diff options
Diffstat (limited to 'youtube_dl/extractor')
188 files changed, 5377 insertions, 2758 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index f7dcabcf7..fede5ff0d 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -3,9 +3,15 @@ from __future__ import unicode_literals from .abc import ABCIE from .abc7news import Abc7NewsIE from .academicearth import AcademicEarthCourseIE +from .acast import ( + ACastIE, + ACastChannelIE, +) from .addanime import AddAnimeIE from .adobetv import ( AdobeTVIE, + AdobeTVShowIE, + AdobeTVChannelIE, AdobeTVVideoIE, ) from .adultswim import AdultSwimIE @@ -37,6 +43,7 @@ from .arte import ( ) from .atresplayer import AtresPlayerIE from .atttechchannel import ATTTechChannelIE +from .audimedia import AudiMediaIE from .audiomack import AudiomackIE, AudiomackAlbumIE from .azubu import AzubuIE from .baidu import BaiduVideoIE @@ -53,13 +60,19 @@ from .beatportpro import BeatportProIE from .bet import BetIE from .bild import BildIE from .bilibili import BiliBiliIE +from .bleacherreport import ( + BleacherReportIE, + BleacherReportCMSIE, +) from .blinkx import BlinkxIE -from .bliptv import BlipTVIE, BlipTVUserIE from .bloomberg import BloombergIE from .bpb import BpbIE from .br import BRIE from .breakcom import BreakIE -from .brightcove import BrightcoveIE +from .brightcove import ( + BrightcoveLegacyIE, + BrightcoveNewIE, +) from .buzzfeed import BuzzFeedIE from .byutv import BYUtvIE from .c56 import C56IE @@ -67,7 +80,6 @@ from .camdemy import ( CamdemyIE, CamdemyFolderIE ) -from .canal13cl import Canal13clIE from .canalplus import CanalplusIE from .canalc2 import Canalc2IE from .cbs import CBSIE @@ -123,10 +135,12 @@ from .dbtv import DBTVIE from .dcn import DCNIE from .dctp import DctpTvIE from .deezer import DeezerPlaylistIE +from .democracynow import DemocracynowIE from .dfb import DFBIE from .dhm import DHMIE from .dotsub import DotsubIE from .douyutv import DouyuTVIE +from .dplay import DPlayIE from .dramafever import ( DramaFeverIE, DramaFeverSeriesIE, @@ -193,7 +207,9 @@ from .francetv import ( from .freesound import FreesoundIE from .freespeech import FreespeechIE from .freevideo import FreeVideoIE +from .funimation import FunimationIE from .funnyordie import FunnyOrDieIE +from .gameinformer import GameInformerIE from .gamekings import GamekingsIE from .gameone import ( GameOneIE, @@ -210,14 +226,18 @@ from .gfycat import GfycatIE from .giantbomb import GiantBombIE from .giga import GigaIE from .glide import GlideIE -from .globo import GloboIE +from .globo import ( + GloboIE, + GloboArticleIE, +) from .godtube import GodTubeIE from .goldenmoustache import GoldenMoustacheIE from .golem import GolemIE +from .googledrive import GoogleDriveIE from .googleplus import GooglePlusIE from .googlesearch import GoogleSearchIE -from .gorillavid import GorillaVidIE from .goshgay import GoshgayIE +from .gputechconf import GPUTechConfIE from .groupon import GrouponIE from .hark import HarkIE from .hearthisat import HearThisAtIE @@ -264,6 +284,7 @@ from .jadorecettepub import JadoreCettePubIE from .jeuxvideo import JeuxVideoIE from .jove import JoveIE from .jukebox import JukeboxIE +from .jwplatform import JWPlatformIE from .jpopsukitv import JpopsukiIE from .kaltura import KalturaIE from .kanalplay import KanalPlayIE @@ -318,6 +339,7 @@ from .lynda import ( from .m6 import M6IE from .macgamestore import MacGameStoreIE from .mailru import MailRuIE +from .makertv import MakerTVIE from .malemotion import MalemotionIE from .mdr import MDRIE from .metacafe import MetacafeIE @@ -341,7 +363,6 @@ from .motherless import MotherlessIE from .motorsport import MotorsportIE from .movieclips import MovieClipsIE from .moviezine import MoviezineIE -from .movshare import MovShareIE from .mtv import ( MTVIE, MTVServicesEmbeddedIE, @@ -407,14 +428,22 @@ from .noco import NocoIE from .normalboots import NormalbootsIE from .nosvideo import NosVideoIE from .nova import NovaIE -from .novamov import NovaMovIE +from .novamov import ( + NovaMovIE, + WholeCloudIE, + NowVideoIE, + VideoWeedIE, + CloudTimeIE, +) from .nowness import ( NownessIE, NownessPlaylistIE, NownessSeriesIE, ) -from .nowtv import NowTVIE -from .nowvideo import NowVideoIE +from .nowtv import ( + NowTVIE, + NowTVListIE, +) from .npo import ( NPOIE, NPOLiveIE, @@ -451,10 +480,7 @@ from .orf import ( from .parliamentliveuk import ParliamentLiveUKIE from .patreon import PatreonIE from .pbs import PBSIE -from .periscope import ( - PeriscopeIE, - QuickscopeIE, -) +from .periscope import PeriscopeIE from .philharmoniedeparis import PhilharmonieDeParisIE from .phoenix import PhoenixIE from .photobucket import PhotobucketIE @@ -546,6 +572,10 @@ from .shahid import ShahidIE from .shared import SharedIE from .sharesix import ShareSixIE from .sina import SinaIE +from .skynewsarabia import ( + SkyNewsArabiaIE, + SkyNewsArabiaArticleIE, +) from .slideshare import SlideshareIE from .slutload import SlutloadIE from .smotri import ( @@ -560,15 +590,12 @@ from .snagfilms import ( ) from .snotr import SnotrIE from .sohu import SohuIE -from .soompi import ( - SoompiIE, - SoompiShowIE, -) from .soundcloud import ( SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE, - SoundcloudPlaylistIE + SoundcloudPlaylistIE, + SoundcloudSearchIE ) from .soundgasm import ( SoundgasmIE, @@ -621,6 +648,7 @@ from .teachingchannel import TeachingChannelIE from .teamcoco import TeamcocoIE from .techtalks import TechTalksIE from .ted import TEDIE +from .tele13 import Tele13IE from .telebruxelles import TeleBruxellesIE from .telecinco import TelecincoIE from .telegraaf import TelegraafIE @@ -649,6 +677,7 @@ from .tnaflix import ( EMPFlixIE, MovieFapIE, ) +from .toggle import ToggleIE from .thvideo import ( THVideoIE, THVideoPlaylistIE @@ -719,16 +748,15 @@ from .vh1 import VH1IE from .vice import ViceIE from .viddler import ViddlerIE from .videodetective import VideoDetectiveIE -from .videolecturesnet import VideoLecturesNetIE from .videofyme import VideofyMeIE from .videomega import VideoMegaIE from .videopremium import VideoPremiumIE from .videott import VideoTtIE -from .videoweed import VideoWeedIE from .vidme import VidmeIE from .vidzi import VidziIE from .vier import VierIE, VierVideosIE from .viewster import ViewsterIE +from .viidea import ViideaIE from .vimeo import ( VimeoIE, VimeoAlbumIE, @@ -781,6 +809,7 @@ from .wrzuta import WrzutaIE from .wsj import WSJIE from .xbef import XBefIE from .xboxclips import XboxClipsIE +from .xfileshare import XFileShareIE from .xhamster import ( XHamsterIE, XHamsterEmbedIE, @@ -824,6 +853,7 @@ from .youtube import ( YoutubeTruncatedIDIE, YoutubeTruncatedURLIE, YoutubeUserIE, + YoutubePlaylistsIE, YoutubeWatchLaterIE, ) from .zapiks import ZapiksIE diff --git a/youtube_dl/extractor/abc.py b/youtube_dl/extractor/abc.py index c0e5d1abf..6a29e587f 100644 --- a/youtube_dl/extractor/abc.py +++ b/youtube_dl/extractor/abc.py @@ -23,6 +23,7 @@ class ABCIE(InfoExtractor): 'title': 'Australia to help staff Ebola treatment centre in Sierra Leone', 'description': 'md5:809ad29c67a05f54eb41f2a105693a67', }, + 'skip': 'this video has expired', }, { 'url': 'http://www.abc.net.au/news/2015-08-17/warren-entsch-introduces-same-sex-marriage-bill/6702326', 'md5': 'db2a5369238b51f9811ad815b69dc086', @@ -36,6 +37,7 @@ class ABCIE(InfoExtractor): 'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill', }, 'add_ie': ['Youtube'], + 'skip': 'Not accessible from Travis CI server', }, { 'url': 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080', 'md5': 'b96eee7c9edf4fc5a358a0252881cc1f', @@ -58,6 +60,9 @@ class ABCIE(InfoExtractor): r'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);', webpage) if mobj is None: + expired = self._html_search_regex(r'(?s)class="expired-(?:video|audio)".+?<span>(.+?)</span>', webpage, 'expired', None) + if expired: + raise ExtractorError('%s said: %s' % (self.IE_NAME, expired), expected=True) raise ExtractorError('Unable to extract video urls') urls_info = self._parse_json( diff --git a/youtube_dl/extractor/acast.py b/youtube_dl/extractor/acast.py new file mode 100644 index 000000000..be7913bc7 --- /dev/null +++ b/youtube_dl/extractor/acast.py @@ -0,0 +1,70 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import int_or_none + + +class ACastBaseIE(InfoExtractor): + _API_BASE_URL = 'https://www.acast.com/api/' + + +class ACastIE(ACastBaseIE): + IE_NAME = 'acast' + _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<channel>[^/]+)/(?P<id>[^/#?]+)' + _TEST = { + 'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan', + 'md5': 'ada3de5a1e3a2a381327d749854788bb', + 'info_dict': { + 'id': '57de3baa-4bb0-487e-9418-2692c1277a34', + 'ext': 'mp3', + 'title': '"Where Are You?": Taipei 101, Taiwan', + 'timestamp': 1196172000000, + 'description': 'md5:0c5d8201dfea2b93218ea986c91eee6e', + 'duration': 211, + } + } + + def _real_extract(self, url): + channel, display_id = re.match(self._VALID_URL, url).groups() + cast_data = self._download_json(self._API_BASE_URL + 'channels/%s/acasts/%s/playback' % (channel, display_id), display_id) + + return { + 'id': compat_str(cast_data['id']), + 'display_id': display_id, + 'url': cast_data['blings'][0]['audio'], + 'title': cast_data['name'], + 'description': cast_data.get('description'), + 'thumbnail': cast_data.get('image'), + 'timestamp': int_or_none(cast_data.get('publishingDate')), + 'duration': int_or_none(cast_data.get('duration')), + } + + +class ACastChannelIE(ACastBaseIE): + IE_NAME = 'acast:channel' + _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<id>[^/#?]+)' + _TEST = { + 'url': 'https://www.acast.com/condenasttraveler', + 'info_dict': { + 'id': '50544219-29bb-499e-a083-6087f4cb7797', + 'title': 'Condé Nast Traveler Podcast', + 'description': 'md5:98646dee22a5b386626ae31866638fbd', + }, + 'playlist_mincount': 20, + } + + @classmethod + def suitable(cls, url): + return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url) + + def _real_extract(self, url): + display_id = self._match_id(url) + channel_data = self._download_json(self._API_BASE_URL + 'channels/%s' % display_id, display_id) + casts = self._download_json(self._API_BASE_URL + 'channels/%s/acasts' % display_id, display_id) + entries = [self.url_result('https://www.acast.com/%s/%s' % (display_id, cast['url']), 'ACast') for cast in casts] + + return self.playlist_result(entries, compat_str(channel_data['id']), channel_data['name'], channel_data.get('description')) diff --git a/youtube_dl/extractor/adobetv.py b/youtube_dl/extractor/adobetv.py index 5e43adc51..8753ee2cf 100644 --- a/youtube_dl/extractor/adobetv.py +++ b/youtube_dl/extractor/adobetv.py @@ -1,23 +1,32 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( parse_duration, unified_strdate, str_to_int, + int_or_none, float_or_none, ISO639Utils, + determine_ext, ) -class AdobeTVIE(InfoExtractor): - _VALID_URL = r'https?://tv\.adobe\.com/watch/[^/]+/(?P<id>[^/]+)' +class AdobeTVBaseIE(InfoExtractor): + _API_BASE_URL = 'http://tv.adobe.com/api/v4/' + + +class AdobeTVIE(AdobeTVBaseIE): + _VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?watch/(?P<show_urlname>[^/]+)/(?P<id>[^/]+)' _TEST = { 'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/', 'md5': '9bc5727bcdd55251f35ad311ca74fa1e', 'info_dict': { - 'id': 'quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop', + 'id': '10981', 'ext': 'mp4', 'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop', 'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311', @@ -29,50 +38,106 @@ class AdobeTVIE(InfoExtractor): } def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - player = self._parse_json( - self._search_regex(r'html5player:\s*({.+?})\s*\n', webpage, 'player'), - video_id) + language, show_urlname, urlname = re.match(self._VALID_URL, url).groups() + if not language: + language = 'en' - title = player.get('title') or self._search_regex( - r'data-title="([^"]+)"', webpage, 'title') - description = self._og_search_description(webpage) - thumbnail = self._og_search_thumbnail(webpage) - - upload_date = unified_strdate( - self._html_search_meta('datepublished', webpage, 'upload date')) - - duration = parse_duration( - self._html_search_meta('duration', webpage, 'duration') or - self._search_regex( - r'Runtime:\s*(\d{2}:\d{2}:\d{2})', - webpage, 'duration', fatal=False)) - - view_count = str_to_int(self._search_regex( - r'<div class="views">\s*Views?:\s*([\d,.]+)\s*</div>', - webpage, 'view count')) + video_data = self._download_json( + self._API_BASE_URL + 'episode/get/?language=%s&show_urlname=%s&urlname=%s&disclosure=standard' % (language, show_urlname, urlname), + urlname)['data'][0] formats = [{ - 'url': source['src'], - 'format_id': source.get('quality') or source['src'].split('-')[-1].split('.')[0] or None, - 'tbr': source.get('bitrate'), - } for source in player['sources']] + 'url': source['url'], + 'format_id': source.get('quality_level') or source['url'].split('-')[-1].split('.')[0] or None, + 'width': int_or_none(source.get('width')), + 'height': int_or_none(source.get('height')), + 'tbr': int_or_none(source.get('video_data_rate')), + } for source in video_data['videos']] self._sort_formats(formats) return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'upload_date': upload_date, - 'duration': duration, - 'view_count': view_count, + 'id': compat_str(video_data['id']), + 'title': video_data['title'], + 'description': video_data.get('description'), + 'thumbnail': video_data.get('thumbnail'), + 'upload_date': unified_strdate(video_data.get('start_date')), + 'duration': parse_duration(video_data.get('duration')), + 'view_count': str_to_int(video_data.get('playcount')), 'formats': formats, } +class AdobeTVPlaylistBaseIE(AdobeTVBaseIE): + def _parse_page_data(self, page_data): + return [self.url_result(self._get_element_url(element_data)) for element_data in page_data] + + def _extract_playlist_entries(self, url, display_id): + page = self._download_json(url, display_id) + entries = self._parse_page_data(page['data']) + for page_num in range(2, page['paging']['pages'] + 1): + entries.extend(self._parse_page_data( + self._download_json(url + '&page=%d' % page_num, display_id)['data'])) + return entries + + +class AdobeTVShowIE(AdobeTVPlaylistBaseIE): + _VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?show/(?P<id>[^/]+)' + + _TEST = { + 'url': 'http://tv.adobe.com/show/the-complete-picture-with-julieanne-kost', + 'info_dict': { + 'id': '36', + 'title': 'The Complete Picture with Julieanne Kost', + 'description': 'md5:fa50867102dcd1aa0ddf2ab039311b27', + }, + 'playlist_mincount': 136, + } + + def _get_element_url(self, element_data): + return element_data['urls'][0] + + def _real_extract(self, url): + language, show_urlname = re.match(self._VALID_URL, url).groups() + if not language: + language = 'en' + query = 'language=%s&show_urlname=%s' % (language, show_urlname) + + show_data = self._download_json(self._API_BASE_URL + 'show/get/?%s' % query, show_urlname)['data'][0] + + return self.playlist_result( + self._extract_playlist_entries(self._API_BASE_URL + 'episode/?%s' % query, show_urlname), + compat_str(show_data['id']), + show_data['show_name'], + show_data['show_description']) + + +class AdobeTVChannelIE(AdobeTVPlaylistBaseIE): + _VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?channel/(?P<id>[^/]+)(?:/(?P<category_urlname>[^/]+))?' + + _TEST = { + 'url': 'http://tv.adobe.com/channel/development', + 'info_dict': { + 'id': 'development', + }, + 'playlist_mincount': 96, + } + + def _get_element_url(self, element_data): + return element_data['url'] + + def _real_extract(self, url): + language, channel_urlname, category_urlname = re.match(self._VALID_URL, url).groups() + if not language: + language = 'en' + query = 'language=%s&channel_urlname=%s' % (language, channel_urlname) + if category_urlname: + query += '&category_urlname=%s' % category_urlname + + return self.playlist_result( + self._extract_playlist_entries(self._API_BASE_URL + 'show/?%s' % query, channel_urlname), + channel_urlname) + + class AdobeTVVideoIE(InfoExtractor): _VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)' @@ -91,28 +156,25 @@ class AdobeTVVideoIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - player_params = self._parse_json(self._search_regex( - r'var\s+bridge\s*=\s*([^;]+);', webpage, 'player parameters'), - video_id) + video_data = self._download_json(url + '?format=json', video_id) formats = [{ + 'format_id': '%s-%s' % (determine_ext(source['src']), source.get('height')), 'url': source['src'], - 'width': source.get('width'), - 'height': source.get('height'), - 'tbr': source.get('bitrate'), - } for source in player_params['sources']] + 'width': int_or_none(source.get('width')), + 'height': int_or_none(source.get('height')), + 'tbr': int_or_none(source.get('bitrate')), + } for source in video_data['sources']] + self._sort_formats(formats) # For both metadata and downloaded files the duration varies among # formats. I just pick the max one duration = max(filter(None, [ float_or_none(source.get('duration'), scale=1000) - for source in player_params['sources']])) + for source in video_data['sources']])) subtitles = {} - for translation in player_params.get('translations', []): + for translation in video_data.get('translations', []): lang_id = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium']) if lang_id not in subtitles: subtitles[lang_id] = [] @@ -124,8 +186,9 @@ class AdobeTVVideoIE(InfoExtractor): return { 'id': video_id, 'formats': formats, - 'title': player_params['title'], - 'description': self._og_search_description(webpage), + 'title': video_data['title'], + 'description': video_data.get('description'), + 'thumbnail': video_data['video'].get('poster'), 'duration': duration, 'subtitles': subtitles, } diff --git a/youtube_dl/extractor/adultswim.py b/youtube_dl/extractor/adultswim.py index 3ae618e71..bf21a6887 100644 --- a/youtube_dl/extractor/adultswim.py +++ b/youtube_dl/extractor/adultswim.py @@ -68,7 +68,7 @@ class AdultSwimIE(InfoExtractor): 'md5': '3e346a2ab0087d687a05e1e7f3b3e529', 'info_dict': { 'id': 'sY3cMUR_TbuE4YmdjzbIcQ-0', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine', 'description': 'Dr. Brule reports live from Wine Country with a special report on wines. \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n', }, @@ -79,6 +79,10 @@ class AdultSwimIE(InfoExtractor): 'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine', 'description': 'Dr. Brule reports live from Wine Country with a special report on wines. \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n', }, + 'params': { + # m3u8 download + 'skip_download': True, + } }] @staticmethod diff --git a/youtube_dl/extractor/aljazeera.py b/youtube_dl/extractor/aljazeera.py index 184a14a4f..5b2c0dc9a 100644 --- a/youtube_dl/extractor/aljazeera.py +++ b/youtube_dl/extractor/aljazeera.py @@ -15,7 +15,7 @@ class AlJazeeraIE(InfoExtractor): 'description': 'As a birth attendant advocating for family planning, Remy is on the frontline of Tondo\'s battle with overcrowding.', 'uploader': 'Al Jazeera English', }, - 'add_ie': ['Brightcove'], + 'add_ie': ['BrightcoveLegacy'], 'skip': 'Not accessible from Travis CI server', } @@ -32,5 +32,5 @@ class AlJazeeraIE(InfoExtractor): 'playerKey=AQ~~%2CAAAAmtVJIFk~%2CTVGOQ5ZTwJbeMWnq5d_H4MOM57xfzApc' '&%40videoPlayer={0}'.format(brightcove_id) ), - 'ie_key': 'Brightcove', + 'ie_key': 'BrightcoveLegacy', } diff --git a/youtube_dl/extractor/amp.py b/youtube_dl/extractor/amp.py new file mode 100644 index 000000000..dcc3c97f1 --- /dev/null +++ b/youtube_dl/extractor/amp.py @@ -0,0 +1,84 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_iso8601, +) + + +class AMPIE(InfoExtractor): + # parse Akamai Adaptive Media Player feed + def _extract_feed_info(self, url): + item = self._download_json( + url, None, 'Downloading Akamai AMP feed', + 'Unable to download Akamai AMP feed')['channel']['item'] + + video_id = item['guid'] + + def get_media_node(name, default=None): + media_name = 'media-%s' % name + media_group = item.get('media-group') or item + return media_group.get(media_name) or item.get(media_name) or item.get(name, default) + + thumbnails = [] + media_thumbnail = get_media_node('thumbnail') + if media_thumbnail: + if isinstance(media_thumbnail, dict): + media_thumbnail = [media_thumbnail] + for thumbnail_data in media_thumbnail: + thumbnail = thumbnail_data['@attributes'] + thumbnails.append({ + 'url': self._proto_relative_url(thumbnail['url'], 'http:'), + 'width': int_or_none(thumbnail.get('width')), + 'height': int_or_none(thumbnail.get('height')), + }) + + subtitles = {} + media_subtitle = get_media_node('subTitle') + if media_subtitle: + if isinstance(media_subtitle, dict): + media_subtitle = [media_subtitle] + for subtitle_data in media_subtitle: + subtitle = subtitle_data['@attributes'] + lang = subtitle.get('lang') or 'en' + subtitles[lang] = [{'url': subtitle['href']}] + + formats = [] + media_content = get_media_node('content') + if isinstance(media_content, dict): + media_content = [media_content] + for media_data in media_content: + media = media_data['@attributes'] + media_type = media['type'] + if media_type == 'video/f4m': + f4m_formats = self._extract_f4m_formats( + media['url'] + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124', + video_id, f4m_id='hds', fatal=False) + if f4m_formats: + formats.extend(f4m_formats) + elif media_type == 'application/x-mpegURL': + m3u8_formats = self._extract_m3u8_formats( + media['url'], video_id, 'mp4', m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + else: + formats.append({ + 'format_id': media_data['media-category']['@attributes']['label'], + 'url': media['url'], + 'tbr': int_or_none(media.get('bitrate')), + 'filesize': int_or_none(media.get('fileSize')), + }) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': get_media_node('title'), + 'description': get_media_node('description'), + 'thumbnails': thumbnails, + 'timestamp': parse_iso8601(item.get('pubDate'), ' '), + 'duration': int_or_none(media_content[0].get('@attributes', {}).get('duration')), + 'formats': formats, + } diff --git a/youtube_dl/extractor/anitube.py b/youtube_dl/extractor/anitube.py index 31f0d417c..23f942ae2 100644 --- a/youtube_dl/extractor/anitube.py +++ b/youtube_dl/extractor/anitube.py @@ -26,8 +26,8 @@ class AnitubeIE(InfoExtractor): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - key = self._html_search_regex( - r'http://www\.anitube\.se/embed/([A-Za-z0-9_-]*)', webpage, 'key') + key = self._search_regex( + r'src=["\']https?://[^/]+/embed/([A-Za-z0-9_-]+)', webpage, 'key') config_xml = self._download_xml( 'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, key) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 6f465789b..73be6d204 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -14,8 +14,8 @@ from ..utils import ( parse_duration, unified_strdate, xpath_text, - parse_xml, ) +from ..compat import compat_etree_fromstring class ARDMediathekIE(InfoExtractor): @@ -161,7 +161,7 @@ class ARDMediathekIE(InfoExtractor): raise ExtractorError('This program is only suitable for those aged 12 and older. Video %s is therefore only available between 20 pm and 6 am.' % video_id, expected=True) if re.search(r'[\?&]rss($|[=&])', url): - doc = parse_xml(webpage) + doc = compat_etree_fromstring(webpage.encode('utf-8')) if doc.tag == 'rss': return GenericIE()._extract_rss(url, video_id, doc) diff --git a/youtube_dl/extractor/atresplayer.py b/youtube_dl/extractor/atresplayer.py index 29f8795d3..7ac3044c7 100644 --- a/youtube_dl/extractor/atresplayer.py +++ b/youtube_dl/extractor/atresplayer.py @@ -2,16 +2,18 @@ from __future__ import unicode_literals import time import hmac +import hashlib +import re from .common import InfoExtractor from ..compat import ( compat_str, compat_urllib_parse, - compat_urllib_request, ) from ..utils import ( int_or_none, float_or_none, + sanitized_Request, xpath_text, ExtractorError, ) @@ -32,6 +34,19 @@ class AtresPlayerIE(InfoExtractor): 'duration': 5527.6, 'thumbnail': 're:^https?://.*\.jpg$', }, + 'skip': 'This video is only available for registered users' + }, + { + 'url': 'http://www.atresplayer.com/television/especial/videoencuentros/temporada-1/capitulo-112-david-bustamante_2014121600375.html', + 'md5': '0d0e918533bbd4b263f2de4d197d4aac', + 'info_dict': { + 'id': 'capitulo-112-david-bustamante', + 'ext': 'flv', + 'title': 'David Bustamante', + 'description': 'md5:f33f1c0a05be57f6708d4dd83a3b81c6', + 'duration': 1439.0, + 'thumbnail': 're:^https?://.*\.jpg$', + }, }, { 'url': 'http://www.atresplayer.com/television/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_2014122400174.html', @@ -50,6 +65,13 @@ class AtresPlayerIE(InfoExtractor): _LOGIN_URL = 'https://servicios.atresplayer.com/j_spring_security_check' + _ERRORS = { + 'UNPUBLISHED': 'We\'re sorry, but this video is not yet available.', + 'DELETED': 'This video has expired and is no longer available for online streaming.', + 'GEOUNPUBLISHED': 'We\'re sorry, but this video is not available in your region due to right restrictions.', + # 'PREMIUM': 'PREMIUM', + } + def _real_initialize(self): self._login() @@ -63,7 +85,7 @@ class AtresPlayerIE(InfoExtractor): 'j_password': password, } - request = compat_urllib_request.Request( + request = sanitized_Request( self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8')) request.add_header('Content-Type', 'application/x-www-form-urlencoded') response = self._download_webpage( @@ -83,58 +105,81 @@ class AtresPlayerIE(InfoExtractor): episode_id = self._search_regex( r'episode="([^"]+)"', webpage, 'episode id') + request = sanitized_Request( + self._PLAYER_URL_TEMPLATE % episode_id, + headers={'User-Agent': self._USER_AGENT}) + player = self._download_json(request, episode_id, 'Downloading player JSON') + + episode_type = player.get('typeOfEpisode') + error_message = self._ERRORS.get(episode_type) + if error_message: + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, error_message), expected=True) + + formats = [] + video_url = player.get('urlVideo') + if video_url: + format_info = { + 'url': video_url, + 'format_id': 'http', + } + mobj = re.search(r'(?P<bitrate>\d+)K_(?P<width>\d+)x(?P<height>\d+)', video_url) + if mobj: + format_info.update({ + 'width': int_or_none(mobj.group('width')), + 'height': int_or_none(mobj.group('height')), + 'tbr': int_or_none(mobj.group('bitrate')), + }) + formats.append(format_info) + + m3u8_url = player.get('urlVideoHls') + if m3u8_url: + m3u8_formats = self._extract_m3u8_formats( + m3u8_url, episode_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + timestamp = int_or_none(self._download_webpage( self._TIME_API_URL, video_id, 'Downloading timestamp', fatal=False), 1000, time.time()) timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT) token = hmac.new( self._MAGIC.encode('ascii'), - (episode_id + timestamp_shifted).encode('utf-8') + (episode_id + timestamp_shifted).encode('utf-8'), hashlib.md5 ).hexdigest() - formats = [] - for fmt in ['windows', 'android_tablet']: - request = compat_urllib_request.Request( - self._URL_VIDEO_TEMPLATE.format(fmt, episode_id, timestamp_shifted, token)) - request.add_header('User-Agent', self._USER_AGENT) - - fmt_json = self._download_json( - request, video_id, 'Downloading %s video JSON' % fmt) - - result = fmt_json.get('resultDes') - if result.lower() != 'ok': - raise ExtractorError( - '%s returned error: %s' % (self.IE_NAME, result), expected=True) - - for format_id, video_url in fmt_json['resultObject'].items(): - if format_id == 'token' or not video_url.startswith('http'): - continue - if video_url.endswith('/Manifest'): - if 'geodeswowsmpra3player' in video_url: - f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0] - f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path) - # this videos are protected by DRM, the f4m downloader doesn't support them - continue - else: - f4m_url = video_url[:-9] + '/manifest.f4m' - formats.extend(self._extract_f4m_formats(f4m_url, video_id)) - else: - formats.append({ - 'url': video_url, - 'format_id': 'android-%s' % format_id, - 'preference': 1, - }) - self._sort_formats(formats) + request = sanitized_Request( + self._URL_VIDEO_TEMPLATE.format('windows', episode_id, timestamp_shifted, token), + headers={'User-Agent': self._USER_AGENT}) - player = self._download_json( - self._PLAYER_URL_TEMPLATE % episode_id, - episode_id) + fmt_json = self._download_json( + request, video_id, 'Downloading windows video JSON') + + result = fmt_json.get('resultDes') + if result.lower() != 'ok': + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, result), expected=True) + + for format_id, video_url in fmt_json['resultObject'].items(): + if format_id == 'token' or not video_url.startswith('http'): + continue + if 'geodeswowsmpra3player' in video_url: + f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0] + f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path) + # this videos are protected by DRM, the f4m downloader doesn't support them + continue + else: + f4m_url = video_url[:-9] + '/manifest.f4m' + f4m_formats = self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False) + if f4m_formats: + formats.extend(f4m_formats) + self._sort_formats(formats) path_data = player.get('pathData') episode = self._download_xml( - self._EPISODE_URL_TEMPLATE % path_data, - video_id, 'Downloading episode XML') + self._EPISODE_URL_TEMPLATE % path_data, video_id, + 'Downloading episode XML') duration = float_or_none(xpath_text( episode, './media/asset/info/technical/contentDuration', 'duration')) diff --git a/youtube_dl/extractor/audimedia.py b/youtube_dl/extractor/audimedia.py new file mode 100644 index 000000000..4382a302b --- /dev/null +++ b/youtube_dl/extractor/audimedia.py @@ -0,0 +1,80 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_iso8601, + sanitized_Request, +) + + +class AudiMediaIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?audimedia\.tv/(?:en|de)/vid/(?P<id>[^/?#]+)' + _TEST = { + 'url': 'https://audimedia.tv/en/vid/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test', + 'md5': '79a8b71c46d49042609795ab59779b66', + 'info_dict': { + 'id': '1565', + 'ext': 'mp4', + 'title': '60 Seconds of Audi Sport 104/2015 - WEC Bahrain, Rookie Test', + 'description': 'md5:60e5d30a78ced725f7b8d34370762941', + 'upload_date': '20151124', + 'timestamp': 1448354940, + 'duration': 74022, + 'view_count': int, + } + } + # extracted from https://audimedia.tv/assets/embed/embedded-player.js (dataSourceAuthToken) + _AUTH_TOKEN = 'e25b42847dba18c6c8816d5d8ce94c326e06823ebf0859ed164b3ba169be97f2' + + def _real_extract(self, url): + 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') + _, stage_mode, video_id, lang = raw_payload.split('-') + + # TODO: handle s and e stage_mode (live streams and ended live streams) + if stage_mode not in ('s', 'e'): + request = sanitized_Request( + 'https://audimedia.tv/api/video/v1/videos/%s?embed[]=video_versions&embed[]=thumbnail_image&where[content_language_iso]=%s' % (video_id, lang), + headers={'X-Auth-Token': self._AUTH_TOKEN}) + json_data = self._download_json(request, video_id)['results'] + formats = [] + + stream_url_hls = json_data.get('stream_url_hls') + if stream_url_hls: + m3u8_formats = self._extract_m3u8_formats(stream_url_hls, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + + stream_url_hds = json_data.get('stream_url_hds') + if stream_url_hds: + f4m_formats = self._extract_f4m_formats(json_data.get('stream_url_hds') + '?hdcore=3.4.0', video_id, -1, f4m_id='hds', fatal=False) + if f4m_formats: + formats.extend(f4m_formats) + + for video_version in json_data.get('video_versions'): + video_version_url = video_version.get('download_url') or video_version.get('stream_url') + if not video_version_url: + continue + formats.append({ + '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')), + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': json_data['title'], + 'description': json_data.get('subtitle'), + 'thumbnail': json_data.get('thumbnail_image', {}).get('file'), + 'timestamp': parse_iso8601(json_data.get('publication_date')), + 'duration': int_or_none(json_data.get('duration')), + 'view_count': int_or_none(json_data.get('view_count')), + 'formats': formats, + } diff --git a/youtube_dl/extractor/audiomack.py b/youtube_dl/extractor/audiomack.py index 693ba22c6..3eed91279 100644 --- a/youtube_dl/extractor/audiomack.py +++ b/youtube_dl/extractor/audiomack.py @@ -56,7 +56,7 @@ class AudiomackIE(InfoExtractor): # API is inconsistent with errors if 'url' not in api_response or not api_response['url'] or 'error' in api_response: - raise ExtractorError('Invalid url %s', url) + raise ExtractorError('Invalid url %s' % url) # Audiomack wraps a lot of soundcloud tracks in their branded wrapper # if so, pass the work off to the soundcloud extractor diff --git a/youtube_dl/extractor/bambuser.py b/youtube_dl/extractor/bambuser.py index 8dff1d6e3..da986e063 100644 --- a/youtube_dl/extractor/bambuser.py +++ b/youtube_dl/extractor/bambuser.py @@ -6,13 +6,13 @@ import itertools from .common import InfoExtractor from ..compat import ( compat_urllib_parse, - compat_urllib_request, compat_str, ) from ..utils import ( ExtractorError, int_or_none, float_or_none, + sanitized_Request, ) @@ -57,7 +57,7 @@ class BambuserIE(InfoExtractor): 'pass': password, } - request = compat_urllib_request.Request( + request = sanitized_Request( self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8')) request.add_header('Referer', self._LOGIN_URL) response = self._download_webpage( @@ -126,7 +126,7 @@ class BambuserChannelIE(InfoExtractor): '&sort=created&access_mode=0%2C1%2C2&limit={count}' '&method=broadcast&format=json&vid_older_than={last}' ).format(user=user, count=self._STEP, last=last_id) - req = compat_urllib_request.Request(req_url) + req = sanitized_Request(req_url) # Without setting this header, we wouldn't get any result req.add_header('Referer', 'http://bambuser.com/channel/%s' % user) data = self._download_json( diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 2cdce1eb9..691aecc0d 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -2,7 +2,6 @@ from __future__ import unicode_literals import re -import xml.etree.ElementTree from .common import InfoExtractor from ..utils import ( @@ -14,18 +13,22 @@ from ..utils import ( remove_end, unescapeHTML, ) -from ..compat import compat_HTTPError +from ..compat import ( + compat_etree_fromstring, + compat_HTTPError, +) class BBCCoUkIE(InfoExtractor): IE_NAME = 'bbc.co.uk' IE_DESC = 'BBC iPlayer' - _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|iplayer(?:/[^/]+)?/(?:episode/|playlist/))|music/clips[/#])(?P<id>[\da-z]{8})' + _ID_REGEX = r'[pb][\da-z]{7}' + _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|iplayer(?:/[^/]+)?/(?:episode/|playlist/))|music/clips[/#])(?P<id>%s)' % _ID_REGEX _MEDIASELECTOR_URLS = [ # Provides HQ HLS streams with even better quality that pc mediaset but fails # with geolocation in some cases when it's even not geo restricted at all (e.g. - # http://www.bbc.co.uk/programmes/b06bp7lf) + # http://www.bbc.co.uk/programmes/b06bp7lf). Also may fail with selectionunavailable. 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s', 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s', ] @@ -44,9 +47,8 @@ class BBCCoUkIE(InfoExtractor): 'info_dict': { 'id': 'b039d07m', 'ext': 'flv', - 'title': 'Kaleidoscope, Leonard Cohen', + 'title': 'Leonard Cohen, Kaleidoscope - BBC Radio 4', 'description': 'The Canadian poet and songwriter reflects on his musical career.', - 'duration': 1740, }, 'params': { # rtmp download @@ -109,7 +111,8 @@ class BBCCoUkIE(InfoExtractor): 'params': { # rtmp download 'skip_download': True, - } + }, + 'skip': 'Episode is no longer available on BBC iPlayer Radio', }, { 'url': 'http://www.bbc.co.uk/music/clips/p02frcc3', 'note': 'Audio', @@ -332,7 +335,7 @@ class BBCCoUkIE(InfoExtractor): return self._download_media_selector_url( mediaselector_url % programme_id, programme_id) except BBCCoUkIE.MediaSelectionError as e: - if e.id in ('notukerror', 'geolocation'): + if e.id in ('notukerror', 'geolocation', 'selectionunavailable'): last_exception = e continue self._raise_extractor_error(e) @@ -343,8 +346,8 @@ class BBCCoUkIE(InfoExtractor): media_selection = self._download_xml( url, programme_id, 'Downloading media selection XML') except ExtractorError as ee: - if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: - media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8')) + if isinstance(ee.cause, compat_HTTPError) and ee.cause.code in (403, 404): + media_selection = compat_etree_fromstring(ee.cause.read().decode('utf-8')) else: raise return self._process_media_selector(media_selection, programme_id) @@ -451,6 +454,7 @@ class BBCCoUkIE(InfoExtractor): webpage = self._download_webpage(url, group_id, 'Downloading video page') programme_id = None + duration = None tviplayer = self._search_regex( r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById', @@ -463,14 +467,16 @@ class BBCCoUkIE(InfoExtractor): if not programme_id: programme_id = self._search_regex( - r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None) + r'"vpid"\s*:\s*"(%s)"' % self._ID_REGEX, webpage, 'vpid', fatal=False, default=None) if programme_id: formats, subtitles = self._download_media_selector(programme_id) title = self._og_search_title(webpage) description = self._search_regex( r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>', - webpage, 'description', fatal=False) + webpage, 'description', default=None) + if not description: + description = self._html_search_meta('description', webpage) else: programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id) @@ -584,6 +590,7 @@ class BBCIE(BBCCoUkIE): 'ext': 'mp4', 'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''', 'duration': 56, + 'description': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''', }, 'params': { 'skip_download': True, @@ -726,6 +733,7 @@ class BBCIE(BBCCoUkIE): # article with multiple videos embedded with playlist.sxml (e.g. # http://www.bbc.com/sport/0/football/34475836) playlists = re.findall(r'<param[^>]+name="playlist"[^>]+value="([^"]+)"', webpage) + playlists.extend(re.findall(r'data-media-id="([^"]+/playlist\.sxml)"', webpage)) if playlists: entries = [ self._extract_from_playlist_sxml(playlist_url, playlist_id, timestamp) @@ -778,8 +786,9 @@ class BBCIE(BBCCoUkIE): # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret) programme_id = self._search_regex( - [r'data-video-player-vpid="([\da-z]{8})"', - r'<param[^>]+name="externalIdentifier"[^>]+value="([\da-z]{8})"'], + [r'data-video-player-vpid="(%s)"' % self._ID_REGEX, + r'<param[^>]+name="externalIdentifier"[^>]+value="(%s)"' % self._ID_REGEX, + r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX], webpage, 'vpid', default=None) if programme_id: @@ -814,7 +823,7 @@ class BBCIE(BBCCoUkIE): # Multiple video article (e.g. # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460) - EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+[\da-z]{8}(?:\b[^"]+)?' + EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+%s(?:\b[^"]+)?' % self._ID_REGEX entries = [] for match in extract_all(r'new\s+SMP\(({.+?})\)'): embed_url = match.get('playerSettings', {}).get('externalEmbedUrl') diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py index e6c928699..c8d921daf 100644 --- a/youtube_dl/extractor/beeg.py +++ b/youtube_dl/extractor/beeg.py @@ -1,6 +1,11 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..compat import ( + compat_chr, + compat_ord, + compat_urllib_parse_unquote, +) from ..utils import ( int_or_none, parse_iso8601, @@ -29,16 +34,49 @@ class BeegIE(InfoExtractor): video_id = self._match_id(url) video = self._download_json( - 'http://beeg.com/api/v1/video/%s' % video_id, video_id) + 'http://beeg.com/api/v5/video/%s' % video_id, video_id) + + def split(o, e): + def cut(s, x): + n.append(s[:x]) + return s[x:] + n = [] + r = len(o) % e + if r > 0: + o = cut(o, r) + while len(o) > e: + o = cut(o, e) + n.append(o) + return n + + def decrypt_key(key): + # Reverse engineered from http://static.beeg.com/cpl/1105.js + a = '5ShMcIQlssOd7zChAIOlmeTZDaUxULbJRnywYaiB' + e = compat_urllib_parse_unquote(key) + o = ''.join([ + compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 21) + for n in range(len(e))]) + return ''.join(split(o, 3)[::-1]) + + def decrypt_url(encrypted_url): + encrypted_url = self._proto_relative_url( + encrypted_url.replace('{DATA_MARKERS}', ''), 'http:') + key = self._search_regex( + r'/key=(.*?)%2Cend=', encrypted_url, 'key', default=None) + if not key: + return encrypted_url + return encrypted_url.replace(key, decrypt_key(key)) formats = [] for format_id, video_url in video.items(): + if not video_url: + continue height = self._search_regex( r'^(\d+)[pP]$', format_id, 'height', default=None) if not height: continue formats.append({ - 'url': self._proto_relative_url(video_url.replace('{DATA_MARKERS}', ''), 'http:'), + 'url': decrypt_url(video_url), 'format_id': format_id, 'height': int(height), }) diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py index ecc17ebeb..59beb11bc 100644 --- a/youtube_dl/extractor/bilibili.py +++ b/youtube_dl/extractor/bilibili.py @@ -2,141 +2,109 @@ from __future__ import unicode_literals import re -import itertools -import json -import xml.etree.ElementTree as ET from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( int_or_none, - unified_strdate, + unescapeHTML, ExtractorError, + xpath_text, ) class BiliBiliIE(InfoExtractor): - _VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>[0-9]+)/' + _VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)(?:/index_(?P<page_num>\d+).html)?' _TESTS = [{ 'url': 'http://www.bilibili.tv/video/av1074402/', 'md5': '2c301e4dab317596e837c3e7633e7d86', 'info_dict': { - 'id': '1074402_part1', + 'id': '1554319', 'ext': 'flv', 'title': '【金坷垃】金泡沫', - 'duration': 308, + 'duration': 308313, 'upload_date': '20140420', 'thumbnail': 're:^https?://.+\.jpg', + 'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923', + 'timestamp': 1397983878, + 'uploader': '菊子桑', }, }, { 'url': 'http://www.bilibili.com/video/av1041170/', 'info_dict': { 'id': '1041170', 'title': '【BD1080P】刀语【诸神&异域】', + 'description': '这是个神奇的故事~每个人不留弹幕不给走哦~切利哦！~', + 'uploader': '枫叶逝去', + 'timestamp': 1396501299, }, 'playlist_count': 9, }] def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - if '(此视频不存在或被删除)' in webpage: - raise ExtractorError( - 'The video does not exist or was deleted', expected=True) - - if '>你没有权限浏览！ 由于版权相关问题 我们不对您所在的地区提供服务<' in webpage: - raise ExtractorError( - 'The video is not available in your region due to copyright reasons', - expected=True) - - video_code = self._search_regex( - r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code') - - title = self._html_search_meta( - 'media:title', video_code, 'title', fatal=True) - duration_str = self._html_search_meta( - 'duration', video_code, 'duration') - if duration_str is None: - duration = None - else: - duration_mobj = re.match( - r'^T(?:(?P<hours>[0-9]+)H)?(?P<minutes>[0-9]+)M(?P<seconds>[0-9]+)S$', - duration_str) - duration = ( - int_or_none(duration_mobj.group('hours'), default=0) * 3600 + - int(duration_mobj.group('minutes')) * 60 + - int(duration_mobj.group('seconds'))) - upload_date = unified_strdate(self._html_search_meta( - 'uploadDate', video_code, fatal=False)) - thumbnail = self._html_search_meta( - 'thumbnailUrl', video_code, 'thumbnail', fatal=False) - - cid = self._search_regex(r'cid=(\d+)', webpage, 'cid') - - entries = [] - - lq_page = self._download_webpage( - 'http://interface.bilibili.com/v_cdn_play?appkey=1&cid=%s' % cid, - video_id, - note='Downloading LQ video info' + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + page_num = mobj.group('page_num') or '1' + + view_data = self._download_json( + 'http://api.bilibili.com/view?type=json&appkey=8e9fc618fbd41e28&id=%s&page=%s' % (video_id, page_num), + video_id) + if 'error' in view_data: + raise ExtractorError('%s said: %s' % (self.IE_NAME, view_data['error']), expected=True) + + cid = view_data['cid'] + title = unescapeHTML(view_data['title']) + + doc = self._download_xml( + 'http://interface.bilibili.com/v_cdn_play?appkey=8e9fc618fbd41e28&cid=%s' % cid, + cid, + 'Downloading page %s/%s' % (page_num, view_data['pages']) ) - try: - err_info = json.loads(lq_page) - raise ExtractorError( - 'BiliBili said: ' + err_info['error_text'], expected=True) - except ValueError: - pass - lq_doc = ET.fromstring(lq_page) - lq_durls = lq_doc.findall('./durl') + if xpath_text(doc, './result') == 'error': + raise ExtractorError('%s said: %s' % (self.IE_NAME, xpath_text(doc, './message')), expected=True) - hq_doc = self._download_xml( - 'http://interface.bilibili.com/playurl?appkey=1&cid=%s' % cid, - video_id, - note='Downloading HQ video info', - fatal=False, - ) - if hq_doc is not False: - hq_durls = hq_doc.findall('./durl') - assert len(lq_durls) == len(hq_durls) - else: - hq_durls = itertools.repeat(None) + entries = [] - i = 1 - for lq_durl, hq_durl in zip(lq_durls, hq_durls): + for durl in doc.findall('./durl'): + size = xpath_text(durl, ['./filesize', './size']) formats = [{ - 'format_id': 'lq', - 'quality': 1, - 'url': lq_durl.find('./url').text, - 'filesize': int_or_none( - lq_durl.find('./size'), get_attr='text'), + 'url': durl.find('./url').text, + 'filesize': int_or_none(size), + 'ext': 'flv', }] - if hq_durl is not None: - formats.append({ - 'format_id': 'hq', - 'quality': 2, - 'ext': 'flv', - 'url': hq_durl.find('./url').text, - 'filesize': int_or_none( - hq_durl.find('./size'), get_attr='text'), - }) - self._sort_formats(formats) + backup_urls = durl.find('./backup_url') + if backup_urls is not None: + for backup_url in backup_urls.findall('./url'): + formats.append({'url': backup_url.text}) + formats.reverse() entries.append({ - 'id': '%s_part%d' % (video_id, i), + 'id': '%s_part%s' % (cid, xpath_text(durl, './order')), 'title': title, + 'duration': int_or_none(xpath_text(durl, './length'), 1000), 'formats': formats, - 'duration': duration, - 'upload_date': upload_date, - 'thumbnail': thumbnail, }) - i += 1 - - return { - '_type': 'multi_video', - 'entries': entries, - 'id': video_id, - 'title': title + info = { + 'id': compat_str(cid), + 'title': title, + 'description': view_data.get('description'), + 'thumbnail': view_data.get('pic'), + 'uploader': view_data.get('author'), + 'timestamp': int_or_none(view_data.get('created')), + 'view_count': int_or_none(view_data.get('play')), + 'duration': int_or_none(xpath_text(doc, './timelength')), } + + if len(entries) == 1: + entries[0].update(info) + return entries[0] + else: + info.update({ + '_type': 'multi_video', + 'id': video_id, + 'entries': entries, + }) + return info diff --git a/youtube_dl/extractor/bleacherreport.py b/youtube_dl/extractor/bleacherreport.py new file mode 100644 index 000000000..38bda3af5 --- /dev/null +++ b/youtube_dl/extractor/bleacherreport.py @@ -0,0 +1,106 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from .amp import AMPIE +from ..utils import ( + ExtractorError, + int_or_none, + parse_iso8601, +) + + +class BleacherReportIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/articles/(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://bleacherreport.com/articles/2496438-fsu-stat-projections-is-jalen-ramsey-best-defensive-player-in-college-football', + 'md5': 'a3ffc3dc73afdbc2010f02d98f990f20', + 'info_dict': { + 'id': '2496438', + 'ext': 'mp4', + 'title': 'FSU Stat Projections: Is Jalen Ramsey Best Defensive Player in College Football?', + 'uploader_id': 3992341, + 'description': 'CFB, ACC, Florida State', + 'timestamp': 1434380212, + 'upload_date': '20150615', + 'uploader': 'Team Stream Now ', + }, + 'add_ie': ['Ooyala'], + }, { + 'url': 'http://bleacherreport.com/articles/2586817-aussie-golfers-get-fright-of-their-lives-after-being-chased-by-angry-kangaroo', + 'md5': 'af5f90dc9c7ba1c19d0a3eac806bbf50', + 'info_dict': { + 'id': '2586817', + 'ext': 'mp4', + 'title': 'Aussie Golfers Get Fright of Their Lives After Being Chased by Angry Kangaroo', + 'timestamp': 1446839961, + 'uploader': 'Sean Fay', + 'description': 'md5:825e94e0f3521df52fa83b2ed198fa20', + 'uploader_id': 6466954, + 'upload_date': '20151011', + }, + 'add_ie': ['Youtube'], + }] + + def _real_extract(self, url): + article_id = self._match_id(url) + + article_data = self._download_json('http://api.bleacherreport.com/api/v1/articles/%s' % article_id, article_id)['article'] + + thumbnails = [] + primary_photo = article_data.get('primaryPhoto') + if primary_photo: + thumbnails = [{ + 'url': primary_photo['url'], + 'width': primary_photo.get('width'), + 'height': primary_photo.get('height'), + }] + + info = { + '_type': 'url_transparent', + 'id': article_id, + 'title': article_data['title'], + 'uploader': article_data.get('author', {}).get('name'), + 'uploader_id': article_data.get('authorId'), + 'timestamp': parse_iso8601(article_data.get('createdAt')), + 'thumbnails': thumbnails, + 'comment_count': int_or_none(article_data.get('commentsCount')), + 'view_count': int_or_none(article_data.get('hitCount')), + } + + video = article_data.get('video') + if video: + video_type = video['type'] + if video_type == 'cms.bleacherreport.com': + info['url'] = 'http://bleacherreport.com/video_embed?id=%s' % video['id'] + elif video_type == 'ooyala.com': + info['url'] = 'ooyala:%s' % video['id'] + elif video_type == 'youtube.com': + info['url'] = video['id'] + elif video_type == 'vine.co': + info['url'] = 'https://vine.co/v/%s' % video['id'] + else: + info['url'] = video_type + video['id'] + return info + else: + raise ExtractorError('no video in the article', expected=True) + + +class BleacherReportCMSIE(AMPIE): + _VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P<id>[0-9a-f-]{36})' + _TESTS = [{ + 'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1', + 'md5': '8c2c12e3af7805152675446c905d159b', + 'info_dict': { + 'id': '8fd44c2f-3dc5-4821-9118-2c825a98c0e1', + 'ext': 'flv', + 'title': 'Cena vs. Rollins Would Expose the Heavyweight Division', + 'description': 'md5:984afb4ade2f9c0db35f3267ed88b36e', + }, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + info = self._extract_feed_info('http://cms.bleacherreport.com/media/items/%s/akamai.json' % video_id) + info['id'] = video_id + return info diff --git a/youtube_dl/extractor/bliptv.py b/youtube_dl/extractor/bliptv.py deleted file mode 100644 index c3296283d..000000000 --- a/youtube_dl/extractor/bliptv.py +++ /dev/null @@ -1,292 +0,0 @@ -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor - -from ..compat import ( - compat_urllib_request, - compat_urlparse, -) -from ..utils import ( - clean_html, - int_or_none, - parse_iso8601, - unescapeHTML, - xpath_text, - xpath_with_ns, -) - - -class BlipTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:\w+\.)?blip\.tv/(?:(?:.+-|rss/flash/)(?P<id>\d+)|((?:play/|api\.swf#)(?P<lookup_id>[\da-zA-Z+_]+)))' - - _TESTS = [ - { - 'url': 'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352', - 'md5': '80baf1ec5c3d2019037c1c707d676b9f', - 'info_dict': { - 'id': '5779306', - 'ext': 'm4v', - 'title': 'CBR EXCLUSIVE: "Gotham City Imposters" Bats VS Jokerz Short 3', - 'description': 'md5:9bc31f227219cde65e47eeec8d2dc596', - 'timestamp': 1323138843, - 'upload_date': '20111206', - 'uploader': 'cbr', - 'uploader_id': '679425', - 'duration': 81, - } - }, - { - # https://github.com/rg3/youtube-dl/pull/2274 - 'note': 'Video with subtitles', - 'url': 'http://blip.tv/play/h6Uag5OEVgI.html', - 'md5': '309f9d25b820b086ca163ffac8031806', - 'info_dict': { - 'id': '6586561', - 'ext': 'mp4', - 'title': 'Red vs. Blue Season 11 Episode 1', - 'description': 'One-Zero-One', - 'timestamp': 1371261608, - 'upload_date': '20130615', - 'uploader': 'redvsblue', - 'uploader_id': '792887', - 'duration': 279, - } - }, - { - # https://bugzilla.redhat.com/show_bug.cgi?id=967465 - 'url': 'http://a.blip.tv/api.swf#h6Uag5KbVwI', - 'md5': '314e87b1ebe7a48fcbfdd51b791ce5a6', - 'info_dict': { - 'id': '6573122', - 'ext': 'mov', - 'upload_date': '20130520', - 'description': 'Two hapless space marines argue over what to do when they realize they have an astronomically huge problem on their hands.', - 'title': 'Red vs. Blue Season 11 Trailer', - 'timestamp': 1369029609, - 'uploader': 'redvsblue', - 'uploader_id': '792887', - } - }, - { - 'url': 'http://blip.tv/play/gbk766dkj4Yn', - 'md5': 'fe0a33f022d49399a241e84a8ea8b8e3', - 'info_dict': { - 'id': '1749452', - 'ext': 'mp4', - 'upload_date': '20090208', - 'description': 'Witness the first appearance of the Nostalgia Critic character, as Doug reviews the movie Transformers.', - 'title': 'Nostalgia Critic: Transformers', - 'timestamp': 1234068723, - 'uploader': 'NostalgiaCritic', - 'uploader_id': '246467', - } - }, - { - # https://github.com/rg3/youtube-dl/pull/4404 - 'note': 'Audio only', - 'url': 'http://blip.tv/hilarios-productions/weekly-manga-recap-kingdom-7119982', - 'md5': '76c0a56f24e769ceaab21fbb6416a351', - 'info_dict': { - 'id': '7103299', - 'ext': 'flv', - 'title': 'Weekly Manga Recap: Kingdom', - 'description': 'And then Shin breaks the enemy line, and he's all like HWAH! And then he slices a guy and it's all like FWASHING! And... it's really hard to describe the best parts of this series without breaking down into sound effects, okay?', - 'timestamp': 1417660321, - 'upload_date': '20141204', - 'uploader': 'The Rollo T', - 'uploader_id': '407429', - 'duration': 7251, - 'vcodec': 'none', - } - }, - { - # missing duration - 'url': 'http://blip.tv/rss/flash/6700880', - 'info_dict': { - 'id': '6684191', - 'ext': 'm4v', - 'title': 'Cowboy Bebop: Gateway Shuffle Review', - 'description': 'md5:3acc480c0f9ae157f5fe88547ecaf3f8', - 'timestamp': 1386639757, - 'upload_date': '20131210', - 'uploader': 'sfdebris', - 'uploader_id': '706520', - } - } - ] - - @staticmethod - def _extract_url(webpage): - mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage) - if mobj: - return 'http://blip.tv/a/a-' + mobj.group(1) - mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage) - if mobj: - return mobj.group(1) - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - lookup_id = mobj.group('lookup_id') - - # See https://github.com/rg3/youtube-dl/issues/857 and - # https://github.com/rg3/youtube-dl/issues/4197 - if lookup_id: - urlh = self._request_webpage( - 'http://blip.tv/play/%s' % lookup_id, lookup_id, 'Resolving lookup id') - url = compat_urlparse.urlparse(urlh.geturl()) - qs = compat_urlparse.parse_qs(url.query) - mobj = re.match(self._VALID_URL, qs['file'][0]) - - video_id = mobj.group('id') - - rss = self._download_xml('http://blip.tv/rss/flash/%s' % video_id, video_id, 'Downloading video RSS') - - def _x(p): - return xpath_with_ns(p, { - 'blip': 'http://blip.tv/dtd/blip/1.0', - 'media': 'http://search.yahoo.com/mrss/', - 'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd', - }) - - item = rss.find('channel/item') - - video_id = xpath_text(item, _x('blip:item_id'), 'video id') or lookup_id - title = xpath_text(item, 'title', 'title', fatal=True) - description = clean_html(xpath_text(item, _x('blip:puredescription'), 'description')) - timestamp = parse_iso8601(xpath_text(item, _x('blip:datestamp'), 'timestamp')) - uploader = xpath_text(item, _x('blip:user'), 'uploader') - uploader_id = xpath_text(item, _x('blip:userid'), 'uploader id') - duration = int_or_none(xpath_text(item, _x('blip:runtime'), 'duration')) - media_thumbnail = item.find(_x('media:thumbnail')) - thumbnail = (media_thumbnail.get('url') if media_thumbnail is not None - else xpath_text(item, 'image', 'thumbnail')) - categories = [category.text for category in item.findall('category') if category is not None] - - formats = [] - subtitles_urls = {} - - media_group = item.find(_x('media:group')) - for media_content in media_group.findall(_x('media:content')): - url = media_content.get('url') - role = media_content.get(_x('blip:role')) - msg = self._download_webpage( - url + '?showplayer=20140425131715&referrer=http://blip.tv&mask=7&skin=flashvars&view=url', - video_id, 'Resolving URL for %s' % role) - real_url = compat_urlparse.parse_qs(msg.strip())['message'][0] - - media_type = media_content.get('type') - if media_type == 'text/srt' or url.endswith('.srt'): - LANGS = { - 'english': 'en', - } - lang = role.rpartition('-')[-1].strip().lower() - langcode = LANGS.get(lang, lang) - subtitles_urls[langcode] = url - elif media_type.startswith('video/'): - formats.append({ - 'url': real_url, - 'format_id': role, - 'format_note': media_type, - 'vcodec': media_content.get(_x('blip:vcodec')) or 'none', - 'acodec': media_content.get(_x('blip:acodec')), - 'filesize': media_content.get('filesize'), - 'width': int_or_none(media_content.get('width')), - 'height': int_or_none(media_content.get('height')), - }) - self._check_formats(formats, video_id) - self._sort_formats(formats) - - subtitles = self.extract_subtitles(video_id, subtitles_urls) - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'timestamp': timestamp, - 'uploader': uploader, - 'uploader_id': uploader_id, - 'duration': duration, - 'thumbnail': thumbnail, - 'categories': categories, - 'formats': formats, - 'subtitles': subtitles, - } - - def _get_subtitles(self, video_id, subtitles_urls): - subtitles = {} - for lang, url in subtitles_urls.items(): - # For some weird reason, blip.tv serves a video instead of subtitles - # when we request with a common UA - req = compat_urllib_request.Request(url) - req.add_header('User-Agent', 'youtube-dl') - subtitles[lang] = [{ - # The extension is 'srt' but it's actually an 'ass' file - 'ext': 'ass', - 'data': self._download_webpage(req, None, note=False), - }] - return subtitles - - -class BlipTVUserIE(InfoExtractor): - _VALID_URL = r'(?:(?:https?://(?:\w+\.)?blip\.tv/)|bliptvuser:)(?!api\.swf)([^/]+)/*$' - _PAGE_SIZE = 12 - IE_NAME = 'blip.tv:user' - _TEST = { - 'url': 'http://blip.tv/actone', - 'info_dict': { - 'id': 'actone', - 'title': 'Act One: The Series', - }, - 'playlist_count': 5, - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - username = mobj.group(1) - - page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1' - - page = self._download_webpage(url, username, 'Downloading user page') - mobj = re.search(r'data-users-id="([^"]+)"', page) - page_base = page_base % mobj.group(1) - title = self._og_search_title(page) - - # Download video ids using BlipTV Ajax calls. Result size per - # query is limited (currently to 12 videos) so we need to query - # page by page until there are no video ids - it means we got - # all of them. - - video_ids = [] - pagenum = 1 - - while True: - url = page_base + "&page=" + str(pagenum) - page = self._download_webpage( - url, username, 'Downloading video ids from page %d' % pagenum) - - # Extract video identifiers - ids_in_page = [] - - for mobj in re.finditer(r'href="/([^"]+)"', page): - if mobj.group(1) not in ids_in_page: - ids_in_page.append(unescapeHTML(mobj.group(1))) - - video_ids.extend(ids_in_page) - - # A little optimization - if current page is not - # "full", ie. does not contain PAGE_SIZE video ids then - # we can assume that this page is the last one - there - # are no more ids on further pages - no need to query - # again. - - if len(ids_in_page) < self._PAGE_SIZE: - break - - pagenum += 1 - - urls = ['http://blip.tv/%s' % video_id for video_id in video_ids] - url_entries = [self.url_result(vurl, 'BlipTV') for vurl in urls] - return self.playlist_result( - url_entries, playlist_title=title, playlist_id=username) diff --git a/youtube_dl/extractor/bloomberg.py b/youtube_dl/extractor/bloomberg.py index 0dca29b71..ebeef8f2a 100644 --- a/youtube_dl/extractor/bloomberg.py +++ b/youtube_dl/extractor/bloomberg.py @@ -6,9 +6,9 @@ from .common import InfoExtractor class BloombergIE(InfoExtractor): - _VALID_URL = r'https?://www\.bloomberg\.com/news/videos/[^/]+/(?P<id>[^/?#]+)' + _VALID_URL = r'https?://(?:www\.)?bloomberg\.com/(?:[^/]+/)*(?P<id>[^/?#]+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.bloomberg.com/news/videos/b/aaeae121-5949-481e-a1ce-4562db6f5df2', # The md5 checksum changes 'info_dict': { @@ -17,22 +17,39 @@ class BloombergIE(InfoExtractor): 'title': 'Shah\'s Presentation on Foreign-Exchange Strategies', 'description': 'md5:a8ba0302912d03d246979735c17d2761', }, - } + }, { + 'url': 'http://www.bloomberg.com/news/articles/2015-11-12/five-strange-things-that-have-been-happening-in-financial-markets', + 'only_matching': True, + }, { + 'url': 'http://www.bloomberg.com/politics/videos/2015-11-25/karl-rove-on-jeb-bush-s-struggles-stopping-trump', + 'only_matching': True, + }] def _real_extract(self, url): name = self._match_id(url) webpage = self._download_webpage(url, name) - video_id = self._search_regex(r'"bmmrId":"(.+?)"', webpage, 'id') + video_id = self._search_regex( + r'["\']bmmrId["\']\s*:\s*(["\'])(?P<url>.+?)\1', + webpage, 'id', group='url') title = re.sub(': Video$', '', self._og_search_title(webpage)) embed_info = self._download_json( 'http://www.bloomberg.com/api/embed?id=%s' % video_id, video_id) formats = [] for stream in embed_info['streams']: - if stream["muxing_format"] == "TS": - formats.extend(self._extract_m3u8_formats(stream['url'], video_id)) + stream_url = stream.get('url') + if not stream_url: + continue + if stream['muxing_format'] == 'TS': + m3u8_formats = self._extract_m3u8_formats( + stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) else: - formats.extend(self._extract_f4m_formats(stream['url'], video_id)) + f4m_formats = self._extract_f4m_formats( + stream_url, video_id, f4m_id='hds', fatal=False) + if f4m_formats: + formats.extend(f4m_formats) self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/br.py b/youtube_dl/extractor/br.py index 66e394e10..e66854538 100644 --- a/youtube_dl/extractor/br.py +++ b/youtube_dl/extractor/br.py @@ -1,18 +1,21 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( ExtractorError, int_or_none, parse_duration, + xpath_element, + xpath_text, ) class BRIE(InfoExtractor): IE_DESC = 'Bayerischer Rundfunk Mediathek' - _VALID_URL = r'https?://(?:www\.)?br\.de/(?:[a-z0-9\-_]+/)+(?P<id>[a-z0-9\-_]+)\.html' - _BASE_URL = 'http://www.br.de' + _VALID_URL = r'(?P<base_url>https?://(?:www\.)?br(?:-klassik)?\.de)/(?:[a-z0-9\-_]+/)+(?P<id>[a-z0-9\-_]+)\.html' _TESTS = [ { @@ -22,7 +25,7 @@ class BRIE(InfoExtractor): 'id': '48f656ef-287e-486f-be86-459122db22cc', 'ext': 'mp4', 'title': 'Die böse Überraschung', - 'description': 'Betriebliche Altersvorsorge: Die böse Überraschung', + 'description': 'md5:ce9ac81b466ce775b8018f6801b48ac9', 'duration': 180, 'uploader': 'Reinhard Weber', 'upload_date': '20150422', @@ -30,23 +33,23 @@ class BRIE(InfoExtractor): }, { 'url': 'http://www.br.de/nachrichten/oberbayern/inhalt/muenchner-polizeipraesident-schreiber-gestorben-100.html', - 'md5': 'a44396d73ab6a68a69a568fae10705bb', + 'md5': 'af3a3a4aa43ff0ce6a89504c67f427ef', 'info_dict': { 'id': 'a4b83e34-123d-4b81-9f4e-c0d3121a4e05', - 'ext': 'mp4', + 'ext': 'flv', 'title': 'Manfred Schreiber ist tot', - 'description': 'Abendschau kompakt: Manfred Schreiber ist tot', + 'description': 'md5:b454d867f2a9fc524ebe88c3f5092d97', 'duration': 26, } }, { - 'url': 'http://www.br.de/radio/br-klassik/sendungen/allegro/premiere-urauffuehrung-the-land-2015-dance-festival-muenchen-100.html', + 'url': 'https://www.br-klassik.de/audio/peeping-tom-premierenkritik-dance-festival-muenchen-100.html', 'md5': '8b5b27c0b090f3b35eac4ab3f7a73d3d', 'info_dict': { 'id': '74c603c9-26d3-48bb-b85b-079aeed66e0b', 'ext': 'aac', 'title': 'Kurzweilig und sehr bewegend', - 'description': '"The Land" von Peeping Tom: Kurzweilig und sehr bewegend', + 'description': 'md5:0351996e3283d64adeb38ede91fac54e', 'duration': 296, } }, @@ -57,7 +60,7 @@ class BRIE(InfoExtractor): 'id': '6ba73750-d405-45d3-861d-1ce8c524e059', 'ext': 'mp4', 'title': 'Umweltbewusster Häuslebauer', - 'description': 'Uwe Erdelt: Umweltbewusster Häuslebauer', + 'description': 'md5:d52dae9792d00226348c1dbb13c9bae2', 'duration': 116, } }, @@ -68,7 +71,7 @@ class BRIE(InfoExtractor): 'id': 'd982c9ce-8648-4753-b358-98abb8aec43d', 'ext': 'mp4', 'title': 'Folge 1 - Metaphysik', - 'description': 'Kant für Anfänger: Folge 1 - Metaphysik', + 'description': 'md5:bb659990e9e59905c3d41e369db1fbe3', 'duration': 893, 'uploader': 'Eva Maria Steimle', 'upload_date': '20140117', @@ -77,28 +80,31 @@ class BRIE(InfoExtractor): ] def _real_extract(self, url): - display_id = self._match_id(url) + base_url, display_id = re.search(self._VALID_URL, url).groups() page = self._download_webpage(url, display_id) xml_url = self._search_regex( r"return BRavFramework\.register\(BRavFramework\('avPlayer_(?:[a-f0-9-]{36})'\)\.setup\({dataURL:'(/(?:[a-z0-9\-]+/)+[a-z0-9/~_.-]+)'}\)\);", page, 'XMLURL') - xml = self._download_xml(self._BASE_URL + xml_url, None) + xml = self._download_xml(base_url + xml_url, display_id) medias = [] for xml_media in xml.findall('video') + xml.findall('audio'): + media_id = xml_media.get('externalId') media = { - 'id': xml_media.get('externalId'), - 'title': xml_media.find('title').text, - 'duration': parse_duration(xml_media.find('duration').text), - 'formats': self._extract_formats(xml_media.find('assets')), - 'thumbnails': self._extract_thumbnails(xml_media.find('teaserImage/variants')), - 'description': ' '.join(xml_media.find('shareTitle').text.splitlines()), - 'webpage_url': xml_media.find('permalink').text + 'id': media_id, + 'title': xpath_text(xml_media, 'title', 'title', True), + 'duration': parse_duration(xpath_text(xml_media, 'duration')), + 'formats': self._extract_formats(xpath_element( + xml_media, 'assets'), media_id), + 'thumbnails': self._extract_thumbnails(xpath_element( + xml_media, 'teaserImage/variants'), base_url), + 'description': xpath_text(xml_media, 'desc'), + 'webpage_url': xpath_text(xml_media, 'permalink'), + 'uploader': xpath_text(xml_media, 'author'), } - if xml_media.find('author').text: - media['uploader'] = xml_media.find('author').text - if xml_media.find('broadcastDate').text: - media['upload_date'] = ''.join(reversed(xml_media.find('broadcastDate').text.split('.'))) + broadcast_date = xpath_text(xml_media, 'broadcastDate') + if broadcast_date: + media['upload_date'] = ''.join(reversed(broadcast_date.split('.'))) medias.append(media) if len(medias) > 1: @@ -109,35 +115,58 @@ class BRIE(InfoExtractor): raise ExtractorError('No media entries found') return medias[0] - def _extract_formats(self, assets): - - def text_or_none(asset, tag): - elem = asset.find(tag) - return None if elem is None else elem.text - - formats = [{ - 'url': text_or_none(asset, 'downloadUrl'), - 'ext': text_or_none(asset, 'mediaType'), - 'format_id': asset.get('type'), - 'width': int_or_none(text_or_none(asset, 'frameWidth')), - 'height': int_or_none(text_or_none(asset, 'frameHeight')), - 'tbr': int_or_none(text_or_none(asset, 'bitrateVideo')), - 'abr': int_or_none(text_or_none(asset, 'bitrateAudio')), - 'vcodec': text_or_none(asset, 'codecVideo'), - 'acodec': text_or_none(asset, 'codecAudio'), - 'container': text_or_none(asset, 'mediaType'), - 'filesize': int_or_none(text_or_none(asset, 'size')), - } for asset in assets.findall('asset') - if asset.find('downloadUrl') is not None] - + def _extract_formats(self, assets, media_id): + formats = [] + for asset in assets.findall('asset'): + format_url = xpath_text(asset, ['downloadUrl', 'url']) + asset_type = asset.get('type') + if asset_type == 'HDS': + f4m_formats = self._extract_f4m_formats( + format_url + '?hdcore=3.2.0', media_id, f4m_id='hds', fatal=False) + if f4m_formats: + formats.extend(f4m_formats) + elif asset_type == 'HLS': + m3u8_formats = self._extract_m3u8_formats( + format_url, media_id, 'mp4', 'm3u8_native', m3u8_id='hds', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + else: + format_info = { + 'ext': xpath_text(asset, 'mediaType'), + 'width': int_or_none(xpath_text(asset, 'frameWidth')), + 'height': int_or_none(xpath_text(asset, 'frameHeight')), + 'tbr': int_or_none(xpath_text(asset, 'bitrateVideo')), + 'abr': int_or_none(xpath_text(asset, 'bitrateAudio')), + 'vcodec': xpath_text(asset, 'codecVideo'), + 'acodec': xpath_text(asset, 'codecAudio'), + 'container': xpath_text(asset, 'mediaType'), + 'filesize': int_or_none(xpath_text(asset, 'size')), + } + format_url = self._proto_relative_url(format_url) + if format_url: + http_format_info = format_info.copy() + http_format_info.update({ + 'url': format_url, + 'format_id': 'http-%s' % asset_type, + }) + formats.append(http_format_info) + server_prefix = xpath_text(asset, 'serverPrefix') + if server_prefix: + rtmp_format_info = format_info.copy() + rtmp_format_info.update({ + 'url': server_prefix, + 'play_path': xpath_text(asset, 'fileName'), + 'format_id': 'rtmp-%s' % asset_type, + }) + formats.append(rtmp_format_info) self._sort_formats(formats) return formats - def _extract_thumbnails(self, variants): + def _extract_thumbnails(self, variants, base_url): thumbnails = [{ - 'url': self._BASE_URL + variant.find('url').text, - 'width': int_or_none(variant.find('width').text), - 'height': int_or_none(variant.find('height').text), - } for variant in variants.findall('variant')] + 'url': base_url + xpath_text(variant, 'url'), + 'width': int_or_none(xpath_text(variant, 'width')), + 'height': int_or_none(xpath_text(variant, 'height')), + } for variant in variants.findall('variant') if xpath_text(variant, 'url')] thumbnails.sort(key=lambda x: x['width'] * x['height'], reverse=True) return thumbnails diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 4721c2293..03a4f446e 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -3,15 +3,14 @@ from __future__ import unicode_literals import re import json -import xml.etree.ElementTree from .common import InfoExtractor from ..compat import ( + compat_etree_fromstring, compat_parse_qs, compat_str, compat_urllib_parse, compat_urllib_parse_urlparse, - compat_urllib_request, compat_urlparse, compat_xml_parse_error, ) @@ -20,12 +19,18 @@ from ..utils import ( ExtractorError, find_xpath_attr, fix_xml_ampersands, + float_or_none, + js_to_json, + int_or_none, + parse_iso8601, + sanitized_Request, unescapeHTML, unsmuggle_url, ) -class BrightcoveIE(InfoExtractor): +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' @@ -119,7 +124,7 @@ class BrightcoveIE(InfoExtractor): object_str = fix_xml_ampersands(object_str) try: - object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8')) + object_doc = compat_etree_fromstring(object_str.encode('utf-8')) except compat_xml_parse_error: return @@ -245,7 +250,7 @@ class BrightcoveIE(InfoExtractor): def _get_video_info(self, video_id, query_str, query, referer=None): request_url = self._FEDERATED_URL_TEMPLATE % query_str - req = compat_urllib_request.Request(request_url) + req = sanitized_Request(request_url) linkBase = query.get('linkBaseURL') if linkBase is not None: referer = linkBase[0] @@ -346,3 +351,183 @@ class BrightcoveIE(InfoExtractor): if 'url' not in info and not info.get('formats'): raise ExtractorError('Unable to extract video url for %s' % info['id']) return info + + +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+)' + _TESTS = [{ + 'url': 'http://players.brightcove.net/929656772001/e41d32dc-ec74-459e-a845-6c69f7b724ea_default/index.html?videoId=4463358922001', + 'md5': 'c8100925723840d4b0d243f7025703be', + 'info_dict': { + 'id': '4463358922001', + 'ext': 'mp4', + 'title': 'Meet the man behind Popcorn Time', + 'description': 'md5:eac376a4fe366edc70279bfb681aea16', + 'duration': 165.768, + 'timestamp': 1441391203, + 'upload_date': '20150904', + 'uploader_id': '929656772001', + 'formats': 'mincount:22', + }, + }, { + # with rtmp streams + 'url': 'http://players.brightcove.net/4036320279001/5d112ed9-283f-485f-a7f9-33f42e8bc042_default/index.html?videoId=4279049078001', + 'info_dict': { + 'id': '4279049078001', + 'ext': 'mp4', + 'title': 'Titansgrave: Chapter 0', + 'description': 'Titansgrave: Chapter 0', + 'duration': 1242.058, + 'timestamp': 1433556729, + 'upload_date': '20150606', + 'uploader_id': '4036320279001', + 'formats': 'mincount:41', + }, + 'params': { + 'skip_download': True, + } + }, { + # ref: prefixed video id + 'url': 'http://players.brightcove.net/3910869709001/21519b5c-4b3b-4363-accb-bdc8f358f823_default/index.html?videoId=ref:7069442', + 'only_matching': True, + }] + + @staticmethod + def _extract_url(webpage): + urls = BrightcoveNewIE._extract_urls(webpage) + return urls[0] if urls else None + + @staticmethod + def _extract_urls(webpage): + # Reference: + # 1. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#setvideoiniframe + # 2. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#setvideousingjavascript + # 3. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/embed-in-page.html + # 4. https://support.brightcove.com/en/video-cloud/docs/dynamically-assigning-videos-player + + entries = [] + + # 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) + + # Look for embed_in_page embeds [2] + for video_id, account_id, player_id, embed in re.findall( + # According to examples from [3] it's unclear whether video id + # may be optional and what to do when it is + # According to [4] data-video-id may be prefixed with ref: + r'''(?sx) + <video[^>]+ + data-video-id=["\']((?:ref:)?\d+)["\'][^>]*>.*? + </video>.*? + <script[^>]+ + src=["\'](?:https?:)?//players\.brightcove\.net/ + (\d+)/([\da-f-]+)_([^/]+)/index\.min\.js + ''', webpage): + entries.append( + 'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s' + % (account_id, player_id, embed, video_id)) + + return entries + + def _real_extract(self, url): + account_id, player_id, embed, video_id = re.match(self._VALID_URL, url).groups() + + webpage = self._download_webpage( + 'http://players.brightcove.net/%s/%s_%s/index.min.js' + % (account_id, player_id, embed), video_id) + + policy_key = None + + catalog = self._search_regex( + r'catalog\(({.+?})\);', webpage, 'catalog', default=None) + if catalog: + catalog = self._parse_json( + js_to_json(catalog), video_id, fatal=False) + if catalog: + policy_key = catalog.get('policyKey') + + if not policy_key: + policy_key = self._search_regex( + 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) + + title = json_data['name'] + + formats = [] + for source in json_data.get('sources', []): + source_type = source.get('type') + src = source.get('src') + if source_type == 'application/x-mpegURL': + if not src: + continue + m3u8_formats = self._extract_m3u8_formats( + src, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + else: + streaming_src = source.get('streaming_src') + stream_name, app_name = source.get('stream_name'), source.get('app_name') + if not src and not streaming_src and (not stream_name or not app_name): + continue + tbr = float_or_none(source.get('avg_bitrate'), 1000) + height = int_or_none(source.get('height')) + 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(), + } + + def build_format_id(kind): + format_id = kind + if tbr: + format_id += '-%dk' % int(tbr) + if height: + format_id += '-%dp' % height + return format_id + + if src or streaming_src: + f.update({ + 'url': src or streaming_src, + 'format_id': build_format_id('http' if src else 'http-streaming'), + 'preference': 2 if src else 1, + }) + else: + f.update({ + 'url': app_name, + 'play_path': stream_name, + 'format_id': build_format_id('rtmp'), + }) + formats.append(f) + self._sort_formats(formats) + + description = json_data.get('description') + thumbnail = json_data.get('thumbnail') + timestamp = parse_iso8601(json_data.get('published_at')) + duration = float_or_none(json_data.get('duration'), 1000) + tags = json_data.get('tags', []) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'timestamp': timestamp, + 'uploader_id': account_id, + 'formats': formats, + 'tags': tags, + } diff --git a/youtube_dl/extractor/byutv.py b/youtube_dl/extractor/byutv.py index 3b2de517e..dda98059e 100644 --- a/youtube_dl/extractor/byutv.py +++ b/youtube_dl/extractor/byutv.py @@ -14,9 +14,10 @@ class BYUtvIE(InfoExtractor): 'info_dict': { 'id': 'studio-c-season-5-episode-5', 'ext': 'mp4', - 'description': 'md5:5438d33774b6bdc662f9485a340401cc', + 'description': 'md5:e07269172baff037f8e8bf9956bc9747', 'title': 'Season 5 Episode 5', - 'thumbnail': 're:^https?://.*\.jpg$' + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 1486.486, }, 'params': { 'skip_download': True, diff --git a/youtube_dl/extractor/canal13cl.py b/youtube_dl/extractor/canal13cl.py deleted file mode 100644 index 93241fefe..000000000 --- a/youtube_dl/extractor/canal13cl.py +++ /dev/null @@ -1,48 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor - - -class Canal13clIE(InfoExtractor): - _VALID_URL = r'^http://(?:www\.)?13\.cl/(?:[^/?#]+/)*(?P<id>[^/?#]+)' - _TEST = { - 'url': 'http://www.13.cl/t13/nacional/el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda', - 'md5': '4cb1fa38adcad8fea88487a078831755', - 'info_dict': { - 'id': '1403022125', - 'display_id': 'el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda', - 'ext': 'mp4', - 'title': 'El "círculo de hierro" de Michelle Bachelet en su regreso a La Moneda', - 'description': '(Foto: Agencia Uno) En nueve días más, Michelle Bachelet va a asumir por segunda vez como presidenta de la República. Entre aquellos que la acompañarán hay caras que se repiten y otras que se consolidan en su entorno de colaboradores más cercanos.', - } - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('id') - - webpage = self._download_webpage(url, display_id) - - title = self._html_search_meta( - 'twitter:title', webpage, 'title', fatal=True) - description = self._html_search_meta( - 'twitter:description', webpage, 'description') - url = self._html_search_regex( - r'articuloVideo = \"(.*?)\"', webpage, 'url') - real_id = self._search_regex( - r'[^0-9]([0-9]{7,})[^0-9]', url, 'id', default=display_id) - thumbnail = self._html_search_regex( - r'articuloImagen = \"(.*?)\"', webpage, 'thumbnail') - - return { - 'id': real_id, - 'display_id': display_id, - 'url': url, - 'title': title, - 'description': description, - 'ext': 'mp4', - 'thumbnail': thumbnail, - } diff --git a/youtube_dl/extractor/cbs.py b/youtube_dl/extractor/cbs.py index 75fffb156..40d07ab18 100644 --- a/youtube_dl/extractor/cbs.py +++ b/youtube_dl/extractor/cbs.py @@ -1,6 +1,10 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..utils import ( + sanitized_Request, + smuggle_url, +) class CBSIE(InfoExtractor): @@ -46,13 +50,19 @@ class CBSIE(InfoExtractor): def _real_extract(self, url): display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) + request = sanitized_Request(url) + # Android UA is served with higher quality (720p) streams (see + # https://github.com/rg3/youtube-dl/issues/7490) + request.add_header('User-Agent', 'Mozilla/5.0 (Linux; Android 4.4; Nexus 5)') + webpage = self._download_webpage(request, display_id) real_id = self._search_regex( [r"video\.settings\.pid\s*=\s*'([^']+)';", r"cbsplayer\.pid\s*=\s*'([^']+)';"], webpage, 'real video ID') return { '_type': 'url_transparent', 'ie_key': 'ThePlatform', - 'url': 'theplatform:%s' % real_id, + 'url': smuggle_url( + 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true&manifest=m3u' % real_id, + {'force_smil_url': True}), 'display_id': display_id, } diff --git a/youtube_dl/extractor/cbsnews.py b/youtube_dl/extractor/cbsnews.py index 52e61d85b..f9a64a0a2 100644 --- a/youtube_dl/extractor/cbsnews.py +++ b/youtube_dl/extractor/cbsnews.py @@ -67,9 +67,12 @@ class CBSNewsIE(InfoExtractor): 'format_id': format_id, } if uri.startswith('rtmp'): + play_path = re.sub( + r'{slistFilePath}', '', + uri.split('<break>')[-1].split('{break}')[-1]) fmt.update({ 'app': 'ondemand?auth=cbs', - 'play_path': 'mp4:' + uri.split('<break>')[-1], + 'play_path': 'mp4:' + play_path, 'player_url': 'http://www.cbsnews.com/[[IMPORT]]/vidtech.cbsinteractive.com/player/3_3_0/CBSI_PLAYER_HD.swf', 'page_url': 'http://www.cbsnews.com', 'ext': 'flv', diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py index e857e66f4..6f7b2a70d 100644 --- a/youtube_dl/extractor/ceskatelevize.py +++ b/youtube_dl/extractor/ceskatelevize.py @@ -5,7 +5,6 @@ import re from .common import InfoExtractor from ..compat import ( - compat_urllib_request, compat_urllib_parse, compat_urllib_parse_unquote, compat_urllib_parse_urlparse, @@ -13,6 +12,7 @@ from ..compat import ( from ..utils import ( ExtractorError, float_or_none, + sanitized_Request, ) @@ -100,7 +100,7 @@ class CeskaTelevizeIE(InfoExtractor): 'requestSource': 'iVysilani', } - req = compat_urllib_request.Request( + req = sanitized_Request( 'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist', data=compat_urllib_parse.urlencode(data)) @@ -115,7 +115,7 @@ class CeskaTelevizeIE(InfoExtractor): if playlist_url == 'error_region': raise ExtractorError(NOT_AVAILABLE_STRING, expected=True) - req = compat_urllib_request.Request(compat_urllib_parse_unquote(playlist_url)) + req = sanitized_Request(compat_urllib_parse_unquote(playlist_url)) req.add_header('Referer', url) playlist_title = self._og_search_title(webpage) diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py index fd1770dac..6d9cd8abd 100644 --- a/youtube_dl/extractor/cinemassacre.py +++ b/youtube_dl/extractor/cinemassacre.py @@ -5,7 +5,6 @@ import re from .common import InfoExtractor from ..utils import ExtractorError -from .bliptv import BlipTVIE from .screenwavemedia import ScreenwaveMediaIE @@ -34,18 +33,17 @@ class CinemassacreIE(InfoExtractor): }, }, { - # blip.tv embedded video + # Youtube embedded video 'url': 'http://cinemassacre.com/2006/12/07/chronologically-confused-about-bad-movie-and-video-game-sequel-titles/', - 'md5': 'ca9b3c8dd5a66f9375daeb5135f5a3de', + 'md5': 'df4cf8a1dcedaec79a73d96d83b99023', 'info_dict': { - 'id': '4065369', - 'ext': 'flv', + 'id': 'OEVzPCY2T-g', + 'ext': 'mp4', 'title': 'AVGN: Chronologically Confused about Bad Movie and Video Game Sequel Titles', 'upload_date': '20061207', - 'uploader': 'cinemassacre', - 'uploader_id': '250778', - 'timestamp': 1283233867, - 'description': 'md5:0a108c78d130676b207d0f6d029ecffd', + 'uploader': 'Cinemassacre', + 'uploader_id': 'JamesNintendoNerd', + 'description': 'md5:784734696c2b8b7f4b8625cc799e07f6', } }, { @@ -89,8 +87,6 @@ class CinemassacreIE(InfoExtractor): ], webpage, 'player data URL', default=None, group='url') if not playerdata_url: - playerdata_url = BlipTVIE._extract_url(webpage) - if not playerdata_url: raise ExtractorError('Unable to find player data') video_title = self._html_search_regex( diff --git a/youtube_dl/extractor/clipfish.py b/youtube_dl/extractor/clipfish.py index 7af903571..3a47f6fa4 100644 --- a/youtube_dl/extractor/clipfish.py +++ b/youtube_dl/extractor/clipfish.py @@ -1,14 +1,9 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( - determine_ext, int_or_none, - js_to_json, - parse_iso8601, - remove_end, + unified_strdate, ) @@ -21,48 +16,47 @@ class ClipfishIE(InfoExtractor): 'id': '3966754', 'ext': 'mp4', 'title': 'FIFA 14 - E3 2013 Trailer', - 'timestamp': 1370938118, + 'description': 'Video zu FIFA 14: E3 2013 Trailer', 'upload_date': '20130611', 'duration': 82, + 'view_count': int, } } def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - video_info = self._parse_json( - js_to_json(self._html_search_regex( - '(?s)videoObject\s*=\s*({.+?});', webpage, 'video object')), - video_id) + video_info = self._download_json( + 'http://www.clipfish.de/devapi/id/%s?format=json&apikey=hbbtv' % video_id, + video_id)['items'][0] formats = [] - for video_url in re.findall(r'var\s+videourl\s*=\s*"([^"]+)"', webpage): - ext = determine_ext(video_url) - if ext == 'm3u8': - formats.append({ - 'url': video_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'), - 'ext': 'mp4', - 'format_id': 'hls', - }) - else: - formats.append({ - 'url': video_url, - 'format_id': ext, - }) - self._sort_formats(formats) - title = remove_end(self._og_search_title(webpage), ' - Video') - thumbnail = self._og_search_thumbnail(webpage) - duration = int_or_none(video_info.get('length')) - timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage, 'upload date')) + m3u8_url = video_info.get('media_videourl_hls') + if m3u8_url: + formats.append({ + 'url': m3u8_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'), + 'ext': 'mp4', + 'format_id': 'hls', + }) + + mp4_url = video_info.get('media_videourl') + if mp4_url: + formats.append({ + 'url': mp4_url, + 'format_id': 'mp4', + 'width': int_or_none(video_info.get('width')), + 'height': int_or_none(video_info.get('height')), + 'tbr': int_or_none(video_info.get('bitrate')), + }) return { 'id': video_id, - 'title': title, + 'title': video_info['title'], + 'description': video_info.get('descr'), 'formats': formats, - 'thumbnail': thumbnail, - 'duration': duration, - 'timestamp': timestamp, + 'thumbnail': video_info.get('media_content_thumbnail_large') or video_info.get('media_thumbnail'), + 'duration': int_or_none(video_info.get('media_length')), + 'upload_date': unified_strdate(video_info.get('pubDate')), + 'view_count': int_or_none(video_info.get('media_views')) } diff --git a/youtube_dl/extractor/cliphunter.py b/youtube_dl/extractor/cliphunter.py index d46592cc5..2996b6b09 100644 --- a/youtube_dl/extractor/cliphunter.py +++ b/youtube_dl/extractor/cliphunter.py @@ -1,7 +1,7 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import determine_ext +from ..utils import int_or_none _translation_table = { @@ -42,31 +42,26 @@ class CliphunterIE(InfoExtractor): video_title = self._search_regex( r'mediaTitle = "([^"]+)"', webpage, 'title') - fmts = {} - for fmt in ('mp4', 'flv'): - fmt_list = self._parse_json(self._search_regex( - r'var %sjson\s*=\s*(\[.*?\]);' % fmt, webpage, '%s formats' % fmt), video_id) - for f in fmt_list: - fmts[f['fname']] = _decode(f['sUrl']) - - qualities = self._parse_json(self._search_regex( - r'var player_btns\s*=\s*(.*?);\n', webpage, 'quality info'), video_id) + gexo_files = self._parse_json( + self._search_regex( + r'var\s+gexoFiles\s*=\s*({.+?});', webpage, 'gexo files'), + video_id) formats = [] - for fname, url in fmts.items(): - f = { - 'url': url, - } - if fname in qualities: - qual = qualities[fname] - f.update({ - 'format_id': '%s_%sp' % (determine_ext(url), qual['h']), - 'width': qual['w'], - 'height': qual['h'], - 'tbr': qual['br'], - }) - formats.append(f) - + for format_id, f in gexo_files.items(): + video_url = f.get('url') + if not video_url: + continue + fmt = f.get('fmt') + height = f.get('h') + format_id = '%s_%sp' % (fmt, height) if fmt and height else format_id + formats.append({ + 'url': _decode(video_url), + 'format_id': format_id, + 'width': int_or_none(f.get('w')), + 'height': int_or_none(height), + 'tbr': int_or_none(f.get('br')), + }) self._sort_formats(formats) thumbnail = self._search_regex( diff --git a/youtube_dl/extractor/cmt.py b/youtube_dl/extractor/cmt.py index e96c59f71..f1311b14f 100644 --- a/youtube_dl/extractor/cmt.py +++ b/youtube_dl/extractor/cmt.py @@ -4,7 +4,7 @@ from .mtv import MTVIE class CMTIE(MTVIE): IE_NAME = 'cmt.com' - _VALID_URL = r'https?://www\.cmt\.com/videos/.+?/(?P<videoid>[^/]+)\.jhtml' + _VALID_URL = r'https?://www\.cmt\.com/(?:videos|shows)/(?:[^/]+/)*(?P<videoid>\d+)' _FEED_URL = 'http://www.cmt.com/sitewide/apps/player/embed/rss/' _TESTS = [{ @@ -16,4 +16,7 @@ class CMTIE(MTVIE): 'title': 'Garth Brooks - "The Call (featuring Trisha Yearwood)"', 'description': 'Blame It All On My Roots', }, + }, { + 'url': 'http://www.cmt.com/shows/party-down-south/party-down-south-ep-407-gone-girl/1738172/playlist/#id=1738172', + 'only_matching': True, }] diff --git a/youtube_dl/extractor/cnet.py b/youtube_dl/extractor/cnet.py index 5dd69bff7..5c3908f72 100644 --- a/youtube_dl/extractor/cnet.py +++ b/youtube_dl/extractor/cnet.py @@ -1,15 +1,11 @@ # coding: utf-8 from __future__ import unicode_literals -import json +from .theplatform import ThePlatformIE +from ..utils import int_or_none -from .common import InfoExtractor -from ..utils import ( - ExtractorError, -) - -class CNETIE(InfoExtractor): +class CNETIE(ThePlatformIE): _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/' _TESTS = [{ 'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/', @@ -18,25 +14,20 @@ class CNETIE(InfoExtractor): 'ext': 'flv', 'title': 'Hands-on with Microsoft Windows 8.1 Update', 'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.', - 'thumbnail': 're:^http://.*/flmswindows8.jpg$', 'uploader_id': '6085384d-619e-11e3-b231-14feb5ca9861', 'uploader': 'Sarah Mitroff', + 'duration': 70, }, - 'params': { - 'skip_download': 'requires rtmpdump', - } }, { 'url': 'http://www.cnet.com/videos/whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187/', 'info_dict': { 'id': '56527b93-d25d-44e3-b738-f989ce2e49ba', 'ext': 'flv', + 'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)', 'description': 'Khail and Ashley wonder what other civic woes can be solved by self-tweeting objects, investigate a new kind of VR camera and watch an origami robot self-assemble, walk, climb, dig and dissolve. #TDPothole', 'uploader_id': 'b163284d-6b73-44fc-b3e6-3da66c392d40', 'uploader': 'Ashley Esqueda', - 'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)', - }, - 'params': { - 'skip_download': True, # requires rtmpdump + 'duration': 1482, }, }] @@ -45,26 +36,13 @@ class CNETIE(InfoExtractor): webpage = self._download_webpage(url, display_id) data_json = self._html_search_regex( - r"<div class=\"cnetVideoPlayer\"\s+.*?data-cnet-video-options='([^']+)'", + r"data-cnet-video(?:-uvp)?-options='([^']+)'", webpage, 'data json') - data = json.loads(data_json) - vdata = data['video'] - if not vdata: - vdata = data['videos'][0] - if not vdata: - raise ExtractorError('Cannot find video data') - - mpx_account = data['config']['players']['default']['mpx_account'] - vid = vdata['files'].get('rtmp', vdata['files']['hds']) - tp_link = 'http://link.theplatform.com/s/%s/%s' % (mpx_account, vid) + data = self._parse_json(data_json, display_id) + vdata = data.get('video') or data['videos'][0] video_id = vdata['id'] - title = vdata.get('headline') - if title is None: - title = vdata.get('title') - if title is None: - raise ExtractorError('Cannot find title!') - thumbnail = vdata.get('image', {}).get('path') + title = vdata['title'] author = vdata.get('author') if author: uploader = '%s %s' % (author['firstName'], author['lastName']) @@ -73,13 +51,34 @@ class CNETIE(InfoExtractor): 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) + description = vdata.get('description') or metadata.get('description') + duration = int_or_none(vdata.get('duration')) or metadata.get('duration') + + formats = [] + subtitles = {} + 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) + if fkey == 'hds': + release_url += '&manifest=f4m' + tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % fkey) + formats.extend(tp_formats) + subtitles = self._merge_subtitles(subtitles, tp_subtitles) + self._sort_formats(formats) + return { - '_type': 'url_transparent', - 'url': tp_link, 'id': video_id, 'display_id': display_id, 'title': title, + 'description': description, + 'thumbnail': metadata.get('thumbnail'), + 'duration': duration, 'uploader': uploader, 'uploader_id': uploader_id, - 'thumbnail': thumbnail, + 'subtitles': subtitles, + 'formats': formats, } diff --git a/youtube_dl/extractor/collegerama.py b/youtube_dl/extractor/collegerama.py index fedd48490..40667a0f1 100644 --- a/youtube_dl/extractor/collegerama.py +++ b/youtube_dl/extractor/collegerama.py @@ -3,10 +3,10 @@ from __future__ import unicode_literals import json from .common import InfoExtractor -from ..compat import compat_urllib_request from ..utils import ( float_or_none, int_or_none, + sanitized_Request, ) @@ -52,7 +52,7 @@ class CollegeRamaIE(InfoExtractor): } } - request = compat_urllib_request.Request( + request = sanitized_Request( 'http://collegerama.tudelft.nl/Mediasite/PlayerService/PlayerService.svc/json/GetPlayerOptions', json.dumps(player_options_request)) request.add_header('Content-Type', 'application/json') diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 10c0d5d1f..828f58f12 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -10,7 +10,6 @@ import re import socket import sys import time -import xml.etree.ElementTree from ..compat import ( compat_cookiejar, @@ -20,9 +19,9 @@ from ..compat import ( compat_urllib_error, compat_urllib_parse, compat_urllib_parse_urlparse, - compat_urllib_request, compat_urlparse, compat_str, + compat_etree_fromstring, ) from ..utils import ( NO_DEFAULT, @@ -31,12 +30,14 @@ from ..utils import ( clean_html, compiled_regex_type, determine_ext, + error_to_compat_str, ExtractorError, fix_xml_ampersands, float_or_none, int_or_none, RegexNotFoundError, sanitize_filename, + sanitized_Request, unescapeHTML, unified_strdate, url_basename, @@ -167,7 +168,7 @@ class InfoExtractor(object): "ext" will be calculated from URL if missing automatic_captions: Like 'subtitles', used by the YoutubeIE for automatically generated captions - duration: Length of the video in seconds, as an integer. + duration: Length of the video in seconds, as an integer or float. view_count: How many users have watched the video on the platform. like_count: Number of positive ratings of the video dislike_count: Number of negative ratings of the video @@ -310,11 +311,11 @@ class InfoExtractor(object): @classmethod def ie_key(cls): """A string for getting the InfoExtractor with get_info_extractor""" - return cls.__name__[:-2] + return compat_str(cls.__name__[:-2]) @property def IE_NAME(self): - return type(self).__name__[:-2] + return compat_str(type(self).__name__[:-2]) def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True): """ Returns the response handle """ @@ -332,7 +333,8 @@ class InfoExtractor(object): return False if errnote is None: errnote = 'Unable to download webpage' - errmsg = '%s: %s' % (errnote, compat_str(err)) + + errmsg = '%s: %s' % (errnote, error_to_compat_str(err)) if fatal: raise ExtractorError(errmsg, sys.exc_info()[2], cause=err) else: @@ -461,7 +463,7 @@ class InfoExtractor(object): return xml_string if transform_source: xml_string = transform_source(xml_string) - return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8')) + return compat_etree_fromstring(xml_string.encode('utf-8')) def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', @@ -622,7 +624,7 @@ class InfoExtractor(object): else: raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) except (IOError, netrc.NetrcParseError) as err: - self._downloader.report_warning('parsing .netrc: %s' % compat_str(err)) + self._downloader.report_warning('parsing .netrc: %s' % error_to_compat_str(err)) return (username, password) @@ -891,6 +893,11 @@ class InfoExtractor(object): if not media_nodes: manifest_version = '2.0' media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media') + base_url = xpath_text( + manifest, ['{http://ns.adobe.com/f4m/1.0}baseURL', '{http://ns.adobe.com/f4m/2.0}baseURL'], + 'base URL', default=None) + if base_url: + base_url = base_url.strip() for i, media_el in enumerate(media_nodes): if manifest_version == '2.0': media_url = media_el.attrib.get('href') or media_el.attrib.get('url') @@ -898,7 +905,7 @@ class InfoExtractor(object): continue manifest_url = ( media_url if media_url.startswith('http://') or media_url.startswith('https://') - else ('/'.join(manifest_url.split('/')[:-1]) + '/' + media_url)) + else ((base_url or '/'.join(manifest_url.split('/')[:-1])) + '/' + media_url)) # If media_url is itself a f4m manifest do the recursive extraction # since bitrates in parent manifest (this one) and media_url manifest # may differ leading to inability to resolve the format by requested @@ -943,13 +950,14 @@ class InfoExtractor(object): if re.match(r'^https?://', u) else compat_urlparse.urljoin(m3u8_url, u)) - m3u8_doc, urlh = self._download_webpage_handle( + res = self._download_webpage_handle( m3u8_url, video_id, note=note or 'Downloading m3u8 information', errnote=errnote or 'Failed to download m3u8 information', fatal=fatal) - if m3u8_doc is False: - return m3u8_doc + if res is False: + return res + m3u8_doc, urlh = res m3u8_url = urlh.geturl() last_info = None last_media = None @@ -1279,7 +1287,7 @@ class InfoExtractor(object): def _get_cookies(self, url): """ Return a compat_cookies.SimpleCookie with the cookies for the url """ - req = compat_urllib_request.Request(url) + req = sanitized_Request(url) self._downloader.cookiejar.add_cookie_header(req) return compat_cookies.SimpleCookie(req.get_header('Cookie')) diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index f8ce10111..00d943f77 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -5,12 +5,12 @@ import re import json import base64 import zlib -import xml.etree.ElementTree from hashlib import sha1 from math import pow, sqrt, floor from .common import InfoExtractor from ..compat import ( + compat_etree_fromstring, compat_urllib_parse, compat_urllib_parse_unquote, compat_urllib_request, @@ -21,7 +21,9 @@ from ..utils import ( bytes_to_intlist, intlist_to_bytes, int_or_none, + lowercase_escape, remove_end, + sanitized_Request, unified_strdate, urlencode_postdata, xpath_text, @@ -45,7 +47,7 @@ class CrunchyrollBaseIE(InfoExtractor): 'name': username, 'password': password, }) - login_request = compat_urllib_request.Request(login_url, data) + login_request = sanitized_Request(login_url, data) login_request.add_header('Content-Type', 'application/x-www-form-urlencoded') self._download_webpage(login_request, None, False, 'Wrong login info') @@ -54,7 +56,7 @@ class CrunchyrollBaseIE(InfoExtractor): def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None): request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request) - else compat_urllib_request.Request(url_or_request)) + else sanitized_Request(url_or_request)) # Accept-Language must be set explicitly to accept any language to avoid issues # similar to https://github.com/rg3/youtube-dl/issues/6797. # Along with IP address Crunchyroll uses Accept-Language to guess whether georestriction @@ -104,7 +106,7 @@ class CrunchyrollIE(CrunchyrollBaseIE): 'id': '589804', 'ext': 'flv', 'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11', - 'description': 'md5:fe2743efedb49d279552926d0bd0cd9e', + 'description': 'md5:2fbc01f90b87e8e9137296f37b461c12', 'thumbnail': 're:^https?://.*\.jpg$', 'uploader': 'Danny Choo Network', 'upload_date': '20120213', @@ -234,7 +236,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text return output def _extract_subtitles(self, subtitle): - sub_root = xml.etree.ElementTree.fromstring(subtitle) + sub_root = compat_etree_fromstring(subtitle) return [{ 'ext': 'srt', 'data': self._convert_subtitles_to_srt(sub_root), @@ -287,11 +289,15 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text if 'To view this, please log in to verify you are 18 or older.' in webpage: self.raise_login_required() - video_title = self._html_search_regex(r'<h1[^>]*>(.+?)</h1>', webpage, 'video_title', flags=re.DOTALL) + video_title = self._html_search_regex( + r'(?s)<h1[^>]*>((?:(?!<h1).)*?<span[^>]+itemprop=["\']title["\'][^>]*>(?:(?!<h1).)+?)</h1>', + webpage, 'video_title') video_title = re.sub(r' {2,}', ' ', video_title) - video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='') - if not video_description: - video_description = None + video_description = self._html_search_regex( + r'<script[^>]*>\s*.+?\[media_id=%s\].+?"description"\s*:\s*"([^"]+)' % video_id, + webpage, 'description', default=None) + if video_description: + video_description = lowercase_escape(video_description.replace(r'\r\n', '\n')) video_upload_date = self._html_search_regex( [r'<div>Availability for free users:(.+?)</div>', r'<div>[^<>]+<span>\s*(.+?\d{4})\s*</span></div>'], webpage, 'video_upload_date', fatal=False, flags=re.DOTALL) @@ -302,7 +308,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'video_uploader', fatal=False) playerdata_url = compat_urllib_parse_unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url')) - playerdata_req = compat_urllib_request.Request(playerdata_url) + playerdata_req = sanitized_Request(playerdata_url) playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url}) playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded') playerdata = self._download_webpage(playerdata_req, video_id, note='Downloading media info') @@ -314,7 +320,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage): stream_quality, stream_format = self._FORMAT_IDS[fmt] video_format = fmt + 'p' - streamdata_req = compat_urllib_request.Request( + streamdata_req = sanitized_Request( 'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s' % (stream_id, stream_format, stream_quality), compat_urllib_parse.urlencode({'current_page': url}).encode('utf-8')) diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index fbefd37d0..7b685d157 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -9,6 +9,7 @@ from ..utils import ( find_xpath_attr, smuggle_url, determine_ext, + ExtractorError, ) from .senateisvp import SenateISVPIE @@ -18,33 +19,32 @@ class CSpanIE(InfoExtractor): IE_DESC = 'C-SPAN' _TESTS = [{ 'url': 'http://www.c-span.org/video/?313572-1/HolderonV', - 'md5': '8e44ce11f0f725527daccc453f553eb0', + 'md5': '94b29a4f131ff03d23471dd6f60b6a1d', 'info_dict': { 'id': '315139', 'ext': 'mp4', 'title': 'Attorney General Eric Holder on Voting Rights Act Decision', - 'description': 'Attorney General Eric Holder spoke to reporters following the Supreme Court decision in Shelby County v. Holder in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced until Congress established new guidelines for review.', + 'description': 'Attorney General Eric Holder speaks to reporters following the Supreme Court decision in [Shelby County v. Holder], in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced.', }, 'skip': 'Regularly fails on travis, for unknown reasons', }, { 'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models', - # For whatever reason, the served video alternates between - # two different ones + 'md5': '8e5fbfabe6ad0f89f3012a7943c1287b', 'info_dict': { - 'id': '340723', + 'id': 'c4486943', 'ext': 'mp4', - 'title': 'International Health Care Models', + 'title': 'CSPAN - International Health Care Models', 'description': 'md5:7a985a2d595dba00af3d9c9f0783c967', } }, { 'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall', - 'md5': '446562a736c6bf97118e389433ed88d4', + 'md5': '2ae5051559169baadba13fc35345ae74', 'info_dict': { 'id': '342759', 'ext': 'mp4', 'title': 'General Motors Ignition Switch Recall', 'duration': 14848, - 'description': 'md5:70c7c3b8fa63fa60d42772440596034c' + 'description': 'md5:118081aedd24bf1d3b68b3803344e7f3' }, }, { # Video from senate.gov @@ -57,67 +57,77 @@ class CSpanIE(InfoExtractor): }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - page_id = mobj.group('id') - webpage = self._download_webpage(url, page_id) - video_id = self._search_regex(r'progid=\'?([0-9]+)\'?>', webpage, 'video id') + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + matches = re.search(r'data-(prog|clip)id=\'([0-9]+)\'', webpage) + if matches: + video_type, video_id = matches.groups() + if video_type == 'prog': + video_type = 'program' + else: + senate_isvp_url = SenateISVPIE._search_iframe_url(webpage) + if senate_isvp_url: + title = self._og_search_title(webpage) + surl = smuggle_url(senate_isvp_url, {'force_title': title}) + return self.url_result(surl, 'SenateISVP', video_id, title) - description = self._html_search_regex( - [ - # The full description - r'<div class=\'expandable\'>(.*?)<a href=\'#\'', - # If the description is small enough the other div is not - # present, otherwise this is a stripped version - r'<p class=\'initial\'>(.*?)</p>' - ], - webpage, 'description', flags=re.DOTALL, default=None) + def get_text_attr(d, attr): + return d.get(attr, {}).get('#text') - info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id - data = self._download_json(info_url, video_id) + data = self._download_json( + 'http://www.c-span.org/assets/player/ajax-player.php?os=android&html5=%s&id=%s' % (video_type, video_id), + video_id)['video'] + if data['@status'] != 'Success': + raise ExtractorError('%s said: %s' % (self.IE_NAME, get_text_attr(data, 'error')), expected=True) doc = self._download_xml( - 'http://www.c-span.org/common/services/flashXml.php?programid=' + video_id, + 'http://www.c-span.org/common/services/flashXml.php?%sid=%s' % (video_type, video_id), video_id) + description = self._html_search_meta('description', webpage) + title = find_xpath_attr(doc, './/string', 'name', 'title').text thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text - senate_isvp_url = SenateISVPIE._search_iframe_url(webpage) - if senate_isvp_url: - surl = smuggle_url(senate_isvp_url, {'force_title': title}) - return self.url_result(surl, 'SenateISVP', video_id, title) - - files = data['video']['files'] - try: - capfile = data['video']['capfile']['#text'] - except KeyError: - capfile = None + files = data['files'] + capfile = get_text_attr(data, 'capfile') - entries = [{ - 'id': '%s_%d' % (video_id, partnum + 1), - 'title': ( - title if len(files) == 1 else - '%s part %d' % (title, partnum + 1)), - 'url': unescapeHTML(f['path']['#text']), - 'description': description, - 'thumbnail': thumbnail, - 'duration': int_or_none(f.get('length', {}).get('#text')), - 'subtitles': { - 'en': [{ - 'url': capfile, - 'ext': determine_ext(capfile, 'dfxp') - }], - } if capfile else None, - } for partnum, f in enumerate(files)] + entries = [] + for partnum, f in enumerate(files): + formats = [] + for quality in f['qualities']: + formats.append({ + 'format_id': '%s-%sp' % (get_text_attr(quality, 'bitrate'), get_text_attr(quality, 'height')), + 'url': unescapeHTML(get_text_attr(quality, 'file')), + 'height': int_or_none(get_text_attr(quality, 'height')), + 'tbr': int_or_none(get_text_attr(quality, 'bitrate')), + }) + self._sort_formats(formats) + entries.append({ + 'id': '%s_%d' % (video_id, partnum + 1), + 'title': ( + title if len(files) == 1 else + '%s part %d' % (title, partnum + 1)), + 'formats': formats, + 'description': description, + 'thumbnail': thumbnail, + 'duration': int_or_none(get_text_attr(f, 'length')), + 'subtitles': { + 'en': [{ + 'url': capfile, + 'ext': determine_ext(capfile, 'dfxp') + }], + } if capfile else None, + }) if len(entries) == 1: entry = dict(entries[0]) - entry['id'] = video_id + entry['id'] = 'c' + video_id if video_type == 'clip' else video_id return entry else: return { '_type': 'playlist', 'entries': entries, 'title': title, - 'id': video_id, + 'id': 'c' + video_id if video_type == 'clip' else video_id, } diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index bc7823931..0c5b6617f 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -7,15 +7,13 @@ import itertools from .common import InfoExtractor -from ..compat import ( - compat_str, - compat_urllib_request, -) from ..utils import ( - ExtractorError, determine_ext, + error_to_compat_str, + ExtractorError, int_or_none, parse_iso8601, + sanitized_Request, str_to_int, unescapeHTML, ) @@ -25,7 +23,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor): @staticmethod def _build_request(url): """Build a request with the family filter disabled""" - request = compat_urllib_request.Request(url) + request = sanitized_Request(url) request.add_header('Cookie', 'family_filter=off; ff=off') return request @@ -101,6 +99,11 @@ class DailymotionIE(DailymotionBaseInfoExtractor): { 'url': 'http://www.dailymotion.com/video/xhza0o', 'only_matching': True, + }, + # with subtitles + { + 'url': 'http://www.dailymotion.com/video/x20su5f_the-power-of-nightmares-1-the-rise-of-the-politics-of-fear-bbc-2004_news', + 'only_matching': True, } ] @@ -124,7 +127,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor): webpage, 'comment count', fatal=False)) player_v5 = self._search_regex( - [r'buildPlayer\(({.+?})\);', r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);'], + [r'buildPlayer\(({.+?})\);\n', # See https://github.com/rg3/youtube-dl/issues/7826 + r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);', + r'buildPlayer\(({.+?})\);'], webpage, 'player v5', default=None) if player_v5: player = self._parse_json(player_v5, video_id) @@ -174,11 +179,13 @@ class DailymotionIE(DailymotionBaseInfoExtractor): uploader_id = metadata.get('owner', {}).get('id') subtitles = {} - for subtitle_lang, subtitle in metadata.get('subtitles', {}).get('data', {}).items(): - subtitles[subtitle_lang] = [{ - 'ext': determine_ext(subtitle_url), - 'url': subtitle_url, - } for subtitle_url in subtitle.get('urls', [])] + subtitles_data = metadata.get('subtitles', {}).get('data', {}) + if subtitles_data and isinstance(subtitles_data, dict): + for subtitle_lang, subtitle in subtitles_data.items(): + subtitles[subtitle_lang] = [{ + 'ext': determine_ext(subtitle_url), + 'url': subtitle_url, + } for subtitle_url in subtitle.get('urls', [])] return { 'id': video_id, @@ -271,7 +278,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor): 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id, video_id, note=False) except ExtractorError as err: - self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err)) + self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err)) return {} info = json.loads(sub_list) if (info['total'] > 0): diff --git a/youtube_dl/extractor/dbtv.py b/youtube_dl/extractor/dbtv.py index 212217625..133cdc50b 100644 --- a/youtube_dl/extractor/dbtv.py +++ b/youtube_dl/extractor/dbtv.py @@ -13,8 +13,8 @@ from ..utils import ( class DBTVIE(InfoExtractor): - _VALID_URL = r'http://dbtv\.no/(?P<id>[0-9]+)#(?P<display_id>.+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?dbtv\.no/(?:(?:lazyplayer|player)/)?(?P<id>[0-9]+)(?:#(?P<display_id>.+))?' + _TESTS = [{ 'url': 'http://dbtv.no/3649835190001#Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen', 'md5': 'b89953ed25dacb6edb3ef6c6f430f8bc', 'info_dict': { @@ -30,12 +30,18 @@ class DBTVIE(InfoExtractor): 'view_count': int, 'categories': list, } - } + }, { + 'url': 'http://dbtv.no/3649835190001', + 'only_matching': True, + }, { + 'url': 'http://www.dbtv.no/lazyplayer/4631135248001', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - display_id = mobj.group('display_id') + display_id = mobj.group('display_id') or video_id data = self._download_json( 'http://api.dbtv.no/discovery/%s' % video_id, display_id) diff --git a/youtube_dl/extractor/dcn.py b/youtube_dl/extractor/dcn.py index 6f2fea5ff..9737cff14 100644 --- a/youtube_dl/extractor/dcn.py +++ b/youtube_dl/extractor/dcn.py @@ -2,13 +2,11 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) +from ..compat import compat_urllib_parse from ..utils import ( int_or_none, parse_iso8601, + sanitized_Request, ) @@ -36,7 +34,7 @@ class DCNIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - request = compat_urllib_request.Request( + request = sanitized_Request( 'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id, headers={'Origin': 'http://www.dcndigital.ae'}) diff --git a/youtube_dl/extractor/democracynow.py b/youtube_dl/extractor/democracynow.py new file mode 100644 index 000000000..6cd395e11 --- /dev/null +++ b/youtube_dl/extractor/democracynow.py @@ -0,0 +1,88 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +import os.path + +from .common import InfoExtractor +from ..compat import compat_urlparse +from ..utils import ( + url_basename, + remove_start, +) + + +class DemocracynowIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?democracynow.org/(?P<id>[^\?]*)' + IE_NAME = 'democracynow' + _TESTS = [{ + 'url': 'http://www.democracynow.org/shows/2015/7/3', + 'md5': 'fbb8fe3d7a56a5e12431ce2f9b2fab0d', + 'info_dict': { + 'id': '2015-0703-001', + 'ext': 'mp4', + 'title': 'July 03, 2015 - Democracy Now!', + 'description': 'A daily independent global news hour with Amy Goodman & Juan González "What to the Slave is 4th of July?": James Earl Jones Reads Frederick Douglass\u2019 Historic Speech : "This Flag Comes Down Today": Bree Newsome Scales SC Capitol Flagpole, Takes Down Confederate Flag : "We Shall Overcome": Remembering Folk Icon, Activist Pete Seeger in His Own Words & Songs', + }, + }, { + 'url': 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree', + 'md5': 'fbb8fe3d7a56a5e12431ce2f9b2fab0d', + 'info_dict': { + 'id': '2015-0703-001', + 'ext': 'mp4', + 'title': '"This Flag Comes Down Today": Bree Newsome Scales SC Capitol Flagpole, Takes Down Confederate Flag', + 'description': 'md5:4d2bc4f0d29f5553c2210a4bc7761a21', + }, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + description = self._og_search_description(webpage) + + json_data = self._parse_json(self._search_regex( + r'<script[^>]+type="text/json"[^>]*>\s*({[^>]+})', webpage, 'json'), + display_id) + video_id = None + formats = [] + + default_lang = 'en' + + subtitles = {} + + def add_subtitle_item(lang, info_dict): + if lang not in subtitles: + subtitles[lang] = [] + subtitles[lang].append(info_dict) + + # chapter_file are not subtitles + if 'caption_file' in json_data: + add_subtitle_item(default_lang, { + 'url': compat_urlparse.urljoin(url, json_data['caption_file']), + }) + + for subtitle_item in json_data.get('captions', []): + lang = subtitle_item.get('language', '').lower() or default_lang + add_subtitle_item(lang, { + 'url': compat_urlparse.urljoin(url, subtitle_item['url']), + }) + + for key in ('file', 'audio', 'video'): + media_url = json_data.get(key, '') + if not media_url: + continue + media_url = re.sub(r'\?.*', '', compat_urlparse.urljoin(url, media_url)) + video_id = video_id or remove_start(os.path.splitext(url_basename(media_url))[0], 'dn') + formats.append({ + 'url': media_url, + }) + + self._sort_formats(formats) + + return { + 'id': video_id or display_id, + 'title': json_data['title'], + 'description': description, + 'subtitles': subtitles, + 'formats': formats, + } diff --git a/youtube_dl/extractor/dplay.py b/youtube_dl/extractor/dplay.py new file mode 100644 index 000000000..6cda56a7f --- /dev/null +++ b/youtube_dl/extractor/dplay.py @@ -0,0 +1,51 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import time + +from .common import InfoExtractor +from ..utils import int_or_none + + +class DPlayIE(InfoExtractor): + _VALID_URL = r'http://www\.dplay\.se/[^/]+/(?P<id>[^/?#]+)' + + _TEST = { + 'url': 'http://www.dplay.se/nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet/', + 'info_dict': { + 'id': '3172', + 'ext': 'mp4', + 'display_id': 'season-1-svensken-lar-sig-njuta-av-livet', + 'title': 'Svensken lär sig njuta av livet', + 'duration': 2650, + }, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + video_id = self._search_regex( + r'data-video-id="(\d+)"', webpage, 'video id') + + info = self._download_json( + 'http://www.dplay.se/api/v2/ajax/videos?video_id=' + video_id, + video_id)['data'][0] + + self._set_cookie( + 'secure.dplay.se', 'dsc-geo', + '{"countryCode":"NL","expiry":%d}' % ((time.time() + 20 * 60) * 1000)) + # TODO: consider adding support for 'stream_type=hds', it seems to + # require setting some cookies + manifest_url = self._download_json( + 'https://secure.dplay.se/secure/api/v2/user/authorization/stream/%s?stream_type=hls' % video_id, + video_id, 'Getting manifest url for hls stream')['hls'] + formats = self._extract_m3u8_formats( + manifest_url, video_id, ext='mp4', entry_protocol='m3u8_native') + + return { + 'id': video_id, + 'display_id': display_id, + 'title': info['title'], + 'formats': formats, + 'duration': int_or_none(info.get('video_metadata_length'), scale=1000), + } diff --git a/youtube_dl/extractor/dramafever.py b/youtube_dl/extractor/dramafever.py index 38e6597c8..60ed438f8 100644 --- a/youtube_dl/extractor/dramafever.py +++ b/youtube_dl/extractor/dramafever.py @@ -3,23 +3,20 @@ from __future__ import unicode_literals import itertools -from .common import InfoExtractor +from .amp import AMPIE from ..compat import ( compat_HTTPError, compat_urllib_parse, - compat_urllib_request, compat_urlparse, ) from ..utils import ( ExtractorError, clean_html, - determine_ext, - int_or_none, - parse_iso8601, + sanitized_Request, ) -class DramaFeverBaseIE(InfoExtractor): +class DramaFeverBaseIE(AMPIE): _LOGIN_URL = 'https://www.dramafever.com/accounts/login/' _NETRC_MACHINE = 'dramafever' @@ -51,7 +48,7 @@ class DramaFeverBaseIE(InfoExtractor): 'password': password, } - request = compat_urllib_request.Request( + request = sanitized_Request( self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8')) response = self._download_webpage( request, None, 'Logging in as %s' % username) @@ -80,60 +77,25 @@ class DramaFeverIE(DramaFeverBaseIE): 'timestamp': 1404336058, 'upload_date': '20140702', 'duration': 343, - } + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, } def _real_extract(self, url): video_id = self._match_id(url).replace('/', '.') try: - feed = self._download_json( - 'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id, - video_id, 'Downloading episode JSON')['channel']['item'] + info = self._extract_feed_info( + 'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError): raise ExtractorError( 'Currently unavailable in your country.', expected=True) raise - media_group = feed.get('media-group', {}) - - formats = [] - for media_content in media_group['media-content']: - src = media_content.get('@attributes', {}).get('url') - if not src: - continue - ext = determine_ext(src) - if ext == 'f4m': - formats.extend(self._extract_f4m_formats( - src, video_id, f4m_id='hds')) - elif ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - src, video_id, 'mp4', m3u8_id='hls')) - else: - formats.append({ - 'url': src, - }) - self._sort_formats(formats) - - title = media_group.get('media-title') - description = media_group.get('media-description') - duration = int_or_none(media_group['media-content'][0].get('@attributes', {}).get('duration')) - thumbnail = self._proto_relative_url( - media_group.get('media-thumbnail', {}).get('@attributes', {}).get('url')) - timestamp = parse_iso8601(feed.get('pubDate'), ' ') - - subtitles = {} - for media_subtitle in media_group.get('media-subTitle', []): - lang = media_subtitle.get('@attributes', {}).get('lang') - href = media_subtitle.get('@attributes', {}).get('href') - if not lang or not href: - continue - subtitles[lang] = [{ - 'ext': 'ttml', - 'url': href, - }] - series_id, episode_number = video_id.split('.') episode_info = self._download_json( # We only need a single episode info, so restricting page size to one episode @@ -146,21 +108,12 @@ class DramaFeverIE(DramaFeverBaseIE): if value: subfile = value[0].get('subfile') or value[0].get('new_subfile') if subfile and subfile != 'http://www.dramafever.com/st/': - subtitles.setdefault('English', []).append({ + info['subtitiles'].setdefault('English', []).append({ 'ext': 'srt', 'url': subfile, }) - return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'timestamp': timestamp, - 'duration': duration, - 'formats': formats, - 'subtitles': subtitles, - } + return info class DramaFeverSeriesIE(DramaFeverBaseIE): diff --git a/youtube_dl/extractor/dumpert.py b/youtube_dl/extractor/dumpert.py index 1f00386fe..e5aadcd25 100644 --- a/youtube_dl/extractor/dumpert.py +++ b/youtube_dl/extractor/dumpert.py @@ -2,14 +2,17 @@ from __future__ import unicode_literals import base64 +import re from .common import InfoExtractor -from ..compat import compat_urllib_request -from ..utils import qualities +from ..utils import ( + qualities, + sanitized_Request, +) class DumpertIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?dumpert\.nl/(?:mediabase|embed)/(?P<id>[0-9]+/[0-9a-zA-Z]+)' + _VALID_URL = r'(?P<protocol>https?)://(?:www\.)?dumpert\.nl/(?:mediabase|embed)/(?P<id>[0-9]+/[0-9a-zA-Z]+)' _TESTS = [{ 'url': 'http://www.dumpert.nl/mediabase/6646981/951bc60f/', 'md5': '1b9318d7d5054e7dcb9dc7654f21d643', @@ -26,10 +29,12 @@ class DumpertIE(InfoExtractor): }] def _real_extract(self, url): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + protocol = mobj.group('protocol') - url = 'https://www.dumpert.nl/mediabase/' + video_id - req = compat_urllib_request.Request(url) + url = '%s://www.dumpert.nl/mediabase/%s' % (protocol, video_id) + req = sanitized_Request(url) req.add_header('Cookie', 'nsfw=1; cpc=10') webpage = self._download_webpage(req, video_id) diff --git a/youtube_dl/extractor/eitb.py b/youtube_dl/extractor/eitb.py index 2cba82532..c83845fc2 100644 --- a/youtube_dl/extractor/eitb.py +++ b/youtube_dl/extractor/eitb.py @@ -1,39 +1,92 @@ # encoding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from .brightcove import BrightcoveIE -from ..utils import ExtractorError +from ..utils import ( + float_or_none, + int_or_none, + parse_iso8601, + sanitized_Request, +) class EitbIE(InfoExtractor): IE_NAME = 'eitb.tv' - _VALID_URL = r'https?://www\.eitb\.tv/(eu/bideoa|es/video)/[^/]+/(?P<playlist_id>\d+)/(?P<chapter_id>\d+)' + _VALID_URL = r'https?://(?:www\.)?eitb\.tv/(?:eu/bideoa|es/video)/[^/]+/\d+/(?P<id>\d+)' _TEST = { - 'add_ie': ['Brightcove'], - 'url': 'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/2677100210001/2743577154001/lasa-y-zabala-30-anos/', + 'url': 'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/4104995148001/4090227752001/lasa-y-zabala-30-anos/', 'md5': 'edf4436247185adee3ea18ce64c47998', 'info_dict': { - 'id': '2743577154001', + 'id': '4090227752001', 'ext': 'mp4', 'title': '60 minutos (Lasa y Zabala, 30 años)', - # All videos from eitb has this description in the brightcove info - 'description': '.', - 'uploader': 'Euskal Telebista', + 'description': 'Programa de reportajes de actualidad.', + 'duration': 3996.76, + 'timestamp': 1381789200, + 'upload_date': '20131014', + 'tags': list, }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - chapter_id = mobj.group('chapter_id') - webpage = self._download_webpage(url, chapter_id) - bc_url = BrightcoveIE._extract_brightcove_url(webpage) - if bc_url is None: - raise ExtractorError('Could not extract the Brightcove url') - # The BrightcoveExperience object doesn't contain the video id, we set - # it manually - bc_url += '&%40videoPlayer={0}'.format(chapter_id) - return self.url_result(bc_url, BrightcoveIE.ie_key()) + video_id = self._match_id(url) + + video = self._download_json( + 'http://mam.eitb.eus/mam/REST/ServiceMultiweb/Video/MULTIWEBTV/%s/' % video_id, + video_id, 'Downloading video JSON') + + media = video['web_media'][0] + + formats = [] + for rendition in media['RENDITIONS']: + video_url = rendition.get('PMD_URL') + if not video_url: + continue + tbr = float_or_none(rendition.get('ENCODING_RATE'), 1000) + format_id = 'http' + if tbr: + format_id += '-%d' % int(tbr) + formats.append({ + 'url': rendition['PMD_URL'], + 'format_id': format_id, + 'width': int_or_none(rendition.get('FRAME_WIDTH')), + 'height': int_or_none(rendition.get('FRAME_HEIGHT')), + 'tbr': tbr, + }) + + hls_url = media.get('HLS_SURL') + if hls_url: + request = sanitized_Request( + 'http://mam.eitb.eus/mam/REST/ServiceMultiweb/DomainRestrictedSecurity/TokenAuth/', + headers={'Referer': url}) + token_data = self._download_json( + request, video_id, 'Downloading auth token', fatal=False) + if token_data: + token = token_data.get('token') + if token: + m3u8_formats = self._extract_m3u8_formats( + '%s?hdnts=%s' % (hls_url, token), video_id, m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + + hds_url = media.get('HDS_SURL') + if hds_url: + f4m_formats = self._extract_f4m_formats( + '%s?hdcore=3.7.0' % hds_url.replace('euskalsvod', 'euskalvod'), + video_id, f4m_id='hds', fatal=False) + if f4m_formats: + formats.extend(f4m_formats) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': media.get('NAME_ES') or media.get('name') or media['NAME_EU'], + 'description': media.get('SHORT_DESC_ES') or video.get('desc_group') or media.get('SHORT_DESC_EU'), + 'thumbnail': media.get('STILL_URL') or media.get('THUMBNAIL_URL'), + 'duration': float_or_none(media.get('LENGTH'), 1000), + 'timestamp': parse_iso8601(media.get('BROADCST_DATE'), ' '), + 'tags': media.get('TAGS'), + 'formats': formats, + } diff --git a/youtube_dl/extractor/escapist.py b/youtube_dl/extractor/escapist.py index c85b4c458..a3d7bbbcb 100644 --- a/youtube_dl/extractor/escapist.py +++ b/youtube_dl/extractor/escapist.py @@ -3,13 +3,12 @@ from __future__ import unicode_literals import json from .common import InfoExtractor -from ..compat import compat_urllib_request - from ..utils import ( determine_ext, clean_html, int_or_none, float_or_none, + sanitized_Request, ) @@ -75,7 +74,7 @@ class EscapistIE(InfoExtractor): video_id = ims_video['videoID'] key = ims_video['hash'] - config_req = compat_urllib_request.Request( + config_req = sanitized_Request( 'http://www.escapistmagazine.com/videos/' 'vidconfig.php?videoID=%s&hash=%s' % (video_id, key)) config_req.add_header('Referer', url) diff --git a/youtube_dl/extractor/everyonesmixtape.py b/youtube_dl/extractor/everyonesmixtape.py index d872d828f..493d38af8 100644 --- a/youtube_dl/extractor/everyonesmixtape.py +++ b/youtube_dl/extractor/everyonesmixtape.py @@ -3,11 +3,9 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_request, -) from ..utils import ( ExtractorError, + sanitized_Request, ) @@ -42,7 +40,7 @@ class EveryonesMixtapeIE(InfoExtractor): playlist_id = mobj.group('id') pllist_url = 'http://everyonesmixtape.com/mixtape.php?a=getMixes&u=-1&linked=%s&explore=' % playlist_id - pllist_req = compat_urllib_request.Request(pllist_url) + pllist_req = sanitized_Request(pllist_url) pllist_req.add_header('X-Requested-With', 'XMLHttpRequest') playlist_list = self._download_json( @@ -55,7 +53,7 @@ class EveryonesMixtapeIE(InfoExtractor): raise ExtractorError('Playlist id not found') pl_url = 'http://everyonesmixtape.com/mixtape.php?a=getMix&id=%s&userId=null&code=' % playlist_no - pl_req = compat_urllib_request.Request(pl_url) + pl_req = sanitized_Request(pl_url) pl_req.add_header('X-Requested-With', 'XMLHttpRequest') playlist = self._download_json( pl_req, playlist_id, note='Downloading playlist info') diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py index c826a5404..3403581fd 100644 --- a/youtube_dl/extractor/extremetube.py +++ b/youtube_dl/extractor/extremetube.py @@ -3,23 +3,20 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_parse_qs, - compat_urllib_request, -) from ..utils import ( - qualities, + int_or_none, + sanitized_Request, str_to_int, ) class ExtremeTubeIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<id>[0-9]+))(?:[/?&]|$)' + _VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?P<id>[^/#?&]+)' _TESTS = [{ 'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431', 'md5': '344d0c6d50e2f16b06e49ca011d8ac69', 'info_dict': { - 'id': '652431', + 'id': 'music-video-14-british-euro-brit-european-cumshots-swallow-652431', 'ext': 'mp4', 'title': 'Music Video 14 british euro brit european cumshots swallow', 'uploader': 'unknown', @@ -29,14 +26,18 @@ class ExtremeTubeIE(InfoExtractor): }, { 'url': 'http://www.extremetube.com/gay/video/abcde-1234', 'only_matching': True, + }, { + 'url': 'http://www.extremetube.com/video/latina-slut-fucked-by-fat-black-dick', + 'only_matching': True, + }, { + 'url': 'http://www.extremetube.com/video/652431', + 'only_matching': True, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - url = 'http://www.' + mobj.group('url') + video_id = self._match_id(url) - req = compat_urllib_request.Request(url) + req = sanitized_Request(url) req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) @@ -49,20 +50,36 @@ class ExtremeTubeIE(InfoExtractor): r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>', webpage, 'view count', fatal=False)) - flash_vars = compat_parse_qs(self._search_regex( - r'<param[^>]+?name="flashvars"[^>]+?value="([^"]+)"', webpage, 'flash vars')) + flash_vars = self._parse_json( + self._search_regex( + r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flash vars'), + video_id) formats = [] - quality = qualities(['180p', '240p', '360p', '480p', '720p', '1080p']) - for k, vals in flash_vars.items(): - m = re.match(r'quality_(?P<quality>[0-9]+p)$', k) - if m is not None: - formats.append({ - 'format_id': m.group('quality'), - 'quality': quality(m.group('quality')), - 'url': vals[0], + for quality_key, video_url in flash_vars.items(): + height = int_or_none(self._search_regex( + r'quality_(\d+)[pP]$', quality_key, 'height', default=None)) + if not height: + continue + f = { + 'url': 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')) + f.update({ + 'format_id': '%dp-%dk' % (height, bitrate), + 'height': height, + 'tbr': bitrate, }) - + else: + f.update({ + 'format_id': '%dp' % height, + 'height': height, + }) + formats.append(f) self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index f53c51615..39c481068 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -7,14 +7,14 @@ import socket from .common import InfoExtractor from ..compat import ( compat_http_client, - compat_str, compat_urllib_error, compat_urllib_parse_unquote, - compat_urllib_request, ) from ..utils import ( + error_to_compat_str, ExtractorError, limit_length, + sanitized_Request, urlencode_postdata, get_element_by_id, clean_html, @@ -73,7 +73,7 @@ class FacebookIE(InfoExtractor): if useremail is None: return - login_page_req = compat_urllib_request.Request(self._LOGIN_URL) + login_page_req = sanitized_Request(self._LOGIN_URL) login_page_req.add_header('Cookie', 'locale=en_US') login_page = self._download_webpage(login_page_req, None, note='Downloading login page', @@ -94,7 +94,7 @@ class FacebookIE(InfoExtractor): 'timezone': '-60', 'trynum': '1', } - request = compat_urllib_request.Request(self._LOGIN_URL, urlencode_postdata(login_form)) + request = sanitized_Request(self._LOGIN_URL, urlencode_postdata(login_form)) request.add_header('Content-Type', 'application/x-www-form-urlencoded') try: login_results = self._download_webpage(request, None, @@ -109,14 +109,14 @@ class FacebookIE(InfoExtractor): r'name="h"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h'), 'name_action_selected': 'dont_save', } - check_req = compat_urllib_request.Request(self._CHECKPOINT_URL, urlencode_postdata(check_form)) + check_req = sanitized_Request(self._CHECKPOINT_URL, urlencode_postdata(check_form)) check_req.add_header('Content-Type', 'application/x-www-form-urlencoded') check_response = self._download_webpage(check_req, None, note='Confirming login') if re.search(r'id="checkpointSubmitButton"', check_response) is not None: self._downloader.report_warning('Unable to confirm login, you have to login in your brower and authorize the login.') except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.report_warning('unable to log in: %s' % compat_str(err)) + self._downloader.report_warning('unable to log in: %s' % error_to_compat_str(err)) return def _real_initialize(self): @@ -164,7 +164,7 @@ class FacebookIE(InfoExtractor): if not video_title: video_title = self._html_search_regex( r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>', - webpage, 'alternative title', fatal=False) + webpage, 'alternative title', default=None) video_title = limit_length(video_title, 80) if not video_title: video_title = 'Facebook video #%s' % video_id diff --git a/youtube_dl/extractor/faz.py b/youtube_dl/extractor/faz.py index cebdd0193..6f9b003c2 100644 --- a/youtube_dl/extractor/faz.py +++ b/youtube_dl/extractor/faz.py @@ -2,6 +2,11 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..utils import ( + xpath_element, + xpath_text, + int_or_none, +) class FazIE(InfoExtractor): @@ -37,31 +42,32 @@ class FazIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) + description = self._og_search_description(webpage) config_xml_url = self._search_regex( - r'writeFLV\(\'(.+?)\',', webpage, 'config xml url') + r'videoXMLURL\s*=\s*"([^"]+)', webpage, 'config xml url') config = self._download_xml( config_xml_url, video_id, 'Downloading config xml') - encodings = config.find('ENCODINGS') + encodings = xpath_element(config, 'ENCODINGS', 'encodings', True) formats = [] for pref, code in enumerate(['LOW', 'HIGH', 'HQ']): - encoding = encodings.find(code) - if encoding is None: - continue - encoding_url = encoding.find('FILENAME').text - formats.append({ - 'url': encoding_url, - 'format_id': code.lower(), - 'quality': pref, - }) + encoding = xpath_element(encodings, code) + if encoding: + encoding_url = xpath_text(encoding, 'FILENAME') + if encoding_url: + formats.append({ + 'url': encoding_url, + 'format_id': code.lower(), + 'quality': pref, + 'tbr': int_or_none(xpath_text(encoding, 'AVERAGEBITRATE')), + }) self._sort_formats(formats) - descr = self._html_search_regex( - r'<p class="Content Copy">(.*?)</p>', webpage, 'description', fatal=False) return { 'id': video_id, 'title': self._og_search_title(webpage), 'formats': formats, - 'description': descr, - 'thumbnail': config.find('STILL/STILL_BIG').text, + 'description': description.strip() if description else None, + 'thumbnail': xpath_text(config, 'STILL/STILL_BIG'), + 'duration': int_or_none(xpath_text(config, 'DURATION')), } diff --git a/youtube_dl/extractor/fc2.py b/youtube_dl/extractor/fc2.py index a406945e8..4c81271d3 100644 --- a/youtube_dl/extractor/fc2.py +++ b/youtube_dl/extractor/fc2.py @@ -12,6 +12,7 @@ from ..compat import ( from ..utils import ( encode_dict, ExtractorError, + sanitized_Request, ) @@ -36,8 +37,8 @@ class FC2IE(InfoExtractor): 'params': { 'username': 'ytdl@yt-dl.org', 'password': '(snip)', - 'skip': 'requires actual password' - } + }, + 'skip': 'requires actual password', }, { 'url': 'http://video.fc2.com/en/a/content/20130926eZpARwsF', 'only_matching': True, @@ -57,7 +58,7 @@ class FC2IE(InfoExtractor): } login_data = compat_urllib_parse.urlencode(encode_dict(login_form_strs)).encode('utf-8') - request = compat_urllib_request.Request( + request = sanitized_Request( 'https://secure.id.fc2.com/index.php?mode=login&switch_language=en', login_data) login_results = self._download_webpage(request, None, note='Logging in', errnote='Unable to log in') @@ -66,7 +67,7 @@ class FC2IE(InfoExtractor): return False # this is also needed - login_redir = compat_urllib_request.Request('http://id.fc2.com/?mode=redirect&login=done') + login_redir = sanitized_Request('http://id.fc2.com/?mode=redirect&login=done') self._download_webpage( login_redir, None, note='Login redirect', errnote='Login redirect failed') diff --git a/youtube_dl/extractor/fktv.py b/youtube_dl/extractor/fktv.py index 40ea27895..5f6e65dae 100644 --- a/youtube_dl/extractor/fktv.py +++ b/youtube_dl/extractor/fktv.py @@ -1,12 +1,10 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( clean_html, determine_ext, - ExtractorError, + js_to_json, ) @@ -32,24 +30,22 @@ class FKTVIE(InfoExtractor): 'http://fernsehkritik.tv/folge-%s/play' % episode, episode) title = clean_html(self._html_search_regex( '<h3>([^<]+)</h3>', webpage, 'title')) - matches = re.search( - r'(?s)<video(?:(?!poster)[^>])+(?:poster="([^"]+)")?[^>]*>(.*)</video>', - webpage) - if matches is None: - raise ExtractorError('Unable to extract the video') - - poster, sources = matches.groups() - if poster is None: - self.report_warning('unable to extract thumbnail') - - urls = re.findall(r'<source[^>]+src="([^"]+)"', sources) - formats = [{ - 'url': furl, - 'format_id': determine_ext(furl), - } for furl in urls] + thumbnail = self._search_regex(r'POSTER\s*=\s*"([^"]+)', webpage, 'thumbnail', fatal=False) + sources = self._parse_json(self._search_regex(r'(?s)MEDIA\s*=\s*(\[.+?\]);', webpage, 'media'), episode, js_to_json) + + formats = [] + for source in sources: + furl = source.get('src') + if furl: + formats.append({ + 'url': furl, + 'format_id': determine_ext(furl), + }) + self._sort_formats(formats) + return { 'id': episode, 'title': title, 'formats': formats, - 'thumbnail': poster, + 'thumbnail': thumbnail, } diff --git a/youtube_dl/extractor/flickr.py b/youtube_dl/extractor/flickr.py index 2fe76d661..18f439df9 100644 --- a/youtube_dl/extractor/flickr.py +++ b/youtube_dl/extractor/flickr.py @@ -1,67 +1,93 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..compat import compat_urllib_request +from ..compat import compat_urllib_parse from ..utils import ( ExtractorError, - find_xpath_attr, + int_or_none, + qualities, ) class FlickrIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.|secure\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*' + _VALID_URL = r'https?://(?:www\.|secure\.)?flickr\.com/photos/[\w\-_@]+/(?P<id>\d+)' _TEST = { 'url': 'http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/', - 'md5': '6fdc01adbc89d72fc9c4f15b4a4ba87b', + 'md5': '164fe3fa6c22e18d448d4d5af2330f31', 'info_dict': { 'id': '5645318632', - 'ext': 'mp4', - "description": "Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up.", - "uploader_id": "forestwander-nature-pictures", - "title": "Dark Hollow Waterfalls" + 'ext': 'mpg', + 'description': 'Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up.', + 'title': 'Dark Hollow Waterfalls', + 'duration': 19, + 'timestamp': 1303528740, + 'upload_date': '20110423', + 'uploader_id': '10922353@N03', + 'uploader': 'Forest Wander', + 'comment_count': int, + 'view_count': int, + 'tags': list, } } - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) + _API_BASE_URL = 'https://api.flickr.com/services/rest?' - video_id = mobj.group('id') - video_uploader_id = mobj.group('uploader_id') - webpage_url = 'http://www.flickr.com/photos/' + video_uploader_id + '/' + video_id - req = compat_urllib_request.Request(webpage_url) - req.add_header( - 'User-Agent', - # it needs a more recent version - 'Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20150101 Firefox/38.0 (Chrome)') - webpage = self._download_webpage(req, video_id) + def _call_api(self, method, video_id, api_key, note, secret=None): + query = { + 'photo_id': video_id, + 'method': 'flickr.%s' % method, + 'api_key': api_key, + 'format': 'json', + 'nojsoncallback': 1, + } + if secret: + query['secret'] = secret + data = self._download_json(self._API_BASE_URL + compat_urllib_parse.urlencode(query), video_id, note) + if data['stat'] != 'ok': + raise ExtractorError(data['message']) + return data - secret = self._search_regex(r'secret"\s*:\s*"(\w+)"', webpage, 'secret') + def _real_extract(self, url): + video_id = self._match_id(url) - first_url = 'https://secure.flickr.com/apps/video/video_mtl_xml.gne?v=x&photo_id=' + video_id + '&secret=' + secret + '&bitrate=700&target=_self' - first_xml = self._download_xml(first_url, video_id, 'Downloading first data webpage') + api_key = self._download_json( + 'https://www.flickr.com/hermes_error_beacon.gne', video_id, + 'Downloading api key')['site_key'] - node_id = find_xpath_attr( - first_xml, './/{http://video.yahoo.com/YEP/1.0/}Item', 'id', - 'id').text + video_info = self._call_api( + 'photos.getInfo', video_id, api_key, 'Downloading video info')['photo'] + if video_info['media'] == 'video': + streams = self._call_api( + 'video.getStreamInfo', video_id, api_key, + 'Downloading streams info', video_info['secret'])['streams'] - second_url = 'https://secure.flickr.com/video_playlist.gne?node_id=' + node_id + '&tech=flash&mode=playlist&bitrate=700&secret=' + secret + '&rd=video.yahoo.com&noad=1' - second_xml = self._download_xml(second_url, video_id, 'Downloading second data webpage') + preference = qualities( + ['288p', 'iphone_wifi', '100', '300', '700', '360p', 'appletv', '720p', '1080p', 'orig']) - self.report_extraction(video_id) + formats = [] + for stream in streams['stream']: + stream_type = str(stream.get('type')) + formats.append({ + 'format_id': stream_type, + 'url': stream['_content'], + 'preference': preference(stream_type), + }) + self._sort_formats(formats) - stream = second_xml.find('.//STREAM') - if stream is None: - raise ExtractorError('Unable to extract video url') - video_url = stream.attrib['APP'] + stream.attrib['FULLPATH'] + owner = video_info.get('owner', {}) - return { - 'id': video_id, - 'url': video_url, - 'ext': 'mp4', - 'title': self._og_search_title(webpage), - 'description': self._og_search_description(webpage), - 'thumbnail': self._og_search_thumbnail(webpage), - 'uploader_id': video_uploader_id, - } + return { + 'id': video_id, + 'title': video_info['title']['_content'], + 'description': video_info.get('description', {}).get('_content'), + 'formats': formats, + 'timestamp': int_or_none(video_info.get('dateuploaded')), + 'duration': int_or_none(video_info.get('video', {}).get('duration')), + 'uploader_id': owner.get('nsid'), + 'uploader': owner.get('realname'), + 'comment_count': int_or_none(video_info.get('comments', {}).get('_content')), + 'view_count': int_or_none(video_info.get('views')), + 'tags': [tag.get('_content') for tag in video_info.get('tags', {}).get('tag', [])] + } + else: + raise ExtractorError('not a video', expected=True) diff --git a/youtube_dl/extractor/footyroom.py b/youtube_dl/extractor/footyroom.py index 4c7dbca40..370fd006f 100644 --- a/youtube_dl/extractor/footyroom.py +++ b/youtube_dl/extractor/footyroom.py @@ -13,6 +13,7 @@ class FootyRoomIE(InfoExtractor): 'title': 'Schalke 04 0 – 2 Real Madrid', }, 'playlist_count': 3, + 'skip': 'Video for this match is not available', }, { 'url': 'http://footyroom.com/georgia-0-2-germany-2015-03/', 'info_dict': { diff --git a/youtube_dl/extractor/fourtube.py b/youtube_dl/extractor/fourtube.py index fb6d108c0..fc4a5a0fb 100644 --- a/youtube_dl/extractor/fourtube.py +++ b/youtube_dl/extractor/fourtube.py @@ -3,12 +3,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_request, -) from ..utils import ( parse_duration, parse_iso8601, + sanitized_Request, str_to_int, ) @@ -93,7 +91,7 @@ class FourTubeIE(InfoExtractor): b'Content-Type': b'application/x-www-form-urlencoded', b'Origin': b'http://www.4tube.com', } - token_req = compat_urllib_request.Request(token_url, b'{}', headers) + token_req = sanitized_Request(token_url, b'{}', headers) tokens = self._download_json(token_req, video_id) formats = [{ 'url': tokens[format]['token'], diff --git a/youtube_dl/extractor/foxnews.py b/youtube_dl/extractor/foxnews.py index 3a4a59135..318ac013d 100644 --- a/youtube_dl/extractor/foxnews.py +++ b/youtube_dl/extractor/foxnews.py @@ -2,14 +2,10 @@ from __future__ import unicode_literals import re -from .common import InfoExtractor -from ..utils import ( - parse_iso8601, - int_or_none, -) +from .amp import AMPIE -class FoxNewsIE(InfoExtractor): +class FoxNewsIE(AMPIE): IE_DESC = 'Fox News and Fox Business Video' _VALID_URL = r'https?://(?P<host>video\.fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)' _TESTS = [ @@ -20,10 +16,10 @@ class FoxNewsIE(InfoExtractor): 'id': '3937480', 'ext': 'flv', 'title': 'Frozen in Time', - 'description': 'Doctors baffled by 16-year-old girl that is the size of a toddler', + 'description': '16-year-old girl is size of toddler', 'duration': 265, - 'timestamp': 1304411491, - 'upload_date': '20110503', + # 'timestamp': 1304411491, + # 'upload_date': '20110503', 'thumbnail': 're:^https?://.*\.jpg$', }, }, @@ -34,10 +30,10 @@ class FoxNewsIE(InfoExtractor): 'id': '3922535568001', 'ext': 'mp4', 'title': "Rep. Luis Gutierrez on if Obama's immigration plan is legal", - 'description': "Congressman discusses the president's executive action", + 'description': "Congressman discusses president's plan", 'duration': 292, - 'timestamp': 1417662047, - 'upload_date': '20141204', + # 'timestamp': 1417662047, + # 'upload_date': '20141204', 'thumbnail': 're:^https?://.*\.jpg$', }, }, @@ -52,52 +48,9 @@ class FoxNewsIE(InfoExtractor): ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - host = mobj.group('host') + host, video_id = re.match(self._VALID_URL, url).groups() - video = self._download_json( - 'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id), video_id) - - item = video['channel']['item'] - title = item['title'] - description = item['description'] - timestamp = parse_iso8601(item['dc-date']) - - media_group = item['media-group'] - duration = None - formats = [] - for media in media_group['media-content']: - attributes = media['@attributes'] - video_url = attributes['url'] - if video_url.endswith('.f4m'): - formats.extend(self._extract_f4m_formats(video_url + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124', video_id)) - elif video_url.endswith('.m3u8'): - formats.extend(self._extract_m3u8_formats(video_url, video_id, 'flv')) - elif not video_url.endswith('.smil'): - duration = int_or_none(attributes.get('duration')) - formats.append({ - 'url': video_url, - 'format_id': media['media-category']['@attributes']['label'], - 'preference': 1, - 'vbr': int_or_none(attributes.get('bitrate')), - 'filesize': int_or_none(attributes.get('fileSize')) - }) - self._sort_formats(formats) - - media_thumbnail = media_group['media-thumbnail']['@attributes'] - thumbnails = [{ - 'url': media_thumbnail['url'], - 'width': int_or_none(media_thumbnail.get('width')), - 'height': int_or_none(media_thumbnail.get('height')), - }] if media_thumbnail else [] - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'duration': duration, - 'timestamp': timestamp, - 'formats': formats, - 'thumbnails': thumbnails, - } + info = self._extract_feed_info( + 'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id)) + info['id'] = video_id + return info diff --git a/youtube_dl/extractor/franceinter.py b/youtube_dl/extractor/franceinter.py index 6613ee17a..fdc51f44f 100644 --- a/youtube_dl/extractor/franceinter.py +++ b/youtube_dl/extractor/franceinter.py @@ -1,8 +1,6 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import int_or_none @@ -23,8 +21,7 @@ class FranceInterIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) @@ -33,7 +30,7 @@ class FranceInterIE(InfoExtractor): video_url = 'http://www.franceinter.fr/' + path title = self._html_search_regex( - r'<span class="title">(.+?)</span>', webpage, 'title') + r'<span class="title-diffusion">(.+?)</span>', webpage, 'title') description = self._html_search_regex( r'<span class="description">(.*?)</span>', webpage, 'description', fatal=False) diff --git a/youtube_dl/extractor/funimation.py b/youtube_dl/extractor/funimation.py new file mode 100644 index 000000000..d1a95d87f --- /dev/null +++ b/youtube_dl/extractor/funimation.py @@ -0,0 +1,193 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + clean_html, + determine_ext, + encode_dict, + int_or_none, + sanitized_Request, + ExtractorError, + urlencode_postdata +) + + +class FunimationIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?funimation\.com/shows/[^/]+/videos/(?:official|promotional)/(?P<id>[^/?#&]+)' + + _NETRC_MACHINE = 'funimation' + + _TESTS = [{ + 'url': 'http://www.funimation.com/shows/air/videos/official/breeze', + 'info_dict': { + 'id': '658', + 'display_id': 'breeze', + 'ext': 'mp4', + 'title': 'Air - 1 - Breeze', + 'description': 'md5:1769f43cd5fc130ace8fd87232207892', + 'thumbnail': 're:https?://.*\.jpg', + }, + }, { + 'url': 'http://www.funimation.com/shows/hacksign/videos/official/role-play', + 'info_dict': { + 'id': '31128', + 'display_id': 'role-play', + 'ext': 'mp4', + 'title': '.hack//SIGN - 1 - Role Play', + 'description': 'md5:b602bdc15eef4c9bbb201bb6e6a4a2dd', + 'thumbnail': 're:https?://.*\.jpg', + }, + }, { + 'url': 'http://www.funimation.com/shows/attack-on-titan-junior-high/videos/promotional/broadcast-dub-preview', + 'info_dict': { + 'id': '9635', + 'display_id': 'broadcast-dub-preview', + 'ext': 'mp4', + 'title': 'Attack on Titan: Junior High - Broadcast Dub Preview', + 'description': 'md5:f8ec49c0aff702a7832cd81b8a44f803', + 'thumbnail': 're:https?://.*\.(?:jpg|png)', + }, + }] + + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + data = urlencode_postdata(encode_dict({ + 'email_field': username, + 'password_field': password, + })) + login_request = sanitized_Request('http://www.funimation.com/login', data, headers={ + 'User-Agent': 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0', + 'Content-Type': 'application/x-www-form-urlencoded' + }) + login_page = self._download_webpage( + login_request, None, 'Logging in as %s' % username) + if any(p in login_page for p in ('funimation.com/logout', '>Log Out<')): + return + error = self._html_search_regex( + r'(?s)<div[^>]+id=["\']errorMessages["\'][^>]*>(.+?)</div>', + login_page, 'error messages', default=None) + if error: + raise ExtractorError('Unable to login: %s' % error, expected=True) + raise ExtractorError('Unable to log in') + + def _real_initialize(self): + self._login() + + def _real_extract(self, url): + display_id = self._match_id(url) + + errors = [] + formats = [] + + ERRORS_MAP = { + 'ERROR_MATURE_CONTENT_LOGGED_IN': 'matureContentLoggedIn', + 'ERROR_MATURE_CONTENT_LOGGED_OUT': 'matureContentLoggedOut', + 'ERROR_SUBSCRIPTION_LOGGED_OUT': 'subscriptionLoggedOut', + 'ERROR_VIDEO_EXPIRED': 'videoExpired', + 'ERROR_TERRITORY_UNAVAILABLE': 'territoryUnavailable', + 'SVODBASIC_SUBSCRIPTION_IN_PLAYER': 'basicSubscription', + 'SVODNON_SUBSCRIPTION_IN_PLAYER': 'nonSubscription', + 'ERROR_PLAYER_NOT_RESPONDING': 'playerNotResponding', + 'ERROR_UNABLE_TO_CONNECT_TO_CDN': 'unableToConnectToCDN', + 'ERROR_STREAM_NOT_FOUND': 'streamNotFound', + } + + USER_AGENTS = ( + # PC UA is served with m3u8 that provides some bonus lower quality formats + ('pc', 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0'), + # Mobile UA allows to extract direct links and also does not fail when + # PC UA fails with hulu error (e.g. + # http://www.funimation.com/shows/hacksign/videos/official/role-play) + ('mobile', 'Mozilla/5.0 (Linux; Android 4.4.2; Nexus 4 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.114 Mobile Safari/537.36'), + ) + + for kind, user_agent in USER_AGENTS: + request = sanitized_Request(url) + request.add_header('User-Agent', user_agent) + webpage = self._download_webpage( + request, display_id, 'Downloading %s webpage' % kind) + + playlist = self._parse_json( + self._search_regex( + r'var\s+playersData\s*=\s*(\[.+?\]);\n', + webpage, 'players data'), + display_id)[0]['playlist'] + + items = next(item['items'] for item in playlist if item.get('items')) + item = next(item for item in items if item.get('itemAK') == display_id) + + error_messages = {} + video_error_messages = self._search_regex( + r'var\s+videoErrorMessages\s*=\s*({.+?});\n', + webpage, 'error messages', default=None) + if video_error_messages: + error_messages_json = self._parse_json(video_error_messages, display_id, fatal=False) + if error_messages_json: + for _, error in error_messages_json.items(): + type_ = error.get('type') + description = error.get('description') + content = error.get('content') + if type_ == 'text' and description and content: + error_message = ERRORS_MAP.get(description) + if error_message: + error_messages[error_message] = content + + for video in item.get('videoSet', []): + auth_token = video.get('authToken') + if not auth_token: + continue + funimation_id = video.get('FUNImationID') or video.get('videoId') + preference = 1 if video.get('languageMode') == 'dub' else 0 + if not auth_token.startswith('?'): + auth_token = '?%s' % auth_token + for quality, height in (('sd', 480), ('hd', 720), ('hd1080', 1080)): + format_url = video.get('%sUrl' % quality) + if not format_url: + continue + if not format_url.startswith(('http', '//')): + errors.append(format_url) + continue + if determine_ext(format_url) == 'm3u8': + m3u8_formats = self._extract_m3u8_formats( + format_url + auth_token, display_id, 'mp4', entry_protocol='m3u8_native', + preference=preference, m3u8_id='%s-hls' % funimation_id, fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + else: + tbr = int_or_none(self._search_regex( + r'-(\d+)[Kk]', format_url, 'tbr', default=None)) + formats.append({ + 'url': format_url + auth_token, + 'format_id': '%s-http-%dp' % (funimation_id, height), + 'height': height, + 'tbr': tbr, + 'preference': preference, + }) + + if not formats and errors: + raise ExtractorError( + '%s returned error: %s' + % (self.IE_NAME, clean_html(error_messages.get(errors[0], errors[0]))), + expected=True) + + self._sort_formats(formats) + + title = item['title'] + artist = item.get('artist') + if artist: + title = '%s - %s' % (artist, title) + description = self._og_search_description(webpage) or item.get('description') + thumbnail = self._og_search_thumbnail(webpage) or item.get('posterUrl') + video_id = item.get('itemId') or display_id + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/funnyordie.py b/youtube_dl/extractor/funnyordie.py index f5f13689c..7f21d7410 100644 --- a/youtube_dl/extractor/funnyordie.py +++ b/youtube_dl/extractor/funnyordie.py @@ -45,11 +45,20 @@ class FunnyOrDieIE(InfoExtractor): links.sort(key=lambda link: 1 if link[1] == 'mp4' else 0) - bitrates = self._html_search_regex(r'<source src="[^"]+/v,((?:\d+,)+)\.mp4\.csmil', webpage, 'video bitrates') - bitrates = [int(b) for b in bitrates.rstrip(',').split(',')] - bitrates.sort() + m3u8_url = self._search_regex( + r'<source[^>]+src=(["\'])(?P<url>.+?/master\.m3u8)\1', + webpage, 'm3u8 url', default=None, group='url') formats = [] + + m3u8_formats = self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + + bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)[,/]', m3u8_url)] + bitrates.sort() + for bitrate in bitrates: for link in links: formats.append({ diff --git a/youtube_dl/extractor/gameinformer.py b/youtube_dl/extractor/gameinformer.py new file mode 100644 index 000000000..25870c131 --- /dev/null +++ b/youtube_dl/extractor/gameinformer.py @@ -0,0 +1,43 @@ +# coding: utf-8 +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', + 'info_dict': { + 'id': '4515472681001', + 'ext': 'm3u8', + 'title': 'Replay - Animal Crossing', + 'description': 'md5:2e211891b215c85d061adc7a4dd2d930', + 'timestamp': 1443457610706, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + } + + 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')), + } diff --git a/youtube_dl/extractor/gametrailers.py b/youtube_dl/extractor/gametrailers.py index a6ab795ae..c3f031d9c 100644 --- a/youtube_dl/extractor/gametrailers.py +++ b/youtube_dl/extractor/gametrailers.py @@ -1,19 +1,62 @@ from __future__ import unicode_literals -from .mtv import MTVServicesInfoExtractor +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_age_limit, + url_basename, +) -class GametrailersIE(MTVServicesInfoExtractor): - _VALID_URL = r'http://www\.gametrailers\.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)' +class GametrailersIE(InfoExtractor): + _VALID_URL = r'http://www\.gametrailers\.com/videos/view/[^/]+/(?P<id>.+)' + _TEST = { - 'url': 'http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer', - 'md5': '4c8e67681a0ea7ec241e8c09b3ea8cf7', + 'url': 'http://www.gametrailers.com/videos/view/gametrailers-com/116437-Just-Cause-3-Review', + 'md5': 'f28c4efa0bdfaf9b760f6507955b6a6a', 'info_dict': { - 'id': '70e9a5d7-cf25-4a10-9104-6f3e7342ae0d', + 'id': '2983958', 'ext': 'mp4', - 'title': 'E3 2013: Debut Trailer', - 'description': 'Faith is back! Check out the World Premiere trailer for Mirror\'s Edge 2 straight from the EA Press Conference at E3 2013!', + 'display_id': '116437-Just-Cause-3-Review', + 'title': 'Just Cause 3 - Review', + 'description': 'It\'s a lot of fun to shoot at things and then watch them explode in Just Cause 3, but should there be more to the experience than that?', }, } - _FEED_URL = 'http://www.gametrailers.com/feeds/mrss' + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + title = self._html_search_regex( + r'<title>(.+?)\|', webpage, 'title').strip() + embed_url = self._proto_relative_url( + self._search_regex( + r'src=\'(//embed.gametrailers.com/embed/[^\']+)\'', webpage, + 'embed url'), + scheme='http:') + video_id = url_basename(embed_url) + embed_page = self._download_webpage(embed_url, video_id) + embed_vars_json = self._search_regex( + r'(?s)var embedVars = (\{.*?\})\s*</script>', embed_page, + 'embed vars') + info = self._parse_json(embed_vars_json, video_id) + + formats = [] + for media in info['media']: + if media['mediaPurpose'] == 'play': + formats.append({ + 'url': media['uri'], + 'height': media['height'], + 'width:': media['width'], + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'formats': formats, + 'thumbnail': info.get('thumbUri'), + 'description': self._og_search_description(webpage), + 'duration': int_or_none(info.get('videoLengthInSeconds')), + 'age_limit': parse_age_limit(info.get('audienceRating')), + } diff --git a/youtube_dl/extractor/gdcvault.py b/youtube_dl/extractor/gdcvault.py index a6834db43..3befd3e7b 100644 --- a/youtube_dl/extractor/gdcvault.py +++ b/youtube_dl/extractor/gdcvault.py @@ -3,13 +3,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) +from ..compat import compat_urllib_parse from ..utils import ( remove_end, HEADRequest, + sanitized_Request, ) @@ -125,7 +123,7 @@ class GDCVaultIE(InfoExtractor): 'password': password, } - request = compat_urllib_request.Request(login_url, compat_urllib_parse.urlencode(login_form)) + request = sanitized_Request(login_url, compat_urllib_parse.urlencode(login_form)) request.add_header('Content-Type', 'application/x-www-form-urlencoded') self._download_webpage(request, display_id, 'Logging in') start_page = self._download_webpage(webpage_url, display_id, 'Getting authenticated video page') diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index ca5fbafb2..3c3066e38 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -9,8 +9,8 @@ import sys from .common import InfoExtractor from .youtube import YoutubeIE from ..compat import ( + compat_etree_fromstring, compat_urllib_parse_unquote, - compat_urllib_request, compat_urlparse, compat_xml_parse_error, ) @@ -21,7 +21,7 @@ from ..utils import ( HEADRequest, is_html, orderedSet, - parse_xml, + sanitized_Request, smuggle_url, unescapeHTML, unified_strdate, @@ -30,7 +30,10 @@ from ..utils import ( url_basename, xpath_text, ) -from .brightcove import BrightcoveIE +from .brightcove import ( + BrightcoveLegacyIE, + BrightcoveNewIE, +) from .nbc import NBCSportsVPlayerIE from .ooyala import OoyalaIE from .rutv import RUTVIE @@ -41,7 +44,6 @@ from .myvi import MyviIE from .condenast import CondeNastIE from .udn import UDNEmbedIE from .senateisvp import SenateISVPIE -from .bliptv import BlipTVIE from .svt import SVTIE from .pornhub import PornHubIE from .xhamster import XHamsterEmbedIE @@ -51,6 +53,9 @@ from .onionstudios import OnionStudiosIE from .snagfilms import SnagFilmsEmbedIE from .screenwavemedia import ScreenwaveMediaIE from .mtv import MTVServicesEmbeddedIE +from .pladform import PladformIE +from .googledrive import GoogleDriveIE +from .jwplatform import JWPlatformIE class GenericIE(InfoExtractor): @@ -141,6 +146,7 @@ class GenericIE(InfoExtractor): 'ext': 'mp4', 'title': 'Automatics, robotics and biocybernetics', 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482', + 'upload_date': '20130627', 'formats': 'mincount:16', 'subtitles': 'mincount:1', }, @@ -274,7 +280,7 @@ class GenericIE(InfoExtractor): # it also tests brightcove videos that need to set the 'Referer' in the # http requests { - 'add_ie': ['Brightcove'], + 'add_ie': ['BrightcoveLegacy'], 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/', 'info_dict': { 'id': '2765128793001', @@ -298,7 +304,7 @@ class GenericIE(InfoExtractor): 'uploader': 'thestar.com', 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.', }, - 'add_ie': ['Brightcove'], + 'add_ie': ['BrightcoveLegacy'], }, { 'url': 'http://www.championat.com/video/football/v/87/87499.html', @@ -313,7 +319,7 @@ class GenericIE(InfoExtractor): }, { # https://github.com/rg3/youtube-dl/issues/3541 - 'add_ie': ['Brightcove'], + 'add_ie': ['BrightcoveLegacy'], 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1', 'info_dict': { 'id': '3866516442001', @@ -335,6 +341,7 @@ class GenericIE(InfoExtractor): 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ', 'ext': 'mp4', 'title': '2cc213299525360.mov', # that's what we get + 'duration': 238.231, }, 'add_ie': ['Ooyala'], }, @@ -346,6 +353,7 @@ class GenericIE(InfoExtractor): 'ext': 'mp4', 'title': '"Steve Jobs: Man in the Machine" trailer', 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."', + 'duration': 135.427, }, 'params': { 'skip_download': True, @@ -819,6 +827,19 @@ class GenericIE(InfoExtractor): 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014', }, }, + # Kaltura embed protected with referrer + { + 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero', + 'info_dict': { + 'id': '1_g4fbemnq', + 'ext': 'mp4', + 'title': 'Violetta - Achter De Schermen - Ruggero', + 'description': 'Achter de schermen met Ruggero', + 'timestamp': 1435133761, + 'upload_date': '20150624', + 'uploader_id': 'echojecka', + }, + }, # Eagle.Platform embed (generic URL) { 'url': 'http://lenta.ru/news/2015/03/06/navalny/', @@ -943,8 +964,9 @@ class GenericIE(InfoExtractor): 'info_dict': { 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs', 'ext': 'mp4', - 'description': 'VIDEO: Index/Match versus VLOOKUP.', + 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.', 'title': 'This is what separates the Excel masters from the wannabes', + 'duration': 191.933, }, 'params': { # m3u8 downloads @@ -1030,6 +1052,31 @@ class GenericIE(InfoExtractor): 'ext': 'mp4', 'title': 'cinemasnob', }, + }, + # BrightcoveInPageEmbed embed + { + 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/', + 'info_dict': { + 'id': '4238694884001', + 'ext': 'flv', + 'title': 'Tabletop: Dread, Last Thoughts', + 'description': 'Tabletop: Dread, Last Thoughts', + 'duration': 51690, + }, + }, + # JWPlayer with M3U8 + { + 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video', + 'info_dict': { + 'id': 'playlist', + 'ext': 'mp4', + 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ', + 'uploader': 'ren.tv', + }, + 'params': { + # m3u8 downloads + 'skip_download': True, + } } ] @@ -1173,7 +1220,7 @@ class GenericIE(InfoExtractor): full_response = None if head_response is False: - request = compat_urllib_request.Request(url) + request = sanitized_Request(url) request.add_header('Accept-Encoding', '*') full_response = self._request_webpage(request, video_id) head_response = full_response @@ -1202,7 +1249,7 @@ class GenericIE(InfoExtractor): '%s on generic information extractor.' % ('Forcing' if force else 'Falling back')) if not full_response: - request = compat_urllib_request.Request(url) + request = sanitized_Request(url) # Some webservers may serve compressed content of rather big size (e.g. gzipped flac) # making it impossible to download only chunk of the file (yet we need only 512kB to # test whether it's HTML or not). According to youtube-dl default Accept-Encoding @@ -1237,7 +1284,7 @@ class GenericIE(InfoExtractor): # Is it an RSS feed, a SMIL file or a XSPF playlist? try: - doc = parse_xml(webpage) + doc = compat_etree_fromstring(webpage.encode('utf-8')) if doc.tag == 'rss': return self._extract_rss(url, video_id, doc) elif re.match(r'^(?:{[^}]+})?smil$', doc.tag): @@ -1289,14 +1336,14 @@ class GenericIE(InfoExtractor): return self.playlist_result( urlrs, playlist_id=video_id, playlist_title=video_title) - # Look for BrightCove: - bc_urls = BrightcoveIE._extract_brightcove_urls(webpage) + # Look for Brightcove Legacy Studio embeds + bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage) if bc_urls: self.to_screen('Brightcove video detected.') entries = [{ '_type': 'url', 'url': smuggle_url(bc_url, {'Referer': url}), - 'ie_key': 'Brightcove' + 'ie_key': 'BrightcoveLegacy' } for bc_url in bc_urls] return { @@ -1306,6 +1353,11 @@ class GenericIE(InfoExtractor): 'entries': entries, } + # Look for Brightcove New Studio embeds + bc_urls = BrightcoveNewIE._extract_urls(webpage) + if bc_urls: + return _playlist_from_matches(bc_urls, ie='BrightcoveNew') + # Look for embedded rtl.nl player matches = re.findall( r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"', @@ -1389,11 +1441,6 @@ class GenericIE(InfoExtractor): 'id': match.group('id') } - # Look for embedded blip.tv player - bliptv_url = BlipTVIE._extract_url(webpage) - if bliptv_url: - return self.url_result(bliptv_url, 'BlipTV') - # Look for SVT player svt_url = SVTIE._extract_url(webpage) if svt_url: @@ -1454,7 +1501,7 @@ class GenericIE(InfoExtractor): re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage)) if mobj is not None: - return OoyalaIE._build_url_result(mobj.group('ec')) + return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url})) # Look for multiple Ooyala embeds on SBN network websites mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage) @@ -1462,7 +1509,7 @@ class GenericIE(InfoExtractor): embeds = self._parse_json(mobj.group(1), video_id, fatal=False) if embeds: return _playlist_from_matches( - embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala') + embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala') # Look for Aparat videos mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage) @@ -1671,10 +1718,12 @@ class GenericIE(InfoExtractor): return self.url_result(mobj.group('url'), 'Zapiks') # Look for Kaltura embeds - mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or - re.search(r'(?s)(["\'])(?:https?:)?//cdnapisec\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?\1.*?entry_id\s*:\s*(["\'])(?P<id>[^\2]+?)\2', webpage)) + mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or + re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage)) if mobj is not None: - return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura') + return self.url_result(smuggle_url( + 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), + {'source_url': url}), 'Kaltura') # Look for Eagle.Platform embeds mobj = re.search( @@ -1689,10 +1738,9 @@ class GenericIE(InfoExtractor): return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform') # Look for Pladform embeds - mobj = re.search( - r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage) - if mobj is not None: - return self.url_result(mobj.group('url'), 'Pladform') + pladform_url = PladformIE._extract_url(webpage) + if pladform_url: + return self.url_result(pladform_url) # Look for Playwire embeds mobj = re.search( @@ -1717,9 +1765,14 @@ class GenericIE(InfoExtractor): if nbc_sports_url: return self.url_result(nbc_sports_url, 'NBCSportsVPlayer') + # Look for Google Drive embeds + google_drive_url = GoogleDriveIE._extract_url(webpage) + if google_drive_url: + return self.url_result(google_drive_url, 'GoogleDrive') + # Look for UDN embeds mobj = re.search( - r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage) + r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage) if mobj is not None: return self.url_result( compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed') @@ -1744,6 +1797,11 @@ class GenericIE(InfoExtractor): if snagfilms_url: return self.url_result(snagfilms_url) + # Look for JWPlatform embeds + jwplatform_url = JWPlatformIE._extract_url(webpage) + if jwplatform_url: + return self.url_result(jwplatform_url, 'JWPlatform') + # Look for ScreenwaveMedia embeds mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage) if mobj is not None: @@ -1839,6 +1897,7 @@ class GenericIE(InfoExtractor): entries = [] for video_url in found: + video_url = video_url.replace('\\/', '/') video_url = compat_urlparse.urljoin(url, video_url) video_id = compat_urllib_parse_unquote(os.path.basename(video_url)) @@ -1850,25 +1909,24 @@ class GenericIE(InfoExtractor): # here's a fun little line of code for you: video_id = os.path.splitext(video_id)[0] + entry_info_dict = { + 'id': video_id, + 'uploader': video_uploader, + 'title': video_title, + 'age_limit': age_limit, + } + ext = determine_ext(video_url) if ext == 'smil': - entries.append({ - 'id': video_id, - 'formats': self._extract_smil_formats(video_url, video_id), - 'uploader': video_uploader, - 'title': video_title, - 'age_limit': age_limit, - }) + entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id) elif ext == 'xspf': return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id) + elif ext == 'm3u8': + entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4') else: - entries.append({ - 'id': video_id, - 'url': video_url, - 'uploader': video_uploader, - 'title': video_title, - 'age_limit': age_limit, - }) + entry_info_dict['url'] = video_url + + entries.append(entry_info_dict) if len(entries) == 1: return entries[0] diff --git a/youtube_dl/extractor/globo.py b/youtube_dl/extractor/globo.py index 33d6432a6..c65ef6bcf 100644 --- a/youtube_dl/extractor/globo.py +++ b/youtube_dl/extractor/globo.py @@ -14,79 +14,58 @@ from ..utils import ( ExtractorError, float_or_none, int_or_none, + str_or_none, ) class GloboIE(InfoExtractor): - _VALID_URL = 'https?://.+?\.globo\.com/(?P<id>.+)' + _VALID_URL = '(?:globo:|https?://.+?\.globo\.com/(?:[^/]+/)*(?:v/(?:[^/]+/)?|videos/))(?P<id>\d{7,})' _API_URL_TEMPLATE = 'http://api.globovideos.com/videos/%s/playlist' _SECURITY_URL_TEMPLATE = 'http://security.video.globo.com/videos/%s/hash?player=flash&version=17.0.0.132&resource_id=%s' - _VIDEOID_REGEXES = [ - r'\bdata-video-id="(\d+)"', - r'\bdata-player-videosids="(\d+)"', - r'<div[^>]+\bid="(\d+)"', - ] - _RESIGN_EXPIRATION = 86400 - _TESTS = [ - { - 'url': 'http://globotv.globo.com/sportv/futebol-nacional/v/os-gols-de-atletico-mg-3-x-2-santos-pela-24a-rodada-do-brasileirao/3654973/', - 'md5': '03ebf41cb7ade43581608b7d9b71fab0', - 'info_dict': { - 'id': '3654973', - 'ext': 'mp4', - 'title': 'Os gols de Atlético-MG 3 x 2 Santos pela 24ª rodada do Brasileirão', - 'duration': 251.585, - 'uploader': 'SporTV', - 'uploader_id': 698, - 'like_count': int, - } - }, - { - 'url': 'http://g1.globo.com/carros/autoesporte/videos/t/exclusivos-do-g1/v/mercedes-benz-gla-passa-por-teste-de-colisao-na-europa/3607726/', - 'md5': 'b3ccc801f75cd04a914d51dadb83a78d', - 'info_dict': { - 'id': '3607726', - 'ext': 'mp4', - 'title': 'Mercedes-Benz GLA passa por teste de colisão na Europa', - 'duration': 103.204, - 'uploader': 'Globo.com', - 'uploader_id': 265, - 'like_count': int, - } - }, - { - 'url': 'http://g1.globo.com/jornal-nacional/noticia/2014/09/novidade-na-fiscalizacao-de-bagagem-pela-receita-provoca-discussoes.html', - 'md5': '307fdeae4390ccfe6ba1aa198cf6e72b', - 'info_dict': { - 'id': '3652183', - 'ext': 'mp4', - 'title': 'Receita Federal explica como vai fiscalizar bagagens de quem retorna ao Brasil de avião', - 'duration': 110.711, - 'uploader': 'Rede Globo', - 'uploader_id': 196, - 'like_count': int, - } + _TESTS = [{ + 'url': 'http://g1.globo.com/carros/autoesporte/videos/t/exclusivos-do-g1/v/mercedes-benz-gla-passa-por-teste-de-colisao-na-europa/3607726/', + 'md5': 'b3ccc801f75cd04a914d51dadb83a78d', + 'info_dict': { + 'id': '3607726', + 'ext': 'mp4', + 'title': 'Mercedes-Benz GLA passa por teste de colisão na Europa', + 'duration': 103.204, + 'uploader': 'Globo.com', + 'uploader_id': '265', }, - { - 'url': 'http://globotv.globo.com/canal-brasil/sangue-latino/t/todos-os-videos/v/ator-e-diretor-argentino-ricado-darin-fala-sobre-utopias-e-suas-perdas/3928201/', - 'md5': 'c1defca721ce25b2354e927d3e4b3dec', - 'info_dict': { - 'id': '3928201', - 'ext': 'mp4', - 'title': 'Ator e diretor argentino, Ricado Darín fala sobre utopias e suas perdas', - 'duration': 1472.906, - 'uploader': 'Canal Brasil', - 'uploader_id': 705, - 'like_count': int, - } + }, { + 'url': 'http://globoplay.globo.com/v/4581987/', + 'md5': 'f36a1ecd6a50da1577eee6dd17f67eff', + 'info_dict': { + 'id': '4581987', + 'ext': 'mp4', + 'title': 'Acidentes de trânsito estão entre as maiores causas de queda de energia em SP', + 'duration': 137.973, + 'uploader': 'Rede Globo', + 'uploader_id': '196', }, - ] - - class MD5(): + }, { + 'url': 'http://canalbrasil.globo.com/programas/sangue-latino/videos/3928201.html', + 'only_matching': True, + }, { + 'url': 'http://globosatplay.globo.com/globonews/v/4472924/', + 'only_matching': True, + }, { + 'url': 'http://globotv.globo.com/t/programa/v/clipe-sexo-e-as-negas-adeus/3836166/', + 'only_matching': True, + }, { + 'url': 'http://globotv.globo.com/canal-brasil/sangue-latino/t/todos-os-videos/v/ator-e-diretor-argentino-ricado-darin-fala-sobre-utopias-e-suas-perdas/3928201/', + 'only_matching': True, + }, { + 'url': 'http://canaloff.globo.com/programas/desejar-profundo/videos/4518560.html', + 'only_matching': True, + }] + + class MD5: HEX_FORMAT_LOWERCASE = 0 HEX_FORMAT_UPPERCASE = 1 BASE64_PAD_CHARACTER_DEFAULT_COMPLIANCE = '' @@ -353,9 +332,6 @@ class GloboIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - video_id = self._search_regex(self._VIDEOID_REGEXES, webpage, 'video id') - video = self._download_json( self._API_URL_TEMPLATE % video_id, video_id)['videos'][0] @@ -364,7 +340,7 @@ class GloboIE(InfoExtractor): formats = [] for resource in video['resources']: resource_id = resource.get('_id') - if not resource_id: + if not resource_id or resource_id.endswith('manifest'): continue security = self._download_json( @@ -393,20 +369,23 @@ class GloboIE(InfoExtractor): resource_url = resource['url'] signed_url = '%s?h=%s&k=%s' % (resource_url, signed_hash, 'flash') if resource_id.endswith('m3u8') or resource_url.endswith('.m3u8'): - formats.extend(self._extract_m3u8_formats(signed_url, resource_id, 'mp4')) + m3u8_formats = self._extract_m3u8_formats( + signed_url, resource_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) else: formats.append({ 'url': signed_url, - 'format_id': resource_id, - 'height': resource.get('height'), + 'format_id': 'http-%s' % resource_id, + 'height': int_or_none(resource.get('height')), }) self._sort_formats(formats) duration = float_or_none(video.get('duration'), 1000) - like_count = int_or_none(video.get('likes')) uploader = video.get('channel') - uploader_id = video.get('channel_id') + uploader_id = str_or_none(video.get('channel_id')) return { 'id': video_id, @@ -414,6 +393,46 @@ class GloboIE(InfoExtractor): 'duration': duration, 'uploader': uploader, 'uploader_id': uploader_id, - 'like_count': like_count, 'formats': formats } + + +class GloboArticleIE(InfoExtractor): + _VALID_URL = 'https?://.+?\.globo\.com/(?:[^/]+/)*(?P<id>[^/]+)\.html' + + _VIDEOID_REGEXES = [ + r'\bdata-video-id=["\'](\d{7,})', + r'\bdata-player-videosids=["\'](\d{7,})', + r'\bvideosIDs\s*:\s*["\'](\d{7,})', + r'\bdata-id=["\'](\d{7,})', + r'<div[^>]+\bid=["\'](\d{7,})', + ] + + _TESTS = [{ + 'url': 'http://g1.globo.com/jornal-nacional/noticia/2014/09/novidade-na-fiscalizacao-de-bagagem-pela-receita-provoca-discussoes.html', + 'md5': '307fdeae4390ccfe6ba1aa198cf6e72b', + 'info_dict': { + 'id': '3652183', + 'ext': 'mp4', + 'title': 'Receita Federal explica como vai fiscalizar bagagens de quem retorna ao Brasil de avião', + 'duration': 110.711, + 'uploader': 'Rede Globo', + 'uploader_id': '196', + } + }, { + 'url': 'http://gq.globo.com/Prazeres/Poder/noticia/2015/10/all-o-desafio-assista-ao-segundo-capitulo-da-serie.html', + 'only_matching': True, + }, { + 'url': 'http://gshow.globo.com/programas/tv-xuxa/O-Programa/noticia/2014/01/xuxa-e-junno-namoram-muuuito-em-luau-de-zeze-di-camargo-e-luciano.html', + 'only_matching': True, + }] + + @classmethod + def suitable(cls, url): + return False if GloboIE.suitable(url) else super(GloboArticleIE, cls).suitable(url) + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + video_id = self._search_regex(self._VIDEOID_REGEXES, webpage, 'video id') + return self.url_result('globo:%s' % video_id, 'Globo') diff --git a/youtube_dl/extractor/googledrive.py b/youtube_dl/extractor/googledrive.py new file mode 100644 index 000000000..f354c9c7a --- /dev/null +++ b/youtube_dl/extractor/googledrive.py @@ -0,0 +1,88 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + int_or_none, +) + + +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 = { + 'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1', + 'md5': '881f7700aec4f538571fa1e0eed4a7b6', + 'info_dict': { + 'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ', + 'ext': 'mp4', + 'title': 'Big Buck Bunny.mp4', + 'duration': 46, + } + } + _FORMATS_EXT = { + '5': 'flv', + '6': 'flv', + '13': '3gp', + '17': '3gp', + '18': 'mp4', + '22': 'mp4', + '34': 'flv', + '35': 'flv', + '36': '3gp', + '37': 'mp4', + '38': 'mp4', + '43': 'webm', + '44': 'webm', + '45': 'webm', + '46': 'webm', + '59': 'mp4', + } + + @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})', + webpage) + if mobj: + return 'https://drive.google.com/file/d/%s' % mobj.group('id') + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage( + 'http://docs.google.com/file/d/%s' % video_id, video_id, encoding='unicode_escape') + + reason = self._search_regex(r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None) + if reason: + raise ExtractorError(reason) + + title = self._search_regex(r'"title"\s*,\s*"([^"]+)', webpage, 'title') + duration = int_or_none(self._search_regex( + r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds', default=None)) + fmt_stream_map = self._search_regex( + r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage, 'fmt stream map').split(',') + fmt_list = self._search_regex(r'"fmt_list"\s*,\s*"([^"]+)', webpage, 'fmt_list').split(',') + + formats = [] + for fmt, fmt_stream in zip(fmt_list, fmt_stream_map): + fmt_id, fmt_url = fmt_stream.split('|') + resolution = fmt.split('/')[1] + width, height = resolution.split('x') + formats.append({ + 'url': fmt_url, + 'format_id': fmt_id, + 'resolution': resolution, + 'width': int_or_none(width), + 'height': int_or_none(height), + 'ext': self._FORMATS_EXT[fmt_id], + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'thumbnail': self._og_search_thumbnail(webpage), + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/googleplus.py b/youtube_dl/extractor/googleplus.py index fcefe54cd..731bacd67 100644 --- a/youtube_dl/extractor/googleplus.py +++ b/youtube_dl/extractor/googleplus.py @@ -61,7 +61,7 @@ class GooglePlusIE(InfoExtractor): 'width': int(width), 'height': int(height), } for width, height, video_url in re.findall( - r'\d+,(\d+),(\d+),"(https?://redirector\.googlevideo\.com.*?)"', webpage)] + r'\d+,(\d+),(\d+),"(https?://[^.]+\.googleusercontent.com.*?)"', webpage)] self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/gputechconf.py b/youtube_dl/extractor/gputechconf.py new file mode 100644 index 000000000..145b55bf3 --- /dev/null +++ b/youtube_dl/extractor/gputechconf.py @@ -0,0 +1,55 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + xpath_element, + xpath_text, + int_or_none, + parse_duration, +) + + +class GPUTechConfIE(InfoExtractor): + _VALID_URL = r'https?://on-demand\.gputechconf\.com/gtc/2015/video/S(?P<id>\d+)\.html' + _TEST = { + 'url': 'http://on-demand.gputechconf.com/gtc/2015/video/S5156.html', + 'md5': 'a8862a00a0fd65b8b43acc5b8e33f798', + 'info_dict': { + 'id': '5156', + 'ext': 'mp4', + 'title': 'Coordinating More Than 3 Million CUDA Threads for Social Network Analysis', + 'duration': 1219, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + root_path = self._search_regex(r'var\s+rootPath\s*=\s*"([^"]+)', webpage, 'root path', 'http://evt.dispeak.com/nvidia/events/gtc15/') + xml_file_id = self._search_regex(r'var\s+xmlFileId\s*=\s*"([^"]+)', webpage, 'xml file id') + + doc = self._download_xml('%sxml/%s.xml' % (root_path, xml_file_id), video_id) + + metadata = xpath_element(doc, 'metadata') + http_host = xpath_text(metadata, 'httpHost', 'http host', True) + mbr_videos = xpath_element(metadata, 'MBRVideos') + + formats = [] + for mbr_video in mbr_videos.findall('MBRVideo'): + stream_name = xpath_text(mbr_video, 'streamName') + if stream_name: + formats.append({ + 'url': 'http://%s/%s' % (http_host, stream_name.replace('mp4:', '')), + 'tbr': int_or_none(xpath_text(mbr_video, 'bitrate')), + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': xpath_text(metadata, 'title'), + 'duration': parse_duration(xpath_text(metadata, 'endTime')), + 'creator': xpath_text(metadata, 'speaker'), + 'formats': formats, + } diff --git a/youtube_dl/extractor/groupon.py b/youtube_dl/extractor/groupon.py index 8b9e0e2f8..63c05b6a6 100644 --- a/youtube_dl/extractor/groupon.py +++ b/youtube_dl/extractor/groupon.py @@ -18,6 +18,8 @@ class GrouponIE(InfoExtractor): 'id': 'tubGNycTo_9Uxg82uESj4i61EYX8nyuf', 'ext': 'mp4', 'title': 'Bikram Yoga Huntington Beach | Orange County', + 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', + 'duration': 44.961, }, }], 'params': { diff --git a/youtube_dl/extractor/hearthisat.py b/youtube_dl/extractor/hearthisat.py index a19b31ac0..7d8698655 100644 --- a/youtube_dl/extractor/hearthisat.py +++ b/youtube_dl/extractor/hearthisat.py @@ -4,12 +4,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_request, - compat_urlparse, -) +from ..compat import compat_urlparse from ..utils import ( HEADRequest, + sanitized_Request, str_to_int, urlencode_postdata, urlhandle_detect_ext, @@ -47,7 +45,7 @@ class HearThisAtIE(InfoExtractor): r'intTrackId\s*=\s*(\d+)', webpage, 'track ID') payload = urlencode_postdata({'tracks[]': track_id}) - req = compat_urllib_request.Request(self._PLAYLIST_URL, payload) + req = sanitized_Request(self._PLAYLIST_URL, payload) req.add_header('Content-type', 'application/x-www-form-urlencoded') track = self._download_json(req, track_id, 'Downloading playlist')[0] diff --git a/youtube_dl/extractor/hotnewhiphop.py b/youtube_dl/extractor/hotnewhiphop.py index 651784b73..31e219945 100644 --- a/youtube_dl/extractor/hotnewhiphop.py +++ b/youtube_dl/extractor/hotnewhiphop.py @@ -3,13 +3,11 @@ from __future__ import unicode_literals import base64 from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) +from ..compat import compat_urllib_parse from ..utils import ( ExtractorError, HEADRequest, + sanitized_Request, ) @@ -41,7 +39,7 @@ class HotNewHipHopIE(InfoExtractor): ('mediaType', 's'), ('mediaId', video_id), ]) - r = compat_urllib_request.Request( + r = sanitized_Request( 'http://www.hotnewhiphop.com/ajax/media/getActions/', data=reqdata) r.add_header('Content-Type', 'application/x-www-form-urlencoded') mkd = self._download_json( diff --git a/youtube_dl/extractor/howcast.py b/youtube_dl/extractor/howcast.py index 16677f179..e8f51e545 100644 --- a/youtube_dl/extractor/howcast.py +++ b/youtube_dl/extractor/howcast.py @@ -16,6 +16,7 @@ class HowcastIE(InfoExtractor): 'description': 'md5:dbe792e5f6f1489027027bf2eba188a3', 'timestamp': 1276081287, 'upload_date': '20100609', + 'duration': 56.823, }, 'params': { # m3u8 download diff --git a/youtube_dl/extractor/hypem.py b/youtube_dl/extractor/hypem.py index aa0724a02..b3706fe6d 100644 --- a/youtube_dl/extractor/hypem.py +++ b/youtube_dl/extractor/hypem.py @@ -4,12 +4,10 @@ import json import time from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) +from ..compat import compat_urllib_parse from ..utils import ( ExtractorError, + sanitized_Request, ) @@ -30,15 +28,12 @@ class HypemIE(InfoExtractor): track_id = self._match_id(url) data = {'ax': 1, 'ts': time.time()} - data_encoded = compat_urllib_parse.urlencode(data) - complete_url = url + "?" + data_encoded - request = compat_urllib_request.Request(complete_url) + request = sanitized_Request(url + '?' + compat_urllib_parse.urlencode(data)) response, urlh = self._download_webpage_handle( request, track_id, 'Downloading webpage with the url') - cookie = urlh.headers.get('Set-Cookie', '') html_tracks = self._html_search_regex( - r'(?ms)<script type="application/json" id="displayList-data">\s*(.*?)\s*</script>', + r'(?ms)<script type="application/json" id="displayList-data">(.+?)</script>', response, 'tracks') try: track_list = json.loads(html_tracks) @@ -48,15 +43,14 @@ class HypemIE(InfoExtractor): key = track['key'] track_id = track['id'] - artist = track['artist'] title = track['song'] - serve_url = "http://hypem.com/serve/source/%s/%s" % (track_id, key) - request = compat_urllib_request.Request( - serve_url, '', {'Content-Type': 'application/json'}) - request.add_header('cookie', cookie) + request = sanitized_Request( + 'http://hypem.com/serve/source/%s/%s' % (track_id, key), + '', {'Content-Type': 'application/json'}) song_data = self._download_json(request, track_id, 'Downloading metadata') - final_url = song_data["url"] + final_url = song_data['url'] + artist = track.get('artist') return { 'id': track_id, diff --git a/youtube_dl/extractor/infoq.py b/youtube_dl/extractor/infoq.py index 71cfd12c5..016af2084 100644 --- a/youtube_dl/extractor/infoq.py +++ b/youtube_dl/extractor/infoq.py @@ -1,3 +1,5 @@ +# coding: utf-8 + from __future__ import unicode_literals import base64 @@ -5,8 +7,9 @@ import base64 from .common import InfoExtractor from ..compat import ( compat_urllib_parse_unquote, - compat_urlparse, + compat_parse_qs, ) +from ..utils import determine_ext class InfoQIE(InfoExtractor): @@ -16,7 +19,7 @@ class InfoQIE(InfoExtractor): 'url': 'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things', 'md5': 'b5ca0e0a8c1fed93b0e65e48e462f9a2', 'info_dict': { - 'id': '12-jan-pythonthings', + 'id': 'A-Few-of-My-Favorite-Python-Things', 'ext': 'mp4', 'description': 'Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.', 'title': 'A Few of My Favorite [Python] Things', @@ -24,40 +27,84 @@ class InfoQIE(InfoExtractor): }, { 'url': 'http://www.infoq.com/fr/presentations/changez-avis-sur-javascript', 'only_matching': True, + }, { + 'url': 'http://www.infoq.com/cn/presentations/openstack-continued-delivery', + 'md5': '4918d0cca1497f2244572caf626687ef', + 'info_dict': { + 'id': 'openstack-continued-delivery', + 'title': 'OpenStack持续交付之路', + 'ext': 'flv', + 'description': 'md5:308d981fb28fa42f49f9568322c683ff', + }, }] - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + def _extract_bokecc_videos(self, webpage, video_id): + # TODO: bokecc.com is a Chinese video cloud platform + # It should have an independent extractor but I don't have other + # examples using bokecc + player_params_str = self._html_search_regex( + r'<script[^>]+src="http://p\.bokecc\.com/player\?([^"]+)', + webpage, 'player params', default=None) - video_title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title') - video_description = self._html_search_meta('description', webpage, 'description') + player_params = compat_parse_qs(player_params_str) + + info_xml = self._download_xml( + 'http://p.bokecc.com/servlet/playinfo?uid=%s&vid=%s&m=1' % ( + player_params['siteid'][0], player_params['vid'][0]), video_id) + + return [{ + 'format_id': 'bokecc', + 'url': quality.find('./copy').attrib['playurl'], + 'preference': int(quality.attrib['value']), + } for quality in info_xml.findall('./video/quality')] + def _extract_rtmp_videos(self, webpage): # The server URL is hardcoded video_url = 'rtmpe://video.infoq.com/cfx/st/' # Extract video URL encoded_id = self._search_regex( - r"jsclassref\s*=\s*'([^']*)'", webpage, 'encoded id') + r"jsclassref\s*=\s*'([^']*)'", webpage, 'encoded id', default=None) + real_id = compat_urllib_parse_unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8')) playpath = 'mp4:' + real_id - video_filename = playpath.split('/')[-1] - video_id, extension = video_filename.split('.') - - http_base = self._search_regex( - r'EXPRESSINSTALL_SWF\s*=\s*[^"]*"((?:https?:)?//[^/"]+/)', webpage, - 'HTTP base URL') - - formats = [{ + return [{ 'format_id': 'rtmp', 'url': video_url, - 'ext': extension, + 'ext': determine_ext(playpath), 'play_path': playpath, - }, { + }] + + def _extract_http_videos(self, webpage): + http_video_url = self._search_regex(r'P\.s\s*=\s*\'([^\']+)\'', webpage, 'video URL') + + policy = self._search_regex(r'InfoQConstants.scp\s*=\s*\'([^\']+)\'', webpage, 'policy') + signature = self._search_regex(r'InfoQConstants.scs\s*=\s*\'([^\']+)\'', webpage, 'signature') + key_pair_id = self._search_regex(r'InfoQConstants.sck\s*=\s*\'([^\']+)\'', webpage, 'key-pair-id') + + return [{ 'format_id': 'http', - 'url': compat_urlparse.urljoin(url, http_base) + real_id, + 'url': http_video_url, + 'http_headers': { + 'Cookie': 'CloudFront-Policy=%s; CloudFront-Signature=%s; CloudFront-Key-Pair-Id=%s' % ( + policy, signature, key_pair_id), + }, }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + video_title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title') + video_description = self._html_search_meta('description', webpage, 'description') + + if '/cn/' in url: + # for China videos, HTTP video URL exists but always fails with 403 + formats = self._extract_bokecc_videos(webpage, video_id) + else: + formats = self._extract_rtmp_videos(webpage) + self._extract_http_videos(webpage) + self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index 3d78f78c4..c158f2064 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -10,8 +10,8 @@ from ..utils import ( class InstagramIE(InfoExtractor): - _VALID_URL = r'https://instagram\.com/p/(?P<id>[\da-zA-Z]+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?instagram\.com/p/(?P<id>[^/?#&]+)' + _TESTS = [{ 'url': 'https://instagram.com/p/aye83DjauH/?foo=bar#abc', 'md5': '0d2da106a9d2631273e192b372806516', 'info_dict': { @@ -21,7 +21,10 @@ class InstagramIE(InfoExtractor): 'title': 'Video by naomipq', 'description': 'md5:1f17f0ab29bd6fe2bfad705f58de3cb8', } - } + }, { + 'url': 'https://instagram.com/p/-Cmh1cukG2/', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) diff --git a/youtube_dl/extractor/iprima.py b/youtube_dl/extractor/iprima.py index 821c8ec10..36baf3245 100644 --- a/youtube_dl/extractor/iprima.py +++ b/youtube_dl/extractor/iprima.py @@ -6,12 +6,10 @@ from random import random from math import floor from .common import InfoExtractor -from ..compat import ( - compat_urllib_request, -) from ..utils import ( ExtractorError, remove_end, + sanitized_Request, ) @@ -61,7 +59,7 @@ class IPrimaIE(InfoExtractor): (floor(random() * 1073741824), floor(random() * 1073741824)) ) - req = compat_urllib_request.Request(player_url) + req = sanitized_Request(player_url) req.add_header('Referer', url) playerpage = self._download_webpage(req, video_id) diff --git a/youtube_dl/extractor/iqiyi.py b/youtube_dl/extractor/iqiyi.py index 2df1da3f0..c3731a110 100644 --- a/youtube_dl/extractor/iqiyi.py +++ b/youtube_dl/extractor/iqiyi.py @@ -205,9 +205,8 @@ class IqiyiIE(InfoExtractor): def get_enc_key(self, swf_url, video_id): # TODO: automatic key extraction - # last update at 2015-10-22 for Zombie::bite - # '7223c67061dbea1259d0ceb44f44b6d62288f4f80c972170de5201d2321060270e05'[2:66][0::2] - enc_key = '2c76de15dcb44bd28ff0927d50d31620' + # last update at 2015-12-18 for Zombie::bite + enc_key = '8b6b683780897eb8d9a48a02ccc4817d'[::-1] return enc_key def _real_extract(self, url): diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index e82594444..029878d24 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -5,11 +5,9 @@ import re import json from .common import InfoExtractor -from ..compat import ( - compat_urllib_request, -) from ..utils import ( ExtractorError, + sanitized_Request, ) @@ -78,7 +76,7 @@ class IviIE(InfoExtractor): ] } - request = compat_urllib_request.Request(api_url, json.dumps(data)) + request = sanitized_Request(api_url, json.dumps(data)) video_json_page = self._download_webpage( request, video_id, 'Downloading video JSON') diff --git a/youtube_dl/extractor/jwplatform.py b/youtube_dl/extractor/jwplatform.py new file mode 100644 index 000000000..cdc095a79 --- /dev/null +++ b/youtube_dl/extractor/jwplatform.py @@ -0,0 +1,71 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import int_or_none + + +class JWPlatformIE(InfoExtractor): + _VALID_URL = r'(?:https?://content\.jwplatform\.com/(?:feeds|players|jw6)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})' + _TEST = { + 'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js', + 'md5': 'fa8899fa601eb7c83a64e9d568bdf325', + 'info_dict': { + 'id': 'nPripu9l', + 'ext': 'mov', + 'title': 'Big Buck Bunny Trailer', + 'description': 'Big Buck Bunny is a short animated film by the Blender Institute. It is made using free and open source software.', + 'upload_date': '20081127', + 'timestamp': 1227796140, + } + } + + @staticmethod + def _extract_url(webpage): + mobj = re.search( + r'<script[^>]+?src=["\'](?P<url>(?:https?:)?//content.jwplatform.com/players/[a-zA-Z0-9]{8})', + webpage) + if mobj: + return mobj.group('url') + + def _real_extract(self, url): + video_id = self._match_id(url) + json_data = self._download_json('http://content.jwplatform.com/feeds/%s.json' % video_id, video_id) + video_data = json_data['playlist'][0] + subtitles = {} + for track in video_data['tracks']: + if track['kind'] == 'captions': + subtitles[track['label']] = [{'url': self._proto_relative_url(track['file'])}] + + formats = [] + for source in video_data['sources']: + source_url = self._proto_relative_url(source['file']) + source_type = source.get('type') or '' + if source_type == 'application/vnd.apple.mpegurl': + m3u8_formats = self._extract_m3u8_formats(source_url, video_id, 'mp4', 'm3u8_native', fatal=None) + if m3u8_formats: + formats.extend(m3u8_formats) + elif source_type.startswith('audio'): + formats.append({ + 'url': source_url, + 'vcodec': 'none', + }) + else: + formats.append({ + 'url': source_url, + 'width': int_or_none(source.get('width')), + 'height': int_or_none(source.get('height')), + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': video_data['title'], + 'description': video_data.get('description'), + 'thumbnail': self._proto_relative_url(video_data.get('image')), + 'timestamp': int_or_none(video_data.get('pubdate')), + 'subtitles': subtitles, + 'formats': formats, + } diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py index 3dca0e566..583b1a5ad 100644 --- a/youtube_dl/extractor/kaltura.py +++ b/youtube_dl/extractor/kaltura.py @@ -2,12 +2,18 @@ from __future__ import unicode_literals import re +import base64 from .common import InfoExtractor -from ..compat import compat_urllib_parse +from ..compat import ( + compat_urllib_parse, + compat_urlparse, +) from ..utils import ( + clean_html, ExtractorError, int_or_none, + unsmuggle_url, ) @@ -16,7 +22,7 @@ class KalturaIE(InfoExtractor): (?: kaltura:(?P<partner_id_s>\d+):(?P<id_s>[0-9a-z_]+)| https?:// - (:?(?:www|cdnapisec)\.)?kaltura\.com/ + (:?(?:www|cdnapi(?:sec)?)\.)?kaltura\.com/ (?: (?: # flash player @@ -121,31 +127,47 @@ class KalturaIE(InfoExtractor): video_id, actions, note='Downloading video info JSON') def _real_extract(self, url): + 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, source_data = self._get_video_info(entry_id, partner_id) - formats = [{ - 'format_id': '%(fileExt)s-%(bitrate)s' % f, - 'ext': f['fileExt'], - 'tbr': f['bitrate'], - 'fps': f.get('frameRate'), - 'filesize_approx': int_or_none(f.get('size'), invscale=1024), - 'container': f.get('containerFormat'), - 'vcodec': f.get('videoCodecId'), - 'height': f.get('height'), - 'width': f.get('width'), - 'url': '%s/flavorId/%s' % (info['dataUrl'], f['id']), - } for f in source_data['flavorAssets']] + source_url = smuggled_data.get('source_url') + if source_url: + referrer = base64.b64encode( + '://'.join(compat_urlparse.urlparse(source_url)[:2]) + .encode('utf-8')).decode('utf-8') + else: + referrer = None + + formats = [] + for f in source_data['flavorAssets']: + video_url = '%s/flavorId/%s' % (info['dataUrl'], f['id']) + if referrer: + video_url += '?referrer=%s' % referrer + formats.append({ + 'format_id': '%(fileExt)s-%(bitrate)s' % f, + 'ext': f.get('fileExt'), + 'tbr': int_or_none(f['bitrate']), + 'fps': int_or_none(f.get('frameRate')), + 'filesize_approx': int_or_none(f.get('size'), invscale=1024), + 'container': f.get('containerFormat'), + 'vcodec': f.get('videoCodecId'), + 'height': int_or_none(f.get('height')), + 'width': int_or_none(f.get('width')), + 'url': video_url, + }) + self._check_formats(formats, entry_id) self._sort_formats(formats) return { 'id': entry_id, 'title': info['name'], 'formats': formats, - 'description': info.get('description'), + 'description': clean_html(info.get('description')), 'thumbnail': info.get('thumbnailUrl'), 'duration': info.get('duration'), 'timestamp': info.get('createdAt'), diff --git a/youtube_dl/extractor/keezmovies.py b/youtube_dl/extractor/keezmovies.py index 82eddec51..126ca13df 100644 --- a/youtube_dl/extractor/keezmovies.py +++ b/youtube_dl/extractor/keezmovies.py @@ -1,12 +1,11 @@ from __future__ import unicode_literals -import os import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse_urlparse, - compat_urllib_request, +from ..utils import ( + sanitized_Request, + url_basename, ) @@ -14,19 +13,20 @@ class KeezMoviesIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P<id>[0-9]+)(?:[/?&]|$)' _TEST = { 'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711', - 'md5': '6e297b7e789329923fcf83abb67c9289', + 'md5': '1c1e75d22ffa53320f45eeb07bc4cdc0', 'info_dict': { 'id': '1214711', 'ext': 'mp4', 'title': 'Petite Asian Lady Mai Playing In Bathtub', 'age_limit': 18, + 'thumbnail': 're:^https?://.*\.jpg$', } } def _real_extract(self, url): video_id = self._match_id(url) - req = compat_urllib_request.Request(url) + req = sanitized_Request(url) req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) @@ -38,21 +38,29 @@ class KeezMoviesIE(InfoExtractor): video_title = self._html_search_regex( r'<h1 [^>]*>([^<]+)', webpage, 'title') - video_url = self._html_search_regex( - r'(?s)html5VideoPlayer = .*?src="([^"]+)"', webpage, 'video URL') - path = compat_urllib_parse_urlparse(video_url).path - extension = os.path.splitext(path)[1][1:] - format = path.split('/')[4].split('_')[:2] - format = "-".join(format) + flashvars = self._parse_json(self._search_regex( + r'var\s+flashvars\s*=\s*([^;]+);', webpage, 'flashvars'), video_id) + + formats = [] + for height in (180, 240, 480): + if flashvars.get('quality_%dp' % height): + video_url = flashvars['quality_%dp' % height] + a_format = { + 'url': video_url, + 'height': height, + 'format_id': '%dp' % height, + } + filename_parts = url_basename(video_url).split('_') + if len(filename_parts) >= 2 and re.match(r'\d+[Kk]', filename_parts[1]): + a_format['tbr'] = int(filename_parts[1][:-1]) + formats.append(a_format) age_limit = self._rta_search(webpage) return { 'id': video_id, 'title': video_title, - 'url': video_url, - 'ext': extension, - 'format': format, - 'format_id': format, + 'formats': formats, 'age_limit': age_limit, + 'thumbnail': flashvars.get('image_url') } diff --git a/youtube_dl/extractor/letv.py b/youtube_dl/extractor/letv.py index effd9eb92..be648000e 100644 --- a/youtube_dl/extractor/letv.py +++ b/youtube_dl/extractor/letv.py @@ -8,13 +8,13 @@ import time from .common import InfoExtractor from ..compat import ( compat_urllib_parse, - compat_urllib_request, compat_ord, ) from ..utils import ( determine_ext, ExtractorError, parse_iso8601, + sanitized_Request, int_or_none, encode_data_uri, ) @@ -114,7 +114,7 @@ class LetvIE(InfoExtractor): 'tkey': self.calc_time_key(int(time.time())), 'domain': 'www.letv.com' } - play_json_req = compat_urllib_request.Request( + play_json_req = sanitized_Request( 'http://api.letv.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params) ) cn_verification_proxy = self._downloader.params.get('cn_verification_proxy') diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py index 5c973e75c..d4e1ae99d 100644 --- a/youtube_dl/extractor/lynda.py +++ b/youtube_dl/extractor/lynda.py @@ -7,12 +7,12 @@ from .common import InfoExtractor from ..compat import ( compat_str, compat_urllib_parse, - compat_urllib_request, ) from ..utils import ( ExtractorError, clean_html, int_or_none, + sanitized_Request, ) @@ -25,7 +25,7 @@ class LyndaBaseIE(InfoExtractor): self._login() def _login(self): - (username, password) = self._get_login_info() + username, password = self._get_login_info() if username is None: return @@ -35,7 +35,7 @@ class LyndaBaseIE(InfoExtractor): 'remember': 'false', 'stayPut': 'false' } - request = compat_urllib_request.Request( + request = sanitized_Request( self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8')) login_page = self._download_webpage( request, None, 'Logging in as %s' % username) @@ -64,7 +64,7 @@ class LyndaBaseIE(InfoExtractor): 'remember': 'false', 'stayPut': 'false', } - request = compat_urllib_request.Request( + request = sanitized_Request( self._LOGIN_URL, compat_urllib_parse.urlencode(confirm_form).encode('utf-8')) login_page = self._download_webpage( request, None, @@ -82,6 +82,15 @@ class LyndaBaseIE(InfoExtractor): expected=True) raise ExtractorError('Unable to log in') + def _logout(self): + username, _ = self._get_login_info() + if username is None: + return + + self._download_webpage( + 'http://www.lynda.com/ajax/logout.aspx', None, + 'Logging out', 'Unable to log out', fatal=False) + class LyndaIE(LyndaBaseIE): IE_NAME = 'lynda' @@ -108,51 +117,47 @@ class LyndaIE(LyndaBaseIE): def _real_extract(self, url): video_id = self._match_id(url) - page = self._download_webpage( + video = self._download_json( 'http://www.lynda.com/ajax/player?videoId=%s&type=video' % video_id, video_id, 'Downloading video JSON') - video_json = json.loads(page) - if 'Status' in video_json: + if 'Status' in video: raise ExtractorError( - 'lynda returned error: %s' % video_json['Message'], expected=True) + 'lynda returned error: %s' % video['Message'], expected=True) - if video_json['HasAccess'] is False: + if video.get('HasAccess') is False: self.raise_login_required('Video %s is only available for members' % video_id) - video_id = compat_str(video_json['ID']) - duration = video_json['DurationInSeconds'] - title = video_json['Title'] + video_id = compat_str(video.get('ID') or video_id) + duration = int_or_none(video.get('DurationInSeconds')) + title = video['Title'] formats = [] - fmts = video_json.get('Formats') + fmts = video.get('Formats') if fmts: - formats.extend([ - { - 'url': fmt['Url'], - 'ext': fmt['Extension'], - 'width': fmt['Width'], - 'height': fmt['Height'], - 'filesize': fmt['FileSize'], - 'format_id': str(fmt['Resolution']) - } for fmt in fmts]) - - prioritized_streams = video_json.get('PrioritizedStreams') + formats.extend([{ + 'url': f['Url'], + 'ext': f.get('Extension'), + 'width': int_or_none(f.get('Width')), + 'height': int_or_none(f.get('Height')), + 'filesize': int_or_none(f.get('FileSize')), + 'format_id': compat_str(f.get('Resolution')) if f.get('Resolution') else None, + } for f in fmts if f.get('Url')]) + + prioritized_streams = video.get('PrioritizedStreams') if prioritized_streams: for prioritized_stream_id, prioritized_stream in prioritized_streams.items(): - formats.extend([ - { - 'url': video_url, - 'width': int_or_none(format_id), - 'format_id': '%s-%s' % (prioritized_stream_id, format_id), - } for format_id, video_url in prioritized_stream.items() - ]) + formats.extend([{ + 'url': video_url, + 'width': int_or_none(format_id), + 'format_id': '%s-%s' % (prioritized_stream_id, format_id), + } for format_id, video_url in prioritized_stream.items()]) self._check_formats(formats, video_id) self._sort_formats(formats) - subtitles = self.extract_subtitles(video_id, page) + subtitles = self.extract_subtitles(video_id) return { 'id': video_id, @@ -183,7 +188,7 @@ class LyndaIE(LyndaBaseIE): if srt: return srt - def _get_subtitles(self, video_id, webpage): + def _get_subtitles(self, video_id): url = 'http://www.lynda.com/ajax/player?videoId=%s&type=transcript' % video_id subs = self._download_json(url, None, False) if subs: @@ -205,12 +210,13 @@ class LyndaCourseIE(LyndaBaseIE): course_path = mobj.group('coursepath') course_id = mobj.group('courseid') - page = self._download_webpage( + course = self._download_json( 'http://www.lynda.com/ajax/player?courseId=%s&type=course' % course_id, course_id, 'Downloading course JSON') - course_json = json.loads(page) - if 'Status' in course_json and course_json['Status'] == 'NotFound': + self._logout() + + if course.get('Status') == 'NotFound': raise ExtractorError( 'Course %s does not exist' % course_id, expected=True) @@ -220,12 +226,13 @@ class LyndaCourseIE(LyndaBaseIE): # Might want to extract videos right here from video['Formats'] as it seems 'Formats' is not provided # by single video API anymore - for chapter in course_json['Chapters']: - for video in chapter['Videos']: - if video['HasAccess'] is False: + for chapter in course['Chapters']: + for video in chapter.get('Videos', []): + if video.get('HasAccess') is False: unaccessible_videos += 1 continue - videos.append(video['ID']) + if video.get('ID'): + videos.append(video['ID']) if unaccessible_videos > 0: self._downloader.report_warning( @@ -238,6 +245,6 @@ class LyndaCourseIE(LyndaBaseIE): 'Lynda') for video_id in videos] - course_title = course_json['Title'] + course_title = course.get('Title') return self.playlist_result(entries, course_id, course_title) diff --git a/youtube_dl/extractor/makertv.py b/youtube_dl/extractor/makertv.py new file mode 100644 index 000000000..3c34d4604 --- /dev/null +++ b/youtube_dl/extractor/makertv.py @@ -0,0 +1,32 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class MakerTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:(?:www\.)?maker\.tv/(?:[^/]+/)*video|makerplayer.com/embed/maker)/(?P<id>[a-zA-Z0-9]{12})' + _TEST = { + 'url': 'http://www.maker.tv/video/Fh3QgymL9gsc', + 'md5': 'ca237a53a8eb20b6dc5bd60564d4ab3e', + 'info_dict': { + 'id': 'Fh3QgymL9gsc', + 'ext': 'mp4', + 'title': 'Maze Runner: The Scorch Trials Official Movie Review', + 'description': 'md5:11ff3362d7ef1d679fdb649f6413975a', + 'upload_date': '20150918', + 'timestamp': 1442549540, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + jwplatform_id = self._search_regex(r'jw_?id="([^"]+)"', webpage, 'jwplatform id') + + return { + '_type': 'url_transparent', + 'id': video_id, + 'url': 'jwplatform:%s' % jwplatform_id, + 'ie_key': 'JWPlatform', + } diff --git a/youtube_dl/extractor/mdr.py b/youtube_dl/extractor/mdr.py index fc7499958..88334889e 100644 --- a/youtube_dl/extractor/mdr.py +++ b/youtube_dl/extractor/mdr.py @@ -1,64 +1,169 @@ +# coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor +from ..compat import compat_urlparse +from ..utils import ( + determine_ext, + int_or_none, + parse_duration, + parse_iso8601, + xpath_text, +) class MDRIE(InfoExtractor): - _VALID_URL = r'^(?P<domain>https?://(?:www\.)?mdr\.de)/(?:.*)/(?P<type>video|audio)(?P<video_id>[^/_]+)(?:_|\.html)' + IE_DESC = 'MDR.DE and KiKA' + _VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z]+(?P<id>\d+)(?:_.+?)?\.html' - # No tests, MDR regularily deletes its videos - _TEST = { + _TESTS = [{ + # MDR regularily deletes its videos 'url': 'http://www.mdr.de/fakt/video189002.html', 'only_matching': True, - } + }, { + # audio + 'url': 'http://www.mdr.de/kultur/audio1312272_zc-15948bad_zs-86171fdd.html', + 'md5': '64c4ee50f0a791deb9479cd7bbe9d2fa', + 'info_dict': { + 'id': '1312272', + 'ext': 'mp3', + 'title': 'Feuilleton vom 30. Oktober 2015', + 'duration': 250, + 'uploader': 'MITTELDEUTSCHER RUNDFUNK', + }, + }, { + 'url': 'http://www.kika.de/baumhaus/videos/video19636.html', + 'md5': '4930515e36b06c111213e80d1e4aad0e', + 'info_dict': { + 'id': '19636', + 'ext': 'mp4', + 'title': 'Baumhaus vom 30. Oktober 2015', + 'duration': 134, + 'uploader': 'KIKA', + }, + }, { + 'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/videos/video8182.html', + 'md5': '5fe9c4dd7d71e3b238f04b8fdd588357', + 'info_dict': { + 'id': '8182', + 'ext': 'mp4', + 'title': 'Beutolomäus und der geheime Weihnachtswunsch', + 'description': 'md5:b69d32d7b2c55cbe86945ab309d39bbd', + 'timestamp': 1419047100, + 'upload_date': '20141220', + 'duration': 4628, + 'uploader': 'KIKA', + }, + }, { + 'url': 'http://www.kika.de/baumhaus/sendungen/video19636_zc-fea7f8a0_zs-4bf89c60.html', + 'only_matching': True, + }, { + 'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/einzelsendung2534.html', + 'only_matching': True, + }] def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('video_id') - domain = m.group('domain') + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + data_url = self._search_regex( + r'dataURL\s*:\s*(["\'])(?P<url>/.+/(?:video|audio)[0-9]+-avCustom\.xml)\1', + webpage, 'data url', group='url') - # determine title and media streams from webpage - html = self._download_webpage(url, video_id) + doc = self._download_xml( + compat_urlparse.urljoin(url, data_url), video_id) - title = self._html_search_regex(r'<h[12]>(.*?)</h[12]>', html, 'title') - xmlurl = self._search_regex( - r'dataURL:\'(/(?:.+)/(?:video|audio)[0-9]+-avCustom.xml)', html, 'XML URL') + title = xpath_text(doc, ['./title', './broadcast/broadcastName'], 'title', fatal=True) - doc = self._download_xml(domain + xmlurl, video_id) formats = [] - for a in doc.findall('./assets/asset'): - url_el = a.find('./progressiveDownloadUrl') - if url_el is None: - continue - abr = int(a.find('bitrateAudio').text) // 1000 - media_type = a.find('mediaType').text - format = { - 'abr': abr, - 'filesize': int(a.find('fileSize').text), - 'url': url_el.text, - } - - vbr_el = a.find('bitrateVideo') - if vbr_el is None: - format.update({ - 'vcodec': 'none', - 'format_id': '%s-%d' % (media_type, abr), - }) - else: - vbr = int(vbr_el.text) // 1000 - format.update({ - 'vbr': vbr, - 'width': int(a.find('frameWidth').text), - 'height': int(a.find('frameHeight').text), - 'format_id': '%s-%d' % (media_type, vbr), - }) - formats.append(format) + processed_urls = [] + for asset in doc.findall('./assets/asset'): + for source in ( + 'progressiveDownload', + 'dynamicHttpStreamingRedirector', + 'adaptiveHttpStreamingRedirector'): + url_el = asset.find('./%sUrl' % source) + if url_el is None: + continue + + video_url = url_el.text + if video_url in processed_urls: + continue + + processed_urls.append(video_url) + + vbr = int_or_none(xpath_text(asset, './bitrateVideo', 'vbr'), 1000) + abr = int_or_none(xpath_text(asset, './bitrateAudio', 'abr'), 1000) + + ext = determine_ext(url_el.text) + if ext == 'm3u8': + url_formats = self._extract_m3u8_formats( + video_url, video_id, 'mp4', entry_protocol='m3u8_native', + preference=0, m3u8_id='HLS', fatal=False) + elif ext == 'f4m': + url_formats = self._extract_f4m_formats( + video_url + '?hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id, + preference=0, f4m_id='HDS', fatal=False) + else: + media_type = xpath_text(asset, './mediaType', 'media type', default='MP4') + vbr = int_or_none(xpath_text(asset, './bitrateVideo', 'vbr'), 1000) + abr = int_or_none(xpath_text(asset, './bitrateAudio', 'abr'), 1000) + filesize = int_or_none(xpath_text(asset, './fileSize', 'file size')) + + f = { + 'url': video_url, + 'format_id': '%s-%d' % (media_type, vbr or abr), + 'filesize': filesize, + 'abr': abr, + 'preference': 1, + } + + if vbr: + width = int_or_none(xpath_text(asset, './frameWidth', 'width')) + height = int_or_none(xpath_text(asset, './frameHeight', 'height')) + f.update({ + 'vbr': vbr, + 'width': width, + 'height': height, + }) + + url_formats = [f] + + if not url_formats: + continue + + if not vbr: + for f in url_formats: + abr = f.get('tbr') or abr + if 'tbr' in f: + del f['tbr'] + f.update({ + 'abr': abr, + 'vcodec': 'none', + }) + + formats.extend(url_formats) + self._sort_formats(formats) + description = xpath_text(doc, './broadcast/broadcastDescription', 'description') + timestamp = parse_iso8601( + xpath_text( + doc, [ + './broadcast/broadcastDate', + './broadcast/broadcastStartDate', + './broadcast/broadcastEndDate'], + 'timestamp', default=None)) + duration = parse_duration(xpath_text(doc, './duration', 'duration')) + uploader = xpath_text(doc, './rights', 'uploader') + return { 'id': video_id, 'title': title, + 'description': description, + 'timestamp': timestamp, + 'duration': duration, + 'uploader': uploader, 'formats': formats, } diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py index 6e2e73a51..67d6271e1 100644 --- a/youtube_dl/extractor/metacafe.py +++ b/youtube_dl/extractor/metacafe.py @@ -7,12 +7,12 @@ from ..compat import ( compat_parse_qs, compat_urllib_parse, compat_urllib_parse_unquote, - compat_urllib_request, ) from ..utils import ( determine_ext, ExtractorError, int_or_none, + sanitized_Request, ) @@ -117,7 +117,7 @@ class MetacafeIE(InfoExtractor): 'filters': '0', 'submit': "Continue - I'm over 18", } - request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form)) + request = sanitized_Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form)) request.add_header('Content-Type', 'application/x-www-form-urlencoded') self.report_age_confirmation() self._download_webpage(request, None, False, 'Unable to confirm age') @@ -142,7 +142,7 @@ class MetacafeIE(InfoExtractor): return self.url_result('theplatform:%s' % ext_id, 'ThePlatform') # Retrieve video webpage to extract further information - req = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id) + req = sanitized_Request('http://www.metacafe.com/watch/%s/' % video_id) # AnyClip videos require the flashversion cookie so that we get the link # to the mp4 file @@ -154,10 +154,10 @@ class MetacafeIE(InfoExtractor): # Extract URL, uploader and title from webpage self.report_extraction(video_id) video_url = None - mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) + mobj = re.search(r'(?m)&(?:media|video)URL=([^&]+)', webpage) if mobj is not None: mediaURL = compat_urllib_parse_unquote(mobj.group(1)) - video_ext = mediaURL[-3:] + video_ext = determine_ext(mediaURL) # Extract gdaKey if available mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) @@ -229,7 +229,7 @@ class MetacafeIE(InfoExtractor): age_limit = ( 18 - if re.search(r'"contentRating":"restricted"', webpage) + if re.search(r'(?:"contentRating":|"rating",)"restricted"', webpage) else 0) if isinstance(video_url, list): diff --git a/youtube_dl/extractor/minhateca.py b/youtube_dl/extractor/minhateca.py index 14934b7ec..e46b23a6f 100644 --- a/youtube_dl/extractor/minhateca.py +++ b/youtube_dl/extractor/minhateca.py @@ -2,14 +2,12 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) +from ..compat import compat_urllib_parse from ..utils import ( int_or_none, parse_duration, parse_filesize, + sanitized_Request, ) @@ -39,7 +37,7 @@ class MinhatecaIE(InfoExtractor): ('fileId', video_id), ('__RequestVerificationToken', token), ] - req = compat_urllib_request.Request( + req = sanitized_Request( 'http://minhateca.com.br/action/License/Download', data=compat_urllib_parse.urlencode(token_data)) req.add_header('Content-Type', 'application/x-www-form-urlencoded') diff --git a/youtube_dl/extractor/miomio.py b/youtube_dl/extractor/miomio.py index a784fc5fb..170ebd9eb 100644 --- a/youtube_dl/extractor/miomio.py +++ b/youtube_dl/extractor/miomio.py @@ -8,6 +8,7 @@ from ..utils import ( xpath_text, int_or_none, ExtractorError, + sanitized_Request, ) @@ -51,6 +52,8 @@ class MioMioIE(InfoExtractor): mioplayer_path = self._search_regex( r'src="(/mioplayer/[^"]+)"', webpage, 'ref_path') + http_headers = {'Referer': 'http://www.miomio.tv%s' % mioplayer_path} + xml_config = self._search_regex( r'flashvars="type=(?:sina|video)&(.+?)&', webpage, 'xml config') @@ -60,14 +63,12 @@ class MioMioIE(InfoExtractor): 'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/xml.php?id=%s&r=%s' % (id, random.randint(100, 999)), video_id) - # the following xml contains the actual configuration information on the video file(s) - vid_config = self._download_xml( + vid_config_request = sanitized_Request( 'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/sina.php?{0}'.format(xml_config), - video_id) + headers=http_headers) - http_headers = { - 'Referer': 'http://www.miomio.tv%s' % mioplayer_path, - } + # the following xml contains the actual configuration information on the video file(s) + vid_config = self._download_xml(vid_config_request, video_id) if not int_or_none(xpath_text(vid_config, 'timelength')): raise ExtractorError('Unable to load videos!', expected=True) diff --git a/youtube_dl/extractor/mit.py b/youtube_dl/extractor/mit.py index f088ab9e2..29ca45778 100644 --- a/youtube_dl/extractor/mit.py +++ b/youtube_dl/extractor/mit.py @@ -86,7 +86,7 @@ class MITIE(TechTVMITIE): webpage = self._download_webpage(url, page_title) embed_url = self._search_regex( r'<iframe .*?src="(.+?)"', webpage, 'embed url') - return self.url_result(embed_url, ie='TechTVMIT') + return self.url_result(embed_url) class OCWMITIE(InfoExtractor): diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py index 3142fcde2..c595f2077 100644 --- a/youtube_dl/extractor/mitele.py +++ b/youtube_dl/extractor/mitele.py @@ -1,7 +1,10 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import compat_urllib_parse +from ..compat import ( + compat_urllib_parse, + compat_urlparse, +) from ..utils import ( encode_dict, get_element_by_attribute, @@ -15,7 +18,7 @@ class MiTeleIE(InfoExtractor): _TESTS = [{ 'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/', - 'md5': '757b0b66cbd7e0a97226d7d3156cb3e9', + 'md5': '0ff1a13aebb35d9bc14081ff633dd324', 'info_dict': { 'id': '0NF1jJnxS1Wu3pHrmvFyw2', 'display_id': 'programa-144', @@ -34,6 +37,7 @@ class MiTeleIE(InfoExtractor): config_url = self._search_regex( r'data-config\s*=\s*"([^"]+)"', webpage, 'data config url') + config_url = compat_urlparse.urljoin(url, config_url) config = self._download_json( config_url, display_id, 'Downloading config JSON') diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index d47aeceda..c2b7ed9ab 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -64,7 +64,8 @@ class MixcloudIE(InfoExtractor): preview_url = self._search_regex( r'\s(?:data-preview-url|m-preview)="([^"]+)"', webpage, 'preview url') - song_url = preview_url.replace('/previews/', '/c/originals/') + song_url = re.sub(r'audiocdn(\d+)', r'stream\1', preview_url) + song_url = song_url.replace('/previews/', '/c/originals/') if not self._check_url(song_url, track_id, 'mp3'): song_url = song_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/') if not self._check_url(song_url, track_id, 'm4a'): diff --git a/youtube_dl/extractor/moevideo.py b/youtube_dl/extractor/moevideo.py index 5a66302f6..d930b9634 100644 --- a/youtube_dl/extractor/moevideo.py +++ b/youtube_dl/extractor/moevideo.py @@ -5,13 +5,11 @@ import json import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) +from ..compat import compat_urllib_parse from ..utils import ( ExtractorError, int_or_none, + sanitized_Request, ) @@ -80,7 +78,7 @@ class MoeVideoIE(InfoExtractor): ] r_json = json.dumps(r) post = compat_urllib_parse.urlencode({'r': r_json}) - req = compat_urllib_request.Request(self._API_URL, post) + req = sanitized_Request(self._API_URL, post) req.add_header('Content-type', 'application/x-www-form-urlencoded') response = self._download_json(req, video_id) diff --git a/youtube_dl/extractor/mofosex.py b/youtube_dl/extractor/mofosex.py index 9bf99a54a..f8226cbb2 100644 --- a/youtube_dl/extractor/mofosex.py +++ b/youtube_dl/extractor/mofosex.py @@ -7,8 +7,8 @@ from .common import InfoExtractor from ..compat import ( compat_urllib_parse_unquote, compat_urllib_parse_urlparse, - compat_urllib_request, ) +from ..utils import sanitized_Request class MofosexIE(InfoExtractor): @@ -29,7 +29,7 @@ class MofosexIE(InfoExtractor): video_id = mobj.group('id') url = 'http://www.' + mobj.group('url') - req = compat_urllib_request.Request(url) + req = sanitized_Request(url) req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) diff --git a/youtube_dl/extractor/moniker.py b/youtube_dl/extractor/moniker.py index 7c0c4e50e..f6bf94f2f 100644 --- a/youtube_dl/extractor/moniker.py +++ b/youtube_dl/extractor/moniker.py @@ -5,13 +5,11 @@ import os.path import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) +from ..compat import compat_urllib_parse from ..utils import ( ExtractorError, remove_start, + sanitized_Request, ) @@ -81,7 +79,7 @@ class MonikerIE(InfoExtractor): orig_webpage, 'builtin URL', default=None, group='url') if builtin_url: - req = compat_urllib_request.Request(builtin_url) + req = sanitized_Request(builtin_url) req.add_header('Referer', url) webpage = self._download_webpage(req, video_id, 'Downloading builtin page') title = self._og_search_title(orig_webpage).strip() @@ -94,7 +92,7 @@ class MonikerIE(InfoExtractor): headers = { b'Content-Type': b'application/x-www-form-urlencoded', } - req = compat_urllib_request.Request(url, post, headers) + req = sanitized_Request(url, post, headers) webpage = self._download_webpage( req, video_id, note='Downloading video page ...') diff --git a/youtube_dl/extractor/mooshare.py b/youtube_dl/extractor/mooshare.py index 7603af5e2..7cc7f054f 100644 --- a/youtube_dl/extractor/mooshare.py +++ b/youtube_dl/extractor/mooshare.py @@ -3,12 +3,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_request, - compat_urllib_parse, -) +from ..compat import compat_urllib_parse from ..utils import ( ExtractorError, + sanitized_Request, ) @@ -59,7 +57,7 @@ class MooshareIE(InfoExtractor): 'hash': hash_key, } - request = compat_urllib_request.Request( + request = sanitized_Request( 'http://mooshare.biz/%s' % video_id, compat_urllib_parse.urlencode(download_form)) request.add_header('Content-Type', 'application/x-www-form-urlencoded') diff --git a/youtube_dl/extractor/movieclips.py b/youtube_dl/extractor/movieclips.py index 04e17d055..1564cb71f 100644 --- a/youtube_dl/extractor/movieclips.py +++ b/youtube_dl/extractor/movieclips.py @@ -1,80 +1,40 @@ +# coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..compat import ( - compat_str, -) -from ..utils import ( - ExtractorError, - clean_html, -) +from ..utils import sanitized_Request class MovieClipsIE(InfoExtractor): - _VALID_URL = r'https?://movieclips\.com/(?P<id>[\da-zA-Z]+)(?:-(?P<display_id>[\da-z-]+))?' + _VALID_URL = r'https?://(?:www.)?movieclips\.com/videos/(?P<id>[^/?#]+)' _TEST = { - 'url': 'http://movieclips.com/Wy7ZU-my-week-with-marilyn-movie-do-you-love-me/', + 'url': 'http://www.movieclips.com/videos/warcraft-trailer-1-561180739597?autoPlay=true&playlistId=5', 'info_dict': { - 'id': 'Wy7ZU', - 'display_id': 'my-week-with-marilyn-movie-do-you-love-me', + 'id': 'pKIGmG83AqD9', + 'display_id': 'warcraft-trailer-1-561180739597', 'ext': 'mp4', - 'title': 'My Week with Marilyn - Do You Love Me?', - 'description': 'md5:e86795bd332fe3cff461e7c8dc542acb', + 'title': 'Warcraft Trailer 1', + 'description': 'Watch Trailer 1 from Warcraft (2016). Legendary’s WARCRAFT is a 3D epic adventure of world-colliding conflict based.', 'thumbnail': 're:^https?://.*\.jpg$', }, - 'params': { - # rtmp download - 'skip_download': True, - } + 'add_ie': ['ThePlatform'], } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - display_id = mobj.group('display_id') - show_id = display_id or video_id - - config = self._download_xml( - 'http://config.movieclips.com/player/config/%s' % video_id, - show_id, 'Downloading player config') - - if config.find('./country-region').text == 'false': - raise ExtractorError( - '%s said: %s' % (self.IE_NAME, config.find('./region_alert').text), expected=True) - - properties = config.find('./video/properties') - smil_file = properties.attrib['smil_file'] + display_id = self._match_id(url) - smil = self._download_xml(smil_file, show_id, 'Downloading SMIL') - base_url = smil.find('./head/meta').attrib['base'] - - formats = [] - for video in smil.findall('./body/switch/video'): - vbr = int(video.attrib['system-bitrate']) / 1000 - src = video.attrib['src'] - formats.append({ - 'url': base_url, - 'play_path': src, - 'ext': src.split(':')[0], - 'vbr': vbr, - 'format_id': '%dk' % vbr, - }) - - self._sort_formats(formats) - - title = '%s - %s' % (properties.attrib['clip_movie_title'], properties.attrib['clip_title']) - description = clean_html(compat_str(properties.attrib['clip_description'])) - thumbnail = properties.attrib['image'] - categories = properties.attrib['clip_categories'].split(',') + req = sanitized_Request(url) + # it doesn't work if it thinks the browser it's too old + req.add_header('User-Agent', 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/43.0 (Chrome)') + webpage = self._download_webpage(req, display_id) + theplatform_link = self._html_search_regex(r'src="(http://player.theplatform.com/p/.*?)"', webpage, 'theplatform link') + title = self._html_search_regex(r'<title[^>]*>([^>]+)-\s*\d+\s*|\s*Movieclips.com</title>', webpage, 'title') + description = self._html_search_meta('description', webpage) return { - 'id': video_id, - 'display_id': display_id, + '_type': 'url_transparent', + 'url': theplatform_link, 'title': title, + 'display_id': display_id, 'description': description, - 'thumbnail': thumbnail, - 'categories': categories, - 'formats': formats, } diff --git a/youtube_dl/extractor/movshare.py b/youtube_dl/extractor/movshare.py deleted file mode 100644 index 6101063f2..000000000 --- a/youtube_dl/extractor/movshare.py +++ /dev/null @@ -1,27 +0,0 @@ -from __future__ import unicode_literals - -from .novamov import NovaMovIE - - -class MovShareIE(NovaMovIE): - IE_NAME = 'movshare' - IE_DESC = 'MovShare' - - _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'movshare\.(?:net|sx|ag)'} - - _HOST = 'www.movshare.net' - - _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' - _TITLE_REGEX = r'<strong>Title:</strong> ([^<]+)</p>' - _DESCRIPTION_REGEX = r'<strong>Description:</strong> ([^<]+)</p>' - - _TEST = { - 'url': 'http://www.movshare.net/video/559e28be54d96', - 'md5': 'abd31a2132947262c50429e1d16c1bfd', - 'info_dict': { - 'id': '559e28be54d96', - 'ext': 'flv', - 'title': 'dissapeared image', - 'description': 'optical illusion dissapeared image magic illusion', - } - } diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index 302c9bf35..d887583e6 100644 --- a/youtube_dl/extractor/mtv.py +++ b/youtube_dl/extractor/mtv.py @@ -5,7 +5,6 @@ import re from .common import InfoExtractor from ..compat import ( compat_urllib_parse, - compat_urllib_request, compat_str, ) from ..utils import ( @@ -13,6 +12,7 @@ from ..utils import ( find_xpath_attr, fix_xml_ampersands, HEADRequest, + sanitized_Request, unescapeHTML, url_basename, RegexNotFoundError, @@ -53,7 +53,7 @@ class MTVServicesInfoExtractor(InfoExtractor): def _extract_mobile_video_formats(self, mtvn_id): webpage_url = self._MOBILE_TEMPLATE % mtvn_id - req = compat_urllib_request.Request(webpage_url) + req = sanitized_Request(webpage_url) # Otherwise we get a webpage that would execute some javascript req.add_header('User-Agent', 'curl/7') webpage = self._download_webpage(req, mtvn_id, diff --git a/youtube_dl/extractor/myvideo.py b/youtube_dl/extractor/myvideo.py index c96f472a3..36ab388b2 100644 --- a/youtube_dl/extractor/myvideo.py +++ b/youtube_dl/extractor/myvideo.py @@ -11,10 +11,10 @@ from ..compat import ( compat_ord, compat_urllib_parse, compat_urllib_parse_unquote, - compat_urllib_request, ) from ..utils import ( ExtractorError, + sanitized_Request, ) @@ -83,7 +83,7 @@ class MyVideoIE(InfoExtractor): mobj = re.search(r'data-video-service="/service/data/video/%s/config' % video_id, webpage) if mobj is not None: - request = compat_urllib_request.Request('http://www.myvideo.de/service/data/video/%s/config' % video_id, '') + request = sanitized_Request('http://www.myvideo.de/service/data/video/%s/config' % video_id, '') response = self._download_webpage(request, video_id, 'Downloading video info') info = json.loads(base64.b64decode(response).decode('utf-8')) diff --git a/youtube_dl/extractor/nba.py b/youtube_dl/extractor/nba.py index 944096e1c..7c6b7841d 100644 --- a/youtube_dl/extractor/nba.py +++ b/youtube_dl/extractor/nba.py @@ -1,63 +1,102 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( - remove_end, parse_duration, + int_or_none, + xpath_text, + xpath_attr, ) class NBAIE(InfoExtractor): - _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video(?P<id>/[^?]*?)/?(?:/index\.html)?(?:\?.*)?$' + _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?P<path>(?:[^/]+/)?video/(?P<id>[^?]*?))/?(?:/index\.html)?(?:\?.*)?$' _TESTS = [{ 'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html', - 'md5': 'c0edcfc37607344e2ff8f13c378c88a4', + 'md5': '9e7729d3010a9c71506fd1248f74e4f4', 'info_dict': { - 'id': '0021200253-okc-bkn-recap.nba', - 'ext': 'mp4', + 'id': '0021200253-okc-bkn-recap', + 'ext': 'flv', 'title': 'Thunder vs. Nets', 'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.', 'duration': 181, + 'timestamp': 1354638466, + 'upload_date': '20121204', }, }, { 'url': 'http://www.nba.com/video/games/hornets/2014/12/05/0021400276-nyk-cha-play5.nba/', 'only_matching': True, }, { - 'url': 'http://watch.nba.com/nba/video/channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba', + 'url': 'http://watch.nba.com/video/channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba', + 'md5': 'b2b39b81cf28615ae0c3360a3f9668c4', 'info_dict': { - 'id': '0041400301-cle-atl-recap.nba', + 'id': '0041400301-cle-atl-recap', 'ext': 'mp4', - 'title': 'NBA GAME TIME | Video: Hawks vs. Cavaliers Game 1', + 'title': 'Hawks vs. Cavaliers Game 1', 'description': 'md5:8094c3498d35a9bd6b1a8c396a071b4d', 'duration': 228, - }, - 'params': { - 'skip_download': True, + 'timestamp': 1432134543, + 'upload_date': '20150520', } }] def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - video_url = 'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4' + path, video_id = re.match(self._VALID_URL, url).groups() + if path.startswith('nba/'): + path = path[3:] + video_info = self._download_xml('http://www.nba.com/%s.xml' % path, video_id) + video_id = xpath_text(video_info, 'slug') + title = xpath_text(video_info, 'headline') + description = xpath_text(video_info, 'description') + duration = parse_duration(xpath_text(video_info, 'length')) + timestamp = int_or_none(xpath_attr(video_info, 'dateCreated', 'uts')) - shortened_video_id = video_id.rpartition('/')[2] - title = remove_end( - self._og_search_title(webpage, default=shortened_video_id), ' : NBA.com') + thumbnails = [] + for image in video_info.find('images'): + thumbnails.append({ + 'id': image.attrib.get('cut'), + 'url': image.text, + 'width': int_or_none(image.attrib.get('width')), + 'height': int_or_none(image.attrib.get('height')), + }) - description = self._og_search_description(webpage) - duration_str = self._html_search_meta( - 'duration', webpage, 'duration', default=None) - if not duration_str: - duration_str = self._html_search_regex( - r'Duration:</b>\s*(\d+:\d+)', webpage, 'duration', fatal=False) - duration = parse_duration(duration_str) + formats = [] + for video_file in video_info.findall('.//file'): + video_url = video_file.text + if video_url.startswith('/'): + continue + if video_url.endswith('.m3u8'): + m3u8_formats = self._extract_m3u8_formats(video_url, video_id, m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + elif video_url.endswith('.f4m'): + f4m_formats = self._extract_f4m_formats(video_url + '?hdcore=3.4.1.1', video_id, f4m_id='hds', fatal=False) + if f4m_formats: + formats.extend(f4m_formats) + else: + key = video_file.attrib.get('bitrate') + format_info = { + 'format_id': key, + 'url': video_url, + } + mobj = re.search(r'(\d+)x(\d+)(?:_(\d+))?', key) + if mobj: + format_info.update({ + 'width': int(mobj.group(1)), + 'height': int(mobj.group(2)), + 'tbr': int_or_none(mobj.group(3)), + }) + formats.append(format_info) + self._sort_formats(formats) return { - 'id': shortened_video_id, - 'url': video_url, + 'id': video_id, 'title': title, 'description': description, 'duration': duration, + 'timestamp': timestamp, + 'thumbnails': thumbnails, + 'formats': formats, } diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index e683d24c4..340c922bd 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -3,14 +3,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_str, - compat_HTTPError, -) +from ..compat import compat_HTTPError from ..utils import ( ExtractorError, find_xpath_attr, lowercase_escape, + smuggle_url, unescapeHTML, ) @@ -62,12 +60,13 @@ class NBCIE(InfoExtractor): theplatform_url = unescapeHTML(lowercase_escape(self._html_search_regex( [ r'(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"', + r'<iframe[^>]+src="((?:https?:)?//player\.theplatform\.com/[^"]+)"', r'"embedURL"\s*:\s*"([^"]+)"' ], webpage, 'theplatform url').replace('_no_endcard', '').replace('\\/', '/'))) if theplatform_url.startswith('//'): theplatform_url = 'http:' + theplatform_url - return self.url_result(theplatform_url) + return self.url_result(smuggle_url(theplatform_url, {'source_url': url})) class NBCSportsVPlayerIE(InfoExtractor): @@ -187,7 +186,7 @@ class NBCNewsIE(InfoExtractor): 'title': info.find('headline').text, 'ext': 'flv', 'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text, - 'description': compat_str(info.find('caption').text), + 'description': info.find('caption').text, 'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text, } else: diff --git a/youtube_dl/extractor/ndr.py b/youtube_dl/extractor/ndr.py index ba06d8a98..894c51399 100644 --- a/youtube_dl/extractor/ndr.py +++ b/youtube_dl/extractor/ndr.py @@ -23,7 +23,7 @@ class NDRBaseIE(InfoExtractor): class NDRIE(NDRBaseIE): IE_NAME = 'ndr' IE_DESC = 'NDR.de - Norddeutscher Rundfunk' - _VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)+(?P<id>[^/?#]+),[\da-z]+\.html' + _VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)*(?P<id>[^/?#]+),[\da-z]+\.html' _TESTS = [{ # httpVideo, same content id 'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html', @@ -78,6 +78,9 @@ class NDRIE(NDRBaseIE): 'params': { 'skip_download': True, }, + }, { + 'url': 'https://www.ndr.de/Fettes-Brot-Ferris-MC-und-Thees-Uhlmann-live-on-stage,festivalsommer116.html', + 'only_matching': True, }] def _extract_embed(self, webpage, display_id): @@ -85,10 +88,10 @@ class NDRIE(NDRBaseIE): 'embedURL', webpage, 'embed URL', fatal=True) description = self._search_regex( r'<p[^>]+itemprop="description">([^<]+)</p>', - webpage, 'description', fatal=False) + webpage, 'description', default=None) or self._og_search_description(webpage) timestamp = parse_iso8601( self._search_regex( - r'<span itemprop="datePublished" content="([^"]+)">', + r'<span[^>]+itemprop="(?:datePublished|uploadDate)"[^>]+content="([^"]+)"', webpage, 'upload date', fatal=False)) return { '_type': 'url_transparent', @@ -102,7 +105,7 @@ class NDRIE(NDRBaseIE): class NJoyIE(NDRBaseIE): IE_NAME = 'njoy' IE_DESC = 'N-JOY' - _VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)+(?:(?P<display_id>[^/?#]+),)?(?P<id>[\da-z]+)\.html' + _VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)*(?:(?P<display_id>[^/?#]+),)?(?P<id>[\da-z]+)\.html' _TESTS = [{ # httpVideo, same content id 'url': 'http://www.n-joy.de/entertainment/comedy/comedy_contest/Benaissa-beim-NDR-Comedy-Contest,comedycontest2480.html', @@ -235,7 +238,7 @@ class NDREmbedBaseIE(InfoExtractor): class NDREmbedIE(NDREmbedBaseIE): IE_NAME = 'ndr:embed' - _VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)+(?P<id>[\da-z]+)-(?:player|externalPlayer)\.html' + _VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)\.html' _TESTS = [{ 'url': 'http://www.ndr.de/fernsehen/sendungen/ndr_aktuell/ndraktuell28488-player.html', 'md5': '8b9306142fe65bbdefb5ce24edb6b0a9', @@ -329,7 +332,7 @@ class NDREmbedIE(NDREmbedBaseIE): class NJoyEmbedIE(NDREmbedBaseIE): IE_NAME = 'njoy:embed' - _VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)+(?P<id>[\da-z]+)-(?:player|externalPlayer)_[^/]+\.html' + _VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)_[^/]+\.html' _TESTS = [{ # httpVideo 'url': 'http://www.n-joy.de/events/reeperbahnfestival/doku948-player_image-bc168e87-5263-4d6d-bd27-bb643005a6de_theme-n-joy.html', diff --git a/youtube_dl/extractor/neteasemusic.py b/youtube_dl/extractor/neteasemusic.py index a8e0a64ed..15eca825a 100644 --- a/youtube_dl/extractor/neteasemusic.py +++ b/youtube_dl/extractor/neteasemusic.py @@ -8,11 +8,11 @@ import re from .common import InfoExtractor from ..compat import ( - compat_urllib_request, compat_urllib_parse, compat_str, compat_itertools_count, ) +from ..utils import sanitized_Request class NetEaseMusicBaseIE(InfoExtractor): @@ -40,7 +40,7 @@ class NetEaseMusicBaseIE(InfoExtractor): if not details: continue formats.append({ - 'url': 'http://m1.music.126.net/%s/%s.%s' % + 'url': 'http://m5.music.126.net/%s/%s.%s' % (cls._encrypt(details['dfsId']), details['dfsId'], details['extension']), 'ext': details.get('extension'), @@ -56,7 +56,7 @@ class NetEaseMusicBaseIE(InfoExtractor): return int(round(ms / 1000.0)) def query_api(self, endpoint, video_id, note): - req = compat_urllib_request.Request('%s%s' % (self._API_BASE, endpoint)) + req = sanitized_Request('%s%s' % (self._API_BASE, endpoint)) req.add_header('Referer', self._API_BASE) return self._download_json(req, video_id, note) diff --git a/youtube_dl/extractor/nfb.py b/youtube_dl/extractor/nfb.py index ea077254b..5bd15f7a7 100644 --- a/youtube_dl/extractor/nfb.py +++ b/youtube_dl/extractor/nfb.py @@ -1,10 +1,8 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import ( - compat_urllib_request, - compat_urllib_parse, -) +from ..compat import compat_urllib_parse +from ..utils import sanitized_Request class NFBIE(InfoExtractor): @@ -40,8 +38,9 @@ class NFBIE(InfoExtractor): uploader = self._html_search_regex(r'<em class="director-name" itemprop="name">([^<]+)</em>', page, 'director name', fatal=False) - request = compat_urllib_request.Request('https://www.nfb.ca/film/%s/player_config' % video_id, - compat_urllib_parse.urlencode({'getConfig': 'true'}).encode('ascii')) + request = sanitized_Request( + 'https://www.nfb.ca/film/%s/player_config' % video_id, + compat_urllib_parse.urlencode({'getConfig': 'true'}).encode('ascii')) request.add_header('Content-Type', 'application/x-www-form-urlencoded') request.add_header('X-NFB-Referer', 'http://www.nfb.ca/medias/flash/NFBVideoPlayer.swf') diff --git a/youtube_dl/extractor/niconico.py b/youtube_dl/extractor/niconico.py index bda1cff05..586e52a4a 100644 --- a/youtube_dl/extractor/niconico.py +++ b/youtube_dl/extractor/niconico.py @@ -8,7 +8,6 @@ import datetime from .common import InfoExtractor from ..compat import ( compat_urllib_parse, - compat_urllib_request, compat_urlparse, ) from ..utils import ( @@ -17,6 +16,7 @@ from ..utils import ( int_or_none, parse_duration, parse_iso8601, + sanitized_Request, xpath_text, determine_ext, ) @@ -102,7 +102,7 @@ class NiconicoIE(InfoExtractor): 'password': password, } login_data = compat_urllib_parse.urlencode(encode_dict(login_form_strs)).encode('utf-8') - request = compat_urllib_request.Request( + request = sanitized_Request( 'https://secure.nicovideo.jp/secure/login', login_data) login_results = self._download_webpage( request, None, note='Logging in', errnote='Unable to log in') @@ -145,7 +145,7 @@ class NiconicoIE(InfoExtractor): 'k': thumb_play_key, 'v': video_id }) - flv_info_request = compat_urllib_request.Request( + flv_info_request = sanitized_Request( 'http://ext.nicovideo.jp/thumb_watch', flv_info_data, {'Content-Type': 'application/x-www-form-urlencoded'}) flv_info_webpage = self._download_webpage( diff --git a/youtube_dl/extractor/noco.py b/youtube_dl/extractor/noco.py index a53e27b27..d440313d5 100644 --- a/youtube_dl/extractor/noco.py +++ b/youtube_dl/extractor/noco.py @@ -9,7 +9,7 @@ from .common import InfoExtractor from ..compat import ( compat_str, compat_urllib_parse, - compat_urllib_request, + compat_urlparse, ) from ..utils import ( clean_html, @@ -17,6 +17,7 @@ from ..utils import ( int_or_none, float_or_none, parse_iso8601, + sanitized_Request, ) @@ -74,7 +75,7 @@ class NocoIE(InfoExtractor): 'username': username, 'password': password, } - request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) + request = sanitized_Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) request.add_header('Content-Type', 'application/x-www-form-urlencoded; charset=UTF-8') login = self._download_json(request, None, 'Logging in as %s' % username) @@ -82,14 +83,21 @@ class NocoIE(InfoExtractor): if 'erreur' in login: raise ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True) + @staticmethod + def _ts(): + return int(time.time() * 1000) + def _call_api(self, path, video_id, note, sub_lang=None): - ts = compat_str(int(time.time() * 1000)) + ts = compat_str(self._ts() + self._ts_offset) tk = hashlib.md5((hashlib.md5(ts.encode('ascii')).hexdigest() + '#8S?uCraTedap6a').encode('ascii')).hexdigest() url = self._API_URL_TEMPLATE % (path, ts, tk) if sub_lang: url += self._SUB_LANG_TEMPLATE % sub_lang - resp = self._download_json(url, video_id, note) + request = sanitized_Request(url) + request.add_header('Referer', self._referer) + + resp = self._download_json(request, video_id, note) if isinstance(resp, dict) and resp.get('error'): self._raise_error(resp['error'], resp['description']) @@ -102,8 +110,22 @@ class NocoIE(InfoExtractor): expected=True) def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) + + # Timestamp adjustment offset between server time and local time + # must be calculated in order to use timestamps closest to server's + # in all API requests (see https://github.com/rg3/youtube-dl/issues/7864) + webpage = self._download_webpage(url, video_id) + + player_url = self._search_regex( + r'(["\'])(?P<player>https?://noco\.tv/(?:[^/]+/)+NocoPlayer.+?\.swf.*?)\1', + webpage, 'noco player', group='player', + default='http://noco.tv/cdata/js/player/NocoPlayer-v1.2.40.swf') + + qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(player_url).query) + ts = int_or_none(qs.get('ts', [None])[0]) + self._ts_offset = ts - self._ts() if ts else 0 + self._referer = player_url medias = self._call_api( 'shows/%s/medias' % video_id, @@ -155,8 +177,8 @@ class NocoIE(InfoExtractor): 'format_id': format_id_extended, 'width': int_or_none(fmt.get('res_width')), 'height': int_or_none(fmt.get('res_lines')), - 'abr': int_or_none(fmt.get('audiobitrate')), - 'vbr': int_or_none(fmt.get('videobitrate')), + 'abr': int_or_none(fmt.get('audiobitrate'), 1000), + 'vbr': int_or_none(fmt.get('videobitrate'), 1000), 'filesize': int_or_none(fmt.get('filesize')), 'format_note': qualities[format_id].get('quality_name'), 'quality': qualities[format_id].get('priority'), diff --git a/youtube_dl/extractor/nosvideo.py b/youtube_dl/extractor/nosvideo.py index f5ef856db..eab816e49 100644 --- a/youtube_dl/extractor/nosvideo.py +++ b/youtube_dl/extractor/nosvideo.py @@ -4,11 +4,9 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_request, -) from ..utils import ( ExtractorError, + sanitized_Request, urlencode_postdata, xpath_text, xpath_with_ns, @@ -41,7 +39,7 @@ class NosVideoIE(InfoExtractor): 'op': 'download1', 'method_free': 'Continue to Video', } - req = compat_urllib_request.Request(url, urlencode_postdata(fields)) + req = sanitized_Request(url, urlencode_postdata(fields)) req.add_header('Content-type', 'application/x-www-form-urlencoded') webpage = self._download_webpage(req, video_id, 'Downloading download page') diff --git a/youtube_dl/extractor/novamov.py b/youtube_dl/extractor/novamov.py index 04d779890..d68c1ad79 100644 --- a/youtube_dl/extractor/novamov.py +++ b/youtube_dl/extractor/novamov.py @@ -3,11 +3,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urlparse, -) +from ..compat import compat_urlparse from ..utils import ( ExtractorError, + NO_DEFAULT, + encode_dict, + sanitized_Request, + urlencode_postdata, ) @@ -15,15 +17,16 @@ class NovaMovIE(InfoExtractor): IE_NAME = 'novamov' IE_DESC = 'NovaMov' - _VALID_URL_TEMPLATE = r'http://(?:(?:www\.)?%(host)s/(?:file|video)/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<id>[a-z\d]{13})' + _VALID_URL_TEMPLATE = r'http://(?:(?:www\.)?%(host)s/(?:file|video|mobile/#/videos)/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<id>[a-z\d]{13})' _VALID_URL = _VALID_URL_TEMPLATE % {'host': 'novamov\.com'} _HOST = 'www.novamov.com' _FILE_DELETED_REGEX = r'This file no longer exists on our servers!</h2>' - _FILEKEY_REGEX = r'flashvars\.filekey="(?P<filekey>[^"]+)";' + _FILEKEY_REGEX = r'flashvars\.filekey=(?P<filekey>"?[^"]+"?);' _TITLE_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>' _DESCRIPTION_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>' + _URL_TEMPLATE = 'http://%s/video/%s' _TEST = { 'url': 'http://www.novamov.com/video/4rurhn9x446jj', @@ -37,20 +40,50 @@ class NovaMovIE(InfoExtractor): 'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)' } - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - page = self._download_webpage( - 'http://%s/video/%s' % (self._HOST, video_id), video_id, 'Downloading video page') - - if re.search(self._FILE_DELETED_REGEX, page) is not None: + def _check_existence(self, webpage, video_id): + if re.search(self._FILE_DELETED_REGEX, webpage) is not None: raise ExtractorError('Video %s does not exist' % video_id, expected=True) - filekey = self._search_regex(self._FILEKEY_REGEX, page, 'filekey') - - title = self._html_search_regex(self._TITLE_REGEX, page, 'title', fatal=False) - description = self._html_search_regex(self._DESCRIPTION_REGEX, page, 'description', default='', fatal=False) + def _real_extract(self, url): + video_id = self._match_id(url) + + url = self._URL_TEMPLATE % (self._HOST, video_id) + + webpage = self._download_webpage( + url, video_id, 'Downloading video page') + + self._check_existence(webpage, video_id) + + def extract_filekey(default=NO_DEFAULT): + filekey = self._search_regex( + self._FILEKEY_REGEX, webpage, 'filekey', default=default) + if filekey is not default and (filekey[0] != '"' or filekey[-1] != '"'): + return self._search_regex( + r'var\s+%s\s*=\s*"([^"]+)"' % re.escape(filekey), webpage, 'filekey', default=default) + else: + return filekey + + filekey = extract_filekey(default=None) + + if not filekey: + fields = self._hidden_inputs(webpage) + post_url = self._search_regex( + r'<form[^>]+action=(["\'])(?P<url>.+?)\1', webpage, + 'post url', default=url, group='url') + if not post_url.startswith('http'): + post_url = compat_urlparse.urljoin(url, post_url) + request = sanitized_Request( + post_url, urlencode_postdata(encode_dict(fields))) + request.add_header('Content-Type', 'application/x-www-form-urlencoded') + request.add_header('Referer', post_url) + webpage = self._download_webpage( + request, video_id, 'Downloading continue to the video page') + self._check_existence(webpage, video_id) + + filekey = extract_filekey() + + title = self._html_search_regex(self._TITLE_REGEX, webpage, 'title', fatal=False) + description = self._html_search_regex(self._DESCRIPTION_REGEX, webpage, 'description', default='', fatal=False) api_response = self._download_webpage( 'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id, @@ -69,3 +102,89 @@ class NovaMovIE(InfoExtractor): 'title': title, 'description': description } + + +class WholeCloudIE(NovaMovIE): + IE_NAME = 'wholecloud' + IE_DESC = 'WholeCloud' + + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': '(?:wholecloud\.net|movshare\.(?:net|sx|ag))'} + + _HOST = 'www.wholecloud.net' + + _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' + _TITLE_REGEX = r'<strong>Title:</strong> ([^<]+)</p>' + _DESCRIPTION_REGEX = r'<strong>Description:</strong> ([^<]+)</p>' + + _TEST = { + 'url': 'http://www.wholecloud.net/video/559e28be54d96', + 'md5': 'abd31a2132947262c50429e1d16c1bfd', + 'info_dict': { + 'id': '559e28be54d96', + 'ext': 'flv', + 'title': 'dissapeared image', + 'description': 'optical illusion dissapeared image magic illusion', + } + } + + +class NowVideoIE(NovaMovIE): + IE_NAME = 'nowvideo' + IE_DESC = 'NowVideo' + + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:to|ch|ec|sx|eu|at|ag|co|li)'} + + _HOST = 'www.nowvideo.to' + + _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' + _TITLE_REGEX = r'<h4>([^<]+)</h4>' + _DESCRIPTION_REGEX = r'</h4>\s*<p>([^<]+)</p>' + + _TEST = { + 'url': 'http://www.nowvideo.sx/video/f1d6fce9a968b', + 'md5': '12c82cad4f2084881d8bc60ee29df092', + 'info_dict': { + 'id': 'f1d6fce9a968b', + 'ext': 'flv', + 'title': 'youtubedl test video BaWjenozKc', + 'description': 'Description', + }, + } + + +class VideoWeedIE(NovaMovIE): + IE_NAME = 'videoweed' + IE_DESC = 'VideoWeed' + + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'videoweed\.(?:es|com)'} + + _HOST = 'www.videoweed.es' + + _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' + _TITLE_REGEX = r'<h1 class="text_shadow">([^<]+)</h1>' + _URL_TEMPLATE = 'http://%s/file/%s' + + _TEST = { + 'url': 'http://www.videoweed.es/file/b42178afbea14', + 'md5': 'abd31a2132947262c50429e1d16c1bfd', + 'info_dict': { + 'id': 'b42178afbea14', + 'ext': 'flv', + 'title': 'optical illusion dissapeared image magic illusion', + 'description': '' + }, + } + + +class CloudTimeIE(NovaMovIE): + IE_NAME = 'cloudtime' + IE_DESC = 'CloudTime' + + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'cloudtime\.to'} + + _HOST = 'www.cloudtime.to' + + _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' + _TITLE_REGEX = r'<div[^>]+class=["\']video_det["\'][^>]*>\s*<strong>([^<]+)</strong>' + + _TEST = None diff --git a/youtube_dl/extractor/nowness.py b/youtube_dl/extractor/nowness.py index b97f62fdb..446f5901c 100644 --- a/youtube_dl/extractor/nowness.py +++ b/youtube_dl/extractor/nowness.py @@ -1,12 +1,15 @@ # encoding: utf-8 from __future__ import unicode_literals -from .brightcove import BrightcoveIE +from .brightcove import ( + BrightcoveLegacyIE, + BrightcoveNewIE, +) from .common import InfoExtractor -from ..utils import ExtractorError -from ..compat import ( - compat_str, - compat_urllib_request, +from ..compat import compat_str +from ..utils import ( + ExtractorError, + sanitized_Request, ) @@ -22,10 +25,13 @@ class NownessBaseIE(InfoExtractor): 'http://www.nowness.com/iframe?id=%s' % video_id, video_id, note='Downloading player JavaScript', errnote='Unable to download player JavaScript') - bc_url = BrightcoveIE._extract_brightcove_url(player_code) - if bc_url is None: - raise ExtractorError('Could not find player definition') - return self.url_result(bc_url, 'Brightcove') + bc_url = BrightcoveLegacyIE._extract_brightcove_url(player_code) + if bc_url: + return self.url_result(bc_url, BrightcoveLegacyIE.ie_key()) + bc_url = BrightcoveNewIE._extract_url(player_code) + if bc_url: + return self.url_result(bc_url, BrightcoveNewIE.ie_key()) + raise ExtractorError('Could not find player definition') elif source == 'vimeo': return self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo') elif source == 'youtube': @@ -37,7 +43,7 @@ class NownessBaseIE(InfoExtractor): def _api_request(self, url, request_path): display_id = self._match_id(url) - request = compat_urllib_request.Request( + request = sanitized_Request( 'http://api.nowness.com/api/' + request_path % display_id, headers={ 'X-Nowness-Language': 'zh-cn' if 'cn.nowness.com' in url else 'en-us', diff --git a/youtube_dl/extractor/nowtv.py b/youtube_dl/extractor/nowtv.py index b0bdffc4e..fd107aca2 100644 --- a/youtube_dl/extractor/nowtv.py +++ b/youtube_dl/extractor/nowtv.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..compat import compat_str from ..utils import ( @@ -13,8 +15,63 @@ from ..utils import ( ) -class NowTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<id>.+?)/(?:player|preview)' +class NowTVBaseIE(InfoExtractor): + _VIDEO_FIELDS = ( + 'id', 'title', 'free', 'geoblocked', 'articleLong', 'articleShort', + 'broadcastStartDate', 'seoUrl', 'duration', 'files', + 'format.defaultImage169Format', 'format.defaultImage169Logo') + + def _extract_video(self, info, display_id=None): + video_id = compat_str(info['id']) + + files = info['files'] + if not files: + if info.get('geoblocked', False): + raise ExtractorError( + 'Video %s is not available from your location due to geo restriction' % video_id, + expected=True) + if not info.get('free', True): + raise ExtractorError( + 'Video %s is not available for free' % video_id, expected=True) + + formats = [] + for item in files['items']: + if determine_ext(item['path']) != 'f4v': + continue + app, play_path = remove_start(item['path'], '/').split('/', 1) + formats.append({ + 'url': 'rtmpe://fms.rtl.de', + 'app': app, + 'play_path': 'mp4:%s' % play_path, + 'ext': 'flv', + 'page_url': 'http://rtlnow.rtl.de', + 'player_url': 'http://cdn.static-fra.de/now/vodplayer.swf', + 'tbr': int_or_none(item.get('bitrate')), + }) + self._sort_formats(formats) + + title = info['title'] + description = info.get('articleLong') or info.get('articleShort') + timestamp = parse_iso8601(info.get('broadcastStartDate'), ' ') + duration = parse_duration(info.get('duration')) + + f = info.get('format', {}) + thumbnail = f.get('defaultImage169Format') or f.get('defaultImage169Logo') + + return { + 'id': video_id, + 'display_id': display_id or info.get('seoUrl'), + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'formats': formats, + } + + +class NowTVIE(NowTVBaseIE): + _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/(?:(?:list/[^/]+|jahr/\d{4}/\d{1,2})/)?(?P<id>[^/]+)/(?:player|preview)' _TESTS = [{ # rtl @@ -23,7 +80,7 @@ class NowTVIE(InfoExtractor): 'id': '203519', 'display_id': 'bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit', 'ext': 'flv', - 'title': 'Die neuen Bauern und eine Hochzeit', + 'title': 'Inka Bause stellt die neuen Bauern vor', 'description': 'md5:e234e1ed6d63cf06be5c070442612e7e', 'thumbnail': 're:^https?://.*\.jpg$', 'timestamp': 1432580700, @@ -133,61 +190,71 @@ class NowTVIE(InfoExtractor): }, { 'url': 'http://www.nowtv.de/rtl2/echtzeit/list/aktuell/schnelles-geld-am-ende-der-welt/player', 'only_matching': True, + }, { + 'url': 'http://www.nowtv.de/rtl2/zuhause-im-glueck/jahr/2015/11/eine-erschuetternde-diagnose/player', + 'only_matching': True, }] def _real_extract(self, url): - display_id = self._match_id(url) - display_id_split = display_id.split('/') - if len(display_id) > 2: - display_id = '/'.join((display_id_split[0], display_id_split[-1])) + mobj = re.match(self._VALID_URL, url) + display_id = '%s/%s' % (mobj.group('show_id'), mobj.group('id')) info = self._download_json( - 'https://api.nowtv.de/v3/movies/%s?fields=id,title,free,geoblocked,articleLong,articleShort,broadcastStartDate,seoUrl,duration,format,files' % display_id, - display_id) + 'https://api.nowtv.de/v3/movies/%s?fields=%s' + % (display_id, ','.join(self._VIDEO_FIELDS)), display_id) - video_id = compat_str(info['id']) + return self._extract_video(info, display_id) - files = info['files'] - if not files: - if info.get('geoblocked', False): - raise ExtractorError( - 'Video %s is not available from your location due to geo restriction' % video_id, - expected=True) - if not info.get('free', True): - raise ExtractorError( - 'Video %s is not available for free' % video_id, expected=True) - formats = [] - for item in files['items']: - if determine_ext(item['path']) != 'f4v': - continue - app, play_path = remove_start(item['path'], '/').split('/', 1) - formats.append({ - 'url': 'rtmpe://fms.rtl.de', - 'app': app, - 'play_path': 'mp4:%s' % play_path, - 'ext': 'flv', - 'page_url': 'http://rtlnow.rtl.de', - 'player_url': 'http://cdn.static-fra.de/now/vodplayer.swf', - 'tbr': int_or_none(item.get('bitrate')), - }) - self._sort_formats(formats) +class NowTVListIE(NowTVBaseIE): + _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/list/(?P<id>[^?/#&]+)$' - title = info['title'] - description = info.get('articleLong') or info.get('articleShort') - timestamp = parse_iso8601(info.get('broadcastStartDate'), ' ') - duration = parse_duration(info.get('duration')) + _SHOW_FIELDS = ('title', ) + _SEASON_FIELDS = ('id', 'headline', 'seoheadline', ) - f = info.get('format', {}) - thumbnail = f.get('defaultImage169Format') or f.get('defaultImage169Logo') + _TESTS = [{ + 'url': 'http://www.nowtv.at/rtl/stern-tv/list/aktuell', + 'info_dict': { + 'id': '17006', + 'title': 'stern TV - Aktuell', + }, + 'playlist_count': 1, + }, { + 'url': 'http://www.nowtv.at/rtl/das-supertalent/list/free-staffel-8', + 'info_dict': { + 'id': '20716', + 'title': 'Das Supertalent - FREE Staffel 8', + }, + 'playlist_count': 14, + }] - return { - 'id': video_id, - 'display_id': display_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'timestamp': timestamp, - 'duration': duration, - 'formats': formats, - } + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + show_id = mobj.group('show_id') + season_id = mobj.group('id') + + fields = [] + fields.extend(self._SHOW_FIELDS) + fields.extend('formatTabs.%s' % field for field in self._SEASON_FIELDS) + fields.extend( + 'formatTabs.formatTabPages.container.movies.%s' % field + for field in self._VIDEO_FIELDS) + + list_info = self._download_json( + 'https://api.nowtv.de/v3/formats/seo?fields=%s&name=%s.php' + % (','.join(fields), show_id), + season_id) + + season = next( + season for season in list_info['formatTabs']['items'] + if season.get('seoheadline') == season_id) + + title = '%s - %s' % (list_info['title'], season['headline']) + + entries = [] + for container in season['formatTabPages']['items']: + for info in ((container.get('container') or {}).get('movies') or {}).get('items') or []: + entries.append(self._extract_video(info)) + + return self.playlist_result( + entries, compat_str(season.get('id') or season_id), title) diff --git a/youtube_dl/extractor/nowvideo.py b/youtube_dl/extractor/nowvideo.py deleted file mode 100644 index 17baa9679..000000000 --- a/youtube_dl/extractor/nowvideo.py +++ /dev/null @@ -1,28 +0,0 @@ -from __future__ import unicode_literals - -from .novamov import NovaMovIE - - -class NowVideoIE(NovaMovIE): - IE_NAME = 'nowvideo' - IE_DESC = 'NowVideo' - - _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:ch|ec|sx|eu|at|ag|co|li)'} - - _HOST = 'www.nowvideo.ch' - - _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' - _FILEKEY_REGEX = r'var fkzd="([^"]+)";' - _TITLE_REGEX = r'<h4>([^<]+)</h4>' - _DESCRIPTION_REGEX = r'</h4>\s*<p>([^<]+)</p>' - - _TEST = { - 'url': 'http://www.nowvideo.ch/video/0mw0yow7b6dxa', - 'md5': 'f8fbbc8add72bd95b7850c6a02fc8817', - 'info_dict': { - 'id': '0mw0yow7b6dxa', - 'ext': 'flv', - 'title': 'youtubedl test video _BaW_jenozKc.mp4', - 'description': 'Description', - } - } diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index 8ac38a174..6ff13050d 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -6,6 +6,7 @@ import re from .common import InfoExtractor from ..compat import compat_urlparse from ..utils import ( + determine_ext, ExtractorError, float_or_none, parse_duration, @@ -48,12 +49,22 @@ class NRKIE(InfoExtractor): 'http://v8.psapi.nrk.no/mediaelement/%s' % video_id, video_id, 'Downloading media JSON') - if data['usageRights']['isGeoBlocked']: - raise ExtractorError( - 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge', - expected=True) + media_url = data.get('mediaUrl') - video_url = data['mediaUrl'] + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81' + if not media_url: + if data['usageRights']['isGeoBlocked']: + raise ExtractorError( + 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge', + expected=True) + + if determine_ext(media_url) == 'f4m': + formats = self._extract_f4m_formats( + media_url + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81', video_id, f4m_id='hds') + else: + formats = [{ + 'url': media_url, + 'ext': 'flv', + }] duration = parse_duration(data.get('duration')) @@ -67,12 +78,11 @@ class NRKIE(InfoExtractor): return { 'id': video_id, - 'url': video_url, - 'ext': 'flv', 'title': data['title'], 'description': data['description'], 'duration': duration, 'thumbnail': thumbnail, + 'formats': formats, } diff --git a/youtube_dl/extractor/nuvid.py b/youtube_dl/extractor/nuvid.py index 57928f2ae..9fa7cefad 100644 --- a/youtube_dl/extractor/nuvid.py +++ b/youtube_dl/extractor/nuvid.py @@ -3,11 +3,9 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_request, -) from ..utils import ( parse_duration, + sanitized_Request, unified_strdate, ) @@ -33,7 +31,7 @@ class NuvidIE(InfoExtractor): formats = [] for dwnld_speed, format_id in [(0, '3gp'), (5, 'mp4')]: - request = compat_urllib_request.Request( + request = sanitized_Request( 'http://m.nuvid.com/play/%s' % video_id) request.add_header('Cookie', 'skip_download_page=1; dwnld_speed=%d; adv_show=1' % dwnld_speed) webpage = self._download_webpage( diff --git a/youtube_dl/extractor/ooyala.py b/youtube_dl/extractor/ooyala.py index a262a9f6d..8603fd692 100644 --- a/youtube_dl/extractor/ooyala.py +++ b/youtube_dl/extractor/ooyala.py @@ -1,108 +1,78 @@ from __future__ import unicode_literals import re -import json import base64 from .common import InfoExtractor from ..utils import ( - unescapeHTML, - ExtractorError, - determine_ext, int_or_none, + float_or_none, + ExtractorError, + unsmuggle_url, ) +from ..compat import compat_urllib_parse class OoyalaBaseIE(InfoExtractor): - def _extract_result(self, info, more_info): - embedCode = info['embedCode'] - video_url = info.get('ipad_url') or info['url'] - - if determine_ext(video_url) == 'm3u8': - formats = self._extract_m3u8_formats(video_url, embedCode, ext='mp4') - else: - formats = [{ - 'url': video_url, - 'ext': 'mp4', - }] - - return { - 'id': embedCode, - 'title': unescapeHTML(info['title']), - 'formats': formats, - 'description': unescapeHTML(more_info['description']), - 'thumbnail': more_info['promo'], + def _extract(self, content_tree_url, video_id, domain='example.org'): + content_tree = self._download_json(content_tree_url, video_id)['content_tree'] + metadata = content_tree[list(content_tree)[0]] + embed_code = metadata['embed_code'] + pcode = metadata.get('asset_pcode') or embed_code + video_info = { + 'id': embed_code, + 'title': metadata['title'], + 'description': metadata.get('description'), + 'thumbnail': metadata.get('thumbnail_image') or metadata.get('promo_image'), + 'duration': float_or_none(metadata.get('duration'), 1000), } - def _extract(self, player_url, video_id): - player = self._download_webpage(player_url, video_id) - mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="', - player, 'mobile player url') - # Looks like some videos are only available for particular devices - # (e.g. http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0 - # is only available for ipad) - # Working around with fetching URLs for all the devices found starting with 'unknown' - # until we succeed or eventually fail for each device. - devices = re.findall(r'device\s*=\s*"([^"]+)";', player) - devices.remove('unknown') - devices.insert(0, 'unknown') - for device in devices: - mobile_player = self._download_webpage( - '%s&device=%s' % (mobile_url, device), video_id, - 'Downloading mobile player JS for %s device' % device) - videos_info = self._search_regex( - r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);', - mobile_player, 'info', fatal=False, default=None) - if videos_info: - break - - if not videos_info: - formats = [] + urls = [] + formats = [] + for supported_format in ('mp4', 'm3u8', 'hds', 'rtmp'): auth_data = self._download_json( - 'http://player.ooyala.com/sas/player_api/v1/authorization/embed_code/%s/%s?domain=www.example.org&supportedFormats=mp4,webm' % (video_id, video_id), - video_id) - - cur_auth_data = auth_data['authorization_data'][video_id] - - for stream in cur_auth_data['streams']: - formats.append({ - 'url': base64.b64decode(stream['url']['data'].encode('ascii')).decode('utf-8'), - 'ext': stream.get('delivery_type'), - 'format': stream.get('video_codec'), - 'format_id': stream.get('profile'), - 'width': int_or_none(stream.get('width')), - 'height': int_or_none(stream.get('height')), - 'abr': int_or_none(stream.get('audio_bitrate')), - 'vbr': int_or_none(stream.get('video_bitrate')), - }) - if formats: - return { - 'id': video_id, - 'formats': formats, - 'title': 'Ooyala video', - } - - if not cur_auth_data['authorized']: - raise ExtractorError(cur_auth_data['message'], expected=True) - - if not videos_info: - raise ExtractorError('Unable to extract info') - videos_info = videos_info.replace('\\"', '"') - videos_more_info = self._search_regex( - r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"', '"') - videos_info = json.loads(videos_info) - videos_more_info = json.loads(videos_more_info) - - if videos_more_info.get('lineup'): - videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])] - return { - '_type': 'playlist', - 'id': video_id, - 'title': unescapeHTML(videos_more_info['title']), - 'entries': videos, - } - else: - return self._extract_result(videos_info[0], videos_more_info) + 'http://player.ooyala.com/sas/player_api/v1/authorization/embed_code/%s/%s?' % (pcode, embed_code) + compat_urllib_parse.urlencode({'domain': domain, 'supportedFormats': supported_format}), + video_id, 'Downloading %s JSON' % supported_format) + + cur_auth_data = auth_data['authorization_data'][embed_code] + + if cur_auth_data['authorized']: + for stream in cur_auth_data['streams']: + url = base64.b64decode(stream['url']['data'].encode('ascii')).decode('utf-8') + if url in urls: + continue + urls.append(url) + delivery_type = stream['delivery_type'] + if delivery_type == 'hls' or '.m3u8' in url: + m3u8_formats = self._extract_m3u8_formats(url, embed_code, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + elif delivery_type == 'hds' or '.f4m' in url: + f4m_formats = self._extract_f4m_formats(url, embed_code, f4m_id='hds', fatal=False) + if f4m_formats: + formats.extend(f4m_formats) + elif '.smil' in url: + smil_formats = self._extract_smil_formats(url, embed_code, fatal=False) + if smil_formats: + formats.extend(smil_formats) + else: + formats.append({ + 'url': url, + 'ext': stream.get('delivery_type'), + 'vcodec': stream.get('video_codec'), + 'format_id': delivery_type, + 'width': int_or_none(stream.get('width')), + 'height': int_or_none(stream.get('height')), + 'abr': int_or_none(stream.get('audio_bitrate')), + 'vbr': int_or_none(stream.get('video_bitrate')), + 'fps': float_or_none(stream.get('framerate')), + }) + else: + raise ExtractorError('%s said: %s' % (self.IE_NAME, cur_auth_data['message']), expected=True) + self._sort_formats(formats) + + video_info['formats'] = formats + return video_info class OoyalaIE(OoyalaBaseIE): @@ -117,6 +87,7 @@ class OoyalaIE(OoyalaBaseIE): 'ext': 'mp4', 'title': 'Explaining Data Recovery from Hard Drives and SSDs', 'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.', + 'duration': 853.386, }, }, { # Only available for ipad @@ -125,7 +96,7 @@ class OoyalaIE(OoyalaBaseIE): 'id': 'x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0', 'ext': 'mp4', 'title': 'Simulation Overview - Levels of Simulation', - 'description': '', + 'duration': 194.948, }, }, { @@ -136,7 +107,8 @@ class OoyalaIE(OoyalaBaseIE): 'info_dict': { 'id': 'FiOG81ZTrvckcchQxmalf4aQj590qTEx', 'ext': 'mp4', - 'title': 'Ooyala video', + 'title': 'Divide Tool Path.mp4', + 'duration': 204.405, } } ] @@ -151,9 +123,11 @@ class OoyalaIE(OoyalaBaseIE): ie=cls.ie_key()) def _real_extract(self, url): + url, smuggled_data = unsmuggle_url(url, {}) embed_code = self._match_id(url) - player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embed_code - return self._extract(player_url, embed_code) + domain = smuggled_data.get('domain') + content_tree_url = 'http://player.ooyala.com/player_api/v1/content_tree/embed_code/%s/%s' % (embed_code, embed_code) + return self._extract(content_tree_url, embed_code, domain) class OoyalaExternalIE(OoyalaBaseIE): @@ -170,7 +144,7 @@ class OoyalaExternalIE(OoyalaBaseIE): .*?&pcode= ) (?P<pcode>.+?) - (&|$) + (?:&|$) ''' _TEST = { @@ -179,7 +153,7 @@ class OoyalaExternalIE(OoyalaBaseIE): 'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG', 'ext': 'mp4', 'title': 'dm_140128_30for30Shorts___JudgingJewellv2', - 'description': '', + 'duration': 1302000, }, 'params': { # m3u8 download @@ -188,9 +162,6 @@ class OoyalaExternalIE(OoyalaBaseIE): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - partner_id = mobj.group('partner_id') - video_id = mobj.group('id') - pcode = mobj.group('pcode') - player_url = 'http://player.ooyala.com/player.js?externalId=%s:%s&pcode=%s' % (partner_id, video_id, pcode) - return self._extract(player_url, video_id) + partner_id, video_id, pcode = re.match(self._VALID_URL, url).groups() + content_tree_url = 'http://player.ooyala.com/player_api/v1/content_tree/external_id/%s/%s:%s' % (pcode, partner_id, video_id) + return self._extract(content_tree_url, video_id) diff --git a/youtube_dl/extractor/patreon.py b/youtube_dl/extractor/patreon.py index 6cdc2638b..ec8876c28 100644 --- a/youtube_dl/extractor/patreon.py +++ b/youtube_dl/extractor/patreon.py @@ -2,9 +2,7 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import ( - js_to_json, -) +from ..utils import js_to_json class PatreonIE(InfoExtractor): @@ -65,7 +63,7 @@ class PatreonIE(InfoExtractor): 'password': password, } - request = compat_urllib_request.Request( + request = sanitized_Request( 'https://www.patreon.com/processLogin', compat_urllib_parse.urlencode(login_form).encode('utf-8') ) diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index 3448736a2..744e4a09a 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -8,22 +8,188 @@ from ..utils import ( ExtractorError, determine_ext, int_or_none, + strip_jsonp, unified_strdate, US_RATINGS, ) class PBSIE(InfoExtractor): + _STATIONS = ( + (r'(?:video|www)\.pbs\.org', 'PBS: Public Broadcasting Service'), # http://www.pbs.org/ + (r'video\.aptv\.org', 'APT - Alabama Public Television (WBIQ)'), # http://aptv.org/ + (r'video\.gpb\.org', 'GPB/Georgia Public Broadcasting (WGTV)'), # http://www.gpb.org/ + (r'video\.mpbonline\.org', 'Mississippi Public Broadcasting (WMPN)'), # http://www.mpbonline.org + (r'video\.wnpt\.org', 'Nashville Public Television (WNPT)'), # http://www.wnpt.org + (r'video\.wfsu\.org', 'WFSU-TV (WFSU)'), # http://wfsu.org/ + (r'video\.wsre\.org', 'WSRE (WSRE)'), # http://www.wsre.org + (r'video\.wtcitv\.org', 'WTCI (WTCI)'), # http://www.wtcitv.org + (r'video\.pba\.org', 'WPBA/Channel 30 (WPBA)'), # http://pba.org/ + (r'video\.alaskapublic\.org', 'Alaska Public Media (KAKM)'), # http://alaskapublic.org/kakm + # (r'kuac\.org', 'KUAC (KUAC)'), # http://kuac.org/kuac-tv/ + # (r'ktoo\.org', '360 North (KTOO)'), # http://www.ktoo.org/ + # (r'azpm\.org', 'KUAT 6 (KUAT)'), # http://www.azpm.org/ + (r'video\.azpbs\.org', 'Arizona PBS (KAET)'), # http://www.azpbs.org + (r'portal\.knme\.org', 'KNME-TV/Channel 5 (KNME)'), # http://www.newmexicopbs.org/ + (r'video\.vegaspbs\.org', 'Vegas PBS (KLVX)'), # http://vegaspbs.org/ + (r'watch\.aetn\.org', 'AETN/ARKANSAS ETV NETWORK (KETS)'), # http://www.aetn.org/ + (r'video\.ket\.org', 'KET (WKLE)'), # http://www.ket.org/ + (r'video\.wkno\.org', 'WKNO/Channel 10 (WKNO)'), # http://www.wkno.org/ + (r'video\.lpb\.org', 'LPB/LOUISIANA PUBLIC BROADCASTING (WLPB)'), # http://www.lpb.org/ + (r'videos\.oeta\.tv', 'OETA (KETA)'), # http://www.oeta.tv + (r'video\.optv\.org', 'Ozarks Public Television (KOZK)'), # http://www.optv.org/ + (r'watch\.wsiu\.org', 'WSIU Public Broadcasting (WSIU)'), # http://www.wsiu.org/ + (r'video\.keet\.org', 'KEET TV (KEET)'), # http://www.keet.org + (r'pbs\.kixe\.org', 'KIXE/Channel 9 (KIXE)'), # http://kixe.org/ + (r'video\.kpbs\.org', 'KPBS San Diego (KPBS)'), # http://www.kpbs.org/ + (r'video\.kqed\.org', 'KQED (KQED)'), # http://www.kqed.org + (r'vids\.kvie\.org', 'KVIE Public Television (KVIE)'), # http://www.kvie.org + (r'video\.pbssocal\.org', 'PBS SoCal/KOCE (KOCE)'), # http://www.pbssocal.org/ + (r'video\.valleypbs\.org', 'ValleyPBS (KVPT)'), # http://www.valleypbs.org/ + (r'video\.cptv\.org', 'CONNECTICUT PUBLIC TELEVISION (WEDH)'), # http://cptv.org + (r'watch\.knpb\.org', 'KNPB Channel 5 (KNPB)'), # http://www.knpb.org/ + (r'video\.soptv\.org', 'SOPTV (KSYS)'), # http://www.soptv.org + # (r'klcs\.org', 'KLCS/Channel 58 (KLCS)'), # http://www.klcs.org + # (r'krcb\.org', 'KRCB Television & Radio (KRCB)'), # http://www.krcb.org + # (r'kvcr\.org', 'KVCR TV/DT/FM :: Vision for the Future (KVCR)'), # http://kvcr.org + (r'video\.rmpbs\.org', 'Rocky Mountain PBS (KRMA)'), # http://www.rmpbs.org + (r'video\.kenw\.org', 'KENW-TV3 (KENW)'), # http://www.kenw.org + (r'video\.kued\.org', 'KUED Channel 7 (KUED)'), # http://www.kued.org + (r'video\.wyomingpbs\.org', 'Wyoming PBS (KCWC)'), # http://www.wyomingpbs.org + (r'video\.cpt12\.org', 'Colorado Public Television / KBDI 12 (KBDI)'), # http://www.cpt12.org/ + (r'video\.kbyueleven\.org', 'KBYU-TV (KBYU)'), # http://www.kbyutv.org/ + (r'video\.thirteen\.org', 'Thirteen/WNET New York (WNET)'), # http://www.thirteen.org + (r'video\.wgbh\.org', 'WGBH/Channel 2 (WGBH)'), # http://wgbh.org + (r'video\.wgby\.org', 'WGBY (WGBY)'), # http://www.wgby.org + (r'watch\.njtvonline\.org', 'NJTV Public Media NJ (WNJT)'), # http://www.njtvonline.org/ + # (r'ripbs\.org', 'Rhode Island PBS (WSBE)'), # http://www.ripbs.org/home/ + (r'watch\.wliw\.org', 'WLIW21 (WLIW)'), # http://www.wliw.org/ + (r'video\.mpt\.tv', 'mpt/Maryland Public Television (WMPB)'), # http://www.mpt.org + (r'watch\.weta\.org', 'WETA Television and Radio (WETA)'), # http://www.weta.org + (r'video\.whyy\.org', 'WHYY (WHYY)'), # http://www.whyy.org + (r'video\.wlvt\.org', 'PBS 39 (WLVT)'), # http://www.wlvt.org/ + (r'video\.wvpt\.net', 'WVPT - Your Source for PBS and More! (WVPT)'), # http://www.wvpt.net + (r'video\.whut\.org', 'Howard University Television (WHUT)'), # http://www.whut.org + (r'video\.wedu\.org', 'WEDU PBS (WEDU)'), # http://www.wedu.org + (r'video\.wgcu\.org', 'WGCU Public Media (WGCU)'), # http://www.wgcu.org/ + # (r'wjct\.org', 'WJCT Public Broadcasting (WJCT)'), # http://www.wjct.org + (r'video\.wpbt2\.org', 'WPBT2 (WPBT)'), # http://www.wpbt2.org + (r'video\.wucftv\.org', 'WUCF TV (WUCF)'), # http://wucftv.org + (r'video\.wuft\.org', 'WUFT/Channel 5 (WUFT)'), # http://www.wuft.org + (r'watch\.wxel\.org', 'WXEL/Channel 42 (WXEL)'), # http://www.wxel.org/home/ + (r'video\.wlrn\.org', 'WLRN/Channel 17 (WLRN)'), # http://www.wlrn.org/ + (r'video\.wusf\.usf\.edu', 'WUSF Public Broadcasting (WUSF)'), # http://wusf.org/ + (r'video\.scetv\.org', 'ETV (WRLK)'), # http://www.scetv.org + (r'video\.unctv\.org', 'UNC-TV (WUNC)'), # http://www.unctv.org/ + # (r'pbsguam\.org', 'PBS Guam (KGTF)'), # http://www.pbsguam.org/ + (r'video\.pbshawaii\.org', 'PBS Hawaii - Oceanic Cable Channel 10 (KHET)'), # http://www.pbshawaii.org/ + (r'video\.idahoptv\.org', 'Idaho Public Television (KAID)'), # http://idahoptv.org + (r'video\.ksps\.org', 'KSPS (KSPS)'), # http://www.ksps.org/home/ + (r'watch\.opb\.org', 'OPB (KOPB)'), # http://www.opb.org + (r'watch\.nwptv\.org', 'KWSU/Channel 10 & KTNW/Channel 31 (KWSU)'), # http://www.kwsu.org + (r'video\.will\.illinois\.edu', 'WILL-TV (WILL)'), # http://will.illinois.edu/ + (r'video\.networkknowledge\.tv', 'Network Knowledge - WSEC/Springfield (WSEC)'), # http://www.wsec.tv + (r'video\.wttw\.com', 'WTTW11 (WTTW)'), # http://www.wttw.com/ + # (r'wtvp\.org', 'WTVP & WTVP.org, Public Media for Central Illinois (WTVP)'), # http://www.wtvp.org/ + (r'video\.iptv\.org', 'Iowa Public Television/IPTV (KDIN)'), # http://www.iptv.org/ + (r'video\.ninenet\.org', 'Nine Network (KETC)'), # http://www.ninenet.org + (r'video\.wfwa\.org', 'PBS39 Fort Wayne (WFWA)'), # http://wfwa.org/ + (r'video\.wfyi\.org', 'WFYI Indianapolis (WFYI)'), # http://www.wfyi.org + (r'video\.mptv\.org', 'Milwaukee Public Television (WMVS)'), # http://www.mptv.org + (r'video\.wnin\.org', 'WNIN (WNIN)'), # http://www.wnin.org/ + (r'video\.wnit\.org', 'WNIT Public Television (WNIT)'), # http://www.wnit.org/ + (r'video\.wpt\.org', 'WPT (WPNE)'), # http://www.wpt.org/ + (r'video\.wvut\.org', 'WVUT/Channel 22 (WVUT)'), # http://wvut.org/ + (r'video\.weiu\.net', 'WEIU/Channel 51 (WEIU)'), # http://www.weiu.net + (r'video\.wqpt\.org', 'WQPT-TV (WQPT)'), # http://www.wqpt.org + (r'video\.wycc\.org', 'WYCC PBS Chicago (WYCC)'), # http://www.wycc.org + # (r'lakeshorepublicmedia\.org', 'Lakeshore Public Television (WYIN)'), # http://lakeshorepublicmedia.org/ + (r'video\.wipb\.org', 'WIPB-TV (WIPB)'), # http://wipb.org + (r'video\.indianapublicmedia\.org', 'WTIU (WTIU)'), # http://indianapublicmedia.org/tv/ + (r'watch\.cetconnect\.org', 'CET (WCET)'), # http://www.cetconnect.org + (r'video\.thinktv\.org', 'ThinkTVNetwork (WPTD)'), # http://www.thinktv.org + (r'video\.wbgu\.org', 'WBGU-TV (WBGU)'), # http://wbgu.org + (r'video\.wgvu\.org', 'WGVU TV (WGVU)'), # http://www.wgvu.org/ + (r'video\.netnebraska\.org', 'NET1 (KUON)'), # http://netnebraska.org + (r'video\.pioneer\.org', 'Pioneer Public Television (KWCM)'), # http://www.pioneer.org + (r'watch\.sdpb\.org', 'SDPB Television (KUSD)'), # http://www.sdpb.org + (r'video\.tpt\.org', 'TPT (KTCA)'), # http://www.tpt.org + (r'watch\.ksmq\.org', 'KSMQ (KSMQ)'), # http://www.ksmq.org/ + (r'watch\.kpts\.org', 'KPTS/Channel 8 (KPTS)'), # http://www.kpts.org/ + (r'watch\.ktwu\.org', 'KTWU/Channel 11 (KTWU)'), # http://ktwu.org + # (r'shptv\.org', 'Smoky Hills Public Television (KOOD)'), # http://www.shptv.org + # (r'kcpt\.org', 'KCPT Kansas City Public Television (KCPT)'), # http://kcpt.org/ + # (r'blueridgepbs\.org', 'Blue Ridge PBS (WBRA)'), # http://www.blueridgepbs.org/ + (r'watch\.easttennesseepbs\.org', 'East Tennessee PBS (WSJK)'), # http://easttennesseepbs.org + (r'video\.wcte\.tv', 'WCTE-TV (WCTE)'), # http://www.wcte.org + (r'video\.wljt\.org', 'WLJT, Channel 11 (WLJT)'), # http://wljt.org/ + (r'video\.wosu\.org', 'WOSU TV (WOSU)'), # http://wosu.org/ + (r'video\.woub\.org', 'WOUB/WOUC (WOUB)'), # http://woub.org/tv/index.php?section=5 + (r'video\.wvpublic\.org', 'WVPB (WVPB)'), # http://wvpublic.org/ + (r'video\.wkyupbs\.org', 'WKYU-PBS (WKYU)'), # http://www.wkyupbs.org + # (r'wyes\.org', 'WYES-TV/New Orleans (WYES)'), # http://www.wyes.org + (r'video\.kera\.org', 'KERA 13 (KERA)'), # http://www.kera.org/ + (r'video\.mpbn\.net', 'MPBN (WCBB)'), # http://www.mpbn.net/ + (r'video\.mountainlake\.org', 'Mountain Lake PBS (WCFE)'), # http://www.mountainlake.org/ + (r'video\.nhptv\.org', 'NHPTV (WENH)'), # http://nhptv.org/ + (r'video\.vpt\.org', 'Vermont PBS (WETK)'), # http://www.vpt.org + (r'video\.witf\.org', 'witf (WITF)'), # http://www.witf.org + (r'watch\.wqed\.org', 'WQED Multimedia (WQED)'), # http://www.wqed.org/ + (r'video\.wmht\.org', 'WMHT Educational Telecommunications (WMHT)'), # http://www.wmht.org/home/ + (r'video\.deltabroadcasting\.org', 'Q-TV (WDCQ)'), # http://www.deltabroadcasting.org + (r'video\.dptv\.org', 'WTVS Detroit Public TV (WTVS)'), # http://www.dptv.org/ + (r'video\.wcmu\.org', 'CMU Public Television (WCMU)'), # http://www.wcmu.org + (r'video\.wkar\.org', 'WKAR-TV (WKAR)'), # http://wkar.org/ + (r'wnmuvideo\.nmu\.edu', 'WNMU-TV Public TV 13 (WNMU)'), # http://wnmutv.nmu.edu + (r'video\.wdse\.org', 'WDSE - WRPT (WDSE)'), # http://www.wdse.org/ + (r'video\.wgte\.org', 'WGTE TV (WGTE)'), # http://www.wgte.org + (r'video\.lptv\.org', 'Lakeland Public Television (KAWE)'), # http://www.lakelandptv.org + # (r'prairiepublic\.org', 'PRAIRIE PUBLIC (KFME)'), # http://www.prairiepublic.org/ + (r'video\.kmos\.org', 'KMOS-TV - Channels 6.1, 6.2 and 6.3 (KMOS)'), # http://www.kmos.org/ + (r'watch\.montanapbs\.org', 'MontanaPBS (KUSM)'), # http://montanapbs.org + (r'video\.krwg\.org', 'KRWG/Channel 22 (KRWG)'), # http://www.krwg.org + (r'video\.kacvtv\.org', 'KACV (KACV)'), # http://www.panhandlepbs.org/home/ + (r'video\.kcostv\.org', 'KCOS/Channel 13 (KCOS)'), # www.kcostv.org + (r'video\.wcny\.org', 'WCNY/Channel 24 (WCNY)'), # http://www.wcny.org + (r'video\.wned\.org', 'WNED (WNED)'), # http://www.wned.org/ + (r'watch\.wpbstv\.org', 'WPBS (WPBS)'), # http://www.wpbstv.org + (r'video\.wskg\.org', 'WSKG Public TV (WSKG)'), # http://wskg.org + (r'video\.wxxi\.org', 'WXXI (WXXI)'), # http://wxxi.org + (r'video\.wpsu\.org', 'WPSU (WPSU)'), # http://www.wpsu.org + # (r'wqln\.org', 'WQLN/Channel 54 (WQLN)'), # http://www.wqln.org + (r'on-demand\.wvia\.org', 'WVIA Public Media Studios (WVIA)'), # http://www.wvia.org/ + (r'video\.wtvi\.org', 'WTVI (WTVI)'), # http://www.wtvi.org/ + # (r'whro\.org', 'WHRO (WHRO)'), # http://whro.org + (r'video\.westernreservepublicmedia\.org', 'Western Reserve PBS (WNEO)'), # http://www.WesternReservePublicMedia.org/ + (r'video\.ideastream\.org', 'WVIZ/PBS ideastream (WVIZ)'), # http://www.wviz.org/ + (r'video\.kcts9\.org', 'KCTS 9 (KCTS)'), # http://kcts9.org/ + (r'video\.basinpbs\.org', 'Basin PBS (KPBT)'), # http://www.basinpbs.org + (r'video\.houstonpbs\.org', 'KUHT / Channel 8 (KUHT)'), # http://www.houstonpublicmedia.org/ + # (r'tamu\.edu', 'KAMU - TV (KAMU)'), # http://KAMU.tamu.edu + # (r'kedt\.org', 'KEDT/Channel 16 (KEDT)'), # http://www.kedt.org + (r'video\.klrn\.org', 'KLRN (KLRN)'), # http://www.klrn.org + (r'video\.klru\.tv', 'KLRU (KLRU)'), # http://www.klru.org + # (r'kmbh\.org', 'KMBH-TV (KMBH)'), # http://www.kmbh.org + # (r'knct\.org', 'KNCT (KNCT)'), # http://www.knct.org + # (r'ktxt\.org', 'KTTZ-TV (KTXT)'), # http://www.ktxt.org + (r'video\.wtjx\.org', 'WTJX Channel 12 (WTJX)'), # http://www.wtjx.org/ + (r'video\.ideastations\.org', 'WCVE PBS (WCVE)'), # http://ideastations.org/ + (r'video\.kbtc\.org', 'KBTC Public Television (KBTC)'), # http://kbtc.org + ) + + IE_NAME = 'pbs' + IE_DESC = 'Public Broadcasting Service (PBS) and member stations: %s' % ', '.join(list(zip(*_STATIONS))[1]) + _VALID_URL = r'''(?x)https?:// (?: # Direct video URL - video\.pbs\.org/(?:viralplayer|video)/(?P<id>[0-9]+)/? | + (?:%s)/(?:viralplayer|video)/(?P<id>[0-9]+)/? | # Article with embedded player (or direct video) (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) | # Player - video\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/ + (?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/ ) - ''' + ''' % '|'.join(list(zip(*_STATIONS))[0]) _TESTS = [ { @@ -153,6 +319,30 @@ class PBSIE(InfoExtractor): 'params': { 'skip_download': True, # requires ffmpeg }, + }, + { + # Frontline video embedded via flp2012.js + 'url': 'http://www.pbs.org/wgbh/pages/frontline/the-atomic-artists', + 'info_dict': { + 'id': '2070868960', + 'display_id': 'the-atomic-artists', + 'ext': 'mp4', + 'title': 'FRONTLINE - The Atomic Artists', + 'description': 'md5:f5bfbefadf421e8bb8647602011caf8e', + 'duration': 723, + 'thumbnail': 're:^https?://.*\.jpg$', + }, + 'params': { + 'skip_download': True, # requires ffmpeg + }, + }, + { + 'url': 'http://player.pbs.org/widget/partnerplayer/2365297708/?start=0&end=0&chapterbar=false&endscreen=false&topbar=true', + 'only_matching': True, + }, + { + 'url': 'http://watch.knpb.org/video/2365616055/', + 'only_matching': True, } ] _ERRORS = { @@ -183,6 +373,7 @@ class PBSIE(InfoExtractor): MEDIA_ID_REGEXES = [ r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed r'class="coveplayerid">([^<]+)<', # coveplayer + r'<section[^>]+data-coveid="(\d+)"', # coveplayer from http://www.pbs.org/wgbh/frontline/film/real-csi/ r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>', # jwplayer ] @@ -191,9 +382,30 @@ class PBSIE(InfoExtractor): if media_id: return media_id, presumptive_id, upload_date - url = self._search_regex( - r'(?s)<iframe[^>]+?(?:[a-z-]+?=["\'].*?["\'][^>]+?)*?\bsrc=["\']([^\'"]+partnerplayer[^\'"]+)["\']', - webpage, 'player URL') + # Fronline video embedded via flp + video_id = self._search_regex( + r'videoid\s*:\s*"([\d+a-z]{7,})"', webpage, 'videoid', default=None) + if video_id: + # pkg_id calculation is reverse engineered from + # http://www.pbs.org/wgbh/pages/frontline/js/flp2012.js + prg_id = self._search_regex( + r'videoid\s*:\s*"([\d+a-z]{7,})"', webpage, 'videoid')[7:] + if 'q' in prg_id: + prg_id = prg_id.split('q')[1] + prg_id = int(prg_id, 16) + getdir = self._download_json( + 'http://www.pbs.org/wgbh/pages/frontline/.json/getdir/getdir%d.json' % prg_id, + presumptive_id, 'Downloading getdir JSON', + transform_source=strip_jsonp) + return getdir['mid'], presumptive_id, upload_date + + for iframe in re.findall(r'(?s)<iframe(.+?)></iframe>', webpage): + url = self._search_regex( + r'src=(["\'])(?P<url>.+?partnerplayer.+?)\1', iframe, + 'player URL', default=None, group='url') + if url: + break + mobj = re.match(self._VALID_URL, url) player_id = mobj.group('player_id') @@ -221,7 +433,7 @@ class PBSIE(InfoExtractor): return self.playlist_result(entries, display_id) info = self._download_json( - 'http://video.pbs.org/videoInfo/%s?format=json&type=partner' % video_id, + 'http://player.pbs.org/videoInfo/%s?format=json&type=partner' % video_id, display_id) formats = [] diff --git a/youtube_dl/extractor/periscope.py b/youtube_dl/extractor/periscope.py index 8ad936758..63cc764bb 100644 --- a/youtube_dl/extractor/periscope.py +++ b/youtube_dl/extractor/periscope.py @@ -2,17 +2,14 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) from ..utils import parse_iso8601 class PeriscopeIE(InfoExtractor): IE_DESC = 'Periscope' - _VALID_URL = r'https?://(?:www\.)?periscope\.tv/w/(?P<id>[^/?#]+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?periscope\.tv/[^/]+/(?P<id>[^/?#]+)' + # Alive example URLs can be found here http://onperiscope.com/ + _TESTS = [{ 'url': 'https://www.periscope.tv/w/aJUQnjY3MjA3ODF8NTYxMDIyMDl2zCg2pECBgwTqRpQuQD352EMPTKQjT4uqlM3cgWFA-g==', 'md5': '65b57957972e503fcbbaeed8f4fa04ca', 'info_dict': { @@ -25,11 +22,18 @@ class PeriscopeIE(InfoExtractor): 'uploader_id': '1465763', }, 'skip': 'Expires in 24 hours', - } + }, { + 'url': 'https://www.periscope.tv/w/1ZkKzPbMVggJv', + 'only_matching': True, + }, { + 'url': 'https://www.periscope.tv/bastaakanoggano/1OdKrlkZZjOJX', + 'only_matching': True, + }] - def _call_api(self, method, token): + def _call_api(self, method, value): + attribute = 'token' if len(value) > 13 else 'broadcast_id' return self._download_json( - 'https://api.periscope.tv/api/v2/%s?token=%s' % (method, token), token) + 'https://api.periscope.tv/api/v2/%s?%s=%s' % (method, attribute, value), value) def _real_extract(self, url): token = self._match_id(url) @@ -76,24 +80,3 @@ class PeriscopeIE(InfoExtractor): 'thumbnails': thumbnails, 'formats': formats, } - - -class QuickscopeIE(InfoExtractor): - IE_DESC = 'Quick Scope' - _VALID_URL = r'https?://watchonperiscope\.com/broadcast/(?P<id>\d+)' - _TEST = { - 'url': 'https://watchonperiscope.com/broadcast/56180087', - 'only_matching': True, - } - - def _real_extract(self, url): - broadcast_id = self._match_id(url) - request = compat_urllib_request.Request( - 'https://watchonperiscope.com/api/accessChannel', compat_urllib_parse.urlencode({ - 'broadcast_id': broadcast_id, - 'entry_ticket': '', - 'from_push': 'false', - 'uses_sessions': 'true', - }).encode('utf-8')) - return self.url_result( - self._download_json(request, broadcast_id)['share_url'], 'Periscope') diff --git a/youtube_dl/extractor/pladform.py b/youtube_dl/extractor/pladform.py index 551c8c9f0..bc559d1df 100644 --- a/youtube_dl/extractor/pladform.py +++ b/youtube_dl/extractor/pladform.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( ExtractorError, @@ -44,6 +46,13 @@ class PladformIE(InfoExtractor): 'only_matching': True, }] + @staticmethod + def _extract_url(webpage): + mobj = re.search( + r'<iframe[^>]+src="(?P<url>(?:https?:)?//out\.pladform\.ru/player\?.+?)"', webpage) + if mobj: + return mobj.group('url') + def _real_extract(self, url): video_id = self._match_id(url) diff --git a/youtube_dl/extractor/played.py b/youtube_dl/extractor/played.py index 8a1c296dd..2856af96f 100644 --- a/youtube_dl/extractor/played.py +++ b/youtube_dl/extractor/played.py @@ -5,12 +5,10 @@ import re import os.path from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) +from ..compat import compat_urllib_parse from ..utils import ( ExtractorError, + sanitized_Request, ) @@ -46,7 +44,7 @@ class PlayedIE(InfoExtractor): headers = { b'Content-Type': b'application/x-www-form-urlencoded', } - req = compat_urllib_request.Request(url, post, headers) + req = sanitized_Request(url, post, headers) webpage = self._download_webpage( req, video_id, note='Downloading video page ...') diff --git a/youtube_dl/extractor/pluralsight.py b/youtube_dl/extractor/pluralsight.py index fd32836cc..55c11b3bf 100644 --- a/youtube_dl/extractor/pluralsight.py +++ b/youtube_dl/extractor/pluralsight.py @@ -2,28 +2,36 @@ from __future__ import unicode_literals import re import json +import random +import collections from .common import InfoExtractor from ..compat import ( compat_str, compat_urllib_parse, - compat_urllib_request, compat_urlparse, ) from ..utils import ( ExtractorError, int_or_none, parse_duration, + qualities, + sanitized_Request, ) -class PluralsightIE(InfoExtractor): +class PluralsightBaseIE(InfoExtractor): + _API_BASE = 'http://app.pluralsight.com' + + +class PluralsightIE(PluralsightBaseIE): IE_NAME = 'pluralsight' - _VALID_URL = r'https?://(?:www\.)?pluralsight\.com/training/player\?author=(?P<author>[^&]+)&name=(?P<name>[^&]+)(?:&mode=live)?&clip=(?P<clip>\d+)&course=(?P<course>[^&]+)' - _LOGIN_URL = 'https://www.pluralsight.com/id/' + _VALID_URL = r'https?://(?:(?:www|app)\.)?pluralsight\.com/training/player\?' + _LOGIN_URL = 'https://app.pluralsight.com/id/' + _NETRC_MACHINE = 'pluralsight' - _TEST = { + _TESTS = [{ 'url': 'http://www.pluralsight.com/training/player?author=mike-mckeown&name=hosting-sql-server-windows-azure-iaas-m7-mgmt&mode=live&clip=3&course=hosting-sql-server-windows-azure-iaas', 'md5': '4d458cf5cf4c593788672419a8dd4cf8', 'info_dict': { @@ -33,7 +41,14 @@ class PluralsightIE(InfoExtractor): 'duration': 338, }, 'skip': 'Requires pluralsight account credentials', - } + }, { + 'url': 'https://app.pluralsight.com/training/player?course=angularjs-get-started&author=scott-allen&name=angularjs-get-started-m1-introduction&clip=0&mode=live', + 'only_matching': True, + }, { + # available without pluralsight account + 'url': 'http://app.pluralsight.com/training/player?author=scott-allen&name=angularjs-get-started-m1-introduction&mode=live&clip=0&course=angularjs-get-started', + 'only_matching': True, + }] def _real_initialize(self): self._login() @@ -41,7 +56,7 @@ class PluralsightIE(InfoExtractor): def _login(self): (username, password) = self._get_login_info() if username is None: - self.raise_login_required('Pluralsight account is required') + return login_page = self._download_webpage( self._LOGIN_URL, None, 'Downloading login page') @@ -60,7 +75,7 @@ class PluralsightIE(InfoExtractor): if not post_url.startswith('http'): post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url) - request = compat_urllib_request.Request( + request = sanitized_Request( post_url, compat_urllib_parse.urlencode(login_form).encode('utf-8')) request.add_header('Content-Type', 'application/x-www-form-urlencoded') @@ -73,31 +88,48 @@ class PluralsightIE(InfoExtractor): if error: raise ExtractorError('Unable to login: %s' % error, expected=True) + if all(p not in response for p in ('__INITIAL_STATE__', '"currentUser"')): + raise ExtractorError('Unable to log in') + def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - author = mobj.group('author') - name = mobj.group('name') - clip_id = mobj.group('clip') - course = mobj.group('course') + qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) + + author = qs.get('author', [None])[0] + name = qs.get('name', [None])[0] + clip_id = qs.get('clip', [None])[0] + course = qs.get('course', [None])[0] + + if any(not f for f in (author, name, clip_id, course,)): + raise ExtractorError('Invalid URL', expected=True) display_id = '%s-%s' % (name, clip_id) webpage = self._download_webpage(url, display_id) - collection = self._parse_json( - self._search_regex( - r'moduleCollection\s*:\s*new\s+ModuleCollection\((\[.+?\])\s*,\s*\$rootScope\)', - webpage, 'modules'), - display_id) + modules = self._search_regex( + r'moduleCollection\s*:\s*new\s+ModuleCollection\((\[.+?\])\s*,\s*\$rootScope\)', + webpage, 'modules', default=None) + + if modules: + collection = self._parse_json(modules, display_id) + else: + # Webpage may be served in different layout (see + # https://github.com/rg3/youtube-dl/issues/7607) + collection = self._parse_json( + self._search_regex( + r'var\s+initialState\s*=\s*({.+?});\n', webpage, 'initial state'), + display_id)['course']['modules'] module, clip = None, None for module_ in collection: - if module_.get('moduleName') == name: + if name in (module_.get('moduleName'), module_.get('name')): module = module_ for clip_ in module_.get('clips', []): clip_index = clip_.get('clipIndex') if clip_index is None: + clip_index = clip_.get('index') + if clip_index is None: continue if compat_str(clip_index) == clip_id: clip = clip_ @@ -110,16 +142,49 @@ class PluralsightIE(InfoExtractor): 'low': {'width': 640, 'height': 480}, 'medium': {'width': 848, 'height': 640}, 'high': {'width': 1024, 'height': 768}, + 'high-widescreen': {'width': 1280, 'height': 720}, } + QUALITIES_PREFERENCE = ('low', 'medium', 'high', 'high-widescreen',) + quality_key = qualities(QUALITIES_PREFERENCE) + + AllowedQuality = collections.namedtuple('AllowedQuality', ['ext', 'qualities']) + ALLOWED_QUALITIES = ( - ('webm', ('high',)), - ('mp4', ('low', 'medium', 'high',)), + AllowedQuality('webm', ['high', ]), + AllowedQuality('mp4', ['low', 'medium', 'high', ]), ) + # Some courses also offer widescreen resolution for high quality (see + # https://github.com/rg3/youtube-dl/issues/7766) + widescreen = True if re.search( + r'courseSupportsWidescreenVideoFormats\s*:\s*true', webpage) else False + best_quality = 'high-widescreen' if widescreen else 'high' + if widescreen: + for allowed_quality in ALLOWED_QUALITIES: + allowed_quality.qualities.append(best_quality) + + # In order to minimize the number of calls to ViewClip API and reduce + # the probability of being throttled or banned by Pluralsight we will request + # only single format until formats listing was explicitly requested. + if self._downloader.params.get('listformats', False): + allowed_qualities = ALLOWED_QUALITIES + else: + def guess_allowed_qualities(): + req_format = self._downloader.params.get('format') or 'best' + req_format_split = req_format.split('-', 1) + if len(req_format_split) > 1: + req_ext, req_quality = req_format_split + for allowed_quality in ALLOWED_QUALITIES: + if req_ext == allowed_quality.ext and req_quality in allowed_quality.qualities: + return (AllowedQuality(req_ext, (req_quality, )), ) + req_ext = 'webm' if self._downloader.params.get('prefer_free_formats') else 'mp4' + return (AllowedQuality(req_ext, (best_quality, )), ) + allowed_qualities = guess_allowed_qualities() + formats = [] - for ext, qualities in ALLOWED_QUALITIES: - for quality in qualities: + for ext, qualities_ in allowed_qualities: + for quality in qualities_: f = QUALITIES[quality].copy() clip_post = { 'a': author, @@ -131,19 +196,31 @@ class PluralsightIE(InfoExtractor): 'mt': ext, 'q': '%dx%d' % (f['width'], f['height']), } - request = compat_urllib_request.Request( - 'http://www.pluralsight.com/training/Player/ViewClip', + request = sanitized_Request( + '%s/training/Player/ViewClip' % self._API_BASE, json.dumps(clip_post).encode('utf-8')) request.add_header('Content-Type', 'application/json;charset=utf-8') format_id = '%s-%s' % (ext, quality) clip_url = self._download_webpage( request, display_id, 'Downloading %s URL' % format_id, fatal=False) + + # Pluralsight tracks multiple sequential calls to ViewClip API and start + # to return 429 HTTP errors after some time (see + # https://github.com/rg3/youtube-dl/pull/6989). Moreover it may even lead + # to account ban (see https://github.com/rg3/youtube-dl/issues/6842). + # To somewhat reduce the probability of these consequences + # we will sleep random amount of time before each call to ViewClip. + self._sleep( + random.randint(2, 5), display_id, + '%(video_id)s: Waiting for %(timeout)s seconds to avoid throttling') + if not clip_url: continue f.update({ 'url': clip_url, 'ext': ext, 'format_id': format_id, + 'quality': quality_key(quality), }) formats.append(f) self._sort_formats(formats) @@ -163,10 +240,10 @@ class PluralsightIE(InfoExtractor): } -class PluralsightCourseIE(InfoExtractor): +class PluralsightCourseIE(PluralsightBaseIE): IE_NAME = 'pluralsight:course' - _VALID_URL = r'https?://(?:www\.)?pluralsight\.com/courses/(?P<id>[^/]+)' - _TEST = { + _VALID_URL = r'https?://(?:(?:www|app)\.)?pluralsight\.com/(?:library/)?courses/(?P<id>[^/]+)' + _TESTS = [{ # Free course from Pluralsight Starter Subscription for Microsoft TechNet # https://offers.pluralsight.com/technet?loc=zTS3z&prod=zOTprodz&tech=zOttechz&prog=zOTprogz&type=zSOz&media=zOTmediaz&country=zUSz 'url': 'http://www.pluralsight.com/courses/hosting-sql-server-windows-azure-iaas', @@ -176,7 +253,14 @@ class PluralsightCourseIE(InfoExtractor): 'description': 'md5:61b37e60f21c4b2f91dc621a977d0986', }, 'playlist_count': 31, - } + }, { + # available without pluralsight account + 'url': 'https://www.pluralsight.com/courses/angularjs-get-started', + 'only_matching': True, + }, { + 'url': 'https://app.pluralsight.com/library/courses/understanding-microsoft-azure-amazon-aws/table-of-contents', + 'only_matching': True, + }] def _real_extract(self, url): course_id = self._match_id(url) @@ -184,14 +268,14 @@ class PluralsightCourseIE(InfoExtractor): # TODO: PSM cookie course = self._download_json( - 'http://www.pluralsight.com/data/course/%s' % course_id, + '%s/data/course/%s' % (self._API_BASE, course_id), course_id, 'Downloading course JSON') title = course['title'] description = course.get('description') or course.get('shortDescription') course_data = self._download_json( - 'http://www.pluralsight.com/data/course/content/%s' % course_id, + '%s/data/course/content/%s' % (self._API_BASE, course_id), course_id, 'Downloading course data JSON') entries = [] @@ -201,7 +285,7 @@ class PluralsightCourseIE(InfoExtractor): if not player_parameters: continue entries.append(self.url_result( - 'http://www.pluralsight.com/training/player?%s' % player_parameters, + '%s/training/player?%s' % (self._API_BASE, player_parameters), 'Pluralsight')) return self.playlist_result(entries, course_id, title, description) diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py index dbb2c3bd9..57c78ba52 100644 --- a/youtube_dl/extractor/pornhd.py +++ b/youtube_dl/extractor/pornhd.py @@ -36,7 +36,8 @@ class PornHdIE(InfoExtractor): webpage = self._download_webpage(url, display_id or video_id) title = self._html_search_regex( - r'<title>(.+) porn HD.+?</title>', webpage, 'title') + [r'<span[^>]+class=["\']video-name["\'][^>]*>([^<]+)', + r'<title>(.+?) - .*?[Pp]ornHD.*?</title>'], webpage, 'title') description = self._html_search_regex( r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False) view_count = int_or_none(self._html_search_regex( diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index a656ad85a..08275687d 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -8,10 +8,10 @@ from ..compat import ( compat_urllib_parse_unquote, compat_urllib_parse_unquote_plus, compat_urllib_parse_urlparse, - compat_urllib_request, ) from ..utils import ( ExtractorError, + sanitized_Request, str_to_int, ) from ..aes import ( @@ -53,7 +53,7 @@ class PornHubIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - req = compat_urllib_request.Request( + req = sanitized_Request( 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id) req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) @@ -147,7 +147,8 @@ class PornHubPlaylistIE(InfoExtractor): entries = [ self.url_result('http://www.pornhub.com/%s' % video_url, 'PornHub') - for video_url in set(re.findall('href="/?(view_video\.php\?viewkey=\d+[^"]*)"', webpage)) + for video_url in set(re.findall( + r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"', webpage)) ] playlist = self._parse_json( diff --git a/youtube_dl/extractor/pornotube.py b/youtube_dl/extractor/pornotube.py index 34735c51e..5398e708b 100644 --- a/youtube_dl/extractor/pornotube.py +++ b/youtube_dl/extractor/pornotube.py @@ -3,11 +3,9 @@ from __future__ import unicode_literals import json from .common import InfoExtractor -from ..compat import ( - compat_urllib_request, -) from ..utils import ( int_or_none, + sanitized_Request, ) @@ -46,7 +44,7 @@ class PornotubeIE(InfoExtractor): 'authenticationSpaceKey': originAuthenticationSpaceKey, 'credentials': 'Clip Application', } - token_req = compat_urllib_request.Request( + token_req = sanitized_Request( 'https://api.aebn.net/auth/v1/token/primal', data=json.dumps(token_req_data).encode('utf-8')) token_req.add_header('Content-Type', 'application/json') @@ -56,7 +54,7 @@ class PornotubeIE(InfoExtractor): token = token_answer['tokenKey'] # Get video URL - delivery_req = compat_urllib_request.Request( + delivery_req = sanitized_Request( 'https://api.aebn.net/delivery/v1/clips/%s/MP4' % video_id) delivery_req.add_header('Authorization', token) delivery_info = self._download_json( @@ -64,7 +62,7 @@ class PornotubeIE(InfoExtractor): video_url = delivery_info['mediaUrl'] # Get additional info (title etc.) - info_req = compat_urllib_request.Request( + info_req = sanitized_Request( 'https://api.aebn.net/content/v1/clips/%s?expand=' 'title,description,primaryImageNumber,startSecond,endSecond,' 'movie.title,movie.MovieId,movie.boxCoverFront,movie.stars,' diff --git a/youtube_dl/extractor/primesharetv.py b/youtube_dl/extractor/primesharetv.py index 304359dc5..85aae9576 100644 --- a/youtube_dl/extractor/primesharetv.py +++ b/youtube_dl/extractor/primesharetv.py @@ -1,11 +1,11 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, +from ..compat import compat_urllib_parse +from ..utils import ( + ExtractorError, + sanitized_Request, ) -from ..utils import ExtractorError class PrimeShareTVIE(InfoExtractor): @@ -41,7 +41,7 @@ class PrimeShareTVIE(InfoExtractor): webpage, 'wait time', default=7)) + 1 self._sleep(wait_time, video_id) - req = compat_urllib_request.Request( + req = sanitized_Request( url, compat_urllib_parse.urlencode(fields), headers) video_page = self._download_webpage( req, video_id, 'Downloading video page') diff --git a/youtube_dl/extractor/promptfile.py b/youtube_dl/extractor/promptfile.py index 8190ed676..d5357283a 100644 --- a/youtube_dl/extractor/promptfile.py +++ b/youtube_dl/extractor/promptfile.py @@ -4,13 +4,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) +from ..compat import compat_urllib_parse from ..utils import ( determine_ext, ExtractorError, + sanitized_Request, ) @@ -37,7 +35,7 @@ class PromptFileIE(InfoExtractor): fields = self._hidden_inputs(webpage) post = compat_urllib_parse.urlencode(fields) - req = compat_urllib_request.Request(url, post) + req = sanitized_Request(url, post) req.add_header('Content-type', 'application/x-www-form-urlencoded') webpage = self._download_webpage( req, video_id, 'Downloading video page') diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py index effcf1db3..baa54a3af 100644 --- a/youtube_dl/extractor/prosiebensat1.py +++ b/youtube_dl/extractor/prosiebensat1.py @@ -20,7 +20,7 @@ from ..utils import ( class ProSiebenSat1IE(InfoExtractor): IE_NAME = 'prosiebensat1' IE_DESC = 'ProSiebenSat.1 Digital' - _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|the-voice-of-germany)\.(?:de|at)|ran\.de|fem\.com)/(?P<id>.+)' + _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|the-voice-of-germany)\.(?:de|at|ch)|ran\.de|fem\.com)/(?P<id>.+)' _TESTS = [ { diff --git a/youtube_dl/extractor/qqmusic.py b/youtube_dl/extractor/qqmusic.py index c98539f6a..1ba3bbddf 100644 --- a/youtube_dl/extractor/qqmusic.py +++ b/youtube_dl/extractor/qqmusic.py @@ -7,11 +7,11 @@ import re from .common import InfoExtractor from ..utils import ( + sanitized_Request, strip_jsonp, unescapeHTML, clean_html, ) -from ..compat import compat_urllib_request class QQMusicIE(InfoExtractor): @@ -201,7 +201,7 @@ class QQMusicSingerIE(QQPlaylistBaseIE): singer_desc = None if singer_id: - req = compat_urllib_request.Request( + req = sanitized_Request( 'http://s.plcloud.music.qq.com/fcgi-bin/fcg_get_singer_desc.fcg?utf8=1&outCharset=utf-8&format=xml&singerid=%s' % singer_id) req.add_header( 'Referer', 'http://s.plcloud.music.qq.com/xhr_proxy_utf8.html') diff --git a/youtube_dl/extractor/rtbf.py b/youtube_dl/extractor/rtbf.py index 04a66df90..e42b319a3 100644 --- a/youtube_dl/extractor/rtbf.py +++ b/youtube_dl/extractor/rtbf.py @@ -9,8 +9,8 @@ from ..utils import ( class RTBFIE(InfoExtractor): - _VALID_URL = r'https?://www.rtbf.be/video/[^\?]+\?id=(?P<id>\d+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?rtbf\.be/(?:video/[^?]+\?.*\bid=|ouftivi/(?:[^/]+/)*[^?]+\?.*\bvideoId=)(?P<id>\d+)' + _TESTS = [{ 'url': 'https://www.rtbf.be/video/detail_les-diables-au-coeur-episode-2?id=1921274', 'md5': '799f334ddf2c0a582ba80c44655be570', 'info_dict': { @@ -19,7 +19,14 @@ class RTBFIE(InfoExtractor): 'title': 'Les Diables au coeur (épisode 2)', 'duration': 3099, } - } + }, { + # geo restricted + 'url': 'http://www.rtbf.be/ouftivi/heros/detail_scooby-doo-mysteres-associes?id=1097&videoId=2057442', + 'only_matching': True, + }, { + 'url': 'http://www.rtbf.be/ouftivi/niouzz?videoId=2055858', + 'only_matching': True, + }] _QUALITIES = [ ('mobile', 'mobile'), diff --git a/youtube_dl/extractor/rtve.py b/youtube_dl/extractor/rtve.py index 5b97d33ca..603d7bd00 100644 --- a/youtube_dl/extractor/rtve.py +++ b/youtube_dl/extractor/rtve.py @@ -6,11 +6,11 @@ import re import time from .common import InfoExtractor -from ..compat import compat_urllib_request, compat_urlparse from ..utils import ( ExtractorError, float_or_none, remove_end, + sanitized_Request, std_headers, struct_unpack, ) @@ -102,20 +102,14 @@ class RTVEALaCartaIE(InfoExtractor): if info['state'] == 'DESPU': raise ExtractorError('The video is no longer available', expected=True) png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id) - png_request = compat_urllib_request.Request(png_url) + png_request = sanitized_Request(png_url) png_request.add_header('Referer', url) png = self._download_webpage(png_request, video_id, 'Downloading url information') video_url = _decrypt_url(png) if not video_url.endswith('.f4m'): - auth_url = video_url.replace( + video_url = video_url.replace( 'resources/', 'auth/resources/' ).replace('.net.rtve', '.multimedia.cdn.rtve') - video_path = self._download_webpage( - auth_url, video_id, 'Getting video url') - # Use mvod1.akcdn instead of flash.akamaihd.multimedia.cdn to get - # the right Content-Length header and the mp4 format - video_url = compat_urlparse.urljoin( - 'http://mvod1.akcdn.rtve.es/', video_path) subtitles = None if info.get('sbtFile') is not None: diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index d94dc7399..9db62adb1 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -9,7 +9,7 @@ from ..compat import ( compat_str, ) from ..utils import ( - ExtractorError, + determine_ext, unified_strdate, ) @@ -17,9 +17,9 @@ from ..utils import ( class RutubeIE(InfoExtractor): IE_NAME = 'rutube' IE_DESC = 'Rutube videos' - _VALID_URL = r'https?://rutube\.ru/video/(?P<id>[\da-z]{32})' + _VALID_URL = r'https?://rutube\.ru/(?:video|play/embed)/(?P<id>[\da-z]{32})' - _TEST = { + _TESTS = [{ 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/', 'info_dict': { 'id': '3eac3b4561676c17df9132a9a1e62e3e', @@ -36,7 +36,10 @@ class RutubeIE(InfoExtractor): # It requires ffmpeg (m3u8 download) 'skip_download': True, }, - } + }, { + 'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -51,10 +54,25 @@ class RutubeIE(InfoExtractor): 'http://rutube.ru/api/play/options/%s/?format=json' % video_id, video_id, 'Downloading options JSON') - m3u8_url = options['video_balancer'].get('m3u8') - if m3u8_url is None: - raise ExtractorError('Couldn\'t find m3u8 manifest url') - formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4') + formats = [] + for format_id, format_url in options['video_balancer'].items(): + ext = determine_ext(format_url) + if ext == 'm3u8': + m3u8_formats = self._extract_m3u8_formats( + format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + elif ext == 'f4m': + f4m_formats = self._extract_f4m_formats( + format_url, video_id, f4m_id=format_id, fatal=False) + if f4m_formats: + formats.extend(f4m_formats) + else: + formats.append({ + 'url': format_url, + 'format_id': format_id, + }) + self._sort_formats(formats) return { 'id': video['id'], @@ -74,9 +92,9 @@ class RutubeIE(InfoExtractor): class RutubeEmbedIE(InfoExtractor): IE_NAME = 'rutube:embed' IE_DESC = 'Rutube embedded videos' - _VALID_URL = 'https?://rutube\.ru/video/embed/(?P<id>[0-9]+)' + _VALID_URL = 'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)' - _TEST = { + _TESTS = [{ 'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=', 'info_dict': { 'id': 'a10e53b86e8f349080f718582ce4c661', @@ -90,7 +108,10 @@ class RutubeEmbedIE(InfoExtractor): 'params': { 'skip_download': 'Requires ffmpeg', }, - } + }, { + 'url': 'http://rutube.ru/play/embed/8083783', + 'only_matching': True, + }] def _real_extract(self, url): embed_id = self._match_id(url) diff --git a/youtube_dl/extractor/ruutu.py b/youtube_dl/extractor/ruutu.py index a16b73ff4..e417bf661 100644 --- a/youtube_dl/extractor/ruutu.py +++ b/youtube_dl/extractor/ruutu.py @@ -57,16 +57,21 @@ class RuutuIE(InfoExtractor): extract_formats(child) elif child.tag.endswith('File'): video_url = child.text - if not video_url or video_url in processed_urls or 'NOT_USED' in video_url: + if (not video_url or video_url in processed_urls or + any(p in video_url for p in ('NOT_USED', 'NOT-USED'))): return processed_urls.append(video_url) ext = determine_ext(video_url) if ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - video_url, video_id, 'mp4', m3u8_id='hls')) + m3u8_formats = self._extract_m3u8_formats( + video_url, video_id, 'mp4', m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) elif ext == 'f4m': - formats.extend(self._extract_f4m_formats( - video_url, video_id, f4m_id='hds')) + f4m_formats = self._extract_f4m_formats( + video_url, video_id, f4m_id='hds', fatal=False) + if f4m_formats: + formats.extend(f4m_formats) else: proto = compat_urllib_parse_urlparse(video_url).scheme if not child.tag.startswith('HTTP') and proto != 'rtmp': diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py index a602af692..7de7b7273 100644 --- a/youtube_dl/extractor/safari.py +++ b/youtube_dl/extractor/safari.py @@ -4,16 +4,14 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from .brightcove import BrightcoveIE +from .brightcove import BrightcoveLegacyIE -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) from ..utils import ( ExtractorError, + sanitized_Request, smuggle_url, std_headers, + urlencode_postdata, ) @@ -58,8 +56,8 @@ class SafariBaseIE(InfoExtractor): 'next': '', } - request = compat_urllib_request.Request( - self._LOGIN_URL, compat_urllib_parse.urlencode(login_form), headers=headers) + request = sanitized_Request( + self._LOGIN_URL, urlencode_postdata(login_form), headers=headers) login_page = self._download_webpage( request, None, 'Logging in as %s' % username) @@ -112,11 +110,11 @@ class SafariIE(SafariBaseIE): '%s/%s/chapter-content/%s.html' % (self._API_BASE, course_id, part), part) - bc_url = BrightcoveIE._extract_brightcove_url(webpage) + bc_url = BrightcoveLegacyIE._extract_brightcove_url(webpage) if not bc_url: raise ExtractorError('Could not extract Brightcove URL from %s' % url, expected=True) - return self.url_result(smuggle_url(bc_url, {'Referer': url}), 'Brightcove') + return self.url_result(smuggle_url(bc_url, {'Referer': url}), 'BrightcoveLegacy') class SafariCourseIE(SafariBaseIE): diff --git a/youtube_dl/extractor/sandia.py b/youtube_dl/extractor/sandia.py index 9c88167f0..759898a49 100644 --- a/youtube_dl/extractor/sandia.py +++ b/youtube_dl/extractor/sandia.py @@ -6,14 +6,12 @@ import json import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_request, - compat_urlparse, -) +from ..compat import compat_urlparse from ..utils import ( int_or_none, js_to_json, mimetype2ext, + sanitized_Request, unified_strdate, ) @@ -37,7 +35,7 @@ class SandiaIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - req = compat_urllib_request.Request(url) + req = sanitized_Request(url) req.add_header('Cookie', 'MediasitePlayerCaps=ClientPlugins=4') webpage = self._download_webpage(req, video_id) diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index c5636e8e9..8eda3c864 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -3,13 +3,11 @@ from __future__ import unicode_literals import base64 from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) +from ..compat import compat_urllib_parse from ..utils import ( ExtractorError, int_or_none, + sanitized_Request, ) @@ -46,7 +44,7 @@ class SharedIE(InfoExtractor): 'Video %s does not exist' % video_id, expected=True) download_form = self._hidden_inputs(webpage) - request = compat_urllib_request.Request( + request = sanitized_Request( url, compat_urllib_parse.urlencode(download_form)) request.add_header('Content-Type', 'application/x-www-form-urlencoded') diff --git a/youtube_dl/extractor/sharesix.py b/youtube_dl/extractor/sharesix.py index ac3e3adf2..f1ea9bdb2 100644 --- a/youtube_dl/extractor/sharesix.py +++ b/youtube_dl/extractor/sharesix.py @@ -4,12 +4,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) +from ..compat import compat_urllib_parse from ..utils import ( parse_duration, + sanitized_Request, ) @@ -50,7 +48,7 @@ class ShareSixIE(InfoExtractor): 'method_free': 'Free' } post = compat_urllib_parse.urlencode(fields) - req = compat_urllib_request.Request(url, post) + req = sanitized_Request(url, post) req.add_header('Content-type', 'application/x-www-form-urlencoded') webpage = self._download_webpage(req, video_id, diff --git a/youtube_dl/extractor/sina.py b/youtube_dl/extractor/sina.py index 0891a441f..b2258a0f6 100644 --- a/youtube_dl/extractor/sina.py +++ b/youtube_dl/extractor/sina.py @@ -4,10 +4,8 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_request, - compat_urllib_parse, -) +from ..compat import compat_urllib_parse +from ..utils import sanitized_Request class SinaIE(InfoExtractor): @@ -61,7 +59,7 @@ class SinaIE(InfoExtractor): if mobj.group('token') is not None: # The video id is in the redirected url self.to_screen('Getting video id') - request = compat_urllib_request.Request(url) + request = sanitized_Request(url) request.get_method = lambda: 'HEAD' (_, urlh) = self._download_webpage_handle(request, 'NA', False) return self._real_extract(urlh.geturl()) diff --git a/youtube_dl/extractor/skynewsarabia.py b/youtube_dl/extractor/skynewsarabia.py new file mode 100644 index 000000000..05e1b02ad --- /dev/null +++ b/youtube_dl/extractor/skynewsarabia.py @@ -0,0 +1,117 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + parse_iso8601, + parse_duration, +) + + +class SkyNewsArabiaBaseIE(InfoExtractor): + _IMAGE_BASE_URL = 'http://www.skynewsarabia.com/web/images' + + def _call_api(self, path, value): + return self._download_json('http://api.skynewsarabia.com/web/rest/v2/%s/%s.json' % (path, value), value) + + def _get_limelight_media_id(self, url): + return self._search_regex(r'/media/[^/]+/([a-z0-9]{32})', url, 'limelight media id') + + def _get_image_url(self, image_path_template, width='1600', height='1200'): + return self._IMAGE_BASE_URL + image_path_template.format(width=width, height=height) + + def _extract_video_info(self, video_data): + video_id = compat_str(video_data['id']) + topic = video_data.get('topicTitle') + return { + '_type': 'url_transparent', + 'url': 'limelight:media:%s' % self._get_limelight_media_id(video_data['videoUrl'][0]['url']), + 'id': video_id, + 'title': video_data['headline'], + 'description': video_data.get('summary'), + 'thumbnail': self._get_image_url(video_data['mediaAsset']['imageUrl']), + 'timestamp': parse_iso8601(video_data.get('date')), + 'duration': parse_duration(video_data.get('runTime')), + 'tags': video_data.get('tags', []), + 'categories': [topic] if topic else [], + 'webpage_url': 'http://www.skynewsarabia.com/web/video/%s' % video_id, + 'ie_key': 'LimelightMedia', + } + + +class SkyNewsArabiaIE(SkyNewsArabiaBaseIE): + IE_NAME = 'skynewsarabia:video' + _VALID_URL = r'https?://(?:www\.)?skynewsarabia\.com/web/video/(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://www.skynewsarabia.com/web/video/794902/%D9%86%D8%B5%D9%81-%D9%85%D9%84%D9%8A%D9%88%D9%86-%D9%85%D8%B5%D8%A8%D8%A7%D8%AD-%D8%B4%D8%AC%D8%B1%D8%A9-%D9%83%D8%B1%D9%8A%D8%B3%D9%85%D8%A7%D8%B3', + 'info_dict': { + 'id': '794902', + 'ext': 'flv', + 'title': 'نصف مليون مصباح على شجرة كريسماس', + 'description': 'md5:22f1b27f0850eeb10c7e59b1f16eb7c6', + 'upload_date': '20151128', + 'timestamp': 1448697198, + 'duration': 2119, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + video_data = self._call_api('video', video_id) + return self._extract_video_info(video_data) + + +class SkyNewsArabiaArticleIE(SkyNewsArabiaBaseIE): + IE_NAME = 'skynewsarabia:video' + _VALID_URL = r'https?://(?:www\.)?skynewsarabia\.com/web/article/(?P<id>[0-9]+)' + _TESTS = [{ + 'url': 'http://www.skynewsarabia.com/web/article/794549/%D8%A7%D9%94%D8%AD%D8%AF%D8%A7%D8%AB-%D8%A7%D9%84%D8%B4%D8%B1%D9%82-%D8%A7%D9%84%D8%A7%D9%94%D9%88%D8%B3%D8%B7-%D8%AE%D8%B1%D9%8A%D8%B7%D8%A9-%D8%A7%D9%84%D8%A7%D9%94%D9%84%D8%B9%D8%A7%D8%A8-%D8%A7%D9%84%D8%B0%D9%83%D9%8A%D8%A9', + 'info_dict': { + 'id': '794549', + 'ext': 'flv', + 'title': 'بالفيديو.. ألعاب ذكية تحاكي واقع المنطقة', + 'description': 'md5:0c373d29919a851e080ee4edd0c5d97f', + 'upload_date': '20151126', + 'timestamp': 1448559336, + 'duration': 281.6, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, { + 'url': 'http://www.skynewsarabia.com/web/article/794844/%D8%A7%D8%B3%D8%AA%D9%87%D8%AF%D8%A7%D9%81-%D9%82%D9%88%D8%A7%D8%B1%D8%A8-%D8%A7%D9%94%D8%B3%D9%84%D8%AD%D8%A9-%D9%84%D9%85%D9%8A%D9%84%D9%8A%D8%B4%D9%8A%D8%A7%D8%AA-%D8%A7%D9%84%D8%AD%D9%88%D8%AB%D9%8A-%D9%88%D8%B5%D8%A7%D9%84%D8%AD', + 'info_dict': { + 'id': '794844', + 'title': 'إحباط تهريب أسلحة لميليشيات الحوثي وصالح بجنوب اليمن', + 'description': 'md5:5c927b8b2e805796e7f693538d96fc7e', + }, + 'playlist_mincount': 2, + }] + + def _real_extract(self, url): + article_id = self._match_id(url) + article_data = self._call_api('article', article_id) + media_asset = article_data['mediaAsset'] + if media_asset['type'] == 'VIDEO': + topic = article_data.get('topicTitle') + return { + '_type': 'url_transparent', + 'url': 'limelight:media:%s' % self._get_limelight_media_id(media_asset['videoUrl'][0]['url']), + 'id': article_id, + 'title': article_data['headline'], + 'description': article_data.get('summary'), + 'thumbnail': self._get_image_url(media_asset['imageUrl']), + 'timestamp': parse_iso8601(article_data.get('date')), + 'tags': article_data.get('tags', []), + 'categories': [topic] if topic else [], + 'webpage_url': url, + 'ie_key': 'LimelightMedia', + } + entries = [self._extract_video_info(item) for item in article_data.get('inlineItems', []) if item['type'] == 'VIDEO'] + return self.playlist_result(entries, article_id, article_data['headline'], article_data.get('summary')) diff --git a/youtube_dl/extractor/smotri.py b/youtube_dl/extractor/smotri.py index 35a81ee87..30210c8a3 100644 --- a/youtube_dl/extractor/smotri.py +++ b/youtube_dl/extractor/smotri.py @@ -7,13 +7,11 @@ import hashlib import uuid from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) +from ..compat import compat_urllib_parse from ..utils import ( ExtractorError, int_or_none, + sanitized_Request, unified_strdate, ) @@ -176,7 +174,7 @@ class SmotriIE(InfoExtractor): if video_password: video_form['pass'] = hashlib.md5(video_password.encode('utf-8')).hexdigest() - request = compat_urllib_request.Request( + request = sanitized_Request( 'http://smotri.com/video/view/url/bot/', compat_urllib_parse.urlencode(video_form)) request.add_header('Content-Type', 'application/x-www-form-urlencoded') @@ -339,7 +337,7 @@ class SmotriBroadcastIE(InfoExtractor): 'password': password, } - request = compat_urllib_request.Request( + request = sanitized_Request( broadcast_url + '/?no_redirect=1', compat_urllib_parse.urlencode(login_form)) request.add_header('Content-Type', 'application/x-www-form-urlencoded') broadcast_page = self._download_webpage( diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py index ba2d5e19b..ea8fc258d 100644 --- a/youtube_dl/extractor/sohu.py +++ b/youtube_dl/extractor/sohu.py @@ -6,11 +6,11 @@ import re from .common import InfoExtractor from ..compat import ( compat_str, - compat_urllib_request, compat_urllib_parse, ) from ..utils import ( ExtractorError, + sanitized_Request, ) @@ -96,7 +96,7 @@ class SohuIE(InfoExtractor): else: base_data_url = 'http://hot.vrs.sohu.com/vrs_flash.action?vid=' - req = compat_urllib_request.Request(base_data_url + vid_id) + req = sanitized_Request(base_data_url + vid_id) cn_verification_proxy = self._downloader.params.get('cn_verification_proxy') if cn_verification_proxy: @@ -158,6 +158,7 @@ class SohuIE(InfoExtractor): 'file': clips_url[i], 'new': su[i], 'prod': 'flash', + 'rb': 1, } if cdnId is not None: diff --git a/youtube_dl/extractor/soompi.py b/youtube_dl/extractor/soompi.py deleted file mode 100644 index 5da66ca9e..000000000 --- a/youtube_dl/extractor/soompi.py +++ /dev/null @@ -1,146 +0,0 @@ -# encoding: utf-8 -from __future__ import unicode_literals - -import re - -from .crunchyroll import CrunchyrollIE - -from .common import InfoExtractor -from ..compat import compat_HTTPError -from ..utils import ( - ExtractorError, - int_or_none, - remove_start, - xpath_text, -) - - -class SoompiBaseIE(InfoExtractor): - def _get_episodes(self, webpage, episode_filter=None): - episodes = self._parse_json( - self._search_regex( - r'VIDEOS\s*=\s*(\[.+?\]);', webpage, 'episodes JSON'), - None) - return list(filter(episode_filter, episodes)) - - -class SoompiIE(SoompiBaseIE, CrunchyrollIE): - IE_NAME = 'soompi' - _VALID_URL = r'https?://tv\.soompi\.com/(?:en/)?watch/(?P<id>[0-9]+)' - _TESTS = [{ - 'url': 'http://tv.soompi.com/en/watch/29235', - 'info_dict': { - 'id': '29235', - 'ext': 'mp4', - 'title': 'Episode 1096', - 'description': '2015-05-20' - }, - 'params': { - 'skip_download': True, - }, - }] - - def _get_episode(self, webpage, video_id): - return self._get_episodes(webpage, lambda x: x['id'] == video_id)[0] - - def _get_subtitles(self, config, video_id): - sub_langs = {} - for subtitle in config.findall('./{default}preload/subtitles/subtitle'): - sub_langs[subtitle.attrib['id']] = subtitle.attrib['title'] - - subtitles = {} - for s in config.findall('./{default}preload/subtitle'): - lang_code = sub_langs.get(s.attrib['id']) - if not lang_code: - continue - sub_id = s.get('id') - data = xpath_text(s, './data', 'data') - iv = xpath_text(s, './iv', 'iv') - if not id or not iv or not data: - continue - subtitle = self._decrypt_subtitles(data, iv, sub_id).decode('utf-8') - subtitles[lang_code] = self._extract_subtitles(subtitle) - return subtitles - - def _real_extract(self, url): - video_id = self._match_id(url) - - try: - webpage = self._download_webpage( - url, video_id, 'Downloading episode page') - except ExtractorError as ee: - if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: - webpage = ee.cause.read() - block_message = self._html_search_regex( - r'(?s)<div class="block-message">(.+?)</div>', webpage, - 'block message', default=None) - if block_message: - raise ExtractorError(block_message, expected=True) - raise - - formats = [] - config = None - for format_id in re.findall(r'\?quality=([0-9a-zA-Z]+)', webpage): - config = self._download_xml( - 'http://tv.soompi.com/en/show/_/%s-config.xml?mode=hls&quality=%s' % (video_id, format_id), - video_id, 'Downloading %s XML' % format_id) - m3u8_url = xpath_text( - config, './{default}preload/stream_info/file', - '%s m3u8 URL' % format_id) - if not m3u8_url: - continue - formats.extend(self._extract_m3u8_formats( - m3u8_url, video_id, 'mp4', m3u8_id=format_id)) - self._sort_formats(formats) - - episode = self._get_episode(webpage, video_id) - - title = episode['name'] - description = episode.get('description') - duration = int_or_none(episode.get('duration')) - - thumbnails = [{ - 'id': thumbnail_id, - 'url': thumbnail_url, - } for thumbnail_id, thumbnail_url in episode.get('img_url', {}).items()] - - subtitles = self.extract_subtitles(config, video_id) - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnails': thumbnails, - 'duration': duration, - 'formats': formats, - 'subtitles': subtitles - } - - -class SoompiShowIE(SoompiBaseIE): - IE_NAME = 'soompi:show' - _VALID_URL = r'https?://tv\.soompi\.com/en/shows/(?P<id>[0-9a-zA-Z\-_]+)' - _TESTS = [{ - 'url': 'http://tv.soompi.com/en/shows/liar-game', - 'info_dict': { - 'id': 'liar-game', - 'title': 'Liar Game', - 'description': 'md5:52c02bce0c1a622a95823591d0589b66', - }, - 'playlist_count': 14, - }] - - def _real_extract(self, url): - show_id = self._match_id(url) - - webpage = self._download_webpage( - url, show_id, 'Downloading show page') - - title = remove_start(self._og_search_title(webpage), 'SoompiTV | ') - description = self._og_search_description(webpage) - - entries = [ - self.url_result('http://tv.soompi.com/en/watch/%s' % episode['id'], 'Soompi') - for episode in self._get_episodes(webpage)] - - return self.playlist_result(entries, show_id, title, description) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 2b60d354a..02e64e094 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -4,13 +4,17 @@ from __future__ import unicode_literals import re import itertools -from .common import InfoExtractor +from .common import ( + InfoExtractor, + SearchInfoExtractor +) from ..compat import ( compat_str, compat_urlparse, compat_urllib_parse, ) from ..utils import ( + encode_dict, ExtractorError, int_or_none, unified_strdate, @@ -469,3 +473,60 @@ class SoundcloudPlaylistIE(SoundcloudIE): 'description': data.get('description'), 'entries': entries, } + + +class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE): + IE_NAME = 'soundcloud:search' + IE_DESC = 'Soundcloud search' + _MAX_RESULTS = float('inf') + _TESTS = [{ + 'url': 'scsearch15:post-avant jazzcore', + 'info_dict': { + 'title': 'post-avant jazzcore', + }, + 'playlist_count': 15, + }] + + _SEARCH_KEY = 'scsearch' + _MAX_RESULTS_PER_PAGE = 200 + _DEFAULT_RESULTS_PER_PAGE = 50 + _API_V2_BASE = 'https://api-v2.soundcloud.com' + + def _get_collection(self, endpoint, collection_id, **query): + limit = min( + query.get('limit', self._DEFAULT_RESULTS_PER_PAGE), + self._MAX_RESULTS_PER_PAGE) + query['limit'] = limit + query['client_id'] = self._CLIENT_ID + query['linked_partitioning'] = '1' + query['offset'] = 0 + data = compat_urllib_parse.urlencode(encode_dict(query)) + next_url = '{0}{1}?{2}'.format(self._API_V2_BASE, endpoint, data) + + collected_results = 0 + + for i in itertools.count(1): + response = self._download_json( + next_url, collection_id, 'Downloading page {0}'.format(i), + 'Unable to download API page') + + collection = response.get('collection', []) + if not collection: + break + + collection = list(filter(bool, collection)) + collected_results += len(collection) + + for item in collection: + yield self.url_result(item['uri'], SoundcloudIE.ie_key()) + + if not collection or collected_results >= limit: + break + + next_url = response.get('next_href') + if not next_url: + break + + def _get_n_results(self, query, n): + tracks = self._get_collection('/search/tracks', query, limit=n, q=query) + return self.playlist_result(tracks, playlist_title=query) diff --git a/youtube_dl/extractor/space.py b/youtube_dl/extractor/space.py index c2d0d36a6..ebb5d6ec0 100644 --- a/youtube_dl/extractor/space.py +++ b/youtube_dl/extractor/space.py @@ -3,14 +3,14 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from .brightcove import BrightcoveIE +from .brightcove import BrightcoveLegacyIE from ..utils import RegexNotFoundError, ExtractorError class SpaceIE(InfoExtractor): _VALID_URL = r'https?://(?:(?:www|m)\.)?space\.com/\d+-(?P<title>[^/\.\?]*?)-video\.html' _TEST = { - 'add_ie': ['Brightcove'], + 'add_ie': ['BrightcoveLegacy'], 'url': 'http://www.space.com/23373-huge-martian-landforms-detail-revealed-by-european-probe-video.html', 'info_dict': { 'id': '2780937028001', @@ -31,8 +31,8 @@ class SpaceIE(InfoExtractor): brightcove_url = self._og_search_video_url(webpage) except RegexNotFoundError: # Other videos works fine with the info from the object - brightcove_url = BrightcoveIE._extract_brightcove_url(webpage) + brightcove_url = BrightcoveLegacyIE._extract_brightcove_url(webpage) if brightcove_url is None: raise ExtractorError( 'The webpage does not contain a video', expected=True) - return self.url_result(brightcove_url, BrightcoveIE.ie_key()) + return self.url_result(brightcove_url, BrightcoveLegacyIE.ie_key()) diff --git a/youtube_dl/extractor/spankwire.py b/youtube_dl/extractor/spankwire.py index 9e8fb35b2..692fd78e8 100644 --- a/youtube_dl/extractor/spankwire.py +++ b/youtube_dl/extractor/spankwire.py @@ -6,9 +6,9 @@ from .common import InfoExtractor from ..compat import ( compat_urllib_parse_unquote, compat_urllib_parse_urlparse, - compat_urllib_request, ) from ..utils import ( + sanitized_Request, str_to_int, unified_strdate, ) @@ -51,7 +51,7 @@ class SpankwireIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - req = compat_urllib_request.Request('http://www.' + mobj.group('url')) + req = sanitized_Request('http://www.' + mobj.group('url')) req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py index 5bd3c0087..39a7aaf9d 100644 --- a/youtube_dl/extractor/spiegel.py +++ b/youtube_dl/extractor/spiegel.py @@ -58,7 +58,8 @@ class SpiegelIE(InfoExtractor): description = self._html_search_meta('description', webpage, 'description') base_url = self._search_regex( - r'var\s+server\s*=\s*"([^"]+)\"', webpage, 'server URL') + [r'server\s*:\s*(["\'])(?P<url>.+?)\1', r'var\s+server\s*=\s*"(?P<url>[^"]+)\"'], + webpage, 'server URL', group='url') xml_url = base_url + video_id + '.xml' idoc = self._download_xml(xml_url, video_id) diff --git a/youtube_dl/extractor/sportdeutschland.py b/youtube_dl/extractor/sportdeutschland.py index 7ec6c613f..ebb75f059 100644 --- a/youtube_dl/extractor/sportdeutschland.py +++ b/youtube_dl/extractor/sportdeutschland.py @@ -4,11 +4,9 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_request, -) from ..utils import ( parse_iso8601, + sanitized_Request, ) @@ -54,7 +52,7 @@ class SportDeutschlandIE(InfoExtractor): api_url = 'http://proxy.vidibusdynamic.net/sportdeutschland.tv/api/permalinks/%s/%s?access_token=true' % ( sport_id, video_id) - req = compat_urllib_request.Request(api_url, headers={ + req = sanitized_Request(api_url, headers={ 'Accept': 'application/vnd.vidibus.v2.html+json', 'Referer': url, }) diff --git a/youtube_dl/extractor/srf.py b/youtube_dl/extractor/srf.py index 77eec0bc7..16e1bf2d6 100644 --- a/youtube_dl/extractor/srf.py +++ b/youtube_dl/extractor/srf.py @@ -11,7 +11,7 @@ from ..utils import ( class SrfIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.srf\.ch/play(?:er)?/tv/[^/]+/video/(?P<display_id>[^?]+)\?id=|tp\.srgssr\.ch/p/flash\?urn=urn:srf:ais:video:)(?P<id>[0-9a-f\-]{36})' + _VALID_URL = r'https?://(?:www\.srf\.ch/play(?:er)?/(?:tv|radio)/[^/]+/(?P<media_type>video|audio)/(?P<display_id>[^?]+)\?id=|tp\.srgssr\.ch/p/flash\?urn=urn:srf:ais:video:)(?P<id>[0-9a-f\-]{36})' _TESTS = [{ 'url': 'http://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5', 'md5': '4cd93523723beff51bb4bee974ee238d', @@ -36,6 +36,20 @@ class SrfIE(InfoExtractor): 'timestamp': 1373493600, }, }, { + 'url': 'http://www.srf.ch/play/radio/hoerspielarchiv-srf-musikwelle/audio/saegel-ohni-wind-von-jakob-stebler?id=415bf3d3-6429-4de7-968d-95866e37cfbc', + 'md5': '', + 'info_dict': { + 'id': '415bf3d3-6429-4de7-968d-95866e37cfbc', + 'display_id': 'saegel-ohni-wind-von-jakob-stebler', + 'ext': 'mp3', + 'upload_date': '20080518', + 'title': '«Sägel ohni Wind» von Jakob Stebler', + 'timestamp': 1211112000, + }, + 'params': { + 'skip_download': True, # requires rtmpdump + }, + }, { 'url': 'http://www.srf.ch/player/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5', 'only_matching': True, }, { @@ -44,11 +58,13 @@ class SrfIE(InfoExtractor): }] def _real_extract(self, url): - video_id = self._match_id(url) - display_id = re.match(self._VALID_URL, url).group('display_id') or video_id + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + media_type = mobj.group('media_type') + display_id = mobj.group('display_id') or video_id video_data = self._download_xml( - 'http://il.srgssr.ch/integrationlayer/1.0/ue/srf/video/play/%s.xml' % video_id, + 'http://il.srgssr.ch/integrationlayer/1.0/ue/srf/%s/play/%s.xml' % (media_type, video_id), display_id) title = xpath_text( @@ -64,7 +80,7 @@ class SrfIE(InfoExtractor): for url_node in item.findall('url'): quality = url_node.attrib['quality'] full_url = url_node.text - original_ext = determine_ext(full_url) + original_ext = determine_ext(full_url).lower() format_id = '%s-%s' % (quality, item.attrib['protocol']) if original_ext == 'f4m': formats.extend(self._extract_f4m_formats( diff --git a/youtube_dl/extractor/streamcloud.py b/youtube_dl/extractor/streamcloud.py index d4e134015..77841b946 100644 --- a/youtube_dl/extractor/streamcloud.py +++ b/youtube_dl/extractor/streamcloud.py @@ -4,10 +4,8 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) +from ..compat import compat_urllib_parse +from ..utils import sanitized_Request class StreamcloudIE(InfoExtractor): @@ -43,7 +41,7 @@ class StreamcloudIE(InfoExtractor): headers = { b'Content-Type': b'application/x-www-form-urlencoded', } - req = compat_urllib_request.Request(url, post, headers) + req = sanitized_Request(url, post, headers) webpage = self._download_webpage( req, video_id, note='Downloading video page ...') diff --git a/youtube_dl/extractor/streamcz.py b/youtube_dl/extractor/streamcz.py index e92b93285..d3d2b7eb7 100644 --- a/youtube_dl/extractor/streamcz.py +++ b/youtube_dl/extractor/streamcz.py @@ -5,11 +5,9 @@ import hashlib import time from .common import InfoExtractor -from ..compat import ( - compat_urllib_request, -) from ..utils import ( int_or_none, + sanitized_Request, ) @@ -54,7 +52,7 @@ class StreamCZIE(InfoExtractor): video_id = self._match_id(url) api_path = '/episode/%s' % video_id - req = compat_urllib_request.Request(self._API_URL + api_path) + req = sanitized_Request(self._API_URL + api_path) req.add_header('Api-Password', _get_api_key(api_path)) data = self._download_json(req, video_id) diff --git a/youtube_dl/extractor/tapely.py b/youtube_dl/extractor/tapely.py index 744f9db38..ed560bd24 100644 --- a/youtube_dl/extractor/tapely.py +++ b/youtube_dl/extractor/tapely.py @@ -4,14 +4,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_request, -) from ..utils import ( clean_html, ExtractorError, float_or_none, parse_iso8601, + sanitized_Request, ) @@ -53,7 +51,7 @@ class TapelyIE(InfoExtractor): display_id = mobj.group('id') playlist_url = self._API_URL.format(display_id) - request = compat_urllib_request.Request(playlist_url) + request = sanitized_Request(playlist_url) request.add_header('X-Requested-With', 'XMLHttpRequest') request.add_header('Accept', 'application/json') request.add_header('Referer', url) diff --git a/youtube_dl/extractor/teachingchannel.py b/youtube_dl/extractor/teachingchannel.py index 117afa9bf..e0477382c 100644 --- a/youtube_dl/extractor/teachingchannel.py +++ b/youtube_dl/extractor/teachingchannel.py @@ -16,6 +16,7 @@ class TeachingChannelIE(InfoExtractor): 'ext': 'mp4', 'title': 'A History of Teaming', 'description': 'md5:2a9033db8da81f2edffa4c99888140b3', + 'duration': 422.255, }, 'params': { # m3u8 download diff --git a/youtube_dl/extractor/tele13.py b/youtube_dl/extractor/tele13.py new file mode 100644 index 000000000..a363b4d40 --- /dev/null +++ b/youtube_dl/extractor/tele13.py @@ -0,0 +1,81 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from .youtube import YoutubeIE +from ..utils import ( + js_to_json, + qualities, + determine_ext, +) + + +class Tele13IE(InfoExtractor): + _VALID_URL = r'^http://(?:www\.)?t13\.cl/videos(?:/[^/]+)+/(?P<id>[\w-]+)' + _TESTS = [ + { + 'url': 'http://www.t13.cl/videos/actualidad/el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda', + 'md5': '4cb1fa38adcad8fea88487a078831755', + 'info_dict': { + 'id': 'el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda', + 'ext': 'mp4', + 'title': 'El círculo de hierro de Michelle Bachelet en su regreso a La Moneda', + }, + 'params': { + # HTTP Error 404: Not Found + 'skip_download': True, + }, + }, + { + 'url': 'http://www.t13.cl/videos/mundo/tendencias/video-captan-misteriosa-bola-fuego-cielos-bangkok', + 'md5': '867adf6a3b3fef932c68a71d70b70946', + 'info_dict': { + 'id': 'rOoKv2OMpOw', + 'ext': 'mp4', + 'title': 'Shooting star seen on 7-Sep-2015', + 'description': 'md5:7292ff2a34b2f673da77da222ae77e1e', + 'uploader': 'Porjai Jaturongkhakun', + 'upload_date': '20150906', + 'uploader_id': 'UCnLY_3ezwNcDSC_Wc6suZxw', + }, + 'add_ie': ['Youtube'], + } + ] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + setup_js = self._search_regex(r"(?s)jwplayer\('player-vivo'\).setup\((\{.*?\})\)", webpage, 'setup code') + sources = self._parse_json(self._search_regex(r'sources\s*:\s*(\[[^\]]+\])', setup_js, 'sources'), display_id, js_to_json) + + preference = qualities(['Móvil', 'SD', 'HD']) + formats = [] + urls = [] + for f in sources: + format_url = f['file'] + if format_url and format_url not in urls: + ext = determine_ext(format_url) + if ext == 'm3u8': + m3u8_formats = self._extract_m3u8_formats(format_url, display_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + elif YoutubeIE.suitable(format_url): + return self.url_result(format_url, 'Youtube') + else: + formats.append({ + 'url': format_url, + 'format_id': f.get('label'), + 'preference': preference(f.get('label')), + 'ext': ext, + }) + urls.append(format_url) + self._sort_formats(formats) + + return { + 'id': display_id, + 'title': self._search_regex(r'title\s*:\s*"([^"]+)"', setup_js, 'title'), + 'description': self._html_search_meta('description', webpage, 'description'), + 'thumbnail': self._search_regex(r'image\s*:\s*"([^"]+)"', setup_js, 'thumbnail', default=None), + 'formats': formats, + } diff --git a/youtube_dl/extractor/tf1.py b/youtube_dl/extractor/tf1.py index 3a68eaa80..6890021cf 100644 --- a/youtube_dl/extractor/tf1.py +++ b/youtube_dl/extractor/tf1.py @@ -6,7 +6,7 @@ from .common import InfoExtractor class TF1IE(InfoExtractor): """TF1 uses the wat.tv player.""" - _VALID_URL = r'http://(?:(?:videos|www|lci)\.tf1|www\.tfou)\.fr/.*?-(?P<id>\d+)(?:-\d+)?\.html' + _VALID_URL = r'http://(?:(?:videos|www|lci)\.tf1|www\.tfou)\.fr/(?:[^/]+/)*(?P<id>.+?)\.html' _TESTS = [{ 'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html', 'info_dict': { @@ -22,7 +22,7 @@ class TF1IE(InfoExtractor): }, { 'url': 'http://www.tfou.fr/chuggington/videos/le-grand-mysterioso-chuggington-7085291-739.html', 'info_dict': { - 'id': '12043945', + 'id': 'le-grand-mysterioso-chuggington-7085291-739', 'ext': 'mp4', 'title': 'Le grand Mystérioso - Chuggington', 'description': 'Le grand Mystérioso - Emery rêve qu\'un article lui soit consacré dans le journal.', @@ -32,22 +32,24 @@ class TF1IE(InfoExtractor): # Sometimes wat serves the whole file with the --test option 'skip_download': True, }, + 'skip': 'HTTP Error 410: Gone', }, { 'url': 'http://www.tf1.fr/tf1/koh-lanta/videos/replay-koh-lanta-22-mai-2015.html', 'only_matching': True, }, { 'url': 'http://lci.tf1.fr/sept-a-huit/videos/sept-a-huit-du-24-mai-2015-8611550.html', 'only_matching': True, + }, { + 'url': 'http://www.tf1.fr/hd1/documentaire/videos/mylene-farmer-d-une-icone.html', + 'only_matching': True, }] def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - embed_url = self._html_search_regex( - r'["\'](https?://www.wat.tv/embedframe/.*?)["\']', webpage, 'embed url') - embed_page = self._download_webpage(embed_url, video_id, - 'Downloading embed player page') - wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id') + wat_id = self._html_search_regex( + r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})\1', + webpage, 'wat id', group='id') wat_info = self._download_json( 'http://www.wat.tv/interface/contentv3/%s' % wat_id, video_id) return self.url_result(wat_info['media']['url'], 'Wat') diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index 25edc3100..0bf6726b5 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -16,11 +16,12 @@ from ..compat import ( from ..utils import ( determine_ext, ExtractorError, - xpath_with_ns, - unsmuggle_url, + float_or_none, int_or_none, + sanitized_Request, + unsmuggle_url, url_basename, - float_or_none, + xpath_with_ns, ) default_ns = 'http://www.w3.org/2005/SMIL21/Language' @@ -139,6 +140,11 @@ class ThePlatformIE(ThePlatformBaseIE): 'upload_date': '20150701', 'categories': ['Today/Shows/Orange Room', 'Today/Sections/Money', 'Today/Topics/Tech', "Today/Topics/Editor's picks"], }, + }, { + # From http://www.nbc.com/the-blacklist/video/sir-crispin-crandall/2928790?onid=137781#vc137781=1 + # geo-restricted (US), HLS encrypted with AES-128 + 'url': 'http://player.theplatform.com/p/NnzsPC/onsite_universal/select/media/guid/2410887629/2928790?fwsitesection=nbc_the_blacklist_video_library&autoPlay=true&carouselID=137781', + 'only_matching': True, }] @staticmethod @@ -182,8 +188,12 @@ class ThePlatformIE(ThePlatformBaseIE): # Seems there's no pattern for the interested script filename, so # I try one by one for script in reversed(scripts): - feed_script = self._download_webpage(script, video_id, 'Downloading feed script') - feed_id = self._search_regex(r'defaultFeedId\s*:\s*"([^"]+)"', feed_script, 'default feed id', default=None) + feed_script = self._download_webpage( + self._proto_relative_url(script, 'http:'), + video_id, 'Downloading feed script') + feed_id = self._search_regex( + r'defaultFeedId\s*:\s*"([^"]+)"', feed_script, + 'default feed id', default=None) if feed_id is not None: break if feed_id is None: @@ -193,6 +203,20 @@ class ThePlatformIE(ThePlatformBaseIE): if smuggled_data.get('force_smil_url', False): smil_url = url + # Explicitly specified SMIL (see https://github.com/rg3/youtube-dl/issues/7385) + elif '/guid/' in url: + headers = {} + source_url = smuggled_data.get('source_url') + if source_url: + headers['Referer'] = source_url + request = sanitized_Request(url, headers=headers) + webpage = self._download_webpage(request, video_id) + smil_url = self._search_regex( + r'<link[^>]+href=(["\'])(?P<url>.+?)\1[^>]+type=["\']application/smil\+xml', + webpage, 'smil url', group='url') + path = self._search_regex( + r'link\.theplatform\.com/s/((?:[^/?#&]+/)+[^/?#&]+)', smil_url, 'path') + smil_url += '?' if '?' not in smil_url else '&' + 'formats=m3u,mpeg4&format=SMIL' elif mobj.group('config'): config_url = url + '&form=json' config_url = config_url.replace('swf/', 'config/') diff --git a/youtube_dl/extractor/tlc.py b/youtube_dl/extractor/tlc.py index 13263614c..d6d038a8d 100644 --- a/youtube_dl/extractor/tlc.py +++ b/youtube_dl/extractor/tlc.py @@ -3,7 +3,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from .brightcove import BrightcoveIE +from .brightcove import BrightcoveLegacyIE from .discovery import DiscoveryIE from ..compat import compat_urlparse @@ -66,6 +66,6 @@ class TlcDeIE(InfoExtractor): return { '_type': 'url', - 'url': BrightcoveIE._extract_brightcove_url(iframe), - 'ie': BrightcoveIE.ie_key(), + 'url': BrightcoveLegacyIE._extract_brightcove_url(iframe), + 'ie': BrightcoveLegacyIE.ie_key(), } diff --git a/youtube_dl/extractor/toggle.py b/youtube_dl/extractor/toggle.py new file mode 100644 index 000000000..a47239952 --- /dev/null +++ b/youtube_dl/extractor/toggle.py @@ -0,0 +1,194 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + ExtractorError, + float_or_none, + int_or_none, + parse_iso8601, + sanitized_Request, +) + + +class ToggleIE(InfoExtractor): + IE_NAME = 'toggle' + _VALID_URL = r'https?://video\.toggle\.sg/(?:en|zh)/(?:series|clips|movies)/(?:[^/]+/)+(?P<id>[0-9]+)' + _TESTS = [{ + 'url': 'http://video.toggle.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115', + 'info_dict': { + 'id': '343115', + 'ext': 'mp4', + 'title': 'Lion Moms Premiere', + 'description': 'md5:aea1149404bff4d7f7b6da11fafd8e6b', + 'upload_date': '20150910', + 'timestamp': 1441858274, + }, + 'params': { + 'skip_download': 'm3u8 download', + } + }, { + 'note': 'DRM-protected video', + 'url': 'http://video.toggle.sg/en/movies/dug-s-special-mission/341413', + 'info_dict': { + 'id': '341413', + 'ext': 'wvm', + 'title': 'Dug\'s Special Mission', + 'description': 'md5:e86c6f4458214905c1772398fabc93e0', + 'upload_date': '20150827', + 'timestamp': 1440644006, + }, + 'params': { + 'skip_download': 'DRM-protected wvm download', + } + }, { + # this also tests correct video id extraction + 'note': 'm3u8 links are geo-restricted, but Android/mp4 is okay', + 'url': 'http://video.toggle.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861', + 'info_dict': { + 'id': '332861', + 'ext': 'mp4', + 'title': '28th SEA Games (5 Show) - Episode 11', + 'description': 'md5:3cd4f5f56c7c3b1340c50a863f896faa', + 'upload_date': '20150605', + 'timestamp': 1433480166, + }, + 'params': { + 'skip_download': 'DRM-protected wvm download', + }, + 'skip': 'm3u8 links are geo-restricted' + }, { + 'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331', + 'only_matching': True, + }, { + 'url': 'http://video.toggle.sg/zh/series/zero-calling-s2-hd/ep13/336367', + 'only_matching': True, + }, { + 'url': 'http://video.toggle.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302', + 'only_matching': True, + }, { + 'url': 'http://video.toggle.sg/en/movies/seven-days/321936', + 'only_matching': True, + }] + + _FORMAT_PREFERENCES = { + 'wvm-STBMain': -10, + 'wvm-iPadMain': -20, + 'wvm-iPhoneMain': -30, + 'wvm-Android': -40, + } + _API_USER = 'tvpapi_147' + _API_PASS = '11111' + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage( + url, video_id, note='Downloading video page') + + api_user = self._search_regex( + r'apiUser\s*:\s*(["\'])(?P<user>.+?)\1', webpage, 'apiUser', + default=self._API_USER, group='user') + api_pass = self._search_regex( + r'apiPass\s*:\s*(["\'])(?P<pass>.+?)\1', webpage, 'apiPass', + default=self._API_PASS, group='pass') + + params = { + 'initObj': { + 'Locale': { + 'LocaleLanguage': '', + 'LocaleCountry': '', + 'LocaleDevice': '', + 'LocaleUserState': 0 + }, + 'Platform': 0, + 'SiteGuid': 0, + 'DomainID': '0', + 'UDID': '', + 'ApiUser': api_user, + 'ApiPass': api_pass + }, + 'MediaID': video_id, + 'mediaType': 0, + } + + req = sanitized_Request( + 'http://tvpapi.as.tvinci.com/v2_9/gateways/jsonpostgw.aspx?m=GetMediaInfo', + json.dumps(params).encode('utf-8')) + info = self._download_json(req, video_id, 'Downloading video info json') + + title = info['MediaName'] + + formats = [] + for video_file in info.get('Files', []): + video_url, vid_format = video_file.get('URL'), video_file.get('Format') + if not video_url or not vid_format: + continue + ext = determine_ext(video_url) + vid_format = vid_format.replace(' ', '') + # if geo-restricted, m3u8 is inaccessible, but mp4 is okay + if ext == 'm3u8': + m3u8_formats = self._extract_m3u8_formats( + video_url, video_id, ext='mp4', m3u8_id=vid_format, + note='Downloading %s m3u8 information' % vid_format, + errnote='Failed to download %s m3u8 information' % vid_format, + fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + elif ext in ('mp4', 'wvm'): + # wvm are drm-protected files + formats.append({ + 'ext': ext, + 'url': video_url, + 'format_id': vid_format, + 'preference': self._FORMAT_PREFERENCES.get(ext + '-' + vid_format) or -1, + 'format_note': 'DRM-protected video' if ext == 'wvm' else None + }) + if not formats: + # Most likely because geo-blocked + raise ExtractorError('No downloadable videos found', expected=True) + self._sort_formats(formats) + + duration = int_or_none(info.get('Duration')) + description = info.get('Description') + created_at = parse_iso8601(info.get('CreationDate') or None) + + average_rating = float_or_none(info.get('Rating')) + view_count = int_or_none(info.get('ViewCounter') or info.get('view_counter')) + like_count = int_or_none(info.get('LikeCounter') or info.get('like_counter')) + + thumbnails = [] + for picture in info.get('Pictures', []): + if not isinstance(picture, dict): + continue + pic_url = picture.get('URL') + if not pic_url: + continue + thumbnail = { + 'url': pic_url, + } + pic_size = picture.get('PicSize', '') + m = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', pic_size) + if m: + thumbnail.update({ + 'width': int(m.group('width')), + 'height': int(m.group('height')), + }) + thumbnails.append(thumbnail) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'duration': duration, + 'timestamp': created_at, + 'average_rating': average_rating, + 'view_count': view_count, + 'like_count': like_count, + 'thumbnails': thumbnails, + 'formats': formats, + } diff --git a/youtube_dl/extractor/trilulilu.py b/youtube_dl/extractor/trilulilu.py index 185accc4b..a800449e9 100644 --- a/youtube_dl/extractor/trilulilu.py +++ b/youtube_dl/extractor/trilulilu.py @@ -1,80 +1,103 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ExtractorError +from ..utils import ( + ExtractorError, + int_or_none, + parse_iso8601, +) class TriluliluIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?trilulilu\.ro/(?:video-[^/]+/)?(?P<id>[^/#\?]+)' - _TEST = { - 'url': 'http://www.trilulilu.ro/video-animatie/big-buck-bunny-1', - 'md5': 'c1450a00da251e2769b74b9005601cac', + _VALID_URL = r'https?://(?:(?:www|m)\.)?trilulilu\.ro/(?:[^/]+/)?(?P<id>[^/#\?]+)' + _TESTS = [{ + 'url': 'http://www.trilulilu.ro/big-buck-bunny-1', + 'md5': '68da087b676a6196a413549212f60cc6', 'info_dict': { 'id': 'ae2899e124140b', 'ext': 'mp4', 'title': 'Big Buck Bunny', 'description': ':) pentru copilul din noi', + 'uploader_id': 'chipy', + 'upload_date': '20120304', + 'timestamp': 1330830647, + 'uploader': 'chipy', + 'view_count': int, + 'like_count': int, + 'comment_count': int, }, - } + }, { + 'url': 'http://www.trilulilu.ro/adena-ft-morreti-inocenta', + 'md5': '929dfb8729dc71750463af88bbbbf4a4', + 'info_dict': { + 'id': 'f299710e3c91c5', + 'ext': 'mp4', + 'title': 'Adena ft. Morreti - Inocenta', + 'description': 'pop music', + 'uploader_id': 'VEVOmixt', + 'upload_date': '20151204', + 'uploader': 'VEVOmixt', + 'timestamp': 1449187937, + 'view_count': int, + 'like_count': int, + 'comment_count': int, + }, + }] def _real_extract(self, url): display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) + media_info = self._download_json('http://m.trilulilu.ro/%s?format=json' % display_id, display_id) - if re.search(r'Fişierul nu este disponibil pentru vizionare în ţara dumneavoastră', webpage): - raise ExtractorError( - 'This video is not available in your country.', expected=True) - elif re.search('Fişierul poate fi accesat doar de către prietenii lui', webpage): + age_limit = 0 + errors = media_info.get('errors', {}) + if errors.get('friends'): raise ExtractorError('This video is private.', expected=True) + elif errors.get('geoblock'): + raise ExtractorError('This video is not available in your country.', expected=True) + elif errors.get('xxx_unlogged'): + age_limit = 18 - flashvars_str = self._search_regex( - r'block_flash_vars\s*=\s*(\{[^\}]+\})', webpage, 'flashvars', fatal=False, default=None) + media_class = media_info.get('class') + if media_class not in ('video', 'audio'): + raise ExtractorError('not a video or an audio') - if flashvars_str: - flashvars = self._parse_json(flashvars_str, display_id) - else: - raise ExtractorError( - 'This page does not contain videos', expected=True) + user = media_info.get('user', {}) - if flashvars['isMP3'] == 'true': - raise ExtractorError( - 'Audio downloads are currently not supported', expected=True) + thumbnail = media_info.get('cover_url') + if thumbnail: + thumbnail.format(width='1600', height='1200') - video_id = flashvars['hash'] - title = self._og_search_title(webpage) - thumbnail = self._og_search_thumbnail(webpage) - description = self._og_search_description(webpage, default=None) - - format_url = ('http://fs%(server)s.trilulilu.ro/%(hash)s/' - 'video-formats2' % flashvars) - format_doc = self._download_xml( - format_url, video_id, - note='Downloading formats', - errnote='Error while downloading formats') - - video_url_template = ( - 'http://fs%(server)s.trilulilu.ro/stream.php?type=video' - '&source=site&hash=%(hash)s&username=%(userid)s&' - 'key=ministhebest&format=%%s&sig=&exp=' % - flashvars) - formats = [ - { - 'format_id': fnode.text.partition('-')[2], - 'url': video_url_template % fnode.text, - 'ext': fnode.text.partition('-')[0] - } - - for fnode in format_doc.findall('./formats/format') - ] + # TODO: get correct ext for audio files + stream_type = media_info.get('stream_type') + formats = [{ + 'url': media_info['href'], + 'ext': stream_type, + }] + if media_info.get('is_hd'): + formats.append({ + 'format_id': 'hd', + 'url': media_info['hrefhd'], + 'ext': stream_type, + }) + if media_class == 'audio': + formats[0]['vcodec'] = 'none' + else: + formats[0]['format_id'] = 'sd' return { - 'id': video_id, + 'id': media_info['identifier'].split('|')[1], 'display_id': display_id, 'formats': formats, - 'title': title, - 'description': description, + 'title': media_info['title'], + 'description': media_info.get('description'), 'thumbnail': thumbnail, + 'uploader_id': user.get('username'), + 'uploader': user.get('fullname'), + 'timestamp': parse_iso8601(media_info.get('published'), ' '), + 'duration': int_or_none(media_info.get('duration')), + 'view_count': int_or_none(media_info.get('count_views')), + 'like_count': int_or_none(media_info.get('count_likes')), + 'comment_count': int_or_none(media_info.get('count_comments')), + 'age_limit': age_limit, } diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py index c9cb69333..46ef61ff5 100644 --- a/youtube_dl/extractor/tube8.py +++ b/youtube_dl/extractor/tube8.py @@ -4,12 +4,10 @@ import json import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse_urlparse, - compat_urllib_request, -) +from ..compat import compat_urllib_parse_urlparse from ..utils import ( int_or_none, + sanitized_Request, str_to_int, ) from ..aes import aes_decrypt_text @@ -42,7 +40,7 @@ class Tube8IE(InfoExtractor): video_id = mobj.group('id') display_id = mobj.group('display_id') - req = compat_urllib_request.Request(url) + req = sanitized_Request(url) req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, display_id) diff --git a/youtube_dl/extractor/tubitv.py b/youtube_dl/extractor/tubitv.py index 4f86b3ee9..6d78b5dfe 100644 --- a/youtube_dl/extractor/tubitv.py +++ b/youtube_dl/extractor/tubitv.py @@ -5,13 +5,11 @@ import codecs import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request -) +from ..compat import compat_urllib_parse from ..utils import ( ExtractorError, int_or_none, + sanitized_Request, ) @@ -44,7 +42,7 @@ class TubiTvIE(InfoExtractor): 'password': password, } payload = compat_urllib_parse.urlencode(form_data).encode('utf-8') - request = compat_urllib_request.Request(self._LOGIN_URL, payload) + request = sanitized_Request(self._LOGIN_URL, payload) request.add_header('Content-Type', 'application/x-www-form-urlencoded') login_page = self._download_webpage( request, None, False, 'Wrong login info') diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index 3ec08b674..69882da63 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -11,7 +11,6 @@ from ..compat import ( compat_str, compat_urllib_parse, compat_urllib_parse_urlparse, - compat_urllib_request, compat_urlparse, ) from ..utils import ( @@ -20,6 +19,7 @@ from ..utils import ( int_or_none, parse_duration, parse_iso8601, + sanitized_Request, ) @@ -48,7 +48,7 @@ class TwitchBaseIE(InfoExtractor): for cookie in self._downloader.cookiejar: if cookie.name == 'api_token': headers['Twitch-Api-Token'] = cookie.value - request = compat_urllib_request.Request(url, headers=headers) + request = sanitized_Request(url, headers=headers) response = super(TwitchBaseIE, self)._download_json(request, video_id, note) self._handle_error(response) return response @@ -80,7 +80,7 @@ class TwitchBaseIE(InfoExtractor): if not post_url.startswith('http'): post_url = compat_urlparse.urljoin(redirect_url, post_url) - request = compat_urllib_request.Request( + request = sanitized_Request( post_url, compat_urllib_parse.urlencode(encode_dict(login_form)).encode('utf-8')) request.add_header('Referer', redirect_url) response = self._download_webpage( diff --git a/youtube_dl/extractor/twitter.py b/youtube_dl/extractor/twitter.py index 9d3e46b94..a161f046b 100644 --- a/youtube_dl/extractor/twitter.py +++ b/youtube_dl/extractor/twitter.py @@ -4,11 +4,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_urllib_request from ..utils import ( float_or_none, xpath_text, remove_end, + int_or_none, + ExtractorError, + sanitized_Request, ) @@ -18,7 +20,7 @@ class TwitterCardIE(InfoExtractor): _TESTS = [ { 'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889', - 'md5': '7d2f6b4d2eb841a7ccc893d479bfceb4', + 'md5': '4fa26a35f9d1bf4b646590ba8e84be19', 'info_dict': { 'id': '560070183650213889', 'ext': 'mp4', @@ -50,6 +52,20 @@ class TwitterCardIE(InfoExtractor): 'uploader': 'OMG! Ubuntu!', 'uploader_id': 'omgubuntu', }, + 'add_ie': ['Youtube'], + }, + { + 'url': 'https://twitter.com/i/cards/tfw/v1/665289828897005568', + 'md5': 'ab2745d0b0ce53319a534fccaa986439', + 'info_dict': { + 'id': 'iBb2x00UVlv', + 'ext': 'mp4', + 'upload_date': '20151113', + 'uploader_id': '1189339351084113920', + 'uploader': '@ArsenalTerje', + 'title': 'Vine by @ArsenalTerje', + }, + 'add_ie': ['Vine'], } ] @@ -65,15 +81,15 @@ class TwitterCardIE(InfoExtractor): config = None formats = [] for user_agent in USER_AGENTS: - request = compat_urllib_request.Request(url) + request = sanitized_Request(url) request.add_header('User-Agent', user_agent) webpage = self._download_webpage(request, video_id) - youtube_url = self._html_search_regex( - r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"', - webpage, 'youtube iframe', default=None) - if youtube_url: - return self.url_result(youtube_url, 'Youtube') + iframe_url = self._html_search_regex( + r'<iframe[^>]+src="((?:https?:)?//(?:www.youtube.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"', + webpage, 'video iframe', default=None) + if iframe_url: + return self.url_result(iframe_url) config = self._parse_json(self._html_search_regex( r'data-player-config="([^"]+)"', webpage, 'data player config'), @@ -120,9 +136,9 @@ class TwitterIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.|m\.|mobile\.)?twitter\.com/(?P<user_id>[^/]+)/status/(?P<id>\d+)' _TEMPLATE_URL = 'https://twitter.com/%s/status/%s' - _TEST = { + _TESTS = [{ 'url': 'https://twitter.com/freethenipple/status/643211948184596480', - 'md5': '31cd83a116fc41f99ae3d909d4caf6a0', + 'md5': 'db6612ec5d03355953c3ca9250c97e5e', 'info_dict': { 'id': '643211948184596480', 'ext': 'mp4', @@ -133,7 +149,30 @@ class TwitterIE(InfoExtractor): 'uploader': 'FREE THE NIPPLE', 'uploader_id': 'freethenipple', }, - } + }, { + 'url': 'https://twitter.com/giphz/status/657991469417025536/photo/1', + 'md5': 'f36dcd5fb92bf7057f155e7d927eeb42', + 'info_dict': { + 'id': '657991469417025536', + 'ext': 'mp4', + 'title': 'Gifs - tu vai cai tu vai cai tu nao eh capaz disso tu vai cai', + 'description': 'Gifs on Twitter: "tu vai cai tu vai cai tu nao eh capaz disso tu vai cai https://t.co/tM46VHFlO5"', + 'thumbnail': 're:^https?://.*\.png', + 'uploader': 'Gifs', + 'uploader_id': 'giphz', + }, + }, { + 'url': 'https://twitter.com/starwars/status/665052190608723968', + 'md5': '39b7199856dee6cd4432e72c74bc69d4', + 'info_dict': { + 'id': '665052190608723968', + 'ext': 'mp4', + 'title': 'Star Wars - A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens.', + 'description': 'Star Wars on Twitter: "A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens."', + 'uploader_id': 'starwars', + 'uploader': 'Star Wars', + }, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -144,23 +183,46 @@ class TwitterIE(InfoExtractor): username = remove_end(self._og_search_title(webpage), ' on Twitter') - title = self._og_search_description(webpage).strip('').replace('\n', ' ') + title = description = self._og_search_description(webpage).strip('').replace('\n', ' ').strip('“”') # strip 'https -_t.co_BJYgOjSeGA' junk from filenames - mobj = re.match(r'“(.*)\s+(https?://[^ ]+)”', title) - title, short_url = mobj.groups() - - card_id = self._search_regex( - r'["\']/i/cards/tfw/v1/(\d+)', webpage, 'twitter card url') - card_url = 'https://twitter.com/i/cards/tfw/v1/' + card_id + title = re.sub(r'\s+(https?://[^ ]+)', '', title) - return { - '_type': 'url_transparent', - 'ie_key': 'TwitterCard', + info = { 'uploader_id': user_id, 'uploader': username, - 'url': card_url, 'webpage_url': url, - 'description': '%s on Twitter: "%s %s"' % (username, title, short_url), + 'description': '%s on Twitter: "%s"' % (username, description), 'title': username + ' - ' + title, } + + card_id = self._search_regex( + r'["\']/i/cards/tfw/v1/(\d+)', webpage, 'twitter card url', default=None) + if card_id: + card_url = 'https://twitter.com/i/cards/tfw/v1/' + card_id + info.update({ + '_type': 'url_transparent', + 'ie_key': 'TwitterCard', + 'url': card_url, + }) + return info + + mobj = re.search(r'''(?x) + <video[^>]+class="animated-gif"[^>]+ + (?:data-height="(?P<height>\d+)")?[^>]+ + (?:data-width="(?P<width>\d+)")?[^>]+ + (?:poster="(?P<poster>[^"]+)")?[^>]*>\s* + <source[^>]+video-src="(?P<url>[^"]+)" + ''', webpage) + + if mobj: + info.update({ + 'id': twid, + 'url': mobj.group('url'), + 'height': int_or_none(mobj.group('height')), + 'width': int_or_none(mobj.group('width')), + 'thumbnail': mobj.group('poster'), + }) + return info + + raise ExtractorError('There\'s not video in this tweet.') diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py index 365d8b4bf..59832b1ec 100644 --- a/youtube_dl/extractor/udemy.py +++ b/youtube_dl/extractor/udemy.py @@ -1,14 +1,16 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..compat import ( + compat_HTTPError, compat_urllib_parse, compat_urllib_request, ) from ..utils import ( ExtractorError, + float_or_none, + int_or_none, + sanitized_Request, ) @@ -17,6 +19,8 @@ class UdemyIE(InfoExtractor): _VALID_URL = r'https?://www\.udemy\.com/(?:[^#]+#/lecture/|lecture/view/?\?lectureId=)(?P<id>\d+)' _LOGIN_URL = 'https://www.udemy.com/join/login-popup/?displayType=ajax&showSkipButton=1' _ORIGIN_URL = 'https://www.udemy.com' + _SUCCESSFULLY_ENROLLED = '>You have enrolled in this course!<' + _ALREADY_ENROLLED = '>You are already taking this course.<' _NETRC_MACHINE = 'udemy' _TESTS = [{ @@ -32,6 +36,29 @@ class UdemyIE(InfoExtractor): 'skip': 'Requires udemy account credentials', }] + def _enroll_course(self, webpage, course_id): + enroll_url = self._search_regex( + r'href=(["\'])(?P<url>https?://(?:www\.)?udemy\.com/course/subscribe/.+?)\1', + webpage, 'enroll url', group='url', + default='https://www.udemy.com/course/subscribe/?courseId=%s' % course_id) + webpage = self._download_webpage(enroll_url, course_id, 'Enrolling in the course') + if self._SUCCESSFULLY_ENROLLED in webpage: + self.to_screen('%s: Successfully enrolled in' % course_id) + elif self._ALREADY_ENROLLED in webpage: + self.to_screen('%s: Already enrolled in' % course_id) + + def _download_lecture(self, course_id, lecture_id): + return self._download_json( + 'https://www.udemy.com/api-2.0/users/me/subscribed-courses/%s/lectures/%s?%s' % ( + course_id, lecture_id, compat_urllib_parse.urlencode({ + 'video_only': '', + 'auto_play': '', + 'fields[lecture]': 'title,description,asset', + 'fields[asset]': 'asset_type,stream_url,thumbnail_url,download_urls,data', + 'instructorPreviewMode': 'False', + })), + lecture_id, 'Downloading lecture JSON') + def _handle_error(self, response): if not isinstance(response, dict): return @@ -53,12 +80,13 @@ class UdemyIE(InfoExtractor): headers['X-Udemy-Client-Id'] = cookie.value elif cookie.name == 'access_token': headers['X-Udemy-Bearer-Token'] = cookie.value + headers['X-Udemy-Authorization'] = 'Bearer %s' % cookie.value if isinstance(url_or_request, compat_urllib_request.Request): for header, value in headers.items(): url_or_request.add_header(header, value) else: - url_or_request = compat_urllib_request.Request(url_or_request, headers=headers) + url_or_request = sanitized_Request(url_or_request, headers=headers) response = super(UdemyIE, self)._download_json(url_or_request, video_id, note) self._handle_error(response) @@ -70,7 +98,7 @@ class UdemyIE(InfoExtractor): def _login(self): (username, password) = self._get_login_info() if username is None: - self.raise_login_required('Udemy account is required') + return login_popup = self._download_webpage( self._LOGIN_URL, None, 'Downloading login popup') @@ -89,7 +117,7 @@ class UdemyIE(InfoExtractor): 'password': password.encode('utf-8'), }) - request = compat_urllib_request.Request( + request = sanitized_Request( self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8')) request.add_header('Referer', self._ORIGIN_URL) request.add_header('Origin', self._ORIGIN_URL) @@ -108,44 +136,76 @@ class UdemyIE(InfoExtractor): def _real_extract(self, url): lecture_id = self._match_id(url) - lecture = self._download_json( - 'https://www.udemy.com/api-1.1/lectures/%s' % lecture_id, - lecture_id, 'Downloading lecture JSON') + webpage = self._download_webpage(url, lecture_id) + + course_id = self._search_regex( + r'data-course-id=["\'](\d+)', webpage, 'course id') + + try: + lecture = self._download_lecture(course_id, lecture_id) + except ExtractorError as e: + # Error could possibly mean we are not enrolled in the course + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + self._enroll_course(webpage, course_id) + lecture_id = self._download_lecture(course_id, lecture_id) + else: + raise + + title = lecture['title'] + description = lecture.get('description') - asset_type = lecture.get('assetType') or lecture.get('asset_type') + asset = lecture['asset'] + + asset_type = asset.get('assetType') or asset.get('asset_type') if asset_type != 'Video': raise ExtractorError( 'Lecture %s is not a video' % lecture_id, expected=True) - asset = lecture['asset'] - stream_url = asset.get('streamUrl') or asset.get('stream_url') - mobj = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', stream_url) - if mobj: - return self.url_result(mobj.group(1), 'Youtube') + if stream_url: + youtube_url = self._search_regex( + r'(https?://www\.youtube\.com/watch\?v=.*)', stream_url, 'youtube URL', default=None) + if youtube_url: + return self.url_result(youtube_url, 'Youtube') video_id = asset['id'] thumbnail = asset.get('thumbnailUrl') or asset.get('thumbnail_url') - duration = asset['data']['duration'] - - download_url = asset.get('downloadUrl') or asset.get('download_url') - - video = download_url.get('Video') or download_url.get('video') - video_480p = download_url.get('Video480p') or download_url.get('video_480p') - - formats = [ - { - 'url': video_480p[0], - 'format_id': '360p', - }, - { - 'url': video[0], - 'format_id': '720p', - }, - ] - - title = lecture['title'] - description = lecture['description'] + duration = float_or_none(asset.get('data', {}).get('duration')) + outputs = asset.get('data', {}).get('outputs', {}) + + formats = [] + for format_ in asset.get('download_urls', {}).get('Video', []): + video_url = format_.get('file') + if not video_url: + continue + format_id = format_.get('label') + f = { + 'url': format_['file'], + 'height': int_or_none(format_id), + } + if format_id: + # Some videos contain additional metadata (e.g. + # https://www.udemy.com/ios9-swift/learn/#/lecture/3383208) + output = outputs.get(format_id) + if isinstance(output, dict): + f.update({ + 'format_id': '%sp' % (output.get('label') or format_id), + 'width': int_or_none(output.get('width')), + 'height': int_or_none(output.get('height')), + 'vbr': int_or_none(output.get('video_bitrate_in_kbps')), + 'vcodec': output.get('video_codec'), + 'fps': int_or_none(output.get('frame_rate')), + 'abr': int_or_none(output.get('audio_bitrate_in_kbps')), + 'acodec': output.get('audio_codec'), + 'asr': int_or_none(output.get('audio_sample_rate')), + 'tbr': int_or_none(output.get('total_bitrate_in_kbps')), + 'filesize': int_or_none(output.get('file_size_in_bytes')), + }) + else: + f['format_id'] = '%sp' % format_id + formats.append(f) + + self._sort_formats(formats) return { 'id': video_id, @@ -159,9 +219,7 @@ class UdemyIE(InfoExtractor): class UdemyCourseIE(UdemyIE): IE_NAME = 'udemy:course' - _VALID_URL = r'https?://www\.udemy\.com/(?P<coursepath>[\da-z-]+)' - _SUCCESSFULLY_ENROLLED = '>You have enrolled in this course!<' - _ALREADY_ENROLLED = '>You are already taking this course.<' + _VALID_URL = r'https?://www\.udemy\.com/(?P<id>[\da-z-]+)' _TESTS = [] @classmethod @@ -169,24 +227,18 @@ class UdemyCourseIE(UdemyIE): return False if UdemyIE.suitable(url) else super(UdemyCourseIE, cls).suitable(url) def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - course_path = mobj.group('coursepath') + course_path = self._match_id(url) + + webpage = self._download_webpage(url, course_path) response = self._download_json( 'https://www.udemy.com/api-1.1/courses/%s' % course_path, course_path, 'Downloading course JSON') - course_id = int(response['id']) - course_title = response['title'] + course_id = response['id'] + course_title = response.get('title') - webpage = self._download_webpage( - 'https://www.udemy.com/course/subscribe/?courseId=%s' % course_id, - course_id, 'Enrolling in the course') - - if self._SUCCESSFULLY_ENROLLED in webpage: - self.to_screen('%s: Successfully enrolled in' % course_id) - elif self._ALREADY_ENROLLED in webpage: - self.to_screen('%s: Already enrolled in' % course_id) + self._enroll_course(webpage, course_id) response = self._download_json( 'https://www.udemy.com/api-1.1/courses/%s/curriculum' % course_id, diff --git a/youtube_dl/extractor/udn.py b/youtube_dl/extractor/udn.py index 2151f8338..ee35b7227 100644 --- a/youtube_dl/extractor/udn.py +++ b/youtube_dl/extractor/udn.py @@ -12,7 +12,8 @@ from ..compat import compat_urlparse class UDNEmbedIE(InfoExtractor): IE_DESC = '聯合影音' - _VALID_URL = r'https?://video\.udn\.com/(?:embed|play)/news/(?P<id>\d+)' + _PROTOCOL_RELATIVE_VALID_URL = r'//video\.udn\.com/(?:embed|play)/news/(?P<id>\d+)' + _VALID_URL = r'https?:' + _PROTOCOL_RELATIVE_VALID_URL _TESTS = [{ 'url': 'http://video.udn.com/embed/news/300040', 'md5': 'de06b4c90b042c128395a88f0384817e', diff --git a/youtube_dl/extractor/vbox7.py b/youtube_dl/extractor/vbox7.py index 722eb5236..1e740fbe6 100644 --- a/youtube_dl/extractor/vbox7.py +++ b/youtube_dl/extractor/vbox7.py @@ -4,11 +4,11 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..compat import ( compat_urllib_parse, - compat_urllib_request, compat_urlparse, ) from ..utils import ( ExtractorError, + sanitized_Request, ) @@ -49,7 +49,7 @@ class Vbox7IE(InfoExtractor): info_url = "http://vbox7.com/play/magare.do" data = compat_urllib_parse.urlencode({'as3': '1', 'vid': video_id}) - info_request = compat_urllib_request.Request(info_url, data) + info_request = sanitized_Request(info_url, data) info_request.add_header('Content-Type', 'application/x-www-form-urlencoded') info_response = self._download_webpage(info_request, video_id, 'Downloading info webpage') if info_response is None: diff --git a/youtube_dl/extractor/veoh.py b/youtube_dl/extractor/veoh.py index 01e258e32..9633f7ffe 100644 --- a/youtube_dl/extractor/veoh.py +++ b/youtube_dl/extractor/veoh.py @@ -4,12 +4,10 @@ import re import json from .common import InfoExtractor -from ..compat import ( - compat_urllib_request, -) from ..utils import ( int_or_none, ExtractorError, + sanitized_Request, ) @@ -110,7 +108,7 @@ class VeohIE(InfoExtractor): if 'class="adultwarning-container"' in webpage: self.report_age_confirmation() age_limit = 18 - request = compat_urllib_request.Request(url) + request = sanitized_Request(url) request.add_header('Cookie', 'confirmedAdult=true') webpage = self._download_webpage(request, video_id) diff --git a/youtube_dl/extractor/vessel.py b/youtube_dl/extractor/vessel.py index 3c8d2a943..1a0ff3395 100644 --- a/youtube_dl/extractor/vessel.py +++ b/youtube_dl/extractor/vessel.py @@ -4,10 +4,10 @@ from __future__ import unicode_literals import json from .common import InfoExtractor -from ..compat import compat_urllib_request from ..utils import ( ExtractorError, parse_iso8601, + sanitized_Request, ) @@ -33,7 +33,7 @@ class VesselIE(InfoExtractor): @staticmethod def make_json_request(url, data): payload = json.dumps(data).encode('utf-8') - req = compat_urllib_request.Request(url, payload) + req = sanitized_Request(url, payload) req.add_header('Content-Type', 'application/json; charset=utf-8') return req diff --git a/youtube_dl/extractor/vevo.py b/youtube_dl/extractor/vevo.py index c17094f81..02dfd36f4 100644 --- a/youtube_dl/extractor/vevo.py +++ b/youtube_dl/extractor/vevo.py @@ -1,15 +1,16 @@ from __future__ import unicode_literals import re -import xml.etree.ElementTree from .common import InfoExtractor from ..compat import ( - compat_urllib_request, + compat_etree_fromstring, + compat_urlparse, ) from ..utils import ( ExtractorError, int_or_none, + sanitized_Request, ) @@ -69,11 +70,22 @@ class VevoIE(InfoExtractor): 'params': { 'skip_download': 'true', } + }, { + 'note': 'No video_info', + 'url': 'http://www.vevo.com/watch/k-camp-1/Till-I-Die/USUV71503000', + 'md5': '8b83cc492d72fc9cf74a02acee7dc1b0', + 'info_dict': { + 'id': 'USUV71503000', + 'ext': 'mp4', + 'title': 'Till I Die - K Camp ft. T.I.', + 'duration': 193, + }, + 'expected_warnings': ['Unable to download SMIL file'], }] _SMIL_BASE_URL = 'http://smil.lvl3.vevo.com/' def _real_initialize(self): - req = compat_urllib_request.Request( + req = sanitized_Request( 'http://www.vevo.com/auth', data=b'') webpage = self._download_webpage( req, None, @@ -83,11 +95,17 @@ class VevoIE(InfoExtractor): if webpage is False: self._oauth_token = None else: + if 'THIS PAGE IS CURRENTLY UNAVAILABLE IN YOUR REGION' in webpage: + raise ExtractorError('%s said: This page is currently unavailable in your region.' % self.IE_NAME, expected=True) + self._oauth_token = self._search_regex( r'access_token":\s*"([^"]+)"', webpage, 'access token', fatal=False) def _formats_from_json(self, video_info): + if not video_info: + return [] + last_version = {'version': -1} for version in video_info['videoVersions']: # These are the HTTP downloads, other types are for different manifests @@ -97,7 +115,7 @@ class VevoIE(InfoExtractor): if last_version['version'] == -1: raise ExtractorError('Unable to extract last version of the video') - renditions = xml.etree.ElementTree.fromstring(last_version['data']) + renditions = compat_etree_fromstring(last_version['data']) formats = [] # Already sorted from worst to best quality for rend in renditions.findall('rendition'): @@ -112,9 +130,8 @@ class VevoIE(InfoExtractor): }) return formats - def _formats_from_smil(self, smil_xml): + def _formats_from_smil(self, smil_doc): formats = [] - smil_doc = xml.etree.ElementTree.fromstring(smil_xml.encode('utf-8')) els = smil_doc.findall('.//{http://www.w3.org/2001/SMIL20/Language}video') for el in els: src = el.attrib['src'] @@ -147,14 +164,14 @@ class VevoIE(InfoExtractor): }) return formats - def _download_api_formats(self, video_id): + def _download_api_formats(self, video_id, video_url): if not self._oauth_token: self._downloader.report_warning( 'No oauth token available, skipping API HLS download') return [] - api_url = 'https://apiv2.vevo.com/video/%s/streams/hls?token=%s' % ( - video_id, self._oauth_token) + api_url = compat_urlparse.urljoin(video_url, '//apiv2.vevo.com/video/%s/streams/hls?token=%s' % ( + video_id, self._oauth_token)) api_data = self._download_json( api_url, video_id, note='Downloading HLS formats', @@ -168,18 +185,26 @@ class VevoIE(InfoExtractor): preference=0) def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) + + webpage = None json_url = 'http://videoplayer.vevo.com/VideoService/AuthenticateVideo?isrc=%s' % video_id response = self._download_json(json_url, video_id) - video_info = response['video'] + video_info = response['video'] or {} - if not video_info: + if not video_info and response.get('statusCode') != 909: if 'statusMessage' in response: raise ExtractorError('%s said: %s' % (self.IE_NAME, response['statusMessage']), expected=True) raise ExtractorError('Unable to extract videos') + if not video_info: + if url.startswith('vevo:'): + raise ExtractorError('Please specify full Vevo URL for downloading', expected=True) + webpage = self._download_webpage(url, video_id) + + title = video_info.get('title') or self._og_search_title(webpage) + formats = self._formats_from_json(video_info) is_explicit = video_info.get('isExplicit') @@ -191,11 +216,11 @@ class VevoIE(InfoExtractor): age_limit = None # Download via HLS API - formats.extend(self._download_api_formats(video_id)) + formats.extend(self._download_api_formats(video_id, url)) # Download SMIL smil_blocks = sorted(( - f for f in video_info['videoVersions'] + f for f in video_info.get('videoVersions', []) if f['sourceType'] == 13), key=lambda f: f['version']) smil_url = '%s/Video/V2/VFILE/%s/%sr.smil' % ( @@ -207,23 +232,26 @@ class VevoIE(InfoExtractor): if smil_url_m is not None: smil_url = smil_url_m if smil_url: - smil_xml = self._download_webpage( - smil_url, video_id, 'Downloading SMIL info', fatal=False) - if smil_xml: - formats.extend(self._formats_from_smil(smil_xml)) + smil_doc = self._download_smil(smil_url, video_id, fatal=False) + if smil_doc: + formats.extend(self._formats_from_smil(smil_doc)) self._sort_formats(formats) - timestamp_ms = int_or_none(self._search_regex( + timestamp = int_or_none(self._search_regex( r'/Date\((\d+)\)/', - video_info['launchDate'], 'launch date', fatal=False)) + video_info['launchDate'], 'launch date', fatal=False), + scale=1000) if video_info else None + + duration = video_info.get('duration') or int_or_none( + self._html_search_meta('video:duration', webpage)) return { 'id': video_id, - 'title': video_info['title'], + 'title': title, 'formats': formats, - 'thumbnail': video_info['imageUrl'], - 'timestamp': timestamp_ms // 1000, - 'uploader': video_info['mainArtists'][0]['artistName'], - 'duration': video_info['duration'], + 'thumbnail': video_info.get('imageUrl'), + 'timestamp': timestamp, + 'uploader': video_info['mainArtists'][0]['artistName'] if video_info else None, + 'duration': duration, 'age_limit': age_limit, } diff --git a/youtube_dl/extractor/vice.py b/youtube_dl/extractor/vice.py index 01af7a995..3db6286e4 100644 --- a/youtube_dl/extractor/vice.py +++ b/youtube_dl/extractor/vice.py @@ -15,6 +15,7 @@ class ViceIE(InfoExtractor): 'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp', 'ext': 'mp4', 'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov', + 'duration': 725.983, }, 'params': { # Requires ffmpeg (m3u8 manifest) diff --git a/youtube_dl/extractor/viddler.py b/youtube_dl/extractor/viddler.py index 8516a2940..40ffbad2a 100644 --- a/youtube_dl/extractor/viddler.py +++ b/youtube_dl/extractor/viddler.py @@ -4,9 +4,7 @@ from .common import InfoExtractor from ..utils import ( float_or_none, int_or_none, -) -from ..compat import ( - compat_urllib_request + sanitized_Request, ) @@ -65,7 +63,7 @@ class ViddlerIE(InfoExtractor): 'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json?video_id=%s&key=v0vhrt7bg2xq1vyxhkct' % video_id) headers = {'Referer': 'http://static.cdn-ec.viddler.com/js/arpeggio/v2/embed.html'} - request = compat_urllib_request.Request(json_url, None, headers) + request = sanitized_Request(json_url, None, headers) data = self._download_json(request, video_id)['video'] formats = [] diff --git a/youtube_dl/extractor/videofyme.py b/youtube_dl/extractor/videofyme.py index 94f9e9be9..cd3f50a63 100644 --- a/youtube_dl/extractor/videofyme.py +++ b/youtube_dl/extractor/videofyme.py @@ -2,8 +2,8 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( - find_xpath_attr, int_or_none, + parse_iso8601, ) @@ -18,33 +18,35 @@ class VideofyMeIE(InfoExtractor): 'id': '1100701', 'ext': 'mp4', 'title': 'This is VideofyMe', - 'description': None, + 'description': '', + 'upload_date': '20130326', + 'timestamp': 1364288959, 'uploader': 'VideofyMe', 'uploader_id': 'thisisvideofyme', 'view_count': int, + 'likes': int, + 'comment_count': int, }, - } def _real_extract(self, url): video_id = self._match_id(url) - config = self._download_xml('http://sunshine.videofy.me/?videoId=%s' % video_id, - video_id) - video = config.find('video') - sources = video.find('sources') - url_node = next(node for node in [find_xpath_attr(sources, 'source', 'id', 'HQ %s' % key) - for key in ['on', 'av', 'off']] if node is not None) - video_url = url_node.find('url').text - view_count = int_or_none(self._search_regex( - r'([0-9]+)', video.find('views').text, 'view count', fatal=False)) + + config = self._download_json('http://vf-player-info-loader.herokuapp.com/%s.json' % video_id, video_id)['videoinfo'] + + video = config.get('video') + blog = config.get('blog', {}) return { 'id': video_id, - 'title': video.find('title').text, - 'url': video_url, - 'thumbnail': video.find('thumb').text, - 'description': video.find('description').text, - 'uploader': config.find('blog/name').text, - 'uploader_id': video.find('identifier').text, - 'view_count': view_count, + 'title': video['title'], + 'url': video['sources']['source']['url'], + 'thumbnail': video.get('thumb'), + 'description': video.get('description'), + 'timestamp': parse_iso8601(video.get('date')), + 'uploader': blog.get('name'), + 'uploader_id': blog.get('identifier'), + 'view_count': int_or_none(self._search_regex(r'([0-9]+)', video.get('views'), 'view count', fatal=False)), + 'likes': int_or_none(video.get('likes')), + 'comment_count': int_or_none(video.get('nrOfComments')), } diff --git a/youtube_dl/extractor/videolecturesnet.py b/youtube_dl/extractor/videolecturesnet.py deleted file mode 100644 index 649ac9433..000000000 --- a/youtube_dl/extractor/videolecturesnet.py +++ /dev/null @@ -1,82 +0,0 @@ -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..compat import ( - compat_HTTPError, - compat_urlparse, -) -from ..utils import ( - ExtractorError, - parse_duration, -) - - -class VideoLecturesNetIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?videolectures\.net/(?P<id>[^/#?]+)/*(?:[#?].*)?$' - IE_NAME = 'videolectures.net' - - _TESTS = [{ - 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/', - 'info_dict': { - 'id': 'promogram_igor_mekjavic_eng', - 'ext': 'mp4', - 'title': 'Automatics, robotics and biocybernetics', - 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482', - 'upload_date': '20130627', - 'duration': 565, - 'thumbnail': 're:http://.*\.jpg', - }, - }, { - # video with invalid direct format links (HTTP 403) - 'url': 'http://videolectures.net/russir2010_filippova_nlp/', - 'info_dict': { - 'id': 'russir2010_filippova_nlp', - 'ext': 'flv', - 'title': 'NLP at Google', - 'description': 'md5:fc7a6d9bf0302d7cc0e53f7ca23747b3', - 'duration': 5352, - 'thumbnail': 're:http://.*\.jpg', - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - }, { - 'url': 'http://videolectures.net/deeplearning2015_montreal/', - 'info_dict': { - 'id': 'deeplearning2015_montreal', - 'title': 'Deep Learning Summer School, Montreal 2015', - 'description': 'md5:90121a40cc6926df1bf04dcd8563ed3b', - }, - 'playlist_count': 30, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - - smil_url = 'http://videolectures.net/%s/video/1/smil.xml' % video_id - - try: - smil = self._download_smil(smil_url, video_id) - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404: - # Probably a playlist - webpage = self._download_webpage(url, video_id) - entries = [ - self.url_result(compat_urlparse.urljoin(url, video_url), 'VideoLecturesNet') - for _, video_url in re.findall(r'<a[^>]+href=(["\'])(.+?)\1[^>]+id=["\']lec=\d+', webpage)] - playlist_title = self._html_search_meta('title', webpage, 'title', fatal=True) - playlist_description = self._html_search_meta('description', webpage, 'description') - return self.playlist_result(entries, video_id, playlist_title, playlist_description) - - info = self._parse_smil(smil, smil_url, video_id) - - info['id'] = video_id - - switch = smil.find('.//switch') - if switch is not None: - info['duration'] = parse_duration(switch.attrib.get('dur')) - - return info diff --git a/youtube_dl/extractor/videomega.py b/youtube_dl/extractor/videomega.py index 78ff6310a..87aca327b 100644 --- a/youtube_dl/extractor/videomega.py +++ b/youtube_dl/extractor/videomega.py @@ -4,7 +4,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_urllib_request +from ..utils import sanitized_Request class VideoMegaIE(InfoExtractor): @@ -30,7 +30,7 @@ class VideoMegaIE(InfoExtractor): video_id = self._match_id(url) iframe_url = 'http://videomega.tv/cdn.php?ref=%s' % video_id - req = compat_urllib_request.Request(iframe_url) + req = sanitized_Request(iframe_url) req.add_header('Referer', url) req.add_header('Cookie', 'noadvtday=0') webpage = self._download_webpage(req, video_id) diff --git a/youtube_dl/extractor/videoweed.py b/youtube_dl/extractor/videoweed.py deleted file mode 100644 index ca2e50935..000000000 --- a/youtube_dl/extractor/videoweed.py +++ /dev/null @@ -1,26 +0,0 @@ -from __future__ import unicode_literals - -from .novamov import NovaMovIE - - -class VideoWeedIE(NovaMovIE): - IE_NAME = 'videoweed' - IE_DESC = 'VideoWeed' - - _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'videoweed\.(?:es|com)'} - - _HOST = 'www.videoweed.es' - - _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' - _TITLE_REGEX = r'<h1 class="text_shadow">([^<]+)</h1>' - - _TEST = { - 'url': 'http://www.videoweed.es/file/b42178afbea14', - 'md5': 'abd31a2132947262c50429e1d16c1bfd', - 'info_dict': { - 'id': 'b42178afbea14', - 'ext': 'flv', - 'title': 'optical illusion dissapeared image magic illusion', - 'description': '' - }, - } diff --git a/youtube_dl/extractor/vidzi.py b/youtube_dl/extractor/vidzi.py index 08a5a7b8d..2ba9f31df 100644 --- a/youtube_dl/extractor/vidzi.py +++ b/youtube_dl/extractor/vidzi.py @@ -20,8 +20,14 @@ class VidziIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - video_url = self._html_search_regex( - r'{\s*file\s*:\s*"([^"]+)"\s*}', webpage, 'video url') + video_host = self._html_search_regex( + r'id=\'vplayer\'><img src="http://(.*?)/i', webpage, + 'video host') + video_hash = self._html_search_regex( + r'\|([a-z0-9]+)\|hls\|type', webpage, 'video_hash') + ext = self._html_search_regex( + r'\|tracks\|([a-z0-9]+)\|', webpage, 'video ext') + video_url = 'http://' + video_host + '/' + video_hash + '/v.' + ext title = self._html_search_regex( r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title') diff --git a/youtube_dl/extractor/viewster.py b/youtube_dl/extractor/viewster.py index 7cf930d69..185b1c119 100644 --- a/youtube_dl/extractor/viewster.py +++ b/youtube_dl/extractor/viewster.py @@ -4,7 +4,6 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..compat import ( compat_HTTPError, - compat_urllib_request, compat_urllib_parse, compat_urllib_parse_unquote, ) @@ -13,6 +12,7 @@ from ..utils import ( ExtractorError, int_or_none, parse_iso8601, + sanitized_Request, HEADRequest, ) @@ -76,7 +76,7 @@ class ViewsterIE(InfoExtractor): _ACCEPT_HEADER = 'application/json, text/javascript, */*; q=0.01' def _download_json(self, url, video_id, note='Downloading JSON metadata', fatal=True): - request = compat_urllib_request.Request(url) + request = sanitized_Request(url) request.add_header('Accept', self._ACCEPT_HEADER) request.add_header('Auth-token', self._AUTH_TOKEN) return super(ViewsterIE, self)._download_json(request, video_id, note, fatal=fatal) diff --git a/youtube_dl/extractor/viidea.py b/youtube_dl/extractor/viidea.py new file mode 100644 index 000000000..525e303d4 --- /dev/null +++ b/youtube_dl/extractor/viidea.py @@ -0,0 +1,188 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import ( + compat_urlparse, + compat_str, +) +from ..utils import ( + parse_duration, + js_to_json, + parse_iso8601, +) + + +class ViideaIE(InfoExtractor): + _VALID_URL = r'''(?x)http://(?:www\.)?(?: + videolectures\.net| + flexilearn\.viidea\.net| + presentations\.ocwconsortium\.org| + video\.travel-zoom\.si| + video\.pomp-forum\.si| + tv\.nil\.si| + video\.hekovnik.com| + video\.szko\.si| + kpk\.viidea\.com| + inside\.viidea\.net| + video\.kiberpipa\.org| + bvvideo\.si| + kongres\.viidea\.net| + edemokracija\.viidea\.com + )(?:/lecture)?/(?P<id>[^/]+)(?:/video/(?P<part>\d+))?/*(?:[#?].*)?$''' + + _TESTS = [{ + 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/', + 'info_dict': { + 'id': '20171', + 'display_id': 'promogram_igor_mekjavic_eng', + 'ext': 'mp4', + 'title': 'Automatics, robotics and biocybernetics', + 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482', + 'thumbnail': 're:http://.*\.jpg', + 'timestamp': 1372349289, + 'upload_date': '20130627', + 'duration': 565, + }, + }, { + # video with invalid direct format links (HTTP 403) + 'url': 'http://videolectures.net/russir2010_filippova_nlp/', + 'info_dict': { + 'id': '14891', + 'display_id': 'russir2010_filippova_nlp', + 'ext': 'flv', + 'title': 'NLP at Google', + 'description': 'md5:fc7a6d9bf0302d7cc0e53f7ca23747b3', + 'thumbnail': 're:http://.*\.jpg', + 'timestamp': 1284375600, + 'upload_date': '20100913', + 'duration': 5352, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, { + # event playlist + 'url': 'http://videolectures.net/deeplearning2015_montreal/', + 'info_dict': { + 'id': '23181', + 'title': 'Deep Learning Summer School, Montreal 2015', + 'description': 'md5:0533a85e4bd918df52a01f0e1ebe87b7', + 'thumbnail': 're:http://.*\.jpg', + 'timestamp': 1438560000, + }, + 'playlist_count': 30, + }, { + # multi part lecture + 'url': 'http://videolectures.net/mlss09uk_bishop_ibi/', + 'info_dict': { + 'id': '9737', + 'display_id': 'mlss09uk_bishop_ibi', + 'title': 'Introduction To Bayesian Inference', + 'thumbnail': 're:http://.*\.jpg', + 'timestamp': 1251622800, + }, + 'playlist': [{ + 'info_dict': { + 'id': '9737_part1', + 'display_id': 'mlss09uk_bishop_ibi_part1', + 'ext': 'wmv', + 'title': 'Introduction To Bayesian Inference (Part 1)', + 'thumbnail': 're:http://.*\.jpg', + 'duration': 4622, + 'timestamp': 1251622800, + 'upload_date': '20090830', + }, + }, { + 'info_dict': { + 'id': '9737_part2', + 'display_id': 'mlss09uk_bishop_ibi_part2', + 'ext': 'wmv', + 'title': 'Introduction To Bayesian Inference (Part 2)', + 'thumbnail': 're:http://.*\.jpg', + 'duration': 5641, + 'timestamp': 1251622800, + 'upload_date': '20090830', + }, + }], + 'playlist_count': 2, + }] + + def _real_extract(self, url): + lecture_slug, explicit_part_id = re.match(self._VALID_URL, url).groups() + + webpage = self._download_webpage(url, lecture_slug) + + cfg = self._parse_json(self._search_regex( + [r'cfg\s*:\s*({.+?})\s*,\s*[\da-zA-Z_]+\s*:\s*\(?\s*function', + r'cfg\s*:\s*({[^}]+})'], + webpage, 'cfg'), lecture_slug, js_to_json) + + lecture_id = compat_str(cfg['obj_id']) + + base_url = self._proto_relative_url(cfg['livepipe'], 'http:') + + lecture_data = self._download_json( + '%s/site/api/lecture/%s?format=json' % (base_url, lecture_id), + lecture_id)['lecture'][0] + + lecture_info = { + 'id': lecture_id, + 'display_id': lecture_slug, + 'title': lecture_data['title'], + 'timestamp': parse_iso8601(lecture_data.get('time')), + 'description': lecture_data.get('description_wiki'), + 'thumbnail': lecture_data.get('thumb'), + } + + playlist_entries = [] + lecture_type = lecture_data.get('type') + parts = [compat_str(video) for video in cfg.get('videos', [])] + if parts: + multipart = len(parts) > 1 + + def extract_part(part_id): + smil_url = '%s/%s/video/%s/smil.xml' % (base_url, lecture_slug, part_id) + smil = self._download_smil(smil_url, lecture_id) + info = self._parse_smil(smil, smil_url, lecture_id) + info['id'] = lecture_id if not multipart else '%s_part%s' % (lecture_id, part_id) + info['display_id'] = lecture_slug if not multipart else '%s_part%s' % (lecture_slug, part_id) + if multipart: + info['title'] += ' (Part %s)' % part_id + switch = smil.find('.//switch') + if switch is not None: + info['duration'] = parse_duration(switch.attrib.get('dur')) + item_info = lecture_info.copy() + item_info.update(info) + return item_info + + if explicit_part_id or not multipart: + result = extract_part(explicit_part_id or parts[0]) + else: + result = { + '_type': 'multi_video', + 'entries': [extract_part(part) for part in parts], + } + result.update(lecture_info) + + # Immediately return explicitly requested part or non event item + if explicit_part_id or lecture_type != 'evt': + return result + + playlist_entries.append(result) + + # It's probably a playlist + if not parts or lecture_type == 'evt': + playlist_webpage = self._download_webpage( + '%s/site/ajax/drilldown/?id=%s' % (base_url, lecture_id), lecture_id) + entries = [ + self.url_result(compat_urlparse.urljoin(url, video_url), 'Viidea') + for _, video_url in re.findall( + r'<a[^>]+href=(["\'])(.+?)\1[^>]+id=["\']lec=\d+', playlist_webpage)] + playlist_entries.extend(entries) + + playlist = self.playlist_result(playlist_entries, lecture_id) + playlist.update(lecture_info) + return playlist diff --git a/youtube_dl/extractor/viki.py b/youtube_dl/extractor/viki.py index ddbd395c8..ca3f20a3d 100644 --- a/youtube_dl/extractor/viki.py +++ b/youtube_dl/extractor/viki.py @@ -7,14 +7,14 @@ import hmac import hashlib import itertools +from .common import InfoExtractor from ..utils import ( ExtractorError, int_or_none, parse_age_limit, parse_iso8601, + sanitized_Request, ) -from ..compat import compat_urllib_request -from .common import InfoExtractor class VikiBaseIE(InfoExtractor): @@ -30,6 +30,12 @@ class VikiBaseIE(InfoExtractor): _token = None + _ERRORS = { + 'geo': 'Sorry, this content is not available in your region.', + 'upcoming': 'Sorry, this content is not yet available.', + # 'paywall': 'paywall', + } + def _prepare_call(self, path, timestamp=None, post_data=None): path += '?' if '?' not in path else '&' if not timestamp: @@ -43,7 +49,7 @@ class VikiBaseIE(InfoExtractor): hashlib.sha1 ).hexdigest() url = self._API_URL_TEMPLATE % (query, sig) - return compat_urllib_request.Request( + return sanitized_Request( url, json.dumps(post_data).encode('utf-8')) if post_data else url def _call_api(self, path, video_id, note, timestamp=None, post_data=None): @@ -67,6 +73,12 @@ class VikiBaseIE(InfoExtractor): '%s returned error: %s' % (self.IE_NAME, error), expected=True) + def _check_errors(self, data): + for reason, status in data.get('blocking', {}).items(): + if status and reason in self._ERRORS: + raise ExtractorError('%s said: %s' % ( + self.IE_NAME, self._ERRORS[reason]), expected=True) + def _real_initialize(self): self._login() @@ -193,6 +205,7 @@ class VikiIE(VikiBaseIE): 'timestamp': 1321985454, 'description': 'md5:44b1e46619df3a072294645c770cef36', 'title': 'Love In Magic', + 'age_limit': 13, }, }] @@ -202,6 +215,8 @@ class VikiIE(VikiBaseIE): video = self._call_api( 'videos/%s.json' % video_id, video_id, 'Downloading video JSON') + self._check_errors(video) + title = self.dict_selection(video.get('titles', {}), 'en') if not title: title = 'Episode %d' % video.get('number') if video.get('type') == 'episode' else video.get('id') or video_id @@ -262,8 +277,11 @@ class VikiIE(VikiBaseIE): r'^(\d+)[pP]$', format_id, 'height', default=None)) for protocol, format_dict in stream_dict.items(): if format_id == 'm3u8': - formats = self._extract_m3u8_formats( - format_dict['url'], video_id, 'mp4', m3u8_id='m3u8-%s' % protocol) + m3u8_formats = self._extract_m3u8_formats( + format_dict['url'], video_id, 'mp4', 'm3u8_native', + m3u8_id='m3u8-%s' % protocol, fatal=None) + if m3u8_formats: + formats.extend(m3u8_formats) else: formats.append({ 'url': format_dict['url'], @@ -315,6 +333,8 @@ class VikiChannelIE(VikiBaseIE): 'containers/%s.json' % channel_id, channel_id, 'Downloading channel JSON') + self._check_errors(channel) + title = self.dict_selection(channel['titles'], 'en') description = self.dict_selection(channel['descriptions'], 'en') diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 2437ae1eb..ce08e6955 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -8,21 +8,22 @@ import itertools from .common import InfoExtractor from ..compat import ( compat_HTTPError, - compat_urllib_parse, - compat_urllib_request, compat_urlparse, ) from ..utils import ( + encode_dict, ExtractorError, InAdvancePagedList, int_or_none, RegexNotFoundError, + sanitized_Request, smuggle_url, std_headers, unified_strdate, unsmuggle_url, urlencode_postdata, unescapeHTML, + parse_filesize, ) @@ -40,17 +41,17 @@ class VimeoBaseInfoExtractor(InfoExtractor): self.report_login() webpage = self._download_webpage(self._LOGIN_URL, None, False) token, vuid = self._extract_xsrft_and_vuid(webpage) - data = urlencode_postdata({ + data = urlencode_postdata(encode_dict({ 'action': 'login', 'email': username, 'password': password, 'service': 'vimeo', 'token': token, - }) - login_request = compat_urllib_request.Request(self._LOGIN_URL, data) + })) + login_request = sanitized_Request(self._LOGIN_URL, data) login_request.add_header('Content-Type', 'application/x-www-form-urlencoded') - login_request.add_header('Cookie', 'vuid=%s' % vuid) login_request.add_header('Referer', self._LOGIN_URL) + self._set_vimeo_cookie('vuid', vuid) self._download_webpage(login_request, None, False, 'Wrong login info') def _extract_xsrft_and_vuid(self, webpage): @@ -62,6 +63,9 @@ class VimeoBaseInfoExtractor(InfoExtractor): webpage, 'vuid', group='vuid') return xsrft, vuid + def _set_vimeo_cookie(self, name, value): + self._set_cookie('vimeo.com', name, value) + class VimeoIE(VimeoBaseInfoExtractor): """Information extractor for vimeo.com.""" @@ -182,10 +186,28 @@ class VimeoIE(VimeoBaseInfoExtractor): }, }, { + # contains original format + 'url': 'https://vimeo.com/33951933', + 'md5': '53c688fa95a55bf4b7293d37a89c5c53', + 'info_dict': { + 'id': '33951933', + 'ext': 'mp4', + 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute', + 'uploader': 'The DMCI', + 'uploader_id': 'dmci', + 'upload_date': '20111220', + 'description': 'md5:ae23671e82d05415868f7ad1aec21147', + }, + }, + { 'url': 'https://vimeo.com/109815029', 'note': 'Video not completely processed, "failed" seed status', 'only_matching': True, }, + { + 'url': 'https://vimeo.com/groups/travelhd/videos/22439234', + 'only_matching': True, + }, ] @staticmethod @@ -208,17 +230,17 @@ class VimeoIE(VimeoBaseInfoExtractor): if password is None: raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True) token, vuid = self._extract_xsrft_and_vuid(webpage) - data = urlencode_postdata({ + data = urlencode_postdata(encode_dict({ 'password': password, 'token': token, - }) + })) if url.startswith('http://'): # vimeo only supports https now, but the user can give an http url url = url.replace('http://', 'https://') - password_request = compat_urllib_request.Request(url + '/password', data) + password_request = sanitized_Request(url + '/password', data) password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') - password_request.add_header('Cookie', 'clip_test2=1; vuid=%s' % vuid) password_request.add_header('Referer', url) + self._set_vimeo_cookie('vuid', vuid) return self._download_webpage( password_request, video_id, 'Verifying the password', 'Wrong password') @@ -227,9 +249,9 @@ class VimeoIE(VimeoBaseInfoExtractor): password = self._downloader.params.get('videopassword', None) if password is None: raise ExtractorError('This video is protected by a password, use the --video-password option') - data = compat_urllib_parse.urlencode({'password': password}) + data = urlencode_postdata(encode_dict({'password': password})) pass_url = url + '/check-password' - password_request = compat_urllib_request.Request(pass_url, data) + password_request = sanitized_Request(pass_url, data) password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') return self._download_json( password_request, video_id, @@ -258,7 +280,7 @@ class VimeoIE(VimeoBaseInfoExtractor): url = 'https://vimeo.com/' + video_id # Retrieve video webpage to extract further information - request = compat_urllib_request.Request(url, None, headers) + request = sanitized_Request(url, None, headers) try: webpage = self._download_webpage(request, video_id) except ExtractorError as ee: @@ -384,47 +406,44 @@ class VimeoIE(VimeoBaseInfoExtractor): like_count = None comment_count = None - # Vimeo specific: extract request signature and timestamp - sig = config['request']['signature'] - timestamp = config['request']['timestamp'] - - # Vimeo specific: extract video codec and quality information - # First consider quality, then codecs, then take everything - codecs = [('vp6', 'flv'), ('vp8', 'flv'), ('h264', 'mp4')] - files = {'hd': [], 'sd': [], 'other': []} - config_files = config["video"].get("files") or config["request"].get("files") - for codec_name, codec_extension in codecs: - for quality in config_files.get(codec_name, []): - format_id = '-'.join((codec_name, quality)).lower() - key = quality if quality in files else 'other' - video_url = None - if isinstance(config_files[codec_name], dict): - file_info = config_files[codec_name][quality] - video_url = file_info.get('url') - else: - file_info = {} - if video_url is None: - video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \ - % (video_id, sig, timestamp, quality, codec_name.upper()) - - files[key].append({ - 'ext': codec_extension, - 'url': video_url, - 'format_id': format_id, - 'width': int_or_none(file_info.get('width')), - 'height': int_or_none(file_info.get('height')), - 'tbr': int_or_none(file_info.get('bitrate')), - }) formats = [] - m3u8_url = config_files.get('hls', {}).get('all') + download_request = sanitized_Request('https://vimeo.com/%s?action=load_download_config' % video_id, headers={ + 'X-Requested-With': 'XMLHttpRequest'}) + download_data = self._download_json(download_request, video_id, fatal=False) + if download_data: + source_file = download_data.get('source_file') + if source_file and not source_file.get('is_cold') and not source_file.get('is_defrosting'): + formats.append({ + 'url': source_file['download_url'], + 'ext': source_file['extension'].lower(), + 'width': int_or_none(source_file.get('width')), + 'height': int_or_none(source_file.get('height')), + 'filesize': parse_filesize(source_file.get('size')), + 'format_id': source_file.get('public_name', 'Original'), + 'preference': 1, + }) + config_files = config['video'].get('files') or config['request'].get('files', {}) + for f in config_files.get('progressive', []): + video_url = f.get('url') + if not video_url: + continue + formats.append({ + 'url': video_url, + 'format_id': 'http-%s' % f.get('quality'), + 'width': int_or_none(f.get('width')), + 'height': int_or_none(f.get('height')), + 'fps': int_or_none(f.get('fps')), + 'tbr': int_or_none(f.get('bitrate')), + }) + m3u8_url = config_files.get('hls', {}).get('url') if m3u8_url: m3u8_formats = self._extract_m3u8_formats( - m3u8_url, video_id, 'mp4', 'm3u8_native', 0, 'hls', fatal=False) + m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) if m3u8_formats: formats.extend(m3u8_formats) - for key in ('other', 'sd', 'hd'): - formats += files[key] - self._sort_formats(formats) + # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps + # at the same time without actual units specified. This lead to wrong sorting. + self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'format_id')) subtitles = {} text_tracks = config['request'].get('text_tracks') @@ -488,21 +507,20 @@ class VimeoChannelIE(VimeoBaseInfoExtractor): token, vuid = self._extract_xsrft_and_vuid(webpage) fields['token'] = token fields['password'] = password - post = urlencode_postdata(fields) + post = urlencode_postdata(encode_dict(fields)) password_path = self._search_regex( r'action="([^"]+)"', login_form, 'password URL') password_url = compat_urlparse.urljoin(page_url, password_path) - password_request = compat_urllib_request.Request(password_url, post) + password_request = sanitized_Request(password_url, post) password_request.add_header('Content-type', 'application/x-www-form-urlencoded') - password_request.add_header('Cookie', 'vuid=%s' % vuid) - self._set_cookie('vimeo.com', 'xsrft', token) + self._set_vimeo_cookie('vuid', vuid) + self._set_vimeo_cookie('xsrft', token) return self._download_webpage( password_request, list_id, 'Verifying the password', 'Wrong password') - def _extract_videos(self, list_id, base_url): - video_ids = [] + def _title_and_entries(self, list_id, base_url): for pagenum in itertools.count(1): page_url = self._page_url(base_url, pagenum) webpage = self._download_webpage( @@ -511,18 +529,18 @@ class VimeoChannelIE(VimeoBaseInfoExtractor): if pagenum == 1: webpage = self._login_list_password(page_url, list_id, webpage) + yield self._extract_list_title(webpage) + + for video_id in re.findall(r'id="clip_(\d+?)"', webpage): + yield self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo') - video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage)) if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None: break - entries = [self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo') - for video_id in video_ids] - return {'_type': 'playlist', - 'id': list_id, - 'title': self._extract_list_title(webpage), - 'entries': entries, - } + def _extract_videos(self, list_id, base_url): + title_and_entries = self._title_and_entries(list_id, base_url) + list_title = next(title_and_entries) + return self.playlist_result(title_and_entries, list_id, list_title) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -583,7 +601,7 @@ class VimeoAlbumIE(VimeoChannelIE): class VimeoGroupsIE(VimeoAlbumIE): IE_NAME = 'vimeo:group' - _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)' + _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)' _TESTS = [{ 'url': 'https://vimeo.com/groups/rolexawards', 'info_dict': { @@ -652,7 +670,7 @@ class VimeoWatchLaterIE(VimeoChannelIE): def _page_url(self, base_url, pagenum): url = '%s/page:%d/' % (base_url, pagenum) - request = compat_urllib_request.Request(url) + request = sanitized_Request(url) # Set the header to get a partial html page with the ids, # the normal page doesn't contain them. request.add_header('X-Requested-With', 'XMLHttpRequest') diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index 765e9e6fd..90557fa61 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -8,16 +8,17 @@ from .common import InfoExtractor from ..compat import ( compat_str, compat_urllib_parse, - compat_urllib_request, ) from ..utils import ( ExtractorError, orderedSet, + sanitized_Request, str_to_int, unescapeHTML, unified_strdate, ) from .vimeo import VimeoIE +from .pladform import PladformIE class VKIE(InfoExtractor): @@ -164,6 +165,11 @@ class VKIE(InfoExtractor): # vk wrapper 'url': 'http://www.biqle.ru/watch/847655_160197695', 'only_matching': True, + }, + { + # pladform embed + 'url': 'https://vk.com/video-76116461_171554880', + 'only_matching': True, } ] @@ -182,7 +188,7 @@ class VKIE(InfoExtractor): 'pass': password.encode('cp1251'), }) - request = compat_urllib_request.Request( + request = sanitized_Request( 'https://login.vk.com/?act=login', compat_urllib_parse.urlencode(login_form).encode('utf-8')) login_page = self._download_webpage( @@ -254,10 +260,13 @@ class VKIE(InfoExtractor): if vimeo_url is not None: return self.url_result(vimeo_url) + pladform_url = PladformIE._extract_url(info_page) + if pladform_url: + return self.url_result(pladform_url) + m_rutube = re.search( r'\ssrc="((?:https?:)?//rutube\.ru\\?/video\\?/embed(?:.*?))\\?"', info_page) if m_rutube is not None: - self.to_screen('rutube video detected') rutube_url = self._proto_relative_url( m_rutube.group(1).replace('\\', '')) return self.url_result(rutube_url) @@ -281,9 +290,13 @@ class VKIE(InfoExtractor): mobj.group(1) + ' ' + mobj.group(2) upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2)) - view_count = str_to_int(self._search_regex( - r'"mv_views_count_number"[^>]*>([\d,.]+) views<', - info_page, 'view count', fatal=False)) + view_count = None + views = self._html_search_regex( + r'"mv_views_count_number"[^>]*>(.+?\bviews?)<', + info_page, 'view count', fatal=False) + if views: + view_count = str_to_int(self._search_regex( + r'([\d,.]+)', views, 'view count', fatal=False)) formats = [{ 'format_id': k, diff --git a/youtube_dl/extractor/vodlocker.py b/youtube_dl/extractor/vodlocker.py index ccf1928b5..357594a11 100644 --- a/youtube_dl/extractor/vodlocker.py +++ b/youtube_dl/extractor/vodlocker.py @@ -2,14 +2,15 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, +from ..compat import compat_urllib_parse +from ..utils import ( + ExtractorError, + sanitized_Request, ) class VodlockerIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?P<id>[0-9a-zA-Z]+)(?:\..*?)?' + _VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:\..*?)?' _TESTS = [{ 'url': 'http://vodlocker.com/e8wvyzz4sl42', @@ -26,12 +27,18 @@ class VodlockerIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) + if any(p in webpage for p in ( + '>THIS FILE WAS DELETED<', + '>File Not Found<', + 'The file you were looking for could not be found, sorry for any inconvenience.<')): + raise ExtractorError('Video %s does not exist' % video_id, expected=True) + fields = self._hidden_inputs(webpage) if fields['op'] == 'download1': self._sleep(3, video_id) # they do detect when requests happen too fast! post = compat_urllib_parse.urlencode(fields) - req = compat_urllib_request.Request(url, post) + req = sanitized_Request(url, post) req.add_header('Content-type', 'application/x-www-form-urlencoded') webpage = self._download_webpage( req, video_id, 'Downloading video page') diff --git a/youtube_dl/extractor/voicerepublic.py b/youtube_dl/extractor/voicerepublic.py index 254383d6c..93d15a556 100644 --- a/youtube_dl/extractor/voicerepublic.py +++ b/youtube_dl/extractor/voicerepublic.py @@ -3,14 +3,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_request, - compat_urlparse, -) +from ..compat import compat_urlparse from ..utils import ( ExtractorError, determine_ext, int_or_none, + sanitized_Request, ) @@ -37,7 +35,7 @@ class VoiceRepublicIE(InfoExtractor): def _real_extract(self, url): display_id = self._match_id(url) - req = compat_urllib_request.Request( + req = sanitized_Request( compat_urlparse.urljoin(url, '/talks/%s' % display_id)) # Older versions of Firefox get redirected to an "upgrade browser" page req.add_header('User-Agent', 'youtube-dl') diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py index b46802306..ef096cbd2 100644 --- a/youtube_dl/extractor/wdr.py +++ b/youtube_dl/extractor/wdr.py @@ -10,8 +10,8 @@ from ..compat import ( compat_urlparse, ) from ..utils import ( - determine_ext, unified_strdate, + qualities, ) @@ -33,6 +33,7 @@ class WDRIE(InfoExtractor): 'params': { 'skip_download': True, }, + 'skip': 'Page Not Found', }, { 'url': 'http://www1.wdr.de/themen/av/videomargaspiegelisttot101-videoplayer.html', @@ -47,6 +48,7 @@ class WDRIE(InfoExtractor): 'params': { 'skip_download': True, }, + 'skip': 'Page Not Found', }, { 'url': 'http://www1.wdr.de/themen/kultur/audioerlebtegeschichtenmargaspiegel100-audioplayer.html', @@ -71,6 +73,7 @@ class WDRIE(InfoExtractor): 'upload_date': '20140717', 'is_live': False }, + 'skip': 'Page Not Found', }, { 'url': 'http://www1.wdr.de/mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100.html', @@ -83,10 +86,10 @@ class WDRIE(InfoExtractor): 'url': 'http://www1.wdr.de/mediathek/video/livestream/index.html', 'info_dict': { 'id': 'mdb-103364', - 'title': 're:^WDR Fernsehen [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'title': 're:^WDR Fernsehen Live [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', 'description': 'md5:ae2ff888510623bf8d4b115f95a9b7c9', 'ext': 'flv', - 'upload_date': '20150212', + 'upload_date': '20150101', 'is_live': True }, 'params': { @@ -150,25 +153,52 @@ class WDRIE(InfoExtractor): if upload_date: upload_date = unified_strdate(upload_date) + formats = [] + preference = qualities(['S', 'M', 'L', 'XL']) + if video_url.endswith('.f4m'): - video_url += '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18' - ext = 'flv' + f4m_formats = self._extract_f4m_formats(video_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18', page_id, f4m_id='hds', fatal=False) + if f4m_formats: + formats.extend(f4m_formats) elif video_url.endswith('.smil'): - fmt = self._extract_smil_formats(video_url, page_id)[0] - video_url = fmt['url'] - sep = '&' if '?' in video_url else '?' - video_url += sep - video_url += 'hdcore=3.3.0&plugin=aasp-3.3.0.99.43' - ext = fmt['ext'] + smil_formats = self._extract_smil_formats(video_url, page_id, False, { + 'hdcore': '3.3.0', + 'plugin': 'aasp-3.3.0.99.43', + }) + if smil_formats: + formats.extend(smil_formats) else: - ext = determine_ext(video_url) + formats.append({ + 'url': video_url, + 'http_headers': { + 'User-Agent': 'mobile', + }, + }) + + m3u8_url = self._search_regex(r'rel="adaptiv"[^>]+href="([^"]+)"', webpage, 'm3u8 url', default=None) + if m3u8_url: + m3u8_formats = self._extract_m3u8_formats(m3u8_url, page_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + + direct_urls = re.findall(r'rel="web(S|M|L|XL)"[^>]+href="([^"]+)"', webpage) + if direct_urls: + for quality, video_url in direct_urls: + formats.append({ + 'url': video_url, + 'preference': preference(quality), + 'http_headers': { + 'User-Agent': 'mobile', + }, + }) + + self._sort_formats(formats) description = self._html_search_meta('Description', webpage, 'description') return { 'id': page_id, - 'url': video_url, - 'ext': ext, + 'formats': formats, 'title': title, 'description': description, 'thumbnail': thumbnail, diff --git a/youtube_dl/extractor/wimp.py b/youtube_dl/extractor/wimp.py index e4f50e64c..041ff6c55 100644 --- a/youtube_dl/extractor/wimp.py +++ b/youtube_dl/extractor/wimp.py @@ -5,7 +5,7 @@ from .youtube import YoutubeIE class WimpIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?wimp\.com/(?P<id>[^/]+)/' + _VALID_URL = r'http://(?:www\.)?wimp\.com/(?P<id>[^/]+)' _TESTS = [{ 'url': 'http://www.wimp.com/maruexhausted/', 'md5': 'ee21217ffd66d058e8b16be340b74883', @@ -28,18 +28,23 @@ class WimpIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) - video_url = self._search_regex( - [r"[\"']file[\"']\s*[:,]\s*[\"'](.+?)[\"']", r"videoId\s*:\s*[\"']([^\"']+)[\"']"], - webpage, 'video URL') - if YoutubeIE.suitable(video_url): - self.to_screen('Found YouTube video') + + youtube_id = self._search_regex( + r"videoId\s*:\s*[\"']([0-9A-Za-z_-]{11})[\"']", + webpage, 'video URL', default=None) + if youtube_id: return { '_type': 'url', - 'url': video_url, + 'url': youtube_id, 'ie_key': YoutubeIE.ie_key(), } + video_url = self._search_regex( + r'<video[^>]+>\s*<source[^>]+src=(["\'])(?P<url>.+?)\1', + webpage, 'video URL', group='url') + return { 'id': video_id, 'url': video_url, diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py index 13a079151..fdb16d91c 100644 --- a/youtube_dl/extractor/wistia.py +++ b/youtube_dl/extractor/wistia.py @@ -1,8 +1,10 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import compat_urllib_request -from ..utils import ExtractorError +from ..utils import ( + ExtractorError, + sanitized_Request, +) class WistiaIE(InfoExtractor): @@ -23,7 +25,7 @@ class WistiaIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - request = compat_urllib_request.Request(self._API_URL.format(video_id)) + request = sanitized_Request(self._API_URL.format(video_id)) request.add_header('Referer', url) # Some videos require this. data_json = self._download_json(request, video_id) if data_json.get('error'): diff --git a/youtube_dl/extractor/wsj.py b/youtube_dl/extractor/wsj.py index 2ddf29a69..5a897371d 100644 --- a/youtube_dl/extractor/wsj.py +++ b/youtube_dl/extractor/wsj.py @@ -84,6 +84,5 @@ class WSJIE(InfoExtractor): 'duration': duration, 'upload_date': upload_date, 'title': title, - 'formats': formats, 'categories': categories, } diff --git a/youtube_dl/extractor/gorillavid.py b/youtube_dl/extractor/xfileshare.py index d23e3eac1..a3236e66c 100644 --- a/youtube_dl/extractor/gorillavid.py +++ b/youtube_dl/extractor/xfileshare.py @@ -1,25 +1,23 @@ -# -*- coding: utf-8 -*- +# coding: utf-8 from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) +from ..compat import compat_urllib_parse from ..utils import ( ExtractorError, encode_dict, int_or_none, + sanitized_Request, ) -class GorillaVidIE(InfoExtractor): - IE_DESC = 'GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net and filehoot.com' +class XFileShareIE(InfoExtractor): + IE_DESC = 'XFileShare based sites: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net, filehoot.com and vidto.me' _VALID_URL = r'''(?x) https?://(?P<host>(?:www\.)? - (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net|filehoot\.com))/ + (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net|filehoot\.com|vidto\.me))/ (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)? ''' @@ -76,6 +74,13 @@ class GorillaVidIE(InfoExtractor): 'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4', 'thumbnail': 're:http://.*\.jpg', } + }, { + 'url': 'http://vidto.me/ku5glz52nqe1.html', + 'info_dict': { + 'id': 'ku5glz52nqe1', + 'ext': 'mp4', + 'title': 'test' + } }] def _real_extract(self, url): @@ -99,18 +104,23 @@ class GorillaVidIE(InfoExtractor): post = compat_urllib_parse.urlencode(encode_dict(fields)) - req = compat_urllib_request.Request(url, post) + req = sanitized_Request(url, post) req.add_header('Content-type', 'application/x-www-form-urlencoded') webpage = self._download_webpage(req, video_id, 'Downloading video page') - title = self._search_regex( - [r'style="z-index: [0-9]+;">([^<]+)</span>', r'<td nowrap>([^<]+)</td>', r'>Watch (.+) '], - webpage, 'title', default=None) or self._og_search_title(webpage) + title = (self._search_regex( + [r'style="z-index: [0-9]+;">([^<]+)</span>', + r'<td nowrap>([^<]+)</td>', + r'>Watch (.+) ', + r'<h2 class="video-page-head">([^<]+)</h2>'], + webpage, 'title', default=None) or self._og_search_title(webpage)).strip() video_url = self._search_regex( - r'file\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'file url') + [r'file\s*:\s*["\'](http[^"\']+)["\'],', + r'file_link\s*=\s*\'(https?:\/\/[0-9a-zA-z.\/\-_]+)'], + webpage, 'file url') thumbnail = self._search_regex( - r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', fatal=False) + r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None) formats = [{ 'format_id': 'sd', diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index 779e4f46a..a1fe24050 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -3,12 +3,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_request, - compat_urllib_parse_unquote, -) +from ..compat import compat_urllib_parse_unquote from ..utils import ( parse_duration, + sanitized_Request, str_to_int, ) @@ -32,7 +30,7 @@ class XTubeIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - req = compat_urllib_request.Request(url) + req = sanitized_Request(url) req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py index 5dcf2fdd1..710ad5041 100644 --- a/youtube_dl/extractor/xvideos.py +++ b/youtube_dl/extractor/xvideos.py @@ -3,14 +3,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse_unquote, - compat_urllib_request, -) +from ..compat import compat_urllib_parse_unquote from ..utils import ( clean_html, ExtractorError, determine_ext, + sanitized_Request, ) @@ -48,7 +46,7 @@ class XVideosIE(InfoExtractor): 'url': video_url, }] - android_req = compat_urllib_request.Request(url) + android_req = sanitized_Request(url) android_req.add_header('User-Agent', self._ANDROID_USER_AGENT) android_webpage = self._download_webpage(android_req, video_id, fatal=False) diff --git a/youtube_dl/extractor/yandexmusic.py b/youtube_dl/extractor/yandexmusic.py index 08dc81f3a..d3cc1a29f 100644 --- a/youtube_dl/extractor/yandexmusic.py +++ b/youtube_dl/extractor/yandexmusic.py @@ -8,11 +8,11 @@ from .common import InfoExtractor from ..compat import ( compat_str, compat_urllib_parse, - compat_urllib_request, ) from ..utils import ( int_or_none, float_or_none, + sanitized_Request, ) @@ -154,7 +154,7 @@ class YandexMusicPlaylistIE(YandexMusicPlaylistBaseIE): if len(tracks) < len(track_ids): present_track_ids = set([compat_str(track['id']) for track in tracks if track.get('id')]) missing_track_ids = set(map(compat_str, track_ids)) - set(present_track_ids) - request = compat_urllib_request.Request( + request = sanitized_Request( 'https://music.yandex.ru/handlers/track-entries.jsx', compat_urllib_parse.urlencode({ 'entries': ','.join(missing_track_ids), diff --git a/youtube_dl/extractor/youku.py b/youtube_dl/extractor/youku.py index 2e81d9223..3a3432be8 100644 --- a/youtube_dl/extractor/youku.py +++ b/youtube_dl/extractor/youku.py @@ -4,12 +4,13 @@ from __future__ import unicode_literals import base64 from .common import InfoExtractor -from ..utils import ExtractorError - from ..compat import ( compat_urllib_parse, compat_ord, - compat_urllib_request, +) +from ..utils import ( + ExtractorError, + sanitized_Request, ) @@ -24,8 +25,8 @@ class YoukuIE(InfoExtractor): ''' _TESTS = [{ + # MD5 is unstable 'url': 'http://v.youku.com/v_show/id_XMTc1ODE5Njcy.html', - 'md5': '5f3af4192eabacc4501508d54a8cabd7', 'info_dict': { 'id': 'XMTc1ODE5Njcy_part1', 'title': '★Smile﹗♡ Git Fresh -Booty Music舞蹈.', @@ -41,6 +42,7 @@ class YoukuIE(InfoExtractor): 'title': '武媚娘传奇 85', }, 'playlist_count': 11, + 'skip': 'Available in China only', }, { 'url': 'http://v.youku.com/v_show/id_XMTI1OTczNDM5Mg==.html', 'info_dict': { @@ -48,7 +50,6 @@ class YoukuIE(InfoExtractor): 'title': '花千骨 04', }, 'playlist_count': 13, - 'skip': 'Available in China only', }, { 'url': 'http://v.youku.com/v_show/id_XNjA1NzA2Njgw.html', 'note': 'Video protected with password', @@ -62,7 +63,7 @@ class YoukuIE(InfoExtractor): }, }] - def construct_video_urls(self, data1, data2): + def construct_video_urls(self, data): # get sid, token def yk_t(s1, s2): ls = list(range(256)) @@ -80,34 +81,24 @@ class YoukuIE(InfoExtractor): return bytes(s) sid, token = yk_t( - b'becaf9be', base64.b64decode(data2['ep'].encode('ascii')) + b'becaf9be', base64.b64decode(data['security']['encrypt_string'].encode('ascii')) ).decode('ascii').split('_') # get oip - oip = data2['ip'] - - # get fileid - string_ls = list( - 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890') - shuffled_string_ls = [] - seed = data1['seed'] - N = len(string_ls) - for ii in range(N): - seed = (seed * 0xd3 + 0x754f) % 0x10000 - idx = seed * len(string_ls) // 0x10000 - shuffled_string_ls.append(string_ls[idx]) - del string_ls[idx] + oip = data['security']['ip'] fileid_dict = {} - for format in data1['streamtypes']: - streamfileid = [ - int(i) for i in data1['streamfileids'][format].strip('*').split('*')] - fileid = ''.join( - [shuffled_string_ls[i] for i in streamfileid]) - fileid_dict[format] = fileid[:8] + '%s' + fileid[10:] + for stream in data['stream']: + format = stream.get('stream_type') + fileid = stream['stream_fileid'] + fileid_dict[format] = fileid def get_fileid(format, n): - fileid = fileid_dict[format] % hex(int(n))[2:].upper().zfill(2) + number = hex(int(str(n), 10))[2:].upper() + if len(number) == 1: + number = '0' + number + streamfileids = fileid_dict[format] + fileid = streamfileids[0:8] + number + streamfileids[10:] return fileid # get ep @@ -122,15 +113,15 @@ class YoukuIE(InfoExtractor): # generate video_urls video_urls_dict = {} - for format in data1['streamtypes']: + for stream in data['stream']: + format = stream.get('stream_type') video_urls = [] - for dt in data1['segs'][format]: - n = str(int(dt['no'])) + for dt in stream['segs']: + n = str(stream['segs'].index(dt)) param = { - 'K': dt['k'], + 'K': dt['key'], 'hd': self.get_hd(format), 'myp': 0, - 'ts': dt['seconds'], 'ypp': 0, 'ctype': 12, 'ev': 1, @@ -141,7 +132,7 @@ class YoukuIE(InfoExtractor): video_url = \ 'http://k.youku.com/player/getFlvPath/' + \ 'sid/' + sid + \ - '_' + str(int(n) + 1).zfill(2) + \ + '_00' + \ '/st/' + self.parse_ext_l(format) + \ '/fileid/' + get_fileid(format, n) + '?' + \ compat_urllib_parse.urlencode(param) @@ -152,23 +143,31 @@ class YoukuIE(InfoExtractor): def get_hd(self, fm): hd_id_dict = { + '3gp': '0', + '3gphd': '1', 'flv': '0', + 'flvhd': '0', 'mp4': '1', + 'mp4hd': '1', + 'mp4hd2': '1', + 'mp4hd3': '1', 'hd2': '2', 'hd3': '3', - '3gp': '0', - '3gphd': '1' } return hd_id_dict[fm] def parse_ext_l(self, fm): ext_dict = { + '3gp': 'flv', + '3gphd': 'mp4', 'flv': 'flv', + 'flvhd': 'flv', 'mp4': 'mp4', + 'mp4hd': 'mp4', + 'mp4hd2': 'flv', + 'mp4hd3': 'flv', 'hd2': 'flv', 'hd3': 'flv', - '3gp': 'flv', - '3gphd': 'mp4' } return ext_dict[fm] @@ -177,9 +176,13 @@ class YoukuIE(InfoExtractor): '3gp': 'h6', '3gphd': 'h5', 'flv': 'h4', + 'flvhd': 'h4', 'mp4': 'h3', + 'mp4hd': 'h3', + 'mp4hd2': 'h4', + 'mp4hd3': 'h4', 'hd2': 'h2', - 'hd3': 'h1' + 'hd3': 'h1', } return _dict[fm] @@ -187,45 +190,46 @@ class YoukuIE(InfoExtractor): video_id = self._match_id(url) def retrieve_data(req_url, note): - req = compat_urllib_request.Request(req_url) + headers = { + 'Referer': req_url, + } + self._set_cookie('youku.com', 'xreferrer', 'http://www.youku.com') + req = sanitized_Request(req_url, headers=headers) cn_verification_proxy = self._downloader.params.get('cn_verification_proxy') if cn_verification_proxy: req.add_header('Ytdl-request-proxy', cn_verification_proxy) raw_data = self._download_json(req, video_id, note=note) - return raw_data['data'][0] + + return raw_data['data'] video_password = self._downloader.params.get('videopassword', None) # request basic data - basic_data_url = 'http://v.youku.com/player/getPlayList/VideoIDS/%s' % video_id + basic_data_url = "http://play.youku.com/play/get.json?vid=%s&ct=12" % video_id if video_password: - basic_data_url += '?password=%s' % video_password - - data1 = retrieve_data( - basic_data_url, - 'Downloading JSON metadata 1') - data2 = retrieve_data( - 'http://v.youku.com/player/getPlayList/VideoIDS/%s/Pf/4/ctype/12/ev/1' % video_id, - 'Downloading JSON metadata 2') - - error_code = data1.get('error_code') - if error_code: - error = data1.get('error') - if error is not None and '因版权原因无法观看此视频' in error: + basic_data_url += '&pwd=%s' % video_password + + data = retrieve_data(basic_data_url, 'Downloading JSON metadata') + + error = data.get('error') + if error: + error_note = error.get('note') + if error_note is not None and '因版权原因无法观看此视频' in error_note: raise ExtractorError( 'Youku said: Sorry, this video is available in China only', expected=True) else: - msg = 'Youku server reported error %i' % error_code - if error is not None: - msg += ': ' + error + msg = 'Youku server reported error %i' % error.get('code') + if error_note is not None: + msg += ': ' + error_note raise ExtractorError(msg) - title = data1['title'] + # get video title + title = data['video']['title'] # generate video_urls_dict - video_urls_dict = self.construct_video_urls(data1, data2) + video_urls_dict = self.construct_video_urls(data) # construct info entries = [{ @@ -234,10 +238,11 @@ class YoukuIE(InfoExtractor): 'formats': [], # some formats are not available for all parts, we have to detect # which one has all - } for i in range(max(len(v) for v in data1['segs'].values()))] - for fm in data1['streamtypes']: + } for i in range(max(len(v.get('segs')) for v in data['stream']))] + for stream in data['stream']: + fm = stream.get('stream_type') video_urls = video_urls_dict[fm] - for video_url, seg, entry in zip(video_urls, data1['segs'][fm], entries): + for video_url, seg, entry in zip(video_urls, stream['segs'], entries): entry['formats'].append({ 'url': video_url, 'format_id': self.get_format_name(fm), diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index 9bf8d1eeb..dd724085a 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -3,9 +3,9 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_urllib_request from ..utils import ( int_or_none, + sanitized_Request, str_to_int, unescapeHTML, unified_strdate, @@ -63,7 +63,7 @@ class YouPornIE(InfoExtractor): video_id = mobj.group('id') display_id = mobj.group('display_id') - request = compat_urllib_request.Request(url) + request = sanitized_Request(url) request.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(request, display_id) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index d7eda7aa7..4aac2cc03 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -20,13 +20,13 @@ from ..compat import ( compat_urllib_parse_unquote, compat_urllib_parse_unquote_plus, compat_urllib_parse_urlparse, - compat_urllib_request, compat_urlparse, compat_str, ) from ..utils import ( clean_html, encode_dict, + error_to_compat_str, ExtractorError, float_or_none, get_element_by_attribute, @@ -34,7 +34,9 @@ from ..utils import ( int_or_none, orderedSet, parse_duration, + remove_quotes, remove_start, + sanitized_Request, smuggle_url, str_to_int, unescapeHTML, @@ -114,7 +116,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor): login_data = compat_urllib_parse.urlencode(encode_dict(login_form_strs)).encode('ascii') - req = compat_urllib_request.Request(self._LOGIN_URL, login_data) + req = sanitized_Request(self._LOGIN_URL, login_data) login_results = self._download_webpage( req, None, note='Logging in', errnote='unable to log in', fatal=False) @@ -147,7 +149,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor): tfa_data = compat_urllib_parse.urlencode(encode_dict(tfa_form_strs)).encode('ascii') - tfa_req = compat_urllib_request.Request(self._TWOFACTOR_URL, tfa_data) + tfa_req = sanitized_Request(self._TWOFACTOR_URL, tfa_data) tfa_results = self._download_webpage( tfa_req, None, note='Submitting TFA code', errnote='unable to submit tfa', fatal=False) @@ -178,15 +180,13 @@ class YoutubeBaseInfoExtractor(InfoExtractor): return -class YoutubePlaylistBaseInfoExtractor(InfoExtractor): - # Extract the video ids from the playlist pages +class YoutubeEntryListBaseInfoExtractor(InfoExtractor): + # Extract entries from page with "Load more" button def _entries(self, page, playlist_id): more_widget_html = content_html = page for page_num in itertools.count(1): - for video_id, video_title in self.extract_videos_from_page(content_html): - yield self.url_result( - video_id, 'Youtube', video_id=video_id, - video_title=video_title) + for entry in self._process_page(content_html): + yield entry mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) if not mobj: @@ -203,6 +203,12 @@ class YoutubePlaylistBaseInfoExtractor(InfoExtractor): break more_widget_html = more['load_more_widget_html'] + +class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): + def _process_page(self, content): + for video_id, video_title in self.extract_videos_from_page(content): + yield self.url_result(video_id, 'Youtube', video_id, video_title) + def extract_videos_from_page(self, page): ids_in_page = [] titles_in_page = [] @@ -224,6 +230,19 @@ class YoutubePlaylistBaseInfoExtractor(InfoExtractor): return zip(ids_in_page, titles_in_page) +class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): + def _process_page(self, content): + for playlist_id in re.findall(r'href="/?playlist\?list=(.+?)"', content): + yield self.url_result( + 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist') + + def _real_extract(self, url): + playlist_id = self._match_id(url) + webpage = self._download_webpage(url, playlist_id) + title = self._og_search_title(webpage, fatal=False) + return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title) + + class YoutubeIE(YoutubeBaseInfoExtractor): IE_DESC = 'YouTube.com' _VALID_URL = r"""(?x)^ @@ -241,7 +260,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): |(?: # or the v= param in all its forms (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) (?:\?|\#!?) # the params delimiter ? or # or #! - (?:.*?&)?? # any other preceding param (like /?s=tuff&v=xxxx) + (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY) v= ) )) @@ -329,6 +348,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, + # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug) '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'}, '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'}, @@ -377,12 +397,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'ext': 'mp4', 'upload_date': '20120506', 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]', + 'alt_title': 'I Love It (feat. Charli XCX)', 'description': 'md5:782e8651347686cba06e58f71ab51773', 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli', 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop', 'iconic ep', 'iconic', 'love', 'it'], 'uploader': 'Icona Pop', 'uploader_id': 'IconaPop', + 'creator': 'Icona Pop', } }, { @@ -393,9 +415,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'ext': 'mp4', 'upload_date': '20130703', 'title': 'Justin Timberlake - Tunnel Vision (Explicit)', + 'alt_title': 'Tunnel Vision', 'description': 'md5:64249768eec3bc4276236606ea996373', 'uploader': 'justintimberlakeVEVO', 'uploader_id': 'justintimberlakeVEVO', + 'creator': 'Justin Timberlake', 'age_limit': 18, } }, @@ -409,7 +433,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012', 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7', 'uploader': 'SET India', - 'uploader_id': 'setindia' + 'uploader_id': 'setindia', + 'age_limit': 18, } }, { @@ -473,10 +498,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': 'nfWlot6h_JM', 'ext': 'm4a', 'title': 'Taylor Swift - Shake It Off', + 'alt_title': 'Shake It Off', 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3', 'uploader': 'TaylorSwiftVEVO', 'uploader_id': 'TaylorSwiftVEVO', 'upload_date': '20140818', + 'creator': 'Taylor Swift', }, 'params': { 'youtube_include_dash_manifest': True, @@ -532,9 +559,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'ext': 'mp4', 'upload_date': '20100430', 'uploader_id': 'deadmau5', + 'creator': 'deadmau5', 'description': 'md5:12c56784b8032162bb936a5f76d55360', 'uploader': 'deadmau5', 'title': 'Deadmau5 - Some Chords (HD)', + 'alt_title': 'Some Chords', }, 'expected_warnings': [ 'DASH manifest missing', @@ -546,7 +575,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'info_dict': { 'id': 'lqQg6PlCWgI', 'ext': 'mp4', - 'upload_date': '20120724', + 'upload_date': '20150827', 'uploader_id': 'olympic', 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', 'uploader': 'Olympics', @@ -674,6 +703,49 @@ class YoutubeIE(YoutubeBaseInfoExtractor): { 'url': 'http://vid.plus/FlRa-iH7PGw', 'only_matching': True, + }, + { + # Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468) + 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg', + 'info_dict': { + 'id': 'lsguqyKfVQg', + 'ext': 'mp4', + 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21', + 'alt_title': 'Dark Walk', + 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a', + 'upload_date': '20151119', + 'uploader_id': 'IronSoulElf', + 'uploader': 'IronSoulElf', + 'creator': 'Todd Haberman, Daniel Law Heath & Aaron Kaplan', + }, + 'params': { + 'skip_download': True, + }, + }, + { + # Tags with '};' (see https://github.com/rg3/youtube-dl/issues/7468) + 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8', + 'only_matching': True, + }, + { + # Video with yt:stretch=17:0 + 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM', + 'info_dict': { + 'id': 'Q39EVAstoRM', + 'ext': 'mp4', + 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4', + 'description': 'md5:ee18a25c350637c8faff806845bddee9', + 'upload_date': '20151107', + 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA', + 'uploader': 'CH GAMER DROID', + }, + 'params': { + 'skip_download': True, + }, + }, + { + 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY', + 'only_matching': True, } ] @@ -703,7 +775,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def _extract_signature_function(self, video_id, player_url, example_sig): id_m = re.match( - r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?)?\.(?P<ext>[a-z]+)$', + r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|/base)?\.(?P<ext>[a-z]+)$', player_url) if not id_m: raise ExtractorError('Cannot identify player %r' % player_url) @@ -832,7 +904,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id, video_id, note=False) except ExtractorError as err: - self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err)) + self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err)) return {} sub_lang_list = {} @@ -858,16 +930,33 @@ class YoutubeIE(YoutubeBaseInfoExtractor): return {} return sub_lang_list + def _get_ytplayer_config(self, video_id, webpage): + patterns = ( + # User data may contain arbitrary character sequences that may affect + # JSON extraction with regex, e.g. when '};' is contained the second + # regex won't capture the whole JSON. Yet working around by trying more + # concrete regex first keeping in mind proper quoted string handling + # to be implemented in future that will replace this workaround (see + # https://github.com/rg3/youtube-dl/issues/7468, + # https://github.com/rg3/youtube-dl/pull/7599) + r';ytplayer\.config\s*=\s*({.+?});ytplayer', + r';ytplayer\.config\s*=\s*({.+?});', + ) + config = self._search_regex( + patterns, webpage, 'ytplayer.config', default=None) + if config: + return self._parse_json( + uppercase_escape(config), video_id, fatal=False) + def _get_automatic_captions(self, video_id, webpage): """We need the webpage for getting the captions url, pass it as an argument to speed up the process.""" self.to_screen('%s: Looking for automatic captions' % video_id) - mobj = re.search(r';ytplayer.config = ({.*?});', webpage) + player_config = self._get_ytplayer_config(video_id, webpage) err_msg = 'Couldn\'t find automatic captions for %s' % video_id - if mobj is None: + if not player_config: self._downloader.report_warning(err_msg) return {} - player_config = json.loads(mobj.group(1)) try: args = player_config['args'] caption_url = args['ttsurl'] @@ -1074,10 +1163,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): age_gate = False video_info = None # Try looking directly into the video webpage - mobj = re.search(r';ytplayer\.config\s*=\s*({.*?});', video_webpage) - if mobj: - json_code = uppercase_escape(mobj.group(1)) - ytplayer_config = json.loads(json_code) + ytplayer_config = self._get_ytplayer_config(video_id, video_webpage) + if ytplayer_config: args = ytplayer_config['args'] if args.get('url_encoded_fmt_stream_map'): # Convert to the same format returned by compat_parse_qs @@ -1107,6 +1194,17 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if not video_info: video_info = get_video_info if 'token' in get_video_info: + # Different get_video_info requests may report different results, e.g. + # some may report video unavailability, but some may serve it without + # any complaint (see https://github.com/rg3/youtube-dl/issues/7362, + # the original webpage as well as el=info and el=embedded get_video_info + # requests report video unavailability due to geo restriction while + # el=detailpage succeeds and returns valid data). This is probably + # due to YouTube measures against IP ranges of hosting providers. + # Working around by preferring the first succeeded video_info containing + # the token if no such video_info yet was found. + if 'token' not in video_info: + video_info = get_video_info break if 'token' not in video_info: if 'reason' in video_info: @@ -1222,6 +1320,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor): upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) upload_date = unified_strdate(upload_date) + m_music = re.search( + r'<h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*<ul[^>]*>\s*<li>(?P<title>.+?) by (?P<creator>.+?)(?:\(.+?\))?</li', + video_webpage) + if m_music: + video_alt_title = remove_quotes(unescapeHTML(m_music.group('title'))) + video_creator = clean_html(m_music.group('creator')) + else: + video_alt_title = video_creator = None + m_cat_container = self._search_regex( r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>', video_webpage, 'categories', default=None) @@ -1332,7 +1439,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): player_desc = 'flash player %s' % player_version else: player_version = self._search_regex( - r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', + [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', r'(?:www|player)-([^/]+)/base\.js'], player_url, 'html5 player', fatal=False) player_desc = 'html5 player %s' % player_version @@ -1394,6 +1501,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): manifest_url = video_info['hlsvp'][0] url_map = self._extract_from_m3u8(manifest_url, video_id) formats = _map_to_format_list(url_map) + # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming + for a_format in formats: + a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True' else: raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info') @@ -1431,10 +1541,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor): r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">', video_webpage) if stretched_m: - ratio = float(stretched_m.group('w')) / float(stretched_m.group('h')) - for f in formats: - if f.get('vcodec') != 'none': - f['stretched_ratio'] = ratio + w = float(stretched_m.group('w')) + h = float(stretched_m.group('h')) + # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0). + # We will only process correct ratios. + if w > 0 and h > 0: + ratio = w / h + for f in formats: + if f.get('vcodec') != 'none': + f['stretched_ratio'] = ratio self._sort_formats(formats) @@ -1443,7 +1558,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader': video_uploader, 'uploader_id': video_uploader_id, 'upload_date': upload_date, + 'creator': video_creator, 'title': video_title, + 'alt_title': video_alt_title, 'thumbnail': video_thumbnail, 'description': video_description, 'categories': video_categories, @@ -1473,7 +1590,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor, YoutubePlaylistBaseInfoExtract youtube\.com/ (?: (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries) - \? (?:.*?&)*? (?:p|a|list)= + \? (?:.*?[&;])*? (?:p|a|list)= | p/ ) ( @@ -1604,7 +1721,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor, YoutubePlaylistBaseInfoExtract self.report_warning('Youtube gives an alert message: ' + match) playlist_title = self._html_search_regex( - r'(?s)<h1 class="pl-header-title[^"]*">\s*(.*?)\s*</h1>', + r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>', page, 'title') return self.playlist_result(self._entries(page, playlist_id), playlist_id, playlist_title) @@ -1658,6 +1775,10 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor): }, }] + @classmethod + def suitable(cls, url): + return False if YoutubePlaylistsIE.suitable(url) else super(YoutubeChannelIE, cls).suitable(url) + def _real_extract(self, url): channel_id = self._match_id(url) @@ -1731,6 +1852,36 @@ class YoutubeUserIE(YoutubeChannelIE): return super(YoutubeUserIE, cls).suitable(url) +class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor): + IE_DESC = 'YouTube.com user/channel playlists' + _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists' + IE_NAME = 'youtube:playlists' + + _TESTS = [{ + 'url': 'http://www.youtube.com/user/ThirstForScience/playlists', + 'playlist_mincount': 4, + 'info_dict': { + 'id': 'ThirstForScience', + 'title': 'Thirst for Science', + }, + }, { + # with "Load more" button + 'url': 'http://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd', + 'playlist_mincount': 70, + 'info_dict': { + 'id': 'igorkle1', + 'title': 'Игорь Клейнер', + }, + }, { + 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists', + 'playlist_mincount': 17, + 'info_dict': { + 'id': 'UCiU1dHvZObB2iP6xkJ__Icw', + 'title': 'Chem Player', + }, + }] + + class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE): IE_DESC = 'YouTube.com searches' # there doesn't appear to be a real limit, for example if you search for @@ -1826,7 +1977,7 @@ class YoutubeSearchURLIE(InfoExtractor): } -class YoutubeShowIE(InfoExtractor): +class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor): IE_DESC = 'YouTube.com (multi-season) shows' _VALID_URL = r'https?://www\.youtube\.com/show/(?P<id>[^?#]*)' IE_NAME = 'youtube:show' @@ -1840,26 +1991,9 @@ class YoutubeShowIE(InfoExtractor): }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - playlist_id = mobj.group('id') - webpage = self._download_webpage( - 'https://www.youtube.com/show/%s/playlists' % playlist_id, playlist_id, 'Downloading show webpage') - # There's one playlist for each season of the show - m_seasons = list(re.finditer(r'href="(/playlist\?list=.*?)"', webpage)) - self.to_screen('%s: Found %s seasons' % (playlist_id, len(m_seasons))) - entries = [ - self.url_result( - 'https://www.youtube.com' + season.group(1), 'YoutubePlaylist') - for season in m_seasons - ] - title = self._og_search_title(webpage, fatal=False) - - return { - '_type': 'playlist', - 'id': playlist_id, - 'title': title, - 'entries': entries, - } + playlist_id = self._match_id(url) + return super(YoutubeShowIE, self)._real_extract( + 'https://www.youtube.com/show/%s/playlists' % playlist_id) class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): |