from_clip('author') or self._og_search_property( + 'audio:artist', webpage, 'uploader', fatal=False) + uploader_url = from_clip('author_url') or self._html_search_meta( + 'audioboo:channel', webpage, 'uploader url') + + return { + 'id': video_id, + 'url': audio_url, + 'title': title, + 'description': description, + 'duration': duration, + 'uploader': uploader, + 'uploader_url': uploader_url, + } diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 9d0dfb961..e62b3860e 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -10,7 +10,6 @@ from ..utils import ( int_or_none, parse_duration, parse_iso8601, - remove_end, unescapeHTML, ) from ..compat import ( @@ -561,7 +560,7 @@ class BBCIE(BBCCoUkIE): 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460', 'info_dict': { 'id': '3662a707-0af9-3149-963f-47bea720b460', - 'title': 'BBC Blogs - Adam Curtis - BUGGER', + 'title': 'BUGGER', }, 'playlist_count': 18, }, { @@ -670,10 +669,18 @@ class BBCIE(BBCCoUkIE): 'url': 'http://www.bbc.com/sport/0/football/34475836', 'info_dict': { 'id': '34475836', - 'title': 'What Liverpool can expect from Klopp', + 'title': 'Jurgen Klopp: Furious football from a witty and winning coach', }, 'playlist_count': 3, }, { + # school report article with single video + 'url': 'http://www.bbc.co.uk/schoolreport/35744779', + 'info_dict': { + 'id': '35744779', + 'title': 'School which breaks down barriers in Jerusalem', + }, + 'playlist_count': 1, + }, { # single video with playlist URL from weather section 'url': 'http://www.bbc.com/weather/features/33601775', 'only_matching': True, @@ -735,8 +742,17 @@ class BBCIE(BBCCoUkIE): json_ld_info = self._search_json_ld(webpage, playlist_id, default=None) timestamp = json_ld_info.get('timestamp') + playlist_title = json_ld_info.get('title') - playlist_description = json_ld_info.get('description') + if not playlist_title: + playlist_title = self._og_search_title( + webpage, default=None) or self._html_search_regex( + r'<title>(.+?)</title>', webpage, 'playlist title', default=None) + if playlist_title: + playlist_title = re.sub(r'(.+)\s*-\s*BBC.*?$', r'\1', playlist_title).strip() + + playlist_description = json_ld_info.get( + 'description') or self._og_search_description(webpage, default=None) if not timestamp: timestamp = parse_iso8601(self._search_regex( @@ -797,8 +813,6 @@ class BBCIE(BBCCoUkIE): playlist.get('progressiveDownloadUrl'), playlist_id, timestamp)) if entries: - playlist_title = playlist_title or remove_end(self._og_search_title(webpage), ' - BBC News') - playlist_description = playlist_description or self._og_search_description(webpage, default=None) return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret) @@ -829,10 +843,6 @@ class BBCIE(BBCCoUkIE): 'subtitles': subtitles, } - playlist_title = self._html_search_regex( - r'<title>(.*?)(?:\s*-\s*BBC [^ ]+)?</title>', webpage, 'playlist title') - playlist_description = self._og_search_description(webpage, default=None) - def extract_all(pattern): return list(filter(None, map( lambda s: self._parse_json(s, playlist_id, fatal=False), diff --git a/youtube_dl/extractor/bleacherreport.py b/youtube_dl/extractor/bleacherreport.py index 38bda3af5..7a8e1f60b 100644 --- a/youtube_dl/extractor/bleacherreport.py +++ b/youtube_dl/extractor/bleacherreport.py @@ -28,10 +28,10 @@ class BleacherReportIE(InfoExtractor): 'add_ie': ['Ooyala'], }, { 'url': 'http://bleacherreport.com/articles/2586817-aussie-golfers-get-fright-of-their-lives-after-being-chased-by-angry-kangaroo', - 'md5': 'af5f90dc9c7ba1c19d0a3eac806bbf50', + 'md5': '6a5cd403418c7b01719248ca97fb0692', 'info_dict': { 'id': '2586817', - 'ext': 'mp4', + 'ext': 'webm', 'title': 'Aussie Golfers Get Fright of Their Lives After Being Chased by Angry Kangaroo', 'timestamp': 1446839961, 'uploader': 'Sean Fay', @@ -93,10 +93,14 @@ class BleacherReportCMSIE(AMPIE): 'md5': '8c2c12e3af7805152675446c905d159b', 'info_dict': { 'id': '8fd44c2f-3dc5-4821-9118-2c825a98c0e1', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Cena vs. Rollins Would Expose the Heavyweight Division', 'description': 'md5:984afb4ade2f9c0db35f3267ed88b36e', }, + 'params': { + # m3u8 download + 'skip_download': True, + }, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index c947337f9..3ab383461 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -13,6 +13,7 @@ from ..compat import ( compat_urllib_parse_urlparse, compat_urlparse, compat_xml_parse_error, + compat_HTTPError, ) from ..utils import ( determine_ext, @@ -23,16 +24,16 @@ from ..utils import ( js_to_json, int_or_none, parse_iso8601, - sanitized_Request, unescapeHTML, unsmuggle_url, + update_url_query, ) class BrightcoveLegacyIE(InfoExtractor): IE_NAME = 'brightcove:legacy' _VALID_URL = r'(?:https?://.*brightcove\.com/(services|viewer).*?\?|brightcove:)(?P<query>.*)' - _FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s' + _FEDERATED_URL = 'http://c.brightcove.com/services/viewer/htmlFederated' _TESTS = [ { @@ -155,8 +156,8 @@ class BrightcoveLegacyIE(InfoExtractor): # Not all pages define this value if playerKey is not None: params['playerKey'] = playerKey - # The three fields hold the id of the video - videoPlayer = find_param('@videoPlayer') or find_param('videoId') or find_param('videoID') + # These fields hold the id of the video + videoPlayer = find_param('@videoPlayer') or find_param('videoId') or find_param('videoID') or find_param('@videoList') if videoPlayer is not None: params['@videoPlayer'] = videoPlayer linkBase = find_param('linkBaseURL') @@ -184,8 +185,7 @@ class BrightcoveLegacyIE(InfoExtractor): @classmethod def _make_brightcove_url(cls, params): - data = compat_urllib_parse.urlencode(params) - return cls._FEDERATED_URL_TEMPLATE % data + return update_url_query(cls._FEDERATED_URL, params) @classmethod def _extract_brightcove_url(cls, webpage): @@ -239,7 +239,7 @@ class BrightcoveLegacyIE(InfoExtractor): # We set the original url as the default 'Referer' header referer = smuggled_data.get('Referer', url) return self._get_video_info( - videoPlayer[0], query_str, query, referer=referer) + videoPlayer[0], query, referer=referer) elif 'playerKey' in query: player_key = query['playerKey'] return self._get_playlist_info(player_key[0]) @@ -248,15 +248,14 @@ class BrightcoveLegacyIE(InfoExtractor): 'Cannot find playerKey= variable. Did you forget quotes in a shell invocation?', expected=True) - def _get_video_info(self, video_id, query_str, query, referer=None): - request_url = self._FEDERATED_URL_TEMPLATE % query_str - req = sanitized_Request(request_url) + def _get_video_info(self, video_id, query, referer=None): + headers = {} linkBase = query.get('linkBaseURL') if linkBase is not None: referer = linkBase[0] if referer is not None: - req.add_header('Referer', referer) - webpage = self._download_webpage(req, video_id) + headers['Referer'] = referer + webpage = self._download_webpage(self._FEDERATED_URL, video_id, headers=headers, query=query) error_msg = self._html_search_regex( r"<h1>We're sorry.</h1>([\s\n]*<p>.*?</p>)+", webpage, @@ -355,7 +354,7 @@ class BrightcoveLegacyIE(InfoExtractor): class BrightcoveNewIE(InfoExtractor): IE_NAME = 'brightcove:new' - _VALID_URL = r'https?://players\.brightcove\.net/(?P<account_id>\d+)/(?P<player_id>[^/]+)_(?P<embed>[^/]+)/index\.html\?.*videoId=(?P<video_id>(?:ref:)?\d+)' + _VALID_URL = r'https?://players\.brightcove\.net/(?P<account_id>\d+)/(?P<player_id>[^/]+)_(?P<embed>[^/]+)/index\.html\?.*videoId=(?P<video_id>\d+|ref:[^&]+)' _TESTS = [{ 'url': 'http://players.brightcove.net/929656772001/e41d32dc-ec74-459e-a845-6c69f7b724ea_default/index.html?videoId=4463358922001', 'md5': 'c8100925723840d4b0d243f7025703be', @@ -391,6 +390,10 @@ class BrightcoveNewIE(InfoExtractor): # ref: prefixed video id 'url': 'http://players.brightcove.net/3910869709001/21519b5c-4b3b-4363-accb-bdc8f358f823_default/index.html?videoId=ref:7069442', 'only_matching': True, + }, { + # non numeric ref: prefixed video id + 'url': 'http://players.brightcove.net/710858724001/default_default/index.html?videoId=ref:event-stream-356', + 'only_matching': True, }] @staticmethod @@ -410,8 +413,8 @@ class BrightcoveNewIE(InfoExtractor): # Look for iframe embeds [1] for _, url in re.findall( - r'<iframe[^>]+src=(["\'])((?:https?:)//players\.brightcove\.net/\d+/[^/]+/index\.html.+?)\1', webpage): - entries.append(url) + r'<iframe[^>]+src=(["\'])((?:https?:)?//players\.brightcove\.net/\d+/[^/]+/index\.html.+?)\1', webpage): + entries.append(url if url.startswith('http') else 'http:' + url) # Look for embed_in_page embeds [2] for video_id, account_id, player_id, embed in re.findall( @@ -420,11 +423,11 @@ class BrightcoveNewIE(InfoExtractor): # According to [4] data-video-id may be prefixed with ref: r'''(?sx) <video[^>]+ - data-video-id=["\']((?:ref:)?\d+)["\'][^>]*>.*? + data-video-id=["\'](\d+|ref:[^"\']+)["\'][^>]*>.*? </video>.*? <script[^>]+ src=["\'](?:https?:)?//players\.brightcove\.net/ - (\d+)/([\da-f-]+)_([^/]+)/index\.min\.js + (\d+)/([\da-f-]+)_([^/]+)/index(?:\.min)?\.js ''', webpage): entries.append( 'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s' @@ -454,24 +457,33 @@ class BrightcoveNewIE(InfoExtractor): r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1', webpage, 'policy key', group='pk') - req = sanitized_Request( - 'https://edge.api.brightcove.com/playback/v1/accounts/%s/videos/%s' - % (account_id, video_id), - headers={'Accept': 'application/json;pk=%s' % policy_key}) - json_data = self._download_json(req, video_id) + api_url = 'https://edge.api.brightcove.com/playback/v1/accounts/%s/videos/%s' % (account_id, video_id) + try: + json_data = self._download_json(api_url, video_id, headers={ + 'Accept': 'application/json;pk=%s' % policy_key + }) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + json_data = self._parse_json(e.cause.read().decode(), video_id) + raise ExtractorError(json_data[0]['message'], expected=True) + raise title = json_data['name'] formats = [] for source in json_data.get('sources', []): + container = source.get('container') source_type = source.get('type') src = source.get('src') - if source_type == 'application/x-mpegURL': + if source_type == 'application/x-mpegURL' or container == 'M2TS': if not src: continue formats.extend(self._extract_m3u8_formats( - src, video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls', fatal=False)) + src, video_id, 'mp4', m3u8_id='hls', fatal=False)) + elif source_type == 'application/dash+xml': + if not src: + continue + formats.extend(self._extract_mpd_formats(src, video_id, 'dash', fatal=False)) else: streaming_src = source.get('streaming_src') stream_name, app_name = source.get('stream_name'), source.get('app_name') @@ -479,15 +491,23 @@ class BrightcoveNewIE(InfoExtractor): continue tbr = float_or_none(source.get('avg_bitrate'), 1000) height = int_or_none(source.get('height')) + width = int_or_none(source.get('width')) f = { 'tbr': tbr, - 'width': int_or_none(source.get('width')), - 'height': height, 'filesize': int_or_none(source.get('size')), - 'container': source.get('container'), - 'vcodec': source.get('codec'), - 'ext': source.get('container').lower(), + 'container': container, + 'ext': container.lower(), } + if width == 0 and height == 0: + f.update({ + 'vcodec': 'none', + }) + else: + f.update({ + 'width': width, + 'height': height, + 'vcodec': source.get('codec'), + }) def build_format_id(kind): format_id = kind diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py index 6d9cd8abd..042c4f2f1 100644 --- a/youtube_dl/extractor/cinemassacre.py +++ b/youtube_dl/extractor/cinemassacre.py @@ -21,6 +21,10 @@ class CinemassacreIE(InfoExtractor): 'title': '“Angry Video Game Nerd: The Movie” – Trailer', 'description': 'md5:fb87405fcb42a331742a0dce2708560b', }, + 'params': { + # m3u8 download + 'skip_download': True, + }, }, { 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940', @@ -31,14 +35,18 @@ class CinemassacreIE(InfoExtractor): 'upload_date': '20131002', 'title': 'The Mummy’s Hand (1940)', }, + 'params': { + # m3u8 download + 'skip_download': True, + }, }, { # Youtube embedded video 'url': 'http://cinemassacre.com/2006/12/07/chronologically-confused-about-bad-movie-and-video-game-sequel-titles/', - 'md5': 'df4cf8a1dcedaec79a73d96d83b99023', + 'md5': 'ec9838a5520ef5409b3e4e42fcb0a3b9', 'info_dict': { 'id': 'OEVzPCY2T-g', - 'ext': 'mp4', + 'ext': 'webm', 'title': 'AVGN: Chronologically Confused about Bad Movie and Video Game Sequel Titles', 'upload_date': '20061207', 'uploader': 'Cinemassacre', @@ -49,12 +57,12 @@ class CinemassacreIE(InfoExtractor): { # Youtube embedded video 'url': 'http://cinemassacre.com/2006/09/01/mckids/', - 'md5': '6eb30961fa795fedc750eac4881ad2e1', + 'md5': '7393c4e0f54602ad110c793eb7a6513a', 'info_dict': { 'id': 'FnxsNhuikpo', - 'ext': 'mp4', + 'ext': 'webm', 'upload_date': '20060901', - 'uploader': 'Cinemassacre Extras', + 'uploader': 'Cinemassacre Extra', 'description': 'md5:de9b751efa9e45fbaafd9c8a1123ed53', 'uploader_id': 'Cinemassacre', 'title': 'AVGN: McKids', @@ -69,7 +77,11 @@ class CinemassacreIE(InfoExtractor): 'description': 'Let’s Play Mario Kart 64 !! Mario Kart 64 is a classic go-kart racing game released for the Nintendo 64 (N64). Today James & Mike do 4 player Battle Mode with Kyle and Bootsy!', 'title': 'Mario Kart 64 (Nintendo 64) James & Mike Mondays', 'upload_date': '20150525', - } + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, } ] diff --git a/youtube_dl/extractor/cnet.py b/youtube_dl/extractor/cnet.py index 5c3908f72..3cf0bf95b 100644 --- a/youtube_dl/extractor/cnet.py +++ b/youtube_dl/extractor/cnet.py @@ -51,9 +51,7 @@ class CNETIE(ThePlatformIE): uploader = None uploader_id = None - mpx_account = data['config']['uvpConfig']['default']['mpx_account'] - - metadata = self.get_metadata('%s/%s' % (mpx_account, list(vdata['files'].values())[0]), video_id) + metadata = self.get_metadata('kYEXFC/%s' % list(vdata['files'].values())[0], video_id) description = vdata.get('description') or metadata.get('description') duration = int_or_none(vdata.get('duration')) or metadata.get('duration') @@ -62,7 +60,7 @@ class CNETIE(ThePlatformIE): for (fkey, vid) in vdata['files'].items(): if fkey == 'hls_phone' and 'hls_tablet' in vdata['files']: continue - release_url = 'http://link.theplatform.com/s/%s/%s?format=SMIL&mbr=true' % (mpx_account, vid) + release_url = 'http://link.theplatform.com/s/kYEXFC/%s?format=SMIL&mbr=true' % vid if fkey == 'hds': release_url += '&manifest=f4m' tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % fkey) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 402f2f436..770105a5b 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -15,13 +15,14 @@ import math from ..compat import ( compat_cookiejar, compat_cookies, + compat_etree_fromstring, compat_getpass, compat_http_client, + compat_os_name, + compat_str, compat_urllib_error, compat_urllib_parse, compat_urlparse, - compat_str, - compat_etree_fromstring, ) from ..utils import ( NO_DEFAULT, @@ -47,6 +48,7 @@ from ..utils import ( determine_protocol, parse_duration, mimetype2ext, + update_url_query, ) @@ -104,7 +106,7 @@ class InfoExtractor(object): * protocol The protocol that will be used for the actual download, lower-case. "http", "https", "rtsp", "rtmp", "rtmpe", - "m3u8", or "m3u8_native". + "m3u8", "m3u8_native" or "http_dash_segments". * preference Order number of this format. If this field is present and not None, the formats get sorted by this field, regardless of all other values. @@ -344,7 +346,7 @@ class InfoExtractor(object): def IE_NAME(self): return compat_str(type(self).__name__[:-2]) - def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True): + def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, data=None, headers=None, query=None): """ Returns the response handle """ if note is None: self.report_download_webpage(video_id) @@ -353,6 +355,12 @@ class InfoExtractor(object): self.to_screen('%s' % (note,)) else: self.to_screen('%s: %s' % (video_id, note)) + # data, headers and query params will be ignored for `Request` objects + if isinstance(url_or_request, compat_str): + if query: + url_or_request = update_url_query(url_or_request, query) + if data or headers: + url_or_request = sanitized_Request(url_or_request, data, headers or {}) try: return self._downloader.urlopen(url_or_request) except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: @@ -368,13 +376,13 @@ class InfoExtractor(object): self._downloader.report_warning(errmsg) return False - def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None): + def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None, data=None, headers=None, query=None): """ Returns a tuple (page content as string, URL handle) """ # Strip hashes from the URL (#1038) if isinstance(url_or_request, (compat_str, str)): url_or_request = url_or_request.partition('#')[0] - urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal) + urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal, data=data, headers=headers, query=query) if urlh is False: assert not fatal return False @@ -427,7 +435,7 @@ class InfoExtractor(object): self.to_screen('Saving request to ' + filename) # Working around MAX_PATH limitation on Windows (see # http://msdn.microsoft.com/en-us/library/windows/desktop/aa365247(v=vs.85).aspx) - if os.name == 'nt': + if compat_os_name == 'nt': absfilepath = os.path.abspath(filename) if len(absfilepath) > 259: filename = '\\\\?\\' + absfilepath @@ -461,13 +469,13 @@ class InfoExtractor(object): return content - def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None): + def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None, data=None, headers=None, query=None): """ Returns the data of the page as a string """ success = False try_count = 0 while success is False: try: - res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding) + res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding, data=data, headers=headers, query=query) success = True except compat_http_client.IncompleteRead as e: try_count += 1 @@ -482,10 +490,10 @@ class InfoExtractor(object): def _download_xml(self, url_or_request, video_id, note='Downloading XML', errnote='Unable to download XML', - transform_source=None, fatal=True, encoding=None): + transform_source=None, fatal=True, encoding=None, data=None, headers=None, query=None): """Return the xml as an xml.etree.ElementTree.Element""" xml_string = self._download_webpage( - url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding) + url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding, data=data, headers=headers, query=query) if xml_string is False: return xml_string if transform_source: @@ -496,10 +504,10 @@ class InfoExtractor(object): note='Downloading JSON metadata', errnote='Unable to download JSON metadata', transform_source=None, - fatal=True, encoding=None): + fatal=True, encoding=None, data=None, headers=None, query=None): json_string = self._download_webpage( url_or_request, video_id, note, errnote, fatal=fatal, - encoding=encoding) + encoding=encoding, data=data, headers=headers, query=query) if (not fatal) and json_string is False: return None return self._parse_json( @@ -596,7 +604,7 @@ class InfoExtractor(object): if mobj: break - if not self._downloader.params.get('no_color') and os.name != 'nt' and sys.stderr.isatty(): + if not self._downloader.params.get('no_color') and compat_os_name != 'nt' and sys.stderr.isatty(): _name = '\033[0;34m%s\033[0m' % name else: _name = name @@ -854,6 +862,7 @@ class InfoExtractor(object): proto_preference = 0 if determine_protocol(f) in ['http', 'https'] else -0.1 if f.get('vcodec') == 'none': # audio only + preference -= 50 if self._downloader.params.get('prefer_free_formats'): ORDER = ['aac', 'mp3', 'm4a', 'webm', 'ogg', 'opus'] else: @@ -864,6 +873,8 @@ class InfoExtractor(object): except ValueError: audio_ext_preference = -1 else: + if f.get('acodec') == 'none': # video only + preference -= 40 if self._downloader.params.get('prefer_free_formats'): ORDER = ['flv', 'mp4', 'webm'] else: @@ -965,6 +976,13 @@ class InfoExtractor(object): if manifest is False: return [] + return self._parse_f4m_formats( + manifest, manifest_url, video_id, preference=preference, f4m_id=f4m_id, + transform_source=transform_source, fatal=fatal) + + def _parse_f4m_formats(self, manifest, manifest_url, video_id, preference=None, f4m_id=None, + transform_source=lambda s: fix_xml_ampersands(s).strip(), + fatal=True): formats = [] manifest_version = '1.0' media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media') @@ -990,7 +1008,8 @@ class InfoExtractor(object): # bitrate in f4m downloader if determine_ext(manifest_url) == 'f4m': formats.extend(self._extract_f4m_formats( - manifest_url, video_id, preference, f4m_id, fatal=fatal)) + manifest_url, video_id, preference=preference, f4m_id=f4m_id, + transform_source=transform_source, fatal=fatal)) continue tbr = int_or_none(media_el.attrib.get('bitrate')) formats.append({ @@ -1139,8 +1158,8 @@ class InfoExtractor(object): out.append('{%s}%s' % (namespace, c)) return '/'.join(out) - def _extract_smil_formats(self, smil_url, video_id, fatal=True, f4m_params=None): - smil = self._download_smil(smil_url, video_id, fatal=fatal) + def _extract_smil_formats(self, smil_url, video_id, fatal=True, f4m_params=None, transform_source=None): + smil = self._download_smil(smil_url, video_id, fatal=fatal, transform_source=transform_source) if smil is False: assert not fatal @@ -1157,10 +1176,10 @@ class InfoExtractor(object): return {} return self._parse_smil(smil, smil_url, video_id, f4m_params=f4m_params) - def _download_smil(self, smil_url, video_id, fatal=True): + def _download_smil(self, smil_url, video_id, fatal=True, transform_source=None): return self._download_xml( smil_url, video_id, 'Downloading SMIL file', - 'Unable to download SMIL file', fatal=fatal) + 'Unable to download SMIL file', fatal=fatal, transform_source=transform_source) def _parse_smil(self, smil, smil_url, video_id, f4m_params=None): namespace = self._parse_smil_namespace(smil) @@ -1446,8 +1465,9 @@ class InfoExtractor(object): continue representation_attrib = adaptation_set.attrib.copy() representation_attrib.update(representation.attrib) - mime_type = representation_attrib.get('mimeType') - content_type = mime_type.split('/')[0] if mime_type else representation_attrib.get('contentType') + # According to page 41 of ISO/IEC 29001-1:2014, @mimeType is mandatory + mime_type = representation_attrib['mimeType'] + content_type = mime_type.split('/')[0] if content_type == 'text': # TODO implement WebVTT downloading pass @@ -1470,6 +1490,7 @@ class InfoExtractor(object): f = { 'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id, 'url': base_url, + 'ext': mimetype2ext(mime_type), 'width': int_or_none(representation_attrib.get('width')), 'height': int_or_none(representation_attrib.get('height')), 'tbr': int_or_none(representation_attrib.get('bandwidth'), 1000), diff --git a/youtube_dl/extractor/douyutv.py b/youtube_dl/extractor/douyutv.py index 373b3b4b4..bdc768c78 100644 --- a/youtube_dl/extractor/douyutv.py +++ b/youtube_dl/extractor/douyutv.py @@ -18,7 +18,7 @@ class DouyuTVIE(InfoExtractor): 'display_id': 'iseven', 'ext': 'flv', 'title': 're:^清晨醒脑!T-ara根本停不下来! [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', - 'description': 'md5:c93d6692dde6fe33809a46edcbecca44', + 'description': 'md5:f34981259a03e980a3c6404190a3ed61', 'thumbnail': 're:^https?://.*\.jpg$', 'uploader': '7师傅', 'uploader_id': '431925', @@ -26,7 +26,7 @@ class DouyuTVIE(InfoExtractor): }, 'params': { 'skip_download': True, - } + }, }, { 'url': 'http://www.douyutv.com/85982', 'info_dict': { @@ -42,7 +42,24 @@ class DouyuTVIE(InfoExtractor): }, 'params': { 'skip_download': True, - } + }, + 'skip': 'Romm not found', + }, { + 'url': 'http://www.douyutv.com/17732', + 'info_dict': { + 'id': '17732', + 'display_id': '17732', + 'ext': 'flv', + 'title': 're:^清晨醒脑!T-ara根本停不下来! [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'description': 'md5:f34981259a03e980a3c6404190a3ed61', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': '7师傅', + 'uploader_id': '431925', + 'is_live': True, + }, + 'params': { + 'skip_download': True, + }, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/dw.py b/youtube_dl/extractor/dw.py new file mode 100644 index 000000000..b6c985547 --- /dev/null +++ b/youtube_dl/extractor/dw.py @@ -0,0 +1,85 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import int_or_none +from ..compat import compat_urlparse + + +class DWIE(InfoExtractor): + IE_NAME = 'dw' + _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+av-(?P<id>\d+)' + _TESTS = [{ + # video + 'url': 'http://www.dw.com/en/intelligent-light/av-19112290', + 'md5': '7372046e1815c5a534b43f3c3c36e6e9', + 'info_dict': { + 'id': '19112290', + 'ext': 'mp4', + 'title': 'Intelligent light', + 'description': 'md5:90e00d5881719f2a6a5827cb74985af1', + 'upload_date': '20160311', + } + }, { + # audio + 'url': 'http://www.dw.com/en/worldlink-my-business/av-19111941', + 'md5': '2814c9a1321c3a51f8a7aeb067a360dd', + 'info_dict': { + 'id': '19111941', + 'ext': 'mp3', + 'title': 'WorldLink: My business', + 'description': 'md5:bc9ca6e4e063361e21c920c53af12405', + 'upload_date': '20160311', + } + }] + + def _real_extract(self, url): + media_id = self._match_id(url) + webpage = self._download_webpage(url, media_id) + hidden_inputs = self._hidden_inputs(webpage) + title = hidden_inputs['media_title'] + + formats = [] + if hidden_inputs.get('player_type') == 'video' and hidden_inputs.get('stream_file') == '1': + formats = self._extract_smil_formats( + 'http://www.dw.com/smil/v-%s' % media_id, media_id, + transform_source=lambda s: s.replace( + 'rtmp://tv-od.dw.de/flash/', + 'http://tv-download.dw.de/dwtv_video/flv/')) + else: + formats = [{'url': hidden_inputs['file_name']}] + + return { + 'id': media_id, + 'title': title, + 'description': self._og_search_description(webpage), + 'thumbnail': hidden_inputs.get('preview_image'), + 'duration': int_or_none(hidden_inputs.get('file_duration')), + 'upload_date': hidden_inputs.get('display_date'), + 'formats': formats, + } + + +class DWArticleIE(InfoExtractor): + IE_NAME = 'dw:article' + _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+a-(?P<id>\d+)' + _TEST = { + 'url': 'http://www.dw.com/en/no-hope-limited-options-for-refugees-in-idomeni/a-19111009', + 'md5': '8ca657f9d068bbef74d6fc38b97fc869', + 'info_dict': { + 'id': '19105868', + 'ext': 'mp4', + 'title': 'The harsh life of refugees in Idomeni', + 'description': 'md5:196015cc7e48ebf474db9399420043c7', + 'upload_date': '20160310', + } + } + + def _real_extract(self, url): + article_id = self._match_id(url) + webpage = self._download_webpage(url, article_id) + hidden_inputs = self._hidden_inputs(webpage) + media_id = hidden_inputs['media_id'] + media_path = self._search_regex(r'href="([^"]+av-%s)"\s+class="overlayLink"' % media_id, webpage, 'media url') + media_url = compat_urlparse.urljoin(url, media_path) + return self.url_result(media_url, 'DW', media_id) diff --git a/youtube_dl/extractor/elpais.py b/youtube_dl/extractor/elpais.py index 00a69e631..8c725a4e6 100644 --- a/youtube_dl/extractor/elpais.py +++ b/youtube_dl/extractor/elpais.py @@ -9,7 +9,7 @@ class ElPaisIE(InfoExtractor): _VALID_URL = r'https?://(?:[^.]+\.)?elpais\.com/.*/(?P<id>[^/#?]+)\.html(?:$|[?#])' IE_DESC = 'El País' - _TEST = { + _TESTS = [{ 'url': 'http://blogs.elpais.com/la-voz-de-inaki/2014/02/tiempo-nuevo-recetas-viejas.html', 'md5': '98406f301f19562170ec071b83433d55', 'info_dict': { @@ -19,30 +19,41 @@ class ElPaisIE(InfoExtractor): 'description': 'De lunes a viernes, a partir de las ocho de la mañana, Iñaki Gabilondo nos cuenta su visión de la actualidad nacional e internacional.', 'upload_date': '20140206', } - } + }, { + 'url': 'http://elcomidista.elpais.com/elcomidista/2016/02/24/articulo/1456340311_668921.html#?id_externo_nwl=newsletter_diaria20160303t', + 'md5': '3bd5b09509f3519d7d9e763179b013de', + 'info_dict': { + 'id': '1456340311_668921', + 'ext': 'mp4', + 'title': 'Cómo hacer el mejor café con cafetera italiana', + 'description': 'Que sí, que las cápsulas son cómodas. Pero si le pides algo más a la vida, quizá deberías aprender a usar bien la cafetera italiana. No tienes más que ver este vídeo y seguir sus siete normas básicas.', + 'upload_date': '20160303', + } + }] def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) prefix = self._html_search_regex( - r'var url_cache = "([^"]+)";', webpage, 'URL prefix') + r'var\s+url_cache\s*=\s*"([^"]+)";', webpage, 'URL prefix') video_suffix = self._search_regex( - r"URLMediaFile = url_cache \+ '([^']+)'", webpage, 'video URL') + r"(?:URLMediaFile|urlVideo_\d+)\s*=\s*url_cache\s*\+\s*'([^']+)'", webpage, 'video URL') video_url = prefix + video_suffix thumbnail_suffix = self._search_regex( - r"URLMediaStill = url_cache \+ '([^']+)'", webpage, 'thumbnail URL', - fatal=False) + r"(?:URLMediaStill|urlFotogramaFijo_\d+)\s*=\s*url_cache\s*\+\s*'([^']+)'", + webpage, 'thumbnail URL', fatal=False) thumbnail = ( None if thumbnail_suffix is None else prefix + thumbnail_suffix) title = self._html_search_regex( - '<h2 class="entry-header entry-title.*?>(.*?)</h2>', + (r"tituloVideo\s*=\s*'([^']+)'", webpage, 'title', + r'<h2 class="entry-header entry-title.*?>(.*?)</h2>'), webpage, 'title') - date_str = self._search_regex( + upload_date = unified_strdate(self._search_regex( r'<p class="date-header date-int updated"\s+title="([^"]+)">', - webpage, 'upload date', fatal=False) - upload_date = (None if date_str is None else unified_strdate(date_str)) + webpage, 'upload date', default=None) or self._html_search_meta( + 'datePublished', webpage, 'timestamp')) return { 'id': video_id, diff --git a/youtube_dl/extractor/engadget.py b/youtube_dl/extractor/engadget.py index e4180701d..e5e57d485 100644 --- a/youtube_dl/extractor/engadget.py +++ b/youtube_dl/extractor/engadget.py @@ -1,21 +1,13 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( - url_basename, -) class EngadgetIE(InfoExtractor): - _VALID_URL = r'''(?x)https?://www.engadget.com/ - (?:video(?:/5min)?/(?P<id>\d+)| - [\d/]+/.*?) - ''' + _VALID_URL = r'https?://www.engadget.com/video/(?P<id>\d+)' _TEST = { - 'url': 'http://www.engadget.com/video/5min/518153925/', + 'url': 'http://www.engadget.com/video/518153925/', 'md5': 'c6820d4828a5064447a4d9fc73f312c9', 'info_dict': { 'id': '518153925', @@ -27,15 +19,4 @@ class EngadgetIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - - if video_id is not None: - return self.url_result('5min:%s' % video_id) - else: - title = url_basename(url) - webpage = self._download_webpage(url, title) - ids = re.findall(r'<iframe[^>]+?playList=(\d+)', webpage) - return { - '_type': 'playlist', - 'title': title, - 'entries': [self.url_result('5min:%s' % vid) for vid in ids] - } + return self.url_result('5min:%s' % video_id) diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index 6c6c3b1bd..f5bbd39d2 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -37,7 +37,9 @@ class FacebookIE(InfoExtractor): video/embed| story\.php )\?(?:.*?)(?:v|video_id|story_fbid)=| - [^/]+/videos/(?:[^/]+/)? + [^/]+/videos/(?:[^/]+/)?| + [^/]+/posts/| + groups/[^/]+/permalink/ )| facebook: ) @@ -50,6 +52,8 @@ class FacebookIE(InfoExtractor): _CHROME_USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.97 Safari/537.36' + _VIDEO_PAGE_TEMPLATE = 'https://www.facebook.com/video/video.php?v=%s' + _TESTS = [{ 'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf', 'md5': '6a40d33c0eccbb1af76cf0485a052659', @@ -82,6 +86,33 @@ class FacebookIE(InfoExtractor): 'uploader': 'Demy de Zeeuw', }, }, { + 'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570', + 'md5': '037b1fa7f3c2d02b7a0d7bc16031ecc6', + 'info_dict': { + 'id': '544765982287235', + 'ext': 'mp4', + 'title': '"What are you doing running in the snow?"', + 'uploader': 'FailArmy', + } + }, { + 'url': 'https://m.facebook.com/story.php?story_fbid=1035862816472149&id=116132035111903', + 'md5': '1deb90b6ac27f7efcf6d747c8a27f5e3', + 'info_dict': { + 'id': '1035862816472149', + 'ext': 'mp4', + 'title': 'What the Flock Is Going On In New Zealand Credit: ViralHog', + 'uploader': 'S. Saint', + }, + }, { + 'note': 'swf params escaped', + 'url': 'https://www.facebook.com/barackobama/posts/10153664894881749', + 'md5': '97ba073838964d12c70566e0085c2b91', + 'info_dict': { + 'id': '10153664894881749', + 'ext': 'mp4', + 'title': 'Facebook video #10153664894881749', + }, + }, { 'url': 'https://www.facebook.com/video.php?v=10204634152394104', 'only_matching': True, }, { @@ -94,7 +125,7 @@ class FacebookIE(InfoExtractor): 'url': 'facebook:544765982287235', 'only_matching': True, }, { - 'url': 'https://m.facebook.com/story.php?story_fbid=1035862816472149&id=116132035111903', + 'url': 'https://www.facebook.com/groups/164828000315060/permalink/764967300301124/', 'only_matching': True, }] @@ -164,19 +195,19 @@ class FacebookIE(InfoExtractor): def _real_initialize(self): self._login() - def _real_extract(self, url): - video_id = self._match_id(url) - req = sanitized_Request('https://www.facebook.com/video/video.php?v=%s' % video_id) + def _extract_from_url(self, url, video_id, fatal_if_no_video=True): + req = sanitized_Request(url) req.add_header('User-Agent', self._CHROME_USER_AGENT) webpage = self._download_webpage(req, video_id) video_data = None - BEFORE = '{swf.addParam(param[0], param[1]);});\n' + BEFORE = '{swf.addParam(param[0], param[1]);});' AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});' - m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage) + m = re.search(re.escape(BEFORE) + '(?:\n|\\\\n)(.*?)' + re.escape(AFTER), webpage) if m: - data = dict(json.loads(m.group(1))) + swf_params = m.group(1).replace('\\\\', '\\').replace('\\"', '"') + data = dict(json.loads(swf_params)) params_raw = compat_urllib_parse_unquote(data['params']) video_data = json.loads(params_raw)['video_data'] @@ -189,13 +220,15 @@ class FacebookIE(InfoExtractor): if not video_data: server_js_data = self._parse_json(self._search_regex( - r'handleServerJS\(({.+})\);', webpage, 'server js data'), video_id) + r'handleServerJS\(({.+})\);', webpage, 'server js data', default='{}'), video_id) for item in server_js_data.get('instances', []): if item[1][0] == 'VideoConfig': video_data = video_data_list2dict(item[2][0]['videoData']) break if not video_data: + if not fatal_if_no_video: + return webpage, False m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage) if m_msg is not None: raise ExtractorError( @@ -241,39 +274,36 @@ class FacebookIE(InfoExtractor): video_title = 'Facebook video #%s' % video_id uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage)) - return { + info_dict = { 'id': video_id, 'title': video_title, 'formats': formats, 'uploader': uploader, } - -class FacebookPostIE(InfoExtractor): - IE_NAME = 'facebook:post' - _VALID_URL = r'https?://(?:\w+\.)?facebook\.com/[^/]+/posts/(?P<id>\d+)' - _TEST = { - 'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570', - 'md5': '037b1fa7f3c2d02b7a0d7bc16031ecc6', - 'info_dict': { - 'id': '544765982287235', - 'ext': 'mp4', - 'title': '"What are you doing running in the snow?"', - 'uploader': 'FailArmy', - } - } + return webpage, info_dict def _real_extract(self, url): - post_id = self._match_id(url) + video_id = self._match_id(url) + + real_url = self._VIDEO_PAGE_TEMPLATE % video_id if url.startswith('facebook:') else url + webpage, info_dict = self._extract_from_url(real_url, video_id, fatal_if_no_video=False) - webpage = self._download_webpage(url, post_id) + if info_dict: + return info_dict - entries = [ - self.url_result('facebook:%s' % video_id, FacebookIE.ie_key()) - for video_id in self._parse_json( - self._search_regex( - r'(["\'])video_ids\1\s*:\s*(?P<ids>\[.+?\])', - webpage, 'video ids', group='ids'), - post_id)] + if '/posts/' in url: + entries = [ + self.url_result('facebook:%s' % vid, FacebookIE.ie_key()) + for vid in self._parse_json( + self._search_regex( + r'(["\'])video_ids\1\s*:\s*(?P<ids>\[.+?\])', + webpage, 'video ids', group='ids'), + video_id)] - return self.playlist_result(entries, post_id) + return self.playlist_result(entries, video_id) + else: + _, info_dict = self._extract_from_url( + self._VIDEO_PAGE_TEMPLATE % video_id, + video_id, fatal_if_no_video=True) + return info_dict diff --git a/youtube_dl/extractor/fivemin.py b/youtube_dl/extractor/fivemin.py index 2955965d9..67d50a386 100644 --- a/youtube_dl/extractor/fivemin.py +++ b/youtube_dl/extractor/fivemin.py @@ -1,5 +1,7 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..compat import ( compat_urllib_parse, @@ -16,12 +18,7 @@ from ..utils import ( class FiveMinIE(InfoExtractor): IE_NAME = '5min' - _VALID_URL = r'''(?x) - (?:https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(?:.*?&)?playList=| - https?://(?:(?:massively|www)\.)?joystiq\.com/video/| - 5min:) - (?P<id>\d+) - ''' + _VALID_URL = r'(?:5min:(?P<id>\d+)(?::(?P<sid>\d+))?|https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(?P<query>.*))' _TESTS = [ { @@ -45,6 +42,7 @@ class FiveMinIE(InfoExtractor): 'title': 'How to Make a Next-Level Fruit Salad', 'duration': 184, }, + 'skip': 'no longer available', }, ] _ERRORS = { @@ -91,20 +89,33 @@ class FiveMinIE(InfoExtractor): } def _real_extract(self, url): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + sid = mobj.group('sid') + + if mobj.group('query'): + qs = compat_parse_qs(mobj.group('query')) + if not qs.get('playList'): + raise ExtractorError('Invalid URL', expected=True) + video_id = qs['playList'][0] + if qs.get('sid'): + sid = qs['sid'][0] + embed_url = 'https://embed.5min.com/playerseed/?playList=%s' % video_id - embed_page = self._download_webpage(embed_url, video_id, - 'Downloading embed page') - sid = self._search_regex(r'sid=(\d+)', embed_page, 'sid') - query = compat_urllib_parse.urlencode({ - 'func': 'GetResults', - 'playlist': video_id, - 'sid': sid, - 'isPlayerSeed': 'true', - 'url': embed_url, - }) + if not sid: + embed_page = self._download_webpage(embed_url, video_id, + 'Downloading embed page') + sid = self._search_regex(r'sid=(\d+)', embed_page, 'sid') + response = self._download_json( - 'https://syn.5min.com/handlers/SenseHandler.ashx?' + query, + 'https://syn.5min.com/handlers/SenseHandler.ashx?' + + compat_urllib_parse.urlencode({ + 'func': 'GetResults', + 'playlist': video_id, + 'sid': sid, + 'isPlayerSeed': 'true', + 'url': embed_url, + }), video_id) if not response['success']: raise ExtractorError( @@ -118,9 +129,7 @@ class FiveMinIE(InfoExtractor): parsed_video_url = compat_urllib_parse_urlparse(compat_parse_qs( compat_urllib_parse_urlparse(info['EmbededURL']).query)['videoUrl'][0]) for rendition in info['Renditions']: - if rendition['RenditionType'] == 'm3u8': - formats.extend(self._extract_m3u8_formats(rendition['Url'], video_id, m3u8_id='hls')) - elif rendition['RenditionType'] == 'aac': + if rendition['RenditionType'] == 'aac' or rendition['RenditionType'] == 'm3u8': continue else: rendition_url = compat_urlparse.urlunparse(parsed_video_url._replace(path=replace_extension(parsed_video_url.path.replace('//', '/%s/' % rendition['ID']), rendition['RenditionType']))) diff --git a/youtube_dl/extractor/foxnews.py b/youtube_dl/extractor/foxnews.py index 318ac013d..1dc50318c 100644 --- a/youtube_dl/extractor/foxnews.py +++ b/youtube_dl/extractor/foxnews.py @@ -36,6 +36,10 @@ class FoxNewsIE(AMPIE): # 'upload_date': '20141204', 'thumbnail': 're:^https?://.*\.jpg$', }, + 'params': { + # m3u8 download + 'skip_download': True, + }, }, { 'url': 'http://video.foxnews.com/v/video-embed.html?video_id=3937480&d=video.foxnews.com', diff --git a/youtube_dl/extractor/freespeech.py b/youtube_dl/extractor/freespeech.py index c210177f7..1477708bb 100644 --- a/youtube_dl/extractor/freespeech.py +++ b/youtube_dl/extractor/freespeech.py @@ -14,7 +14,7 @@ class FreespeechIE(InfoExtractor): 'url': 'https://www.freespeech.org/video/obama-romney-campaign-colorado-ahead-debate-0', 'info_dict': { 'id': 'poKsVCZ64uU', - 'ext': 'mp4', + 'ext': 'webm', 'title': 'Obama, Romney Campaign in Colorado Ahead of Debate', 'description': 'Obama, Romney Campaign in Colorado Ahead of Debate', 'uploader': 'freespeechtv', diff --git a/youtube_dl/extractor/gameinformer.py b/youtube_dl/extractor/gameinformer.py index 25870c131..a66e309de 100644 --- a/youtube_dl/extractor/gameinformer.py +++ b/youtube_dl/extractor/gameinformer.py @@ -2,42 +2,27 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import compat_str -from ..utils import int_or_none class GameInformerIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?gameinformer\.com/(?:[^/]+/)*(?P<id>.+)\.aspx' _TEST = { 'url': 'http://www.gameinformer.com/b/features/archive/2015/09/26/replay-animal-crossing.aspx', + 'md5': '292f26da1ab4beb4c9099f1304d2b071', 'info_dict': { 'id': '4515472681001', - 'ext': 'm3u8', + 'ext': 'mp4', 'title': 'Replay - Animal Crossing', 'description': 'md5:2e211891b215c85d061adc7a4dd2d930', - 'timestamp': 1443457610706, - }, - 'params': { - # m3u8 download - 'skip_download': True, + 'timestamp': 1443457610, + 'upload_date': '20150928', + 'uploader_id': '694940074001', }, } + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/694940074001/default_default/index.html?videoId=%s' def _real_extract(self, url): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) - - bc_api_url = self._search_regex(r"getVideo\('([^']+)'", webpage, 'brightcove api url') - json_data = self._download_json( - bc_api_url + '&video_fields=id,name,shortDescription,publishedDate,videoStillURL,length,IOSRenditions', - display_id) - - return { - 'id': compat_str(json_data['id']), - 'display_id': display_id, - 'url': json_data['IOSRenditions'][0]['url'], - 'title': json_data['name'], - 'description': json_data.get('shortDescription'), - 'timestamp': int_or_none(json_data.get('publishedDate')), - 'duration': int_or_none(json_data.get('length')), - } + brightcove_id = self._search_regex(r"getVideo\('[^']+video_id=(\d+)", webpage, 'brightcove id') + return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index ca745ae41..8121f04a5 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -1242,28 +1242,34 @@ class GenericIE(InfoExtractor): full_response = self._request_webpage(request, video_id) head_response = full_response + info_dict = { + 'id': video_id, + 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), + } + # Check for direct link to a video content_type = head_response.headers.get('Content-Type', '') m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>.+)$', content_type) if m: upload_date = unified_strdate( head_response.headers.get('Last-Modified')) - formats = [] - if m.group('format_id').endswith('mpegurl'): + format_id = m.group('format_id') + if format_id.endswith('mpegurl'): formats = self._extract_m3u8_formats(url, video_id, 'mp4') + elif format_id == 'f4m': + formats = self._extract_f4m_formats(url, video_id) else: formats = [{ 'format_id': m.group('format_id'), 'url': url, 'vcodec': 'none' if m.group('type') == 'audio' else None }] - return { - 'id': video_id, - 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), + info_dict.update({ 'direct': True, 'formats': formats, 'upload_date': upload_date, - } + }) + return info_dict if not self._downloader.params.get('test', False) and not is_intentional: force = self._downloader.params.get('force_generic_extractor', False) @@ -1291,13 +1297,12 @@ class GenericIE(InfoExtractor): 'URL could be a direct video link, returning it as such.') upload_date = unified_strdate( head_response.headers.get('Last-Modified')) - return { - 'id': video_id, - 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), + info_dict.update({ 'direct': True, 'url': url, 'upload_date': upload_date, - } + }) + return info_dict webpage = self._webpage_read_content( full_response, url, video_id, prefix=first_bytes) @@ -1314,12 +1319,12 @@ class GenericIE(InfoExtractor): elif doc.tag == '{http://xspf.org/ns/0/}playlist': return self.playlist_result(self._parse_xspf(doc, video_id), video_id) elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag): - return { - 'id': video_id, - 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), - 'formats': self._parse_mpd_formats( - doc, video_id, mpd_base_url=url.rpartition('/')[0]), - } + info_dict['formats'] = self._parse_mpd_formats( + doc, video_id, mpd_base_url=url.rpartition('/')[0]) + return info_dict + elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag): + info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id) + return info_dict except compat_xml_parse_error: pass @@ -1985,6 +1990,8 @@ class GenericIE(InfoExtractor): entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4') elif ext == 'mpd': entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id) + elif ext == 'f4m': + entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id) else: entry_info_dict['url'] = video_url diff --git a/youtube_dl/extractor/googledrive.py b/youtube_dl/extractor/googledrive.py index 37be34091..766fc26d0 100644 --- a/youtube_dl/extractor/googledrive.py +++ b/youtube_dl/extractor/googledrive.py @@ -10,8 +10,8 @@ from ..utils import ( class GoogleDriveIE(InfoExtractor): - _VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28})' - _TEST = { + _VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28,})' + _TESTS = [{ 'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1', 'md5': '881f7700aec4f538571fa1e0eed4a7b6', 'info_dict': { @@ -20,7 +20,11 @@ class GoogleDriveIE(InfoExtractor): 'title': 'Big Buck Bunny.mp4', 'duration': 46, } - } + }, { + # video id is longer than 28 characters + 'url': 'https://drive.google.com/file/d/1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ/edit', + 'only_matching': True, + }] _FORMATS_EXT = { '5': 'flv', '6': 'flv', @@ -43,7 +47,7 @@ class GoogleDriveIE(InfoExtractor): @staticmethod def _extract_url(webpage): mobj = re.search( - r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28})', + r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28,})', webpage) if mobj: return 'https://drive.google.com/file/d/%s' % mobj.group('id') diff --git a/youtube_dl/extractor/indavideo.py b/youtube_dl/extractor/indavideo.py index 12fb5e8e1..9622f198a 100644 --- a/youtube_dl/extractor/indavideo.py +++ b/youtube_dl/extractor/indavideo.py @@ -73,7 +73,7 @@ class IndavideoEmbedIE(InfoExtractor): 'url': self._proto_relative_url(thumbnail) } for thumbnail in video.get('thumbnails', [])] - tags = [tag['title'] for tag in video.get('tags', [])] + tags = [tag['title'] for tag in video.get('tags') or []] return { 'id': video.get('id') or video_id, diff --git a/youtube_dl/extractor/iqiyi.py b/youtube_dl/extractor/iqiyi.py index d3bee3a19..e7c0cb3f6 100644 --- a/youtube_dl/extractor/iqiyi.py +++ b/youtube_dl/extractor/iqiyi.py @@ -501,7 +501,7 @@ class IqiyiIE(InfoExtractor): def get_enc_key(self, video_id): # TODO: automatic key extraction # last update at 2016-01-22 for Zombie::bite - enc_key = '6ab6d0280511493ba85594779759d4ed' + enc_key = '8ed797d224d043e7ac23d95b70227d32' return enc_key def _extract_playlist(self, webpage): diff --git a/youtube_dl/extractor/jeuxvideo.py b/youtube_dl/extractor/jeuxvideo.py index eef7daa29..137db873c 100644 --- a/youtube_dl/extractor/jeuxvideo.py +++ b/youtube_dl/extractor/jeuxvideo.py @@ -30,7 +30,7 @@ class JeuxVideoIE(InfoExtractor): webpage = self._download_webpage(url, title) title = self._html_search_meta('name', webpage) or self._og_search_title(webpage) config_url = self._html_search_regex( - r'data-src="(/contenu/medias/video.php.*?)"', + r'data-src(?:set-video)?="(/contenu/medias/video.php.*?)"', webpage, 'config URL') config_url = 'http://www.jeuxvideo.com' + config_url diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py index ccbc39c66..44d7c84a1 100644 --- a/youtube_dl/extractor/kaltura.py +++ b/youtube_dl/extractor/kaltura.py @@ -8,6 +8,7 @@ from .common import InfoExtractor from ..compat import ( compat_urllib_parse, compat_urlparse, + compat_parse_qs, ) from ..utils import ( clean_html, @@ -20,21 +21,17 @@ from ..utils import ( class KalturaIE(InfoExtractor): _VALID_URL = r'''(?x) (?: - kaltura:(?P<partner_id_s>\d+):(?P<id_s>[0-9a-z_]+)| + kaltura:(?P<partner_id>\d+):(?P<id>[0-9a-z_]+)| https?:// (:?(?:www|cdnapi(?:sec)?)\.)?kaltura\.com/ (?: (?: # flash player - index\.php/kwidget/ - (?:[^/]+/)*?wid/_(?P<partner_id>\d+)/ - (?:[^/]+/)*?entry_id/(?P<id>[0-9a-z_]+)| + index\.php/kwidget| # html5 player - html5/html5lib/ - (?:[^/]+/)*?entry_id/(?P<id_html5>[0-9a-z_]+) - .*\?.*\bwid=_(?P<partner_id_html5>\d+) + html5/html5lib/[^/]+/mwEmbedFrame\.php ) - ) + )(?:/(?P<path>[^?]+))?(?:\?(?P<query>.*))? ) ''' _API_BASE = 'http://cdnapi.kaltura.com/api_v3/index.php?' @@ -127,10 +124,41 @@ class KalturaIE(InfoExtractor): url, smuggled_data = unsmuggle_url(url, {}) mobj = re.match(self._VALID_URL, url) - partner_id = mobj.group('partner_id_s') or mobj.group('partner_id') or mobj.group('partner_id_html5') - entry_id = mobj.group('id_s') or mobj.group('id') or mobj.group('id_html5') - - info, flavor_assets = self._get_video_info(entry_id, partner_id) + partner_id, entry_id = mobj.group('partner_id', 'id') + ks = None + if partner_id and entry_id: + info, flavor_assets = self._get_video_info(entry_id, partner_id) + else: + path, query = mobj.group('path', 'query') + if not path and not query: + raise ExtractorError('Invalid URL', expected=True) + params = {} + if query: + params = compat_parse_qs(query) + if path: + splitted_path = path.split('/') + params.update(dict((zip(splitted_path[::2], [[v] for v in splitted_path[1::2]])))) + if 'wid' in params: + partner_id = params['wid'][0][1:] + elif 'p' in params: + partner_id = params['p'][0] + else: + raise ExtractorError('Invalid URL', expected=True) + if 'entry_id' in params: + entry_id = params['entry_id'][0] + info, flavor_assets = self._get_video_info(entry_id, partner_id) + elif 'uiconf_id' in params and 'flashvars[referenceId]' in params: + reference_id = params['flashvars[referenceId]'][0] + webpage = self._download_webpage(url, reference_id) + entry_data = self._parse_json(self._search_regex( + r'window\.kalturaIframePackageData\s*=\s*({.*});', + webpage, 'kalturaIframePackageData'), + reference_id)['entryResult'] + info, flavor_assets = entry_data['meta'], entry_data['contextData']['flavorAssets'] + entry_id = info['id'] + else: + raise ExtractorError('Invalid URL', expected=True) + ks = params.get('flashvars[ks]', [None])[0] source_url = smuggled_data.get('source_url') if source_url: @@ -140,14 +168,19 @@ class KalturaIE(InfoExtractor): else: referrer = None + def sign_url(unsigned_url): + if ks: + unsigned_url += '/ks/%s' % ks + if referrer: + unsigned_url += '?referrer=%s' % referrer + return unsigned_url + formats = [] for f in flavor_assets: # Continue if asset is not ready if f['status'] != 2: continue - video_url = '%s/flavorId/%s' % (info['dataUrl'], f['id']) - if referrer: - video_url += '?referrer=%s' % referrer + video_url = sign_url('%s/flavorId/%s' % (info['dataUrl'], f['id'])) formats.append({ 'format_id': '%(fileExt)s-%(bitrate)s' % f, 'ext': f.get('fileExt'), @@ -160,9 +193,7 @@ class KalturaIE(InfoExtractor): 'width': int_or_none(f.get('width')), 'url': video_url, }) - m3u8_url = info['dataUrl'].replace('format/url', 'format/applehttp') - if referrer: - m3u8_url += '?referrer=%s' % referrer + m3u8_url = sign_url(info['dataUrl'].replace('format/url', 'format/applehttp')) formats.extend(self._extract_m3u8_formats( m3u8_url, entry_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) diff --git a/youtube_dl/extractor/khanacademy.py b/youtube_dl/extractor/khanacademy.py index 08a671fa8..61739efa7 100644 --- a/youtube_dl/extractor/khanacademy.py +++ b/youtube_dl/extractor/khanacademy.py @@ -14,10 +14,10 @@ class KhanAcademyIE(InfoExtractor): _TESTS = [{ 'url': 'http://www.khanacademy.org/video/one-time-pad', - 'md5': '7021db7f2d47d4fff89b13177cb1e8f4', + 'md5': '7b391cce85e758fb94f763ddc1bbb979', 'info_dict': { 'id': 'one-time-pad', - 'ext': 'mp4', + 'ext': 'webm', 'title': 'The one-time pad', 'description': 'The perfect cipher', 'duration': 176, diff --git a/youtube_dl/extractor/kusi.py b/youtube_dl/extractor/kusi.py new file mode 100644 index 000000000..931f34c9b --- /dev/null +++ b/youtube_dl/extractor/kusi.py @@ -0,0 +1,99 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import random +import re + +from .common import InfoExtractor +from ..compat import compat_urllib_parse_unquote_plus +from ..utils import ( + int_or_none, + float_or_none, + timeconvert, + update_url_query, + xpath_text, +) + + +class KUSIIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?kusi\.com/(?P<path>story/.+|video\?clipId=(?P<clipId>\d+))' + _TESTS = [{ + 'url': 'http://www.kusi.com/story/31183873/turko-files-case-closed-put-on-hold', + 'md5': 'f926e7684294cf8cb7bdf8858e1b3988', + 'info_dict': { + 'id': '12203019', + 'ext': 'mp4', + 'title': 'Turko Files: Case Closed! & Put On Hold!', + 'duration': 231.0, + 'upload_date': '20160210', + 'timestamp': 1455087571, + 'thumbnail': 're:^https?://.*\.jpg$' + }, + }, { + 'url': 'http://kusi.com/video?clipId=12203019', + 'info_dict': { + 'id': '12203019', + 'ext': 'mp4', + 'title': 'Turko Files: Case Closed! & Put On Hold!', + 'duration': 231.0, + 'upload_date': '20160210', + 'timestamp': 1455087571, + 'thumbnail': 're:^https?://.*\.jpg$' + }, + 'params': { + 'skip_download': True, # Same as previous one + }, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + clip_id = mobj.group('clipId') + video_id = clip_id or mobj.group('path') + + webpage = self._download_webpage(url, video_id) + + if clip_id is None: + video_id = clip_id = self._html_search_regex( + r'"clipId"\s*,\s*"(\d+)"', webpage, 'clip id') + + affiliate_id = self._search_regex( + r'affiliateId\s*:\s*\'([^\']+)\'', webpage, 'affiliate id') + + # See __Packages/worldnow/model/GalleryModel.as of WNGallery.swf + xml_url = update_url_query('http://www.kusi.com/build.asp', { + 'buildtype': 'buildfeaturexmlrequest', + 'featureType': 'Clip', + 'featureid': clip_id, + 'affiliateno': affiliate_id, + 'clientgroupid': '1', + 'rnd': int(round(random.random() * 1000000)), + }) + + doc = self._download_xml(xml_url, video_id) + + video_title = xpath_text(doc, 'HEADLINE', fatal=True) + duration = float_or_none(xpath_text(doc, 'DURATION'), scale=1000) + description = xpath_text(doc, 'ABSTRACT') + thumbnail = xpath_text(doc, './THUMBNAILIMAGE/FILENAME') + createtion_time = timeconvert(xpath_text(doc, 'rfc822creationdate')) + + quality_options = doc.find('{http://search.yahoo.com/mrss/}group').findall('{http://search.yahoo.com/mrss/}content') + formats = [] + for quality in quality_options: + formats.append({ + 'url': compat_urllib_parse_unquote_plus(quality.attrib['url']), + 'height': int_or_none(quality.attrib.get('height')), + 'width': int_or_none(quality.attrib.get('width')), + 'vbr': float_or_none(quality.attrib.get('bitratebits'), scale=1000), + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': video_title, + 'description': description, + 'duration': duration, + 'formats': formats, + 'thumbnail': thumbnail, + 'timestamp': createtion_time, + } diff --git a/youtube_dl/extractor/kuwo.py b/youtube_dl/extractor/kuwo.py index 700e44b63..f94804d06 100644 --- a/youtube_dl/extractor/kuwo.py +++ b/youtube_dl/extractor/kuwo.py @@ -23,7 +23,7 @@ class KuwoBaseIE(InfoExtractor): {'format': 'aac', 'ext': 'aac', 'abr': 48, 'preference': 10} ] - def _get_formats(self, song_id): + def _get_formats(self, song_id, tolerate_ip_deny=False): formats = [] for file_format in self._FORMATS: song_url = self._download_webpage( @@ -32,7 +32,7 @@ class KuwoBaseIE(InfoExtractor): song_id, note='Download %s url info' % file_format['format'], ) - if song_url == 'IPDeny': + if song_url == 'IPDeny' and not tolerate_ip_deny: raise ExtractorError('This song is blocked in this region', expected=True) if song_url.startswith('http://') or song_url.startswith('https://'): @@ -43,7 +43,12 @@ class KuwoBaseIE(InfoExtractor): 'preference': file_format['preference'], 'abr': file_format.get('abr'), }) - self._sort_formats(formats) + + # XXX _sort_formats fails if there are not formats, while it's not the + # desired behavior if 'IPDeny' is ignored + # This check can be removed if https://github.com/rg3/youtube-dl/pull/8051 is merged + if not tolerate_ip_deny: + self._sort_formats(formats) return formats @@ -288,10 +293,16 @@ class KuwoMvIE(KuwoBaseIE): 'url': 'http://www.kuwo.cn/mv/6480076/', 'info_dict': { 'id': '6480076', - 'ext': 'mkv', - 'title': '我们家MV', + 'ext': 'mp4', + 'title': 'My HouseMV', 'creator': '2PM', }, + # In this video, music URLs (anti.s) are blocked outside China and + # USA, while the MV URL (mvurl) is available globally, so force the MV + # URL for consistent results in different countries + 'params': { + 'format': 'mv', + }, } _FORMATS = KuwoBaseIE._FORMATS + [ {'format': 'mkv', 'ext': 'mkv', 'preference': 250}, @@ -313,7 +324,17 @@ class KuwoMvIE(KuwoBaseIE): else: raise ExtractorError('Unable to find song or singer names') - formats = self._get_formats(song_id) + formats = self._get_formats(song_id, tolerate_ip_deny=True) + + mv_url = self._download_webpage( + 'http://www.kuwo.cn/yy/st/mvurl?rid=MUSIC_%s' % song_id, + song_id, note='Download %s MV URL' % song_id) + formats.append({ + 'url': mv_url, + 'format_id': 'mv', + }) + + self._sort_formats(formats) return { 'id': song_id, diff --git a/youtube_dl/extractor/leeco.py b/youtube_dl/extractor/leeco.py index d0cd3f591..df47e88ba 100644 --- a/youtube_dl/extractor/leeco.py +++ b/youtube_dl/extractor/leeco.py @@ -217,14 +217,8 @@ class LePlaylistIE(InfoExtractor): 'playlist_mincount': 96 }, { 'url': 'http://tv.le.com/pzt/lswjzzjc/index.shtml', - 'info_dict': { - 'id': 'lswjzzjc', - # The title should be "劲舞青春", but I can't find a simple way to - # determine the playlist title - 'title': '乐视午间自制剧场', - 'description': 'md5:b1eef244f45589a7b5b1af9ff25a4489' - }, - 'playlist_mincount': 7 + # This series is moved to http://www.le.com/tv/10005297.html + 'only_matching': True, }, { 'url': 'http://www.le.com/comic/92063.html', 'only_matching': True, @@ -338,7 +332,7 @@ class LetvCloudIE(InfoExtractor): formats.append({ 'url': url, 'ext': determine_ext(decoded_url), - 'format_id': int_or_none(play_url.get('vtype')), + 'format_id': str_or_none(play_url.get('vtype')), 'format_note': str_or_none(play_url.get('definition')), 'width': int_or_none(play_url.get('vwidth')), 'height': int_or_none(play_url.get('vheight')), diff --git a/youtube_dl/extractor/livestream.py b/youtube_dl/extractor/livestream.py index 38fb3d9e4..eada7c299 100644 --- a/youtube_dl/extractor/livestream.py +++ b/youtube_dl/extractor/livestream.py @@ -14,6 +14,7 @@ from ..utils import ( xpath_with_ns, xpath_text, orderedSet, + update_url_query, int_or_none, float_or_none, parse_iso8601, @@ -64,7 +65,7 @@ class LivestreamIE(InfoExtractor): def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None): base_ele = find_xpath_attr( smil, self._xpath_ns('.//meta', namespace), 'name', 'httpBase') - base = base_ele.get('content') if base_ele else 'http://livestreamvod-f.akamaihd.net/' + base = base_ele.get('content') if base_ele is not None else 'http://livestreamvod-f.akamaihd.net/' formats = [] video_nodes = smil.findall(self._xpath_ns('.//video', namespace)) @@ -72,7 +73,10 @@ class LivestreamIE(InfoExtractor): for vn in video_nodes: tbr = int_or_none(vn.attrib.get('system-bitrate'), 1000) furl = ( - '%s%s?v=3.0.3&fp=WIN%%2014,0,0,145' % (base, vn.attrib['src'])) + update_url_query(compat_urlparse.urljoin(base, vn.attrib['src']), { + 'v': '3.0.3', + 'fp': 'WIN% 14,0,0,145', + })) if 'clipBegin' in vn.attrib: furl += '&ssek=' + vn.attrib['clipBegin'] formats.append({ diff --git a/youtube_dl/extractor/makerschannel.py b/youtube_dl/extractor/makerschannel.py new file mode 100644 index 000000000..f5d00e61d --- /dev/null +++ b/youtube_dl/extractor/makerschannel.py @@ -0,0 +1,40 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class MakersChannelIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?makerschannel\.com/.*(?P<id_type>video|production)_id=(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://makerschannel.com/en/zoomin/community-highlights?video_id=849', + 'md5': '624a512c6969236b5967bf9286345ad1', + 'info_dict': { + 'id': '849', + 'ext': 'mp4', + 'title': 'Landing a bus on a plane is an epic win', + 'uploader': 'ZoomIn', + 'description': 'md5:cd9cca2ea7b69b78be81d07020c97139', + } + } + + def _real_extract(self, url): + id_type, url_id = re.match(self._VALID_URL, url).groups() + webpage = self._download_webpage(url, url_id) + video_data = self._html_search_regex(r'<div([^>]+data-%s-id="%s"[^>]+)>' % (id_type, url_id), webpage, 'video data') + + def extract_data_val(attr, fatal=False): + return self._html_search_regex(r'data-%s\s*=\s*"([^"]+)"' % attr, video_data, attr, fatal=fatal) + minoto_id = self._search_regex(r'/id/([a-zA-Z0-9]+)', extract_data_val('video-src', True), 'minoto id') + + return { + '_type': 'url_transparent', + 'url': 'minoto:%s' % minoto_id, + 'id': extract_data_val('video-id', True), + 'title': extract_data_val('title', True), + 'description': extract_data_val('description'), + 'thumbnail': extract_data_val('image'), + 'uploader': extract_data_val('channel'), + } diff --git a/youtube_dl/extractor/minoto.py b/youtube_dl/extractor/minoto.py new file mode 100644 index 000000000..959a10589 --- /dev/null +++ b/youtube_dl/extractor/minoto.py @@ -0,0 +1,56 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import int_or_none + + +class MinotoIE(InfoExtractor): + _VALID_URL = r'(?:minoto:|https?://(?:play|iframe|embed)\.minoto-video\.com/(?P<player_id>[0-9]+)/)(?P<id>[a-zA-Z0-9]+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + player_id = mobj.group('player_id') or '1' + video_id = mobj.group('id') + video_data = self._download_json('http://play.minoto-video.com/%s/%s.js' % (player_id, video_id), video_id) + video_metadata = video_data['video-metadata'] + formats = [] + for fmt in video_data['video-files']: + fmt_url = fmt.get('url') + if not fmt_url: + continue + container = fmt.get('container') + if container == 'hls': + formats.extend(fmt_url, video_id, 'mp4', m3u8_id='hls', fatal=False) + else: + fmt_profile = fmt.get('profile') or {} + f = { + 'format_id': fmt_profile.get('name-short'), + 'format_note': fmt_profile.get('name'), + 'url': fmt_url, + 'container': container, + 'tbr': int_or_none(fmt.get('bitrate')), + 'filesize': int_or_none(fmt.get('filesize')), + 'width': int_or_none(fmt.get('width')), + 'height': int_or_none(fmt.get('height')), + } + codecs = fmt.get('codecs') + if codecs: + codecs = codecs.split(',') + if len(codecs) == 2: + f.update({ + 'vcodec': codecs[0], + 'acodec': codecs[1], + }) + formats.append(f) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': video_metadata['title'], + 'description': video_metadata.get('description'), + 'thumbnail': video_metadata.get('video-poster', {}).get('url'), + 'formats': formats, + } diff --git a/youtube_dl/extractor/mit.py b/youtube_dl/extractor/mit.py index 29ca45778..819c1b90b 100644 --- a/youtube_dl/extractor/mit.py +++ b/youtube_dl/extractor/mit.py @@ -99,7 +99,7 @@ class OCWMITIE(InfoExtractor): 'url': 'http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041-probabilistic-systems-analysis-and-applied-probability-fall-2010/video-lectures/lecture-7-multiple-variables-expectations-independence/', 'info_dict': { 'id': 'EObHWIEKGjA', - 'ext': 'mp4', + 'ext': 'webm', 'title': 'Lecture 7: Multiple Discrete Random Variables: Expectations, Conditioning, Independence', 'description': 'In this lecture, the professor discussed multiple random variables, expectations, and binomial distribution.', 'upload_date': '20121109', diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index c2b7ed9ab..101497118 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -7,6 +7,7 @@ from ..compat import compat_urllib_parse_unquote from ..utils import ( ExtractorError, HEADRequest, + parse_count, str_to_int, ) @@ -85,8 +86,8 @@ class MixcloudIE(InfoExtractor): uploader_id = self._search_regex( r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False) description = self._og_search_description(webpage) - like_count = str_to_int(self._search_regex( - r'\bbutton-favorite\b[^>]+m-ajax-toggle-count="([^"]+)"', + like_count = parse_count(self._search_regex( + r'\bbutton-favorite[^>]+>.*?<span[^>]+class=["\']toggle-number[^>]+>\s*([^<]+)', webpage, 'like count', fatal=False)) view_count = str_to_int(self._search_regex( [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"', diff --git a/youtube_dl/extractor/noz.py b/youtube_dl/extractor/noz.py index 0ffb44b47..656443c49 100644 --- a/youtube_dl/extractor/noz.py +++ b/youtube_dl/extractor/noz.py @@ -5,7 +5,9 @@ from .common import InfoExtractor from ..compat import compat_urllib_parse_unquote from ..utils import ( int_or_none, + find_xpath_attr, xpath_text, + update_url_query, ) @@ -46,17 +48,32 @@ class NozIE(InfoExtractor): doc, './/article/movie/file/duration')) formats = [] for qnode in doc.findall('.//article/movie/file/qualities/qual'): - video_node = qnode.find('./html_urls/video_url[@format="video/mp4"]') - if video_node is None: - continue # auto - formats.append({ - 'url': video_node.text, - 'format_name': xpath_text(qnode, './name'), - 'format_id': xpath_text(qnode, './id'), - 'height': int_or_none(xpath_text(qnode, './height')), - 'width': int_or_none(xpath_text(qnode, './width')), - 'tbr': int_or_none(xpath_text(qnode, './bitrate'), scale=1000), - }) + http_url_ele = find_xpath_attr( + qnode, './html_urls/video_url', 'format', 'video/mp4') + http_url = http_url_ele.text if http_url_ele is not None else None + if http_url: + formats.append({ + 'url': http_url, + 'format_name': xpath_text(qnode, './name'), + 'format_id': '%s-%s' % ('http', xpath_text(qnode, './id')), + 'height': int_or_none(xpath_text(qnode, './height')), + 'width': int_or_none(xpath_text(qnode, './width')), + 'tbr': int_or_none(xpath_text(qnode, './bitrate'), scale=1000), + }) + else: + f4m_url = xpath_text(qnode, 'url_hd2') + if f4m_url: + formats.extend(self._extract_f4m_formats( + update_url_query(f4m_url, {'hdcore': '3.4.0'}), + video_id, f4m_id='hds', fatal=False)) + m3u8_url_ele = find_xpath_attr( + qnode, './html_urls/video_url', + 'format', 'application/vnd.apple.mpegurl') + m3u8_url = m3u8_url_ele.text if m3u8_url_ele is not None else None + if m3u8_url: + formats.extend(self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/pyvideo.py b/youtube_dl/extractor/pyvideo.py index 6d5732d45..30a5f2de4 100644 --- a/youtube_dl/extractor/pyvideo.py +++ b/youtube_dl/extractor/pyvideo.py @@ -12,14 +12,14 @@ class PyvideoIE(InfoExtractor): _TESTS = [ { 'url': 'http://pyvideo.org/video/1737/become-a-logging-expert-in-30-minutes', - 'md5': 'de317418c8bc76b1fd8633e4f32acbc6', + 'md5': '520915673e53a5c5d487c36e0c4d85b5', 'info_dict': { 'id': '24_4WWkSmNo', - 'ext': 'mp4', + 'ext': 'webm', 'title': 'Become a logging expert in 30 minutes', 'description': 'md5:9665350d466c67fb5b1598de379021f7', 'upload_date': '20130320', - 'uploader': 'NextDayVideo', + 'uploader': 'Next Day Video', 'uploader_id': 'NextDayVideo', }, 'add_ie': ['Youtube'], diff --git a/youtube_dl/extractor/revision3.py b/youtube_dl/extractor/revision3.py index b1b8800b9..99979ebe1 100644 --- a/youtube_dl/extractor/revision3.py +++ b/youtube_dl/extractor/revision3.py @@ -19,7 +19,7 @@ class Revision3IE(InfoExtractor): 'url': 'http://www.revision3.com/technobuffalo/5-google-predictions-for-2016', 'md5': 'd94a72d85d0a829766de4deb8daaf7df', 'info_dict': { - 'id': '73034', + 'id': '71089', 'display_id': 'technobuffalo/5-google-predictions-for-2016', 'ext': 'webm', 'title': '5 Google Predictions for 2016', @@ -31,6 +31,7 @@ class Revision3IE(InfoExtractor): 'uploader_id': 'technobuffalo', } }, { + # Show 'url': 'http://testtube.com/brainstuff', 'info_dict': { 'id': '251', @@ -41,7 +42,7 @@ class Revision3IE(InfoExtractor): }, { 'url': 'https://testtube.com/dnews/5-weird-ways-plants-can-eat-animals?utm_source=FB&utm_medium=DNews&utm_campaign=DNewsSocial', 'info_dict': { - 'id': '60163', + 'id': '58227', 'display_id': 'dnews/5-weird-ways-plants-can-eat-animals', 'duration': 275, 'ext': 'webm', @@ -52,18 +53,72 @@ class Revision3IE(InfoExtractor): 'uploader': 'DNews', 'uploader_id': 'dnews', }, + }, { + 'url': 'http://testtube.com/tt-editors-picks/the-israel-palestine-conflict-explained-in-ten-min', + 'info_dict': { + 'id': '71618', + 'ext': 'mp4', + 'display_id': 'tt-editors-picks/the-israel-palestine-conflict-explained-in-ten-min', + 'title': 'The Israel-Palestine Conflict Explained in Ten Minutes', + 'description': 'If you\'d like to learn about the struggle between Israelis and Palestinians, this video is a great place to start', + 'uploader': 'Editors\' Picks', + 'uploader_id': 'tt-editors-picks', + 'timestamp': 1453309200, + 'upload_date': '20160120', + }, + 'add_ie': ['Youtube'], + }, { + # Tag + 'url': 'http://testtube.com/tech-news', + 'info_dict': { + 'id': '21018', + 'title': 'tech news', + }, + 'playlist_mincount': 9, }] _PAGE_DATA_TEMPLATE = 'http://www.%s/apiProxy/ddn/%s?domain=%s' _API_KEY = 'ba9c741bce1b9d8e3defcc22193f3651b8867e62' def _real_extract(self, url): domain, display_id = re.match(self._VALID_URL, url).groups() + site = domain.split('.')[0] page_info = self._download_json( self._PAGE_DATA_TEMPLATE % (domain, display_id, domain), display_id) - if page_info['data']['type'] == 'episode': - episode_data = page_info['data'] - video_id = compat_str(episode_data['video']['data']['id']) + page_data = page_info['data'] + page_type = page_data['type'] + if page_type in ('episode', 'embed'): + show_data = page_data['show']['data'] + page_id = compat_str(page_data['id']) + video_id = compat_str(page_data['video']['data']['id']) + + preference = qualities(['mini', 'small', 'medium', 'large']) + thumbnails = [{ + 'url': image_url, + 'id': image_id, + 'preference': preference(image_id) + } for image_id, image_url in page_data.get('images', {}).items()] + + info = { + 'id': page_id, + 'display_id': display_id, + 'title': unescapeHTML(page_data['name']), + 'description': unescapeHTML(page_data.get('summary')), + 'timestamp': parse_iso8601(page_data.get('publishTime'), ' '), + 'author': page_data.get('author'), + 'uploader': show_data.get('name'), + 'uploader_id': show_data.get('slug'), + 'thumbnails': thumbnails, + 'extractor_key': site, + } + + if page_type == 'embed': + info.update({ + '_type': 'url_transparent', + 'url': page_data['video']['data']['embed'], + }) + return info + video_data = self._download_json( 'http://revision3.com/api/getPlaylist.json?api_key=%s&codecs=h264,vp8,theora&video_id=%s' % (self._API_KEY, video_id), video_id)['items'][0] @@ -84,36 +139,30 @@ class Revision3IE(InfoExtractor): }) self._sort_formats(formats) - preference = qualities(['mini', 'small', 'medium', 'large']) - thumbnails = [{ - 'url': image_url, - 'id': image_id, - 'preference': preference(image_id) - } for image_id, image_url in video_data.get('images', {}).items()] - - return { - 'id': video_id, - 'display_id': display_id, + info.update({ 'title': unescapeHTML(video_data['title']), 'description': unescapeHTML(video_data.get('summary')), - 'timestamp': parse_iso8601(episode_data.get('publishTime'), ' '), - 'author': episode_data.get('author'), 'uploader': video_data.get('show', {}).get('name'), 'uploader_id': video_data.get('show', {}).get('slug'), 'duration': int_or_none(video_data.get('duration')), - 'thumbnails': thumbnails, 'formats': formats, - } + }) + return info else: - show_data = page_info['show']['data'] + list_data = page_info[page_type]['data'] episodes_data = page_info['episodes']['data'] num_episodes = page_info['meta']['totalEpisodes'] processed_episodes = 0 entries = [] page_num = 1 while True: - entries.extend([self.url_result( - 'http://%s/%s/%s' % (domain, display_id, episode['slug'])) for episode in episodes_data]) + entries.extend([{ + '_type': 'url', + 'url': 'http://%s%s' % (domain, episode['path']), + 'id': compat_str(episode['id']), + 'ie_key': 'Revision3', + 'extractor_key': site, + } for episode in episodes_data]) processed_episodes += len(episodes_data) if processed_episodes == num_episodes: break @@ -123,5 +172,5 @@ class Revision3IE(InfoExtractor): display_id)['episodes']['data'] return self.playlist_result( - entries, compat_str(show_data['id']), - show_data.get('name'), show_data.get('summary')) + entries, compat_str(list_data['id']), + list_data.get('name'), list_data.get('summary')) diff --git a/youtube_dl/extractor/rice.py b/youtube_dl/extractor/rice.py new file mode 100644 index 000000000..f855719ac --- /dev/null +++ b/youtube_dl/extractor/rice.py @@ -0,0 +1,116 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_parse_qs +from ..utils import ( + xpath_text, + xpath_element, + int_or_none, + parse_iso8601, + ExtractorError, +) + + +class RICEIE(InfoExtractor): + _VALID_URL = r'https?://mediahub\.rice\.edu/app/[Pp]ortal/video\.aspx\?(?P<query>.+)' + _TEST = { + 'url': 'https://mediahub.rice.edu/app/Portal/video.aspx?PortalID=25ffd62c-3d01-4b29-8c70-7c94270efb3e&DestinationID=66bc9434-03bd-4725-b47e-c659d8d809db&ContentID=YEWIvbhb40aqdjMD1ALSqw', + 'md5': '9b83b4a2eead4912dc3b7fac7c449b6a', + 'info_dict': { + 'id': 'YEWIvbhb40aqdjMD1ALSqw', + 'ext': 'mp4', + 'title': 'Active Learning in Archeology', + 'upload_date': '20140616', + 'timestamp': 1402926346, + } + } + _NS = 'http://schemas.datacontract.org/2004/07/ensembleVideo.Data.Service.Contracts.Models.Player.Config' + + def _real_extract(self, url): + qs = compat_parse_qs(re.match(self._VALID_URL, url).group('query')) + if not qs.get('PortalID') or not qs.get('DestinationID') or not qs.get('ContentID'): + raise ExtractorError('Invalid URL', expected=True) + + portal_id = qs['PortalID'][0] + playlist_id = qs['DestinationID'][0] + content_id = qs['ContentID'][0] + + content_data = self._download_xml('https://mediahub.rice.edu/api/portal/GetContentTitle', content_id, query={ + 'portalId': portal_id, + 'playlistId': playlist_id, + 'contentId': content_id + }) + metadata = xpath_element(content_data, './/metaData', fatal=True) + title = xpath_text(metadata, 'primaryTitle', fatal=True) + encodings = xpath_element(content_data, './/encodings', fatal=True) + player_data = self._download_xml('https://mediahub.rice.edu/api/player/GetPlayerConfig', content_id, query={ + 'temporaryLinkId': xpath_text(encodings, 'temporaryLinkId', fatal=True), + 'contentId': content_id, + }) + + common_fmt = {} + dimensions = xpath_text(encodings, 'dimensions') + if dimensions: + wh = dimensions.split('x') + if len(wh) == 2: + common_fmt.update({ + 'width': int_or_none(wh[0]), + 'height': int_or_none(wh[1]), + }) + + formats = [] + rtsp_path = xpath_text(player_data, self._xpath_ns('RtspPath', self._NS)) + if rtsp_path: + fmt = { + 'url': rtsp_path, + 'format_id': 'rtsp', + } + fmt.update(common_fmt) + formats.append(fmt) + for source in player_data.findall(self._xpath_ns('.//Source', self._NS)): + video_url = xpath_text(source, self._xpath_ns('File', self._NS)) + if not video_url: + continue + if '.m3u8' in video_url: + formats.extend(self._extract_m3u8_formats(video_url, content_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) + else: + fmt = { + 'url': video_url, + 'format_id': video_url.split(':')[0], + } + fmt.update(common_fmt) + rtmp = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+))/(?P<playpath>mp4:.+)$', video_url) + if rtmp: + fmt.update({ + 'url': rtmp.group('url'), + 'play_path': rtmp.group('playpath'), + 'app': rtmp.group('app'), + 'ext': 'flv', + }) + formats.append(fmt) + self._sort_formats(formats) + + thumbnails = [] + for content_asset in content_data.findall('.//contentAssets'): + asset_type = xpath_text(content_asset, 'type') + if asset_type == 'image': + image_url = xpath_text(content_asset, 'httpPath') + if not image_url: + continue + thumbnails.append({ + 'id': xpath_text(content_asset, 'ID'), + 'url': image_url, + }) + + return { + 'id': content_id, + 'title': title, + 'description': xpath_text(metadata, 'abstract'), + 'duration': int_or_none(xpath_text(metadata, 'duration')), + 'timestamp': parse_iso8601(xpath_text(metadata, 'dateUpdated')), + 'thumbnails': thumbnails, + 'formats': formats, + } diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py index 7de7b7273..256396bb8 100644 --- a/youtube_dl/extractor/safari.py +++ b/youtube_dl/extractor/safari.py @@ -4,14 +4,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from .brightcove import BrightcoveLegacyIE from ..utils import ( ExtractorError, sanitized_Request, - smuggle_url, std_headers, urlencode_postdata, + update_url_query, ) @@ -20,28 +19,30 @@ class SafariBaseIE(InfoExtractor): _SUCCESSFUL_LOGIN_REGEX = r'<a href="/accounts/logout/"[^>]*>Sign Out</a>' _NETRC_MACHINE = 'safari' - _API_BASE = 'https://www.safaribooksonline.com/api/v1/book' + _API_BASE = 'https://www.safaribooksonline.com/api/v1' _API_FORMAT = 'json' LOGGED_IN = False def _real_initialize(self): - # We only need to log in once for courses or individual videos - if not self.LOGGED_IN: - self._login() - SafariBaseIE.LOGGED_IN = True + self._login() def _login(self): + # We only need to log in once for courses or individual videos + if self.LOGGED_IN: + return + (username, password) = self._get_login_info() if username is None: - self.raise_login_required('safaribooksonline.com account is required') + return - headers = std_headers + headers = std_headers.copy() if 'Referer' not in headers: headers['Referer'] = self._LOGIN_URL + login_page_request = sanitized_Request(self._LOGIN_URL, headers=headers) login_page = self._download_webpage( - self._LOGIN_URL, None, + login_page_request, None, 'Downloading login form') csrf = self._html_search_regex( @@ -66,6 +67,8 @@ class SafariBaseIE(InfoExtractor): 'Login failed; make sure your credentials are correct and try again.', expected=True) + SafariBaseIE.LOGGED_IN = True + self.to_screen('Login successful') @@ -85,13 +88,15 @@ class SafariIE(SafariBaseIE): _TESTS = [{ 'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html', - 'md5': '5b0c4cc1b3c1ba15dda7344085aa5592', + 'md5': 'dcc5a425e79f2564148652616af1f2a3', 'info_dict': { - 'id': '2842601850001', + 'id': '0_qbqx90ic', 'ext': 'mp4', - 'title': 'Introduction', + 'title': 'Introduction to Hadoop Fundamentals LiveLessons', + 'timestamp': 1437758058, + 'upload_date': '20150724', + 'uploader_id': 'stork', }, - 'skip': 'Requires safaribooksonline account credentials', }, { 'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html', 'only_matching': True, @@ -106,15 +111,30 @@ class SafariIE(SafariBaseIE): course_id = mobj.group('course_id') part = mobj.group('part') - webpage = self._download_webpage( - '%s/%s/chapter-content/%s.html' % (self._API_BASE, course_id, part), - part) + webpage = self._download_webpage(url, '%s/%s' % (course_id, part)) + reference_id = self._search_regex(r'data-reference-id="([^"]+)"', webpage, 'kaltura reference id') + partner_id = self._search_regex(r'data-partner-id="([^"]+)"', webpage, 'kaltura widget id') + ui_id = self._search_regex(r'data-ui-id="([^"]+)"', webpage, 'kaltura uiconf id') + + query = { + 'wid': '_%s' % partner_id, + 'uiconf_id': ui_id, + 'flashvars[referenceId]': reference_id, + } - bc_url = BrightcoveLegacyIE._extract_brightcove_url(webpage) - if not bc_url: - raise ExtractorError('Could not extract Brightcove URL from %s' % url, expected=True) + if self.LOGGED_IN: + kaltura_session = self._download_json( + '%s/player/kaltura_session/?reference_id=%s' % (self._API_BASE, reference_id), + course_id, 'Downloading kaltura session JSON', + 'Unable to download kaltura session JSON', fatal=False) + if kaltura_session: + session = kaltura_session.get('session') + if session: + query['flashvars[ks]'] = session - return self.url_result(smuggle_url(bc_url, {'Referer': url}), 'BrightcoveLegacy') + return self.url_result(update_url_query( + 'https://cdnapisec.kaltura.com/html5/html5lib/v2.37.1/mwEmbedFrame.php', query), + 'Kaltura') class SafariCourseIE(SafariBaseIE): @@ -140,7 +160,7 @@ class SafariCourseIE(SafariBaseIE): course_id = self._match_id(url) course_json = self._download_json( - '%s/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT), + '%s/book/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT), course_id, 'Downloading course JSON') if 'chapters' not in course_json: diff --git a/youtube_dl/extractor/sexu.py b/youtube_dl/extractor/sexu.py index 6365a8779..a99b2a8e7 100644 --- a/youtube_dl/extractor/sexu.py +++ b/youtube_dl/extractor/sexu.py @@ -1,7 +1,5 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor @@ -14,7 +12,7 @@ class SexuIE(InfoExtractor): 'id': '961791', 'ext': 'mp4', 'title': 'md5:4d05a19a5fc049a63dbbaf05fb71d91b', - 'description': 'md5:c5ed8625eb386855d5a7967bd7b77a54', + 'description': 'md5:2b75327061310a3afb3fbd7d09e2e403', 'categories': list, # NSFW 'thumbnail': 're:https?://.*\.jpg$', 'age_limit': 18, @@ -25,13 +23,18 @@ class SexuIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - quality_arr = self._search_regex( - r'sources:\s*\[([^\]]+)\]', webpage, 'forrmat string') + jwvideo = self._parse_json( + self._search_regex(r'\.setup\(\s*({.+?})\s*\);', webpage, 'jwvideo'), + video_id) + + sources = jwvideo['sources'] + formats = [{ - 'url': fmt[0].replace('\\', ''), - 'format_id': fmt[1], - 'height': int(fmt[1][:3]), - } for fmt in re.findall(r'"file":"([^"]+)","label":"([^"]+)"', quality_arr)] + 'url': source['file'].replace('\\', ''), + 'format_id': source.get('label'), + 'height': self._search_regex( + r'^(\d+)[pP]', source.get('label', ''), 'height', default=None), + } for source in sources if source.get('file')] self._sort_formats(formats) title = self._html_search_regex( @@ -40,9 +43,7 @@ class SexuIE(InfoExtractor): description = self._html_search_meta( 'description', webpage, 'description') - thumbnail = self._html_search_regex( - r'image:\s*"([^"]+)"', - webpage, 'thumbnail', fatal=False) + thumbnail = jwvideo.get('image') categories_str = self._html_search_meta( 'keywords', webpage, 'categories') diff --git a/youtube_dl/extractor/svt.py b/youtube_dl/extractor/svt.py index 399c3b8ee..2ab30e45f 100644 --- a/youtube_dl/extractor/svt.py +++ b/youtube_dl/extractor/svt.py @@ -19,20 +19,25 @@ class SVTBaseIE(InfoExtractor): video_info = info['video'] formats = [] for vr in video_info['videoReferences']: + player_type = vr.get('playerType') vurl = vr['url'] ext = determine_ext(vurl) if ext == 'm3u8': formats.extend(self._extract_m3u8_formats( vurl, video_id, ext='mp4', entry_protocol='m3u8_native', - m3u8_id=vr.get('playerType'))) + m3u8_id=player_type, fatal=False)) elif ext == 'f4m': formats.extend(self._extract_f4m_formats( vurl + '?hdcore=3.3.0', video_id, - f4m_id=vr.get('playerType'))) + f4m_id=player_type, fatal=False)) + elif ext == 'mpd': + if player_type == 'dashhbbtv': + formats.extend(self._extract_mpd_formats( + vurl, video_id, mpd_id=player_type, fatal=False)) else: formats.append({ - 'format_id': vr.get('playerType'), + 'format_id': player_type, 'url': vurl, }) self._sort_formats(formats) diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index a48d77c30..cf8851438 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -73,7 +73,7 @@ class TEDIE(InfoExtractor): 'add_ie': ['Youtube'], 'info_dict': { 'id': '_ZG8HBuDjgc', - 'ext': 'mp4', + 'ext': 'webm', 'title': 'Douglas Adams: Parrots the Universe and Everything', 'description': 'md5:01ad1e199c49ac640cb1196c0e9016af', 'uploader': 'University of California Television (UCTV)', diff --git a/youtube_dl/extractor/thestar.py b/youtube_dl/extractor/thestar.py new file mode 100644 index 000000000..b7e9af2af --- /dev/null +++ b/youtube_dl/extractor/thestar.py @@ -0,0 +1,31 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from .brightcove import BrightcoveLegacyIE +from ..compat import compat_parse_qs + + +class TheStarIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?thestar\.com/(?:[^/]+/)*(?P<id>.+)\.html' + _TEST = { + 'url': 'http://www.thestar.com/life/2016/02/01/mankind-why-this-woman-started-a-men-s-skincare-line.html', + 'md5': '2c62dd4db2027e35579fefb97a8b6554', + 'info_dict': { + 'id': '4732393888001', + 'ext': 'mp4', + 'title': 'Mankind: Why this woman started a men\'s skin care line', + 'description': 'Robert Cribb talks to Young Lee, the founder of Uncle Peter\'s MAN.', + 'uploader_id': '794267642001', + 'timestamp': 1454353482, + 'upload_date': '20160201', + } + } + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/794267642001/default_default/index.html?videoId=%s' + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage) + brightcove_id = compat_parse_qs(brightcove_legacy_url)['@videoPlayer'][0] + return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id) diff --git a/youtube_dl/extractor/tlc.py b/youtube_dl/extractor/tlc.py index adc05ed5f..17add9543 100644 --- a/youtube_dl/extractor/tlc.py +++ b/youtube_dl/extractor/tlc.py @@ -4,12 +4,12 @@ import re from .common import InfoExtractor from .brightcove import BrightcoveLegacyIE -from ..compat import compat_urlparse +from ..compat import compat_parse_qs class TlcDeIE(InfoExtractor): IE_NAME = 'tlc.de' - _VALID_URL = r'http://www\.tlc\.de/sendungen/[^/]+/videos/(?P<title>[^/?]+)' + _VALID_URL = r'http://www\.tlc\.de/(?:[^/]+/)*videos/(?P<title>[^/?#]+)?(?:.*#(?P<id>\d+))?' _TEST = { 'url': 'http://www.tlc.de/sendungen/breaking-amish/videos/#3235167922001', @@ -17,32 +17,23 @@ class TlcDeIE(InfoExtractor): 'id': '3235167922001', 'ext': 'mp4', 'title': 'Breaking Amish: Die Welt da draußen', - 'uploader': 'Discovery Networks - Germany', 'description': ( 'Vier Amische und eine Mennonitin wagen in New York' ' den Sprung in ein komplett anderes Leben. Begleitet sie auf' ' ihrem spannenden Weg.'), + 'timestamp': 1396598084, + 'upload_date': '20140404', + 'uploader_id': '1659832546', }, } + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1659832546/default_default/index.html?videoId=%s' def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - title = mobj.group('title') - webpage = self._download_webpage(url, title) - iframe_url = self._search_regex( - '<iframe src="(http://www\.tlc\.de/wp-content/.+?)"', webpage, - 'iframe url') - # Otherwise we don't get the correct 'BrightcoveExperience' element, - # example: http://www.tlc.de/sendungen/cake-boss/videos/cake-boss-cannoli-drama/ - iframe_url = iframe_url.replace('.htm?', '.php?') - url_fragment = compat_urlparse.urlparse(url).fragment - if url_fragment: - # Since the fragment is not send to the server, we always get the same iframe - iframe_url = re.sub(r'playlist=(\d+)', 'playlist=%s' % url_fragment, iframe_url) - iframe = self._download_webpage(iframe_url, title) - - return { - '_type': 'url', - 'url': BrightcoveLegacyIE._extract_brightcove_url(iframe), - 'ie': BrightcoveLegacyIE.ie_key(), - } + brightcove_id = mobj.group('id') + if not brightcove_id: + title = mobj.group('title') + webpage = self._download_webpage(url, title) + brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage) + brightcove_id = compat_parse_qs(brightcove_legacy_url)['@videoPlayer'][0] + return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id) diff --git a/youtube_dl/extractor/tv3.py b/youtube_dl/extractor/tv3.py new file mode 100644 index 000000000..d3f690dc7 --- /dev/null +++ b/youtube_dl/extractor/tv3.py @@ -0,0 +1,33 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class TV3IE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?tv3\.co\.nz/(?P<id>[^/]+)/tabid/\d+/articleID/\d+/MCat/\d+/Default\.aspx' + _TEST = { + 'url': 'http://www.tv3.co.nz/MOTORSPORT-SRS-SsangYong-Hampton-Downs-Round-3/tabid/3692/articleID/121615/MCat/2915/Default.aspx', + 'info_dict': { + 'id': '4659127992001', + 'ext': 'mp4', + 'title': 'CRC Motorsport: SRS SsangYong Hampton Downs Round 3 - S2015 Ep3', + 'description': 'SsangYong Racing Series returns for Round 3 with drivers from New Zealand and Australia taking to the grid at Hampton Downs raceway.', + 'uploader_id': '3812193411001', + 'upload_date': '20151213', + 'timestamp': 1449975272, + }, + 'expected_warnings': [ + 'Failed to download MPD manifest' + ], + 'params': { + 'skip_download': True, + }, + } + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/3812193411001/default_default/index.html?videoId=%s' + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + brightcove_id = self._search_regex(r'<param\s*name="@videoPlayer"\s*value="(\d+)"', webpage, 'brightcove id') + return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id) diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index 5b8586097..d4169ec6d 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -17,6 +17,7 @@ from ..utils import ( encode_dict, ExtractorError, int_or_none, + orderedSet, parse_duration, parse_iso8601, sanitized_Request, @@ -251,6 +252,7 @@ class TwitchVodIE(TwitchItemBaseIE): self._USHER_BASE, item_id, compat_urllib_parse.urlencode({ 'allow_source': 'true', + 'allow_audio_only': 'true', 'allow_spectre': 'true', 'player': 'twitchweb', 'nauth': access_token['token'], @@ -281,17 +283,37 @@ class TwitchPlaylistBaseIE(TwitchBaseIE): entries = [] offset = 0 limit = self._PAGE_LIMIT + broken_paging_detected = False + counter_override = None for counter in itertools.count(1): response = self._download_json( self._PLAYLIST_URL % (channel_id, offset, limit), - channel_id, 'Downloading %s videos JSON page %d' % (self._PLAYLIST_TYPE, counter)) + channel_id, + 'Downloading %s videos JSON page %s' + % (self._PLAYLIST_TYPE, counter_override or counter)) page_entries = self._extract_playlist_page(response) if not page_entries: break + total = int_or_none(response.get('_total')) + # Since the beginning of March 2016 twitch's paging mechanism + # is completely broken on the twitch side. It simply ignores + # a limit and returns the whole offset number of videos. + # Working around by just requesting all videos at once. + # Upd: pagination bug was fixed by twitch on 15.03.2016. + if not broken_paging_detected and total and len(page_entries) > limit: + self.report_warning( + 'Twitch pagination is broken on twitch side, requesting all videos at once', + channel_id) + broken_paging_detected = True + offset = total + counter_override = '(all at once)' + continue entries.extend(page_entries) + if broken_paging_detected or total and len(page_entries) >= total: + break offset += limit return self.playlist_result( - [self.url_result(entry) for entry in set(entries)], + [self.url_result(entry) for entry in orderedSet(entries)], channel_id, channel_name) def _extract_playlist_page(self, response): @@ -303,7 +325,6 @@ class TwitchPlaylistBaseIE(TwitchBaseIE): class TwitchProfileIE(TwitchPlaylistBaseIE): - _WORKING = False IE_NAME = 'twitch:profile' _VALID_URL = r'%s/(?P<id>[^/]+)/profile/?(?:\#.*)?$' % TwitchBaseIE._VALID_URL_BASE _PLAYLIST_TYPE = 'profile' @@ -319,7 +340,6 @@ class TwitchProfileIE(TwitchPlaylistBaseIE): class TwitchPastBroadcastsIE(TwitchPlaylistBaseIE): - _WORKING = False IE_NAME = 'twitch:past_broadcasts' _VALID_URL = r'%s/(?P<id>[^/]+)/profile/past_broadcasts/?(?:\#.*)?$' % TwitchBaseIE._VALID_URL_BASE _PLAYLIST_URL = TwitchPlaylistBaseIE._PLAYLIST_URL + '&broadcasts=true' @@ -336,7 +356,6 @@ class TwitchPastBroadcastsIE(TwitchPlaylistBaseIE): class TwitchBookmarksIE(TwitchPlaylistBaseIE): - _WORKING = False IE_NAME = 'twitch:bookmarks' _VALID_URL = r'%s/(?P<id>[^/]+)/profile/bookmarks/?(?:\#.*)?$' % TwitchBaseIE._VALID_URL_BASE _PLAYLIST_URL = '%s/api/bookmark/?user=%%s&offset=%%d&limit=%%d' % TwitchBaseIE._API_BASE @@ -414,6 +433,7 @@ class TwitchStreamIE(TwitchBaseIE): query = { 'allow_source': 'true', + 'allow_audio_only': 'true', 'p': random.randint(1000000, 10000000), 'player': 'twitchweb', 'segment_preference': '4', diff --git a/youtube_dl/extractor/twitter.py b/youtube_dl/extractor/twitter.py index 67762a003..e70b2ab3c 100644 --- a/youtube_dl/extractor/twitter.py +++ b/youtube_dl/extractor/twitter.py @@ -102,6 +102,14 @@ class TwitterCardIE(TwitterBaseIE): r'data-(?:player-)?config="([^"]+)"', webpage, 'data player config'), video_id) + def _search_dimensions_in_video_url(a_format, video_url): + m = re.search(r'/(?P<width>\d+)x(?P<height>\d+)/', video_url) + if m: + a_format.update({ + 'width': int(m.group('width')), + 'height': int(m.group('height')), + }) + playlist = config.get('playlist') if playlist: video_url = playlist[0]['source'] @@ -110,12 +118,8 @@ class TwitterCardIE(TwitterBaseIE): 'url': video_url, } - m = re.search(r'/(?P<width>\d+)x(?P<height>\d+)/', video_url) - if m: - f.update({ - 'width': int(m.group('width')), - 'height': int(m.group('height')), - }) + _search_dimensions_in_video_url(f, video_url) + formats.append(f) vmap_url = config.get('vmapUrl') or config.get('vmap_url') @@ -148,6 +152,8 @@ class TwitterCardIE(TwitterBaseIE): if not a_format['vbr']: del a_format['vbr'] + _search_dimensions_in_video_url(a_format, media_url) + formats.append(a_format) duration = float_or_none(media_info.get('duration', {}).get('nanos'), scale=1e9) diff --git a/youtube_dl/extractor/usatoday.py b/youtube_dl/extractor/usatoday.py new file mode 100644 index 000000000..e5678dc78 --- /dev/null +++ b/youtube_dl/extractor/usatoday.py @@ -0,0 +1,48 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + get_element_by_attribute, + parse_duration, + update_url_query, + ExtractorError, +) +from ..compat import compat_str + + +class USATodayIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?usatoday\.com/(?:[^/]+/)*(?P<id>[^?/#]+)' + _TEST = { + 'url': 'http://www.usatoday.com/media/cinematic/video/81729424/us-france-warn-syrian-regime-ahead-of-new-peace-talks/', + 'md5': '4d40974481fa3475f8bccfd20c5361f8', + 'info_dict': { + 'id': '81729424', + 'ext': 'mp4', + 'title': 'US, France warn Syrian regime ahead of new peace talks', + 'timestamp': 1457891045, + 'description': 'md5:7e50464fdf2126b0f533748d3c78d58f', + 'uploader_id': '29906170001', + 'upload_date': '20160313', + } + } + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/29906170001/38a9eecc-bdd8-42a3-ba14-95397e48b3f8_default/index.html?videoId=%s' + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(update_url_query(url, {'ajax': 'true'}), display_id) + ui_video_data = get_element_by_attribute('class', 'ui-video-data', webpage) + if not ui_video_data: + raise ExtractorError('no video on the webpage', expected=True) + video_data = self._parse_json(ui_video_data, display_id) + + return { + '_type': 'url_transparent', + 'url': self.BRIGHTCOVE_URL_TEMPLATE % video_data['brightcove_id'], + 'id': compat_str(video_data['id']), + 'title': video_data['title'], + 'thumbnail': video_data.get('thumbnail'), + 'description': video_data.get('description'), + 'duration': parse_duration(video_data.get('length')), + 'ie_key': 'BrightcoveNew', + } diff --git a/youtube_dl/extractor/vgtv.py b/youtube_dl/extractor/vgtv.py index 14e945d49..e148b1ef5 100644 --- a/youtube_dl/extractor/vgtv.py +++ b/youtube_dl/extractor/vgtv.py @@ -20,6 +20,7 @@ class VGTVIE(XstreamIE): 'aftenbladet.no/tv': 'satv', 'fvn.no/fvntv': 'fvntv', 'aftenposten.no/webtv': 'aptv', + 'ap.vgtv.no/webtv': 'aptv', } _APP_NAME_TO_VENDOR = { @@ -35,7 +36,7 @@ class VGTVIE(XstreamIE): (?P<host> %s ) - / + /? (?: \#!/(?:video|live)/| embed?.*id= @@ -107,19 +108,27 @@ class VGTVIE(XstreamIE): 'md5': 'fd828cd29774a729bf4d4425fe192972', 'info_dict': { 'id': '21039', - 'ext': 'mov', + 'ext': 'mp4', 'title': 'TRAILER: «SWEATSHOP» - I can´t take any more', 'description': 'md5:21891f2b0dd7ec2f78d84a50e54f8238', 'duration': 66, 'timestamp': 1417002452, 'upload_date': '20141126', 'view_count': int, - } + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, }, { 'url': 'http://www.bt.no/tv/#!/video/100250/norling-dette-er-forskjellen-paa-1-divisjon-og-eliteserien', 'only_matching': True, }, + { + 'url': 'http://ap.vgtv.no/webtv#!/video/111084/de-nye-bysyklene-lettere-bedre-gir-stoerre-hjul-og-feste-til-mobil', + 'only_matching': True, + }, ] def _real_extract(self, url): @@ -144,8 +153,6 @@ class VGTVIE(XstreamIE): if len(video_id) == 5: if appname == 'bttv': info = self._extract_video_info('btno', video_id) - elif appname == 'aptv': - info = self._extract_video_info('ap', video_id) streams = data['streamUrls'] stream_type = data.get('streamType') diff --git a/youtube_dl/extractor/vice.py b/youtube_dl/extractor/vice.py index 3db6286e4..46c785ae1 100644 --- a/youtube_dl/extractor/vice.py +++ b/youtube_dl/extractor/vice.py @@ -1,31 +1,37 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor from .ooyala import OoyalaIE from ..utils import ExtractorError class ViceIE(InfoExtractor): - _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)+(?P<id>.+)' - - _TESTS = [ - { - 'url': 'http://www.vice.com/Fringes/cowboy-capitalists-part-1', - 'info_dict': { - 'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp', - 'ext': 'mp4', - 'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov', - 'duration': 725.983, - }, - 'params': { - # Requires ffmpeg (m3u8 manifest) - 'skip_download': True, - }, - }, { - 'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab', - 'only_matching': True, - } - ] + _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?videos?/(?P<id>[^/?#&]+)' + + _TESTS = [{ + 'url': 'http://www.vice.com/video/cowboy-capitalists-part-1', + 'info_dict': { + 'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp', + 'ext': 'mp4', + 'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov', + 'duration': 725.983, + }, + 'params': { + # Requires ffmpeg (m3u8 manifest) + 'skip_download': True, + }, + }, { + 'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab', + 'only_matching': True, + }, { + 'url': 'http://www.vice.com/ru/video/big-night-out-ibiza-clive-martin-229', + 'only_matching': True, + }, { + 'url': 'https://munchies.vice.com/en/videos/watch-the-trailer-for-our-new-series-the-pizza-show', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -38,3 +44,35 @@ class ViceIE(InfoExtractor): except ExtractorError: raise ExtractorError('The page doesn\'t contain a video', expected=True) return self.url_result(ooyala_url, ie='Ooyala') + + +class ViceShowIE(InfoExtractor): + _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?show/(?P<id>[^/?#&]+)' + + _TEST = { + 'url': 'https://munchies.vice.com/en/show/fuck-thats-delicious-2', + 'info_dict': { + 'id': 'fuck-thats-delicious-2', + 'title': "Fuck, That's Delicious", + 'description': 'Follow the culinary adventures of rapper Action Bronson during his ongoing world tour.', + }, + 'playlist_count': 17, + } + + def _real_extract(self, url): + show_id = self._match_id(url) + webpage = self._download_webpage(url, show_id) + + entries = [ + self.url_result(video_url, ViceIE.ie_key()) + for video_url, _ in re.findall( + r'<h2[^>]+class="article-title"[^>]+data-id="\d+"[^>]*>\s*<a[^>]+href="(%s.*?)"' + % ViceIE._VALID_URL, webpage)] + + title = self._search_regex( + r'<title>(.+?)</title>', webpage, 'title', default=None) + if title: + title = re.sub(r'(.+)\s*\|\s*.+$', r'\1', title).strip() + description = self._html_search_meta('description', webpage, 'description') + + return self.playlist_result(entries, show_id, title, description) diff --git a/youtube_dl/extractor/viki.py b/youtube_dl/extractor/viki.py index 433fc9914..e04b814c8 100644 --- a/youtube_dl/extractor/viki.py +++ b/youtube_dl/extractor/viki.py @@ -176,13 +176,13 @@ class VikiIE(VikiBaseIE): }, { # youtube external 'url': 'http://www.viki.com/videos/50562v-poor-nastya-complete-episode-1', - 'md5': '216d1afdc0c64d1febc1e9f2bd4b864b', + 'md5': '63f8600c1da6f01b7640eee7eca4f1da', 'info_dict': { 'id': '50562v', - 'ext': 'mp4', + 'ext': 'webm', 'title': 'Poor Nastya [COMPLETE] - Episode 1', 'description': '', - 'duration': 607, + 'duration': 606, 'timestamp': 1274949505, 'upload_date': '20101213', 'uploader': 'ad14065n', diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 9f282a1da..71c30d2cd 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -73,15 +73,26 @@ class VimeoIE(VimeoBaseInfoExtractor): # _VALID_URL matches Vimeo URLs _VALID_URL = r'''(?x) - https?:// - (?:(?:www|(?P<player>player))\.)? - vimeo(?P<pro>pro)?\.com/ - (?!channels/[^/?#]+/?(?:$|[?#])|album/) - (?:.*?/)? - (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)? - (?:videos?/)? - (?P<id>[0-9]+) - /?(?:[?&].*)?(?:[#].*)?$''' + https?:// + (?: + (?: + www| + (?P<player>player) + ) + \. + )? + vimeo(?P<pro>pro)?\.com/ + (?!channels/[^/?#]+/?(?:$|[?#])|(?:album|ondemand)/) + (?:.*?/)? + (?: + (?: + play_redirect_hls| + moogaloop\.swf)\?clip_id= + )? + (?:videos?/)? + (?P<id>[0-9]+) + /?(?:[?&].*)?(?:[#].*)?$ + ''' IE_NAME = 'vimeo' _TESTS = [ { @@ -277,9 +288,8 @@ class VimeoIE(VimeoBaseInfoExtractor): def _real_extract(self, url): url, data = unsmuggle_url(url, {}) - headers = std_headers + headers = std_headers.copy() if 'http_headers' in data: - headers = headers.copy() headers.update(data['http_headers']) if 'Referer' not in headers: headers['Referer'] = url @@ -294,7 +304,7 @@ class VimeoIE(VimeoBaseInfoExtractor): url = 'https://vimeo.com/' + video_id # Retrieve video webpage to extract further information - request = sanitized_Request(url, None, headers) + request = sanitized_Request(url, headers=headers) try: webpage = self._download_webpage(request, video_id) except ExtractorError as ee: @@ -498,6 +508,38 @@ class VimeoIE(VimeoBaseInfoExtractor): } +class VimeoOndemandIE(VimeoBaseInfoExtractor): + IE_NAME = 'vimeo:ondemand' + _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?P<id>[^/?#&]+)' + _TESTS = [{ + # ondemand video not available via https://vimeo.com/id + 'url': 'https://vimeo.com/ondemand/20704', + 'md5': 'c424deda8c7f73c1dfb3edd7630e2f35', + 'info_dict': { + 'id': '105442900', + 'ext': 'mp4', + 'title': 'המעבדה - במאי יותם פלדמן', + 'uploader': 'גם סרטים', + 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/gumfilms', + 'uploader_id': 'gumfilms', + }, + }, { + 'url': 'https://vimeo.com/ondemand/nazmaalik', + 'only_matching': True, + }, { + 'url': 'https://vimeo.com/ondemand/141692381', + 'only_matching': True, + }, { + 'url': 'https://vimeo.com/ondemand/thelastcolony/150274832', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + return self.url_result(self._og_search_video_url(webpage), VimeoIE.ie_key()) + + class VimeoChannelIE(VimeoBaseInfoExtractor): IE_NAME = 'vimeo:channel' _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])' diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index 670a438af..d560a4b5e 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -142,10 +142,10 @@ class VKIE(InfoExtractor): 'url': 'https://vk.com/video276849682_170681728', 'info_dict': { 'id': 'V3K4mi0SYkc', - 'ext': 'mp4', + 'ext': 'webm', 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate", 'description': 'md5:bf9c26cfa4acdfb146362682edd3827a', - 'duration': 179, + 'duration': 178, 'upload_date': '20130116', 'uploader': "Children's Joy Foundation", 'uploader_id': 'thecjf', diff --git a/youtube_dl/extractor/wimp.py b/youtube_dl/extractor/wimp.py index 041ff6c55..fb0accac7 100644 --- a/youtube_dl/extractor/wimp.py +++ b/youtube_dl/extractor/wimp.py @@ -20,7 +20,7 @@ class WimpIE(InfoExtractor): 'md5': '4e2986c793694b55b37cf92521d12bb4', 'info_dict': { 'id': 'clowncar', - 'ext': 'mp4', + 'ext': 'webm', 'title': 'It\'s like a clown car.', 'description': 'md5:0e56db1370a6e49c5c1d19124c0d2fb2', }, diff --git a/youtube_dl/extractor/yandexmusic.py b/youtube_dl/extractor/yandexmusic.py index d3cc1a29f..e699e663f 100644 --- a/youtube_dl/extractor/yandexmusic.py +++ b/youtube_dl/extractor/yandexmusic.py @@ -10,13 +10,27 @@ from ..compat import ( compat_urllib_parse, ) from ..utils import ( + ExtractorError, int_or_none, float_or_none, sanitized_Request, ) -class YandexMusicTrackIE(InfoExtractor): +class YandexMusicBaseIE(InfoExtractor): + @staticmethod + def _handle_error(response): + error = response.get('error') + if error: + raise ExtractorError(error, expected=True) + + def _download_json(self, *args, **kwargs): + response = super(YandexMusicBaseIE, self)._download_json(*args, **kwargs) + self._handle_error(response) + return response + + +class YandexMusicTrackIE(YandexMusicBaseIE): IE_NAME = 'yandexmusic:track' IE_DESC = 'Яндекс.Музыка - Трек' _VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/album/(?P<album_id>\d+)/track/(?P<id>\d+)' @@ -73,7 +87,7 @@ class YandexMusicTrackIE(InfoExtractor): return self._get_track_info(track) -class YandexMusicPlaylistBaseIE(InfoExtractor): +class YandexMusicPlaylistBaseIE(YandexMusicBaseIE): def _build_playlist(self, tracks): return [ self.url_result( diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index b29baafc4..1124fe6c2 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -75,7 +75,7 @@ class YouPornIE(InfoExtractor): links = [] sources = self._search_regex( - r'sources\s*:\s*({.+?})', webpage, 'sources', default=None) + r'(?s)sources\s*:\s*({.+?})', webpage, 'sources', default=None) if sources: for _, link in re.findall(r'[^:]+\s*:\s*(["\'])(http.+?)\1', sources): links.append(link) @@ -101,8 +101,9 @@ class YouPornIE(InfoExtractor): } # Video URL's path looks like this: # /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4 + # /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4 # We will benefit from it by extracting some metadata - mobj = re.search(r'/(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+/', video_url) + mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+/', video_url) if mobj: height = int(mobj.group('height')) bitrate = int(mobj.group('bitrate')) |