diff options
Diffstat (limited to 'youtube_dl/extractor')
30 files changed, 454 insertions, 211 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index d131d3ec3..79bcd9106 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -339,8 +339,7 @@ from .newstube import NewstubeIE from .nextmedia import ( NextMediaIE, NextMediaActionNewsIE, - AppleDailyRealtimeNewsIE, - AppleDailyAnimationNewsIE + AppleDailyIE, ) from .nfb import NFBIE from .nfl import NFLIE @@ -573,7 +572,10 @@ from .tumblr import TumblrIE from .tunein import TuneInIE from .turbo import TurboIE from .tutv import TutvIE -from .tv2 import TV2IE +from .tv2 import ( + TV2IE, + TV2ArticleIE, +) from .tv4 import TV4IE from .tvigle import TvigleIE from .tvp import TvpIE, TvpSeriesIE @@ -645,7 +647,10 @@ from .vine import ( VineIE, VineUserIE, ) -from .viki import VikiIE +from .viki import ( + VikiIE, + VikiChannelIE, +) from .vk import ( VKIE, VKUserVideosIE, diff --git a/youtube_dl/extractor/chilloutzone.py b/youtube_dl/extractor/chilloutzone.py index c922f6959..0206d96db 100644 --- a/youtube_dl/extractor/chilloutzone.py +++ b/youtube_dl/extractor/chilloutzone.py @@ -57,7 +57,7 @@ class ChilloutzoneIE(InfoExtractor): base64_video_info = self._html_search_regex( r'var cozVidData = "(.+?)";', webpage, 'video data') - decoded_video_info = base64.b64decode(base64_video_info).decode("utf-8") + decoded_video_info = base64.b64decode(base64_video_info.encode('utf-8')).decode('utf-8') video_info_dict = json.loads(decoded_video_info) # get video information from dict diff --git a/youtube_dl/extractor/cnn.py b/youtube_dl/extractor/cnn.py index 5efc5f4fe..3b1bd4033 100644 --- a/youtube_dl/extractor/cnn.py +++ b/youtube_dl/extractor/cnn.py @@ -12,7 +12,7 @@ from ..utils import ( class CNNIE(InfoExtractor): _VALID_URL = r'''(?x)https?://(?:(?:edition|www)\.)?cnn\.com/video/(?:data/.+?|\?)/ - (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:[a-z]{3,5})(?:-ap)?|(?=&)))''' + (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:[a-z\-]+)|(?=&)))''' _TESTS = [{ 'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn', diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py index f25ab319e..baa24c6d1 100644 --- a/youtube_dl/extractor/drtv.py +++ b/youtube_dl/extractor/drtv.py @@ -1,8 +1,11 @@ # coding: utf-8 from __future__ import unicode_literals -from .common import InfoExtractor, ExtractorError -from ..utils import parse_iso8601 +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + parse_iso8601, +) class DRTVIE(InfoExtractor): @@ -60,19 +63,31 @@ class DRTVIE(InfoExtractor): restricted_to_denmark = asset['RestrictedToDenmark'] spoken_subtitles = asset['Target'] == 'SpokenSubtitles' for link in asset['Links']: - target = link['Target'] uri = link['Uri'] + target = link['Target'] format_id = target - preference = -1 if target == 'HDS' else -2 + preference = None if spoken_subtitles: - preference -= 2 + preference = -1 format_id += '-spoken-subtitles' - formats.append({ - 'url': uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43' if target == 'HDS' else uri, - 'format_id': format_id, - 'ext': link['FileFormat'], - 'preference': preference, - }) + if target == 'HDS': + formats.extend(self._extract_f4m_formats( + uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43', + video_id, preference, f4m_id=format_id)) + elif target == 'HLS': + formats.extend(self._extract_m3u8_formats( + uri, video_id, 'mp4', preference=preference, + m3u8_id=format_id)) + else: + bitrate = link.get('Bitrate') + if bitrate: + format_id += '-%s' % bitrate + formats.append({ + 'url': uri, + 'format_id': format_id, + 'tbr': bitrate, + 'ext': link.get('FileFormat'), + }) subtitles_list = asset.get('SubtitlesList') if isinstance(subtitles_list, list): LANGS = { diff --git a/youtube_dl/extractor/empflix.py b/youtube_dl/extractor/empflix.py index 70f8efe27..9a5a8f4bb 100644 --- a/youtube_dl/extractor/empflix.py +++ b/youtube_dl/extractor/empflix.py @@ -4,22 +4,28 @@ from .tnaflix import TNAFlixIE class EMPFlixIE(TNAFlixIE): - _VALID_URL = r'^https?://www\.empflix\.com/videos/(?P<display_id>[0-9a-zA-Z-]+)-(?P<id>[0-9]+)\.html' + _VALID_URL = r'https?://(?:www\.)?empflix\.com/videos/(?P<display_id>.+?)-(?P<id>[0-9]+)\.html' _TITLE_REGEX = r'name="title" value="(?P<title>[^"]*)"' _DESCRIPTION_REGEX = r'name="description" value="([^"]*)"' _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"' - _TEST = { - 'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html', - 'md5': 'b1bc15b6412d33902d6e5952035fcabc', - 'info_dict': { - 'id': '33051', - 'display_id': 'Amateur-Finger-Fuck', - 'ext': 'mp4', - 'title': 'Amateur Finger Fuck', - 'description': 'Amateur solo finger fucking.', - 'thumbnail': 're:https?://.*\.jpg$', - 'age_limit': 18, + _TESTS = [ + { + 'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html', + 'md5': 'b1bc15b6412d33902d6e5952035fcabc', + 'info_dict': { + 'id': '33051', + 'display_id': 'Amateur-Finger-Fuck', + 'ext': 'mp4', + 'title': 'Amateur Finger Fuck', + 'description': 'Amateur solo finger fucking.', + 'thumbnail': 're:https?://.*\.jpg$', + 'age_limit': 18, + } + }, + { + 'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html', + 'matching_only': True, } - } + ] diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index 65f6ca103..b10755788 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -7,9 +7,9 @@ from ..utils import int_or_none class InstagramIE(InfoExtractor): - _VALID_URL = r'https?://instagram\.com/p/(?P<id>[\da-zA-Z]+)' + _VALID_URL = r'https://instagram\.com/p/(?P<id>[\da-zA-Z]+)' _TEST = { - 'url': 'http://instagram.com/p/aye83DjauH/?foo=bar#abc', + 'url': 'https://instagram.com/p/aye83DjauH/?foo=bar#abc', 'md5': '0d2da106a9d2631273e192b372806516', 'info_dict': { 'id': 'aye83DjauH', @@ -41,11 +41,11 @@ class InstagramIE(InfoExtractor): class InstagramUserIE(InfoExtractor): - _VALID_URL = r'http://instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])' + _VALID_URL = r'https://instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])' IE_DESC = 'Instagram user profile' IE_NAME = 'instagram:user' _TEST = { - 'url': 'http://instagram.com/porsche', + 'url': 'https://instagram.com/porsche', 'info_dict': { 'id': 'porsche', 'title': 'porsche', diff --git a/youtube_dl/extractor/letv.py b/youtube_dl/extractor/letv.py index 1484ac0d2..da896caf1 100644 --- a/youtube_dl/extractor/letv.py +++ b/youtube_dl/extractor/letv.py @@ -50,9 +50,7 @@ class LetvIE(InfoExtractor): 'title': '与龙共舞 完整版', 'description': 'md5:7506a5eeb1722bb9d4068f85024e3986', }, - 'params': { - 'cn_verification_proxy': 'http://proxy.uku.im:8888' - }, + 'skip': 'Only available in China', }] @staticmethod diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py index d8897eb90..7091f3335 100644 --- a/youtube_dl/extractor/mitele.py +++ b/youtube_dl/extractor/mitele.py @@ -20,7 +20,6 @@ class MiTeleIE(InfoExtractor): _TESTS = [{ 'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/', - 'md5': '6a75fe9d0d3275bead0cb683c616fddb', 'info_dict': { 'id': '0fce117d', 'ext': 'mp4', @@ -29,6 +28,10 @@ class MiTeleIE(InfoExtractor): 'display_id': 'programa-144', 'duration': 2913, }, + 'params': { + # m3u8 download + 'skip_download': True, + }, }] def _real_extract(self, url): @@ -56,12 +59,14 @@ class MiTeleIE(InfoExtractor): episode, transform_source=strip_jsonp ) + formats = self._extract_m3u8_formats( + token_info['tokenizedUrl'], episode, ext='mp4') return { 'id': embed_data['videoId'], 'display_id': episode, 'title': info_el.find('title').text, - 'url': token_info['tokenizedUrl'], + 'formats': formats, 'description': get_element_by_attribute('class', 'text', webpage), 'thumbnail': info_el.find('thumb').text, 'duration': parse_duration(info_el.find('duration').text), diff --git a/youtube_dl/extractor/nba.py b/youtube_dl/extractor/nba.py index 862b706bf..944096e1c 100644 --- a/youtube_dl/extractor/nba.py +++ b/youtube_dl/extractor/nba.py @@ -22,6 +22,18 @@ class NBAIE(InfoExtractor): }, { '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', + 'info_dict': { + 'id': '0041400301-cle-atl-recap.nba', + 'ext': 'mp4', + 'title': 'NBA GAME TIME | Video: Hawks vs. Cavaliers Game 1', + 'description': 'md5:8094c3498d35a9bd6b1a8c396a071b4d', + 'duration': 228, + }, + 'params': { + 'skip_download': True, + } }] def _real_extract(self, url): @@ -35,8 +47,12 @@ class NBAIE(InfoExtractor): self._og_search_title(webpage, default=shortened_video_id), ' : NBA.com') description = self._og_search_description(webpage) - duration = parse_duration( - self._html_search_meta('duration', webpage, 'duration')) + 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) return { 'id': shortened_video_id, diff --git a/youtube_dl/extractor/nextmedia.py b/youtube_dl/extractor/nextmedia.py index 02dba4ef6..d1b7cff4c 100644 --- a/youtube_dl/extractor/nextmedia.py +++ b/youtube_dl/extractor/nextmedia.py @@ -89,8 +89,8 @@ class NextMediaActionNewsIE(NextMediaIE): return self._extract_from_nextmedia_page(news_id, url, article_page) -class AppleDailyRealtimeNewsIE(NextMediaIE): - _VALID_URL = r'http://(www|ent).appledaily.com.tw/(realtimenews|enews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?' +class AppleDailyIE(NextMediaIE): + _VALID_URL = r'http://(www|ent).appledaily.com.tw/(?:animation|appledaily|enews|realtimenews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?' _TESTS = [{ 'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694', 'md5': 'a843ab23d150977cc55ef94f1e2c1e4d', @@ -99,7 +99,7 @@ class AppleDailyRealtimeNewsIE(NextMediaIE): 'ext': 'mp4', 'title': '周亭羽走過摩鐵陰霾2男陪吃 九把刀孤寒看醫生', 'thumbnail': 're:^https?://.*\.jpg$', - 'description': 'md5:b23787119933404ce515c6356a8c355c', + 'description': 'md5:2acd430e59956dc47cd7f67cb3c003f4', 'upload_date': '20150128', } }, { @@ -110,26 +110,10 @@ class AppleDailyRealtimeNewsIE(NextMediaIE): 'ext': 'mp4', 'title': '不滿被踩腳 山東兩大媽一路打下車', 'thumbnail': 're:^https?://.*\.jpg$', - 'description': 'md5:2648aaf6fc4f401f6de35a91d111aa1d', + 'description': 'md5:175b4260c1d7c085993474217e4ab1b4', 'upload_date': '20150128', } - }] - - _URL_PATTERN = r'\{url: \'(.+)\'\}' - - def _fetch_title(self, page): - return self._html_search_regex(r'<h1 id="h1">([^<>]+)</h1>', page, 'news title') - - def _fetch_thumbnail(self, page): - return self._html_search_regex(r"setInitialImage\(\'([^']+)'\)", page, 'video thumbnail', fatal=False) - - def _fetch_timestamp(self, page): - return None - - -class AppleDailyAnimationNewsIE(AppleDailyRealtimeNewsIE): - _VALID_URL = 'http://www.appledaily.com.tw/animation/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?' - _TESTS = [{ + }, { 'url': 'http://www.appledaily.com.tw/animation/realtimenews/new/20150128/5003671', 'md5': '03df296d95dedc2d5886debbb80cb43f', 'info_dict': { @@ -154,10 +138,22 @@ class AppleDailyAnimationNewsIE(AppleDailyRealtimeNewsIE): 'expected_warnings': [ 'video thumbnail', ] + }, { + 'url': 'http://www.appledaily.com.tw/appledaily/article/supplement/20140417/35770334/', + 'only_matching': True, }] + _URL_PATTERN = r'\{url: \'(.+)\'\}' + def _fetch_title(self, page): - return self._html_search_meta('description', page, 'news title') + return (self._html_search_regex(r'<h1 id="h1">([^<>]+)</h1>', page, 'news title', default=None) or + self._html_search_meta('description', page, 'news title')) + + def _fetch_thumbnail(self, page): + return self._html_search_regex(r"setInitialImage\(\'([^']+)'\)", page, 'video thumbnail', fatal=False) + + def _fetch_timestamp(self, page): + return None def _fetch_description(self, page): return self._html_search_meta('description', page, 'news description') diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py index 7cc799664..255d4abc1 100644 --- a/youtube_dl/extractor/prosiebensat1.py +++ b/youtube_dl/extractor/prosiebensat1.py @@ -17,7 +17,7 @@ from ..utils import ( class ProSiebenSat1IE(InfoExtractor): IE_NAME = 'prosiebensat1' IE_DESC = 'ProSiebenSat.1 Digital' - _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|ran|the-voice-of-germany)\.de|fem\.com)/(?P<id>.+)' + _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|the-voice-of-germany)\.(?:de|at)|ran\.de|fem\.com)/(?P<id>.+)' _TESTS = [ { diff --git a/youtube_dl/extractor/qqmusic.py b/youtube_dl/extractor/qqmusic.py index 13113820b..b540033e2 100644 --- a/youtube_dl/extractor/qqmusic.py +++ b/youtube_dl/extractor/qqmusic.py @@ -26,7 +26,7 @@ class QQMusicIE(InfoExtractor): 'title': '可惜没如果', 'upload_date': '20141227', 'creator': '林俊杰', - 'description': 'md5:4348ff1dd24036906baa7b6f973f8d30', + 'description': 'md5:d327722d0361576fde558f1ac68a7065', } }] @@ -60,6 +60,8 @@ class QQMusicIE(InfoExtractor): lrc_content = self._html_search_regex( r'<div class="content" id="lrc_content"[^<>]*>([^<>]+)</div>', detail_info_page, 'LRC lyrics', default=None) + if lrc_content: + lrc_content = lrc_content.replace('\\n', '\n') guid = self.m_r_get_ruin() diff --git a/youtube_dl/extractor/rtve.py b/youtube_dl/extractor/rtve.py index 849300140..82cd98ac7 100644 --- a/youtube_dl/extractor/rtve.py +++ b/youtube_dl/extractor/rtve.py @@ -17,7 +17,7 @@ from ..utils import ( def _decrypt_url(png): - encrypted_data = base64.b64decode(png) + encrypted_data = base64.b64decode(png.encode('utf-8')) text_index = encrypted_data.find(b'tEXt') text_chunk = encrypted_data[text_index - 4:] length = struct_unpack('!I', text_chunk[:4])[0] diff --git a/youtube_dl/extractor/rutv.py b/youtube_dl/extractor/rutv.py index 55604637d..d9df06861 100644 --- a/youtube_dl/extractor/rutv.py +++ b/youtube_dl/extractor/rutv.py @@ -104,7 +104,7 @@ class RUTVIE(InfoExtractor): @classmethod def _extract_url(cls, webpage): mobj = re.search( - r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.rutv\.ru/(?:iframe/(?:swf|video|live)/id|index/iframe/cast_id)/.+?)\1', webpage) + r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.(?:rutv\.ru|vgtrk\.com)/(?:iframe/(?:swf|video|live)/id|index/iframe/cast_id)/.+?)\1', webpage) if mobj: return mobj.group('url') diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index 26ced716e..9f3e944e7 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -47,7 +47,7 @@ class SharedIE(InfoExtractor): video_url = self._html_search_regex( r'data-url="([^"]+)"', video_page, 'video URL') title = base64.b64decode(self._html_search_meta( - 'full:title', webpage, 'title')).decode('utf-8') + 'full:title', webpage, 'title').encode('utf-8')).decode('utf-8') filesize = int_or_none(self._html_search_meta( 'full:size', webpage, 'file size', fatal=False)) thumbnail = self._html_search_regex( diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py index eab4adfca..29bd9ce6f 100644 --- a/youtube_dl/extractor/sohu.py +++ b/youtube_dl/extractor/sohu.py @@ -23,9 +23,7 @@ class SohuIE(InfoExtractor): 'ext': 'mp4', 'title': 'MV:Far East Movement《The Illest》', }, - 'params': { - 'cn_verification_proxy': 'proxy.uku.im:8888' - } + 'skip': 'On available in China', }, { 'url': 'http://tv.sohu.com/20150305/n409385080.shtml', 'md5': 'ac9a5d322b4bf9ae184d53e4711e4f1a', diff --git a/youtube_dl/extractor/sportbox.py b/youtube_dl/extractor/sportbox.py index 8686f9d11..86d509ae5 100644 --- a/youtube_dl/extractor/sportbox.py +++ b/youtube_dl/extractor/sportbox.py @@ -6,8 +6,7 @@ import re from .common import InfoExtractor from ..compat import compat_urlparse from ..utils import ( - parse_duration, - parse_iso8601, + unified_strdate, ) @@ -20,11 +19,9 @@ class SportBoxIE(InfoExtractor): 'id': '80822', 'ext': 'mp4', 'title': 'Гонка 2 заезд ««Объединенный 2000»: классы Туринг и Супер-продакшн', - 'description': 'md5:81715fa9c4ea3d9e7915dc8180c778ed', + 'description': 'md5:3d72dc4a006ab6805d82f037fdc637ad', 'thumbnail': 're:^https?://.*\.jpg$', - 'timestamp': 1411896237, 'upload_date': '20140928', - 'duration': 4846, }, 'params': { # m3u8 download @@ -48,17 +45,13 @@ class SportBoxIE(InfoExtractor): r'src="/?(vdl/player/[^"]+)"', webpage, 'player') title = self._html_search_regex( - r'<h1 itemprop="name">([^<]+)</h1>', webpage, 'title') - description = self._html_search_regex( - r'(?s)<div itemprop="description">(.+?)</div>', - webpage, 'description', fatal=False) + [r'"nodetitle"\s*:\s*"([^"]+)"', r'class="node-header_{1,2}title">([^<]+)'], + webpage, 'title') + description = self._og_search_description(webpage) or self._html_search_meta( + 'description', webpage, 'description') thumbnail = self._og_search_thumbnail(webpage) - timestamp = parse_iso8601(self._search_regex( - r'<span itemprop="uploadDate">([^<]+)</span>', - webpage, 'timestamp', fatal=False)) - duration = parse_duration(self._html_search_regex( - r'<meta itemprop="duration" content="PT([^"]+)">', - webpage, 'duration', fatal=False)) + upload_date = unified_strdate(self._html_search_meta( + 'dateCreated', webpage, 'upload date')) return { '_type': 'url_transparent', @@ -67,8 +60,7 @@ class SportBoxIE(InfoExtractor): 'title': title, 'description': description, 'thumbnail': thumbnail, - 'timestamp': timestamp, - 'duration': duration, + 'upload_date': upload_date, } diff --git a/youtube_dl/extractor/telecinco.py b/youtube_dl/extractor/telecinco.py index 251a68680..a0c744fd1 100644 --- a/youtube_dl/extractor/telecinco.py +++ b/youtube_dl/extractor/telecinco.py @@ -16,6 +16,10 @@ class TelecincoIE(MiTeleIE): 'title': 'Con Martín Berasategui, hacer un bacalao al ...', 'duration': 662, }, + 'params': { + # m3u8 download + 'skip_download': True, + }, }, { 'url': 'http://www.telecinco.es/informativos/nacional/Pablo_Iglesias-Informativos_Telecinco-entrevista-Pedro_Piqueras_2_1945155182.html', 'only_matching': True, diff --git a/youtube_dl/extractor/tnaflix.py b/youtube_dl/extractor/tnaflix.py index d48cbbf14..59af9aba0 100644 --- a/youtube_dl/extractor/tnaflix.py +++ b/youtube_dl/extractor/tnaflix.py @@ -10,26 +10,32 @@ from ..utils import ( class TNAFlixIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/(?P<cat_id>[\w-]+)/(?P<display_id>[\w-]+)/video(?P<id>\d+)' + _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)' _TITLE_REGEX = r'<title>(.+?) - TNAFlix Porn Videos</title>' _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>' _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"' - _TEST = { - 'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878', - 'md5': 'ecf3498417d09216374fc5907f9c6ec0', - 'info_dict': { - 'id': '553878', - 'display_id': 'Carmella-Decesare-striptease', - 'ext': 'mp4', - 'title': 'Carmella Decesare - striptease', - 'description': '', - 'thumbnail': 're:https?://.*\.jpg$', - 'duration': 91, - 'age_limit': 18, + _TESTS = [ + { + 'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878', + 'md5': 'ecf3498417d09216374fc5907f9c6ec0', + 'info_dict': { + 'id': '553878', + 'display_id': 'Carmella-Decesare-striptease', + 'ext': 'mp4', + 'title': 'Carmella Decesare - striptease', + 'description': '', + 'thumbnail': 're:https?://.*\.jpg$', + 'duration': 91, + 'age_limit': 18, + } + }, + { + 'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632', + 'matching_only': True, } - } + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/tutv.py b/youtube_dl/extractor/tutv.py index 4de0aac52..fad720b68 100644 --- a/youtube_dl/extractor/tutv.py +++ b/youtube_dl/extractor/tutv.py @@ -26,7 +26,7 @@ class TutvIE(InfoExtractor): data_content = self._download_webpage( 'http://tu.tv/flvurl.php?codVideo=%s' % internal_id, video_id, 'Downloading video info') - video_url = base64.b64decode(compat_parse_qs(data_content)['kpt'][0]).decode('utf-8') + video_url = base64.b64decode(compat_parse_qs(data_content)['kpt'][0].encode('utf-8')).decode('utf-8') return { 'id': internal_id, diff --git a/youtube_dl/extractor/tv2.py b/youtube_dl/extractor/tv2.py index 2dcc0e971..fa338b936 100644 --- a/youtube_dl/extractor/tv2.py +++ b/youtube_dl/extractor/tv2.py @@ -1,12 +1,15 @@ # encoding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( determine_ext, int_or_none, float_or_none, parse_iso8601, + remove_end, ) @@ -91,3 +94,33 @@ class TV2IE(InfoExtractor): 'categories': categories, 'formats': formats, } + + +class TV2ArticleIE(InfoExtractor): + _VALID_URL = 'http://(?:www\.)?tv2\.no/(?:a|\d{4}/\d{2}/\d{2}(/[^/]+)+)/(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://www.tv2.no/2015/05/16/nyheter/alesund/krim/pingvin/6930542', + 'info_dict': { + 'id': '6930542', + 'title': 'Russen hetses etter pingvintyveri – innrømmer å ha åpnet luken på buret', + 'description': 'md5:339573779d3eea3542ffe12006190954', + }, + 'playlist_count': 2, + }, { + 'url': 'http://www.tv2.no/a/6930542', + 'only_matching': True, + }] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + entries = [ + self.url_result('http://www.tv2.no/v/%s' % video_id, 'TV2') + for video_id in re.findall(r'data-assetid="(\d+)"', webpage)] + + title = remove_end(self._og_search_title(webpage), ' - TV2.no') + description = remove_end(self._og_search_description(webpage), ' - TV2.no') + + return self.playlist_result(entries, playlist_id, title, description) diff --git a/youtube_dl/extractor/ultimedia.py b/youtube_dl/extractor/ultimedia.py index 96c809eaf..c4751050e 100644 --- a/youtube_dl/extractor/ultimedia.py +++ b/youtube_dl/extractor/ultimedia.py @@ -4,6 +4,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_urllib_parse_urlparse from ..utils import ( ExtractorError, qualities, @@ -44,9 +45,9 @@ class UltimediaIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - deliver_url = self._search_regex( - r'<iframe[^>]+src="(https?://(?:www\.)?ultimedia\.com/deliver/[^"]+)"', - webpage, 'deliver URL') + deliver_url = self._proto_relative_url(self._search_regex( + r'<iframe[^>]+src="((?:https?:)?//(?:www\.)?ultimedia\.com/deliver/[^"]+)"', + webpage, 'deliver URL'), compat_urllib_parse_urlparse(url).scheme + ':') deliver_page = self._download_webpage( deliver_url, video_id, 'Downloading iframe page') @@ -57,7 +58,8 @@ class UltimediaIE(InfoExtractor): player = self._parse_json( self._search_regex( - r"jwplayer\('player(?:_temp)?'\)\.setup\(({.+?})\)\.on", deliver_page, 'player'), + r"jwplayer\('player(?:_temp)?'\)\.setup\(({.+?})\)\.on", + deliver_page, 'player'), video_id) quality = qualities(['flash', 'html5']) diff --git a/youtube_dl/extractor/videott.py b/youtube_dl/extractor/videott.py index ececc7ee0..591024ead 100644 --- a/youtube_dl/extractor/videott.py +++ b/youtube_dl/extractor/videott.py @@ -43,7 +43,7 @@ class VideoTtIE(InfoExtractor): formats = [ { - 'url': base64.b64decode(res['u']).decode('utf-8'), + 'url': base64.b64decode(res['u'].encode('utf-8')).decode('utf-8'), 'ext': 'flv', 'format_id': res['l'], } for res in settings['res'] if res['u'] diff --git a/youtube_dl/extractor/vier.py b/youtube_dl/extractor/vier.py index 619039e51..15377097e 100644 --- a/youtube_dl/extractor/vier.py +++ b/youtube_dl/extractor/vier.py @@ -38,11 +38,14 @@ class VierIE(InfoExtractor): webpage = self._download_webpage(url, display_id) video_id = self._search_regex( - r'"nid"\s*:\s*"(\d+)"', webpage, 'video id') + [r'data-nid="(\d+)"', r'"nid"\s*:\s*"(\d+)"'], + webpage, 'video id') application = self._search_regex( - r'"application"\s*:\s*"([^"]+)"', webpage, 'application', default='vier_vod') + [r'data-application="([^"]+)"', r'"application"\s*:\s*"([^"]+)"'], + webpage, 'application', default='vier_vod') filename = self._search_regex( - r'"filename"\s*:\s*"([^"]+)"', webpage, 'filename') + [r'data-filename="([^"]+)"', r'"filename"\s*:\s*"([^"]+)"'], + webpage, 'filename') playlist_url = 'http://vod.streamcloud.be/%s/mp4:_definst_/%s.mp4/playlist.m3u8' % (application, filename) formats = self._extract_m3u8_formats(playlist_url, display_id, 'mp4') diff --git a/youtube_dl/extractor/viki.py b/youtube_dl/extractor/viki.py index cf6af1e5c..7f2fb1ca8 100644 --- a/youtube_dl/extractor/viki.py +++ b/youtube_dl/extractor/viki.py @@ -1,29 +1,65 @@ from __future__ import unicode_literals -import re +import time +import hmac +import hashlib +import itertools -from ..compat import ( - compat_urlparse, - compat_urllib_request, -) from ..utils import ( ExtractorError, - unescapeHTML, - unified_strdate, - US_RATINGS, - determine_ext, - mimetype2ext, + int_or_none, + parse_age_limit, + parse_iso8601, ) from .common import InfoExtractor -class VikiIE(InfoExtractor): - IE_NAME = 'viki' +class VikiBaseIE(InfoExtractor): + _VALID_URL_BASE = r'https?://(?:www\.)?viki\.(?:com|net|mx|jp|fr)/' + _API_QUERY_TEMPLATE = '/v4/%sapp=%s&t=%s&site=www.viki.com' + _API_URL_TEMPLATE = 'http://api.viki.io%s&sig=%s' + + _APP = '65535a' + _APP_VERSION = '2.2.5.1428709186' + _APP_SECRET = '-$iJ}@p7!G@SyU/je1bEyWg}upLu-6V6-Lg9VD(]siH,r.,m-r|ulZ,U4LC/SeR)' + + def _prepare_call(self, path, timestamp=None): + path += '?' if '?' not in path else '&' + if not timestamp: + timestamp = int(time.time()) + query = self._API_QUERY_TEMPLATE % (path, self._APP, timestamp) + sig = hmac.new( + self._APP_SECRET.encode('ascii'), + query.encode('ascii'), + hashlib.sha1 + ).hexdigest() + return self._API_URL_TEMPLATE % (query, sig) + + def _call_api(self, path, video_id, note, timestamp=None): + resp = self._download_json( + self._prepare_call(path, timestamp), video_id, note) + + error = resp.get('error') + if error: + if error == 'invalid timestamp': + resp = self._download_json( + self._prepare_call(path, int(resp['current_timestamp'])), + video_id, '%s (retry)' % note) + error = resp.get('error') + if error: + self._raise_error(resp['error']) + + return resp - # iPad2 - _USER_AGENT = 'Mozilla/5.0(iPad; U; CPU OS 4_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8F191 Safari/6533.18.5' + def _raise_error(self, error): + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, error), + expected=True) - _VALID_URL = r'^https?://(?:www\.)?viki\.com/videos/(?P<id>[0-9]+v)' + +class VikiIE(VikiBaseIE): + IE_NAME = 'viki' + _VALID_URL = r'%s(?:videos|player)/(?P<id>[0-9]+v)' % VikiBaseIE._VALID_URL_BASE _TESTS = [{ 'url': 'http://www.viki.com/videos/1023585v-heirs-episode-14', 'info_dict': { @@ -37,111 +73,218 @@ class VikiIE(InfoExtractor): }, 'skip': 'Blocked in the US', }, { + # clip 'url': 'http://www.viki.com/videos/1067139v-the-avengers-age-of-ultron-press-conference', - 'md5': 'ca6493e6f0a6ec07da9aa8d6304b4b2c', + 'md5': '86c0b5dbd4d83a6611a79987cc7a1989', 'info_dict': { 'id': '1067139v', 'ext': 'mp4', + 'title': "'The Avengers: Age of Ultron' Press Conference", 'description': 'md5:d70b2f9428f5488321bfe1db10d612ea', + 'duration': 352, + 'timestamp': 1430380829, 'upload_date': '20150430', - 'title': '\'The Avengers: Age of Ultron\' Press Conference', + 'uploader': 'Arirang TV', + 'like_count': int, + 'age_limit': 0, } }, { 'url': 'http://www.viki.com/videos/1048879v-ankhon-dekhi', 'info_dict': { 'id': '1048879v', 'ext': 'mp4', - 'upload_date': '20140820', - 'description': 'md5:54ff56d51bdfc7a30441ec967394e91c', 'title': 'Ankhon Dekhi', + 'duration': 6512, + 'timestamp': 1408532356, + 'upload_date': '20140820', + 'uploader': 'Spuul', + 'like_count': int, + 'age_limit': 13, }, 'params': { - # requires ffmpeg + # m3u8 download 'skip_download': True, } + }, { + # episode + 'url': 'http://www.viki.com/videos/44699v-boys-over-flowers-episode-1', + 'md5': '190f3ef426005ba3a080a63325955bc3', + 'info_dict': { + 'id': '44699v', + 'ext': 'mp4', + 'title': 'Boys Over Flowers - Episode 1', + 'description': 'md5:52617e4f729c7d03bfd4bcbbb6e946f2', + 'duration': 4155, + 'timestamp': 1270496524, + 'upload_date': '20100405', + 'uploader': 'group8', + 'like_count': int, + 'age_limit': 13, + } + }, { + # youtube external + 'url': 'http://www.viki.com/videos/50562v-poor-nastya-complete-episode-1', + 'md5': '216d1afdc0c64d1febc1e9f2bd4b864b', + 'info_dict': { + 'id': '50562v', + 'ext': 'mp4', + 'title': 'Poor Nastya [COMPLETE] - Episode 1', + 'description': '', + 'duration': 607, + 'timestamp': 1274949505, + 'upload_date': '20101213', + 'uploader': 'ad14065n', + 'uploader_id': 'ad14065n', + 'like_count': int, + 'age_limit': 13, + } + }, { + 'url': 'http://www.viki.com/player/44699v', + 'only_matching': True, }] def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - title = self._og_search_title(webpage) - description = self._og_search_description(webpage) - thumbnail = self._og_search_thumbnail(webpage) - - uploader_m = re.search( - r'<strong>Broadcast Network: </strong>\s*([^<]*)<', webpage) - if uploader_m is None: - uploader = None - else: - uploader = uploader_m.group(1).strip() - - rating_str = self._html_search_regex( - r'<strong>Rating: </strong>\s*([^<]*)<', webpage, - 'rating information', default='').strip() - age_limit = US_RATINGS.get(rating_str) - - req = compat_urllib_request.Request( - 'http://www.viki.com/player5_fragment/%s?action=show&controller=videos' % video_id) - req.add_header('User-Agent', self._USER_AGENT) - info_webpage = self._download_webpage( - req, video_id, note='Downloading info page') - err_msg = self._html_search_regex(r'<div[^>]+class="video-error[^>]+>(.+)</div>', info_webpage, 'error message', default=None) - if err_msg: - if 'not available in your region' in err_msg: - raise ExtractorError( - 'Video %s is blocked from your location.' % video_id, - expected=True) - else: - raise ExtractorError('Viki said: ' + err_msg) - mobj = re.search( - r'<source[^>]+type="(?P<mime_type>[^"]+)"[^>]+src="(?P<url>[^"]+)"', info_webpage) - if not mobj: - raise ExtractorError('Unable to find video URL') - video_url = unescapeHTML(mobj.group('url')) - video_ext = mimetype2ext(mobj.group('mime_type')) - - if determine_ext(video_url) == 'm3u8': - formats = self._extract_m3u8_formats( - video_url, video_id, ext=video_ext) - else: - formats = [{ - 'url': video_url, - 'ext': video_ext, - }] - - upload_date_str = self._html_search_regex( - r'"created_at":"([^"]+)"', info_webpage, 'upload date') - upload_date = ( - unified_strdate(upload_date_str) - if upload_date_str is not None - else None - ) - - # subtitles - video_subtitles = self.extract_subtitles(video_id, info_webpage) - - return { + video = self._call_api( + 'videos/%s.json' % video_id, video_id, 'Downloading video JSON') + + title = None + titles = video.get('titles') + if titles: + title = titles.get('en') or titles[titles.keys()[0]] + if not title: + title = 'Episode %d' % video.get('number') if video.get('type') == 'episode' else video.get('id') or video_id + container_titles = video.get('container', {}).get('titles') + if container_titles: + container_title = container_titles.get('en') or container_titles[container_titles.keys()[0]] + title = '%s - %s' % (container_title, title) + + descriptions = video.get('descriptions') + description = descriptions.get('en') or descriptions[titles.keys()[0]] if descriptions else None + + duration = int_or_none(video.get('duration')) + timestamp = parse_iso8601(video.get('created_at')) + uploader = video.get('author') + like_count = int_or_none(video.get('likes', {}).get('count')) + age_limit = parse_age_limit(video.get('rating')) + + thumbnails = [] + for thumbnail_id, thumbnail in video.get('images', {}).items(): + thumbnails.append({ + 'id': thumbnail_id, + 'url': thumbnail.get('url'), + }) + + subtitles = {} + for subtitle_lang, _ in video.get('subtitle_completions', {}).items(): + subtitles[subtitle_lang] = [{ + 'ext': subtitles_format, + 'url': self._prepare_call( + 'videos/%s/subtitles/%s.%s' % (video_id, subtitle_lang, subtitles_format)), + } for subtitles_format in ('srt', 'vtt')] + + result = { 'id': video_id, 'title': title, - 'formats': formats, 'description': description, - 'thumbnail': thumbnail, - 'age_limit': age_limit, + 'duration': duration, + 'timestamp': timestamp, 'uploader': uploader, - 'subtitles': video_subtitles, - 'upload_date': upload_date, + 'like_count': like_count, + 'age_limit': age_limit, + 'thumbnails': thumbnails, + 'subtitles': subtitles, } - def _get_subtitles(self, video_id, info_webpage): - res = {} - for sturl_html in re.findall(r'<track src="([^"]+)"', info_webpage): - sturl = unescapeHTML(sturl_html) - m = re.search(r'/(?P<lang>[a-z]+)\.vtt', sturl) - if not m: - continue - res[m.group('lang')] = [{ - 'url': compat_urlparse.urljoin('http://www.viki.com', sturl), - 'ext': 'vtt', - }] - return res + streams = self._call_api( + 'videos/%s/streams.json' % video_id, video_id, + 'Downloading video streams JSON') + + if 'external' in streams: + result.update({ + '_type': 'url_transparent', + 'url': streams['external']['url'], + }) + return result + + formats = [] + for format_id, stream_dict in streams.items(): + height = self._search_regex( + 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) + else: + formats.append({ + 'url': format_dict['url'], + 'format_id': '%s-%s' % (format_id, protocol), + 'height': height, + }) + self._sort_formats(formats) + + result['formats'] = formats + return result + + +class VikiChannelIE(VikiBaseIE): + IE_NAME = 'viki:channel' + _VALID_URL = r'%s(?:tv|news|movies|artists)/(?P<id>[0-9]+c)' % VikiBaseIE._VALID_URL_BASE + _TESTS = [{ + 'url': 'http://www.viki.com/tv/50c-boys-over-flowers', + 'info_dict': { + 'id': '50c', + 'title': 'Boys Over Flowers', + 'description': 'md5:ecd3cff47967fe193cff37c0bec52790', + }, + 'playlist_count': 70, + }, { + 'url': 'http://www.viki.com/tv/1354c-poor-nastya-complete', + 'info_dict': { + 'id': '1354c', + 'title': 'Poor Nastya [COMPLETE]', + 'description': 'md5:05bf5471385aa8b21c18ad450e350525', + }, + 'playlist_count': 127, + }, { + 'url': 'http://www.viki.com/news/24569c-showbiz-korea', + 'only_matching': True, + }, { + 'url': 'http://www.viki.com/movies/22047c-pride-and-prejudice-2005', + 'only_matching': True, + }, { + 'url': 'http://www.viki.com/artists/2141c-shinee', + 'only_matching': True, + }] + + _PER_PAGE = 25 + + def _real_extract(self, url): + channel_id = self._match_id(url) + + channel = self._call_api( + 'containers/%s.json' % channel_id, channel_id, + 'Downloading channel JSON') + + titles = channel['titles'] + title = titles.get('en') or titles[titles.keys()[0]] + + descriptions = channel['descriptions'] + description = descriptions.get('en') or descriptions[descriptions.keys()[0]] + + entries = [] + for video_type in ('episodes', 'clips', 'movies'): + for page_num in itertools.count(1): + page = self._call_api( + 'containers/%s/%s.json?per_page=%d&sort=number&direction=asc&with_paging=true&page=%d' + % (channel_id, video_type, self._PER_PAGE, page_num), channel_id, + 'Downloading %s JSON page #%d' % (video_type, page_num)) + for video in page['response']: + video_id = video['id'] + entries.append(self.url_result( + 'http://www.viki.com/videos/%s' % video_id, 'Viki')) + if not page['pagination']['next']: + break + + return self.playlist_result(entries, channel_id, title, description) diff --git a/youtube_dl/extractor/vuclip.py b/youtube_dl/extractor/vuclip.py index c3fde53f5..a6d9b5fee 100644 --- a/youtube_dl/extractor/vuclip.py +++ b/youtube_dl/extractor/vuclip.py @@ -49,7 +49,7 @@ class VuClipIE(InfoExtractor): links_code = self._search_regex( r'''(?xs) (?: - <img\s+src="/im/play.gif".*?>| + <img\s+src="[^"]*/play.gif".*?>| <!--\ player\ end\ -->\s*</div><!--\ thumb\ end--> ) (.*?) diff --git a/youtube_dl/extractor/vulture.py b/youtube_dl/extractor/vulture.py index 1eb24a3d6..faa167e65 100644 --- a/youtube_dl/extractor/vulture.py +++ b/youtube_dl/extractor/vulture.py @@ -44,7 +44,7 @@ class VultureIE(InfoExtractor): query_webpage = self._download_webpage( query_url, display_id, note='Downloading query page') params_json = self._search_regex( - r'(?sm)new MagnifyEmbeddablePlayer\({.*?contentItem:\s*(\{.*?\})\n,\n', + r'(?sm)new MagnifyEmbeddablePlayer\({.*?contentItem:\s*(\{.*?\})\n?,\n', query_webpage, 'player params') params = json.loads(params_json) diff --git a/youtube_dl/extractor/wimp.py b/youtube_dl/extractor/wimp.py index d6dec25ca..f69d46a28 100644 --- a/youtube_dl/extractor/wimp.py +++ b/youtube_dl/extractor/wimp.py @@ -37,7 +37,8 @@ class WimpIE(InfoExtractor): video_id = mobj.group(1) webpage = self._download_webpage(url, video_id) video_url = self._search_regex( - r"[\"']file[\"']\s*[:,]\s*[\"'](.+?)[\"']", webpage, 'video URL') + [r"[\"']file[\"']\s*[:,]\s*[\"'](.+?)[\"']", r"videoId\s*:\s*[\"']([^\"']+)[\"']"], + webpage, 'video URL') if YoutubeIE.suitable(video_url): self.to_screen('Found YouTube video') return { diff --git a/youtube_dl/extractor/xminus.py b/youtube_dl/extractor/xminus.py index 8c6241aed..7c9d8af6f 100644 --- a/youtube_dl/extractor/xminus.py +++ b/youtube_dl/extractor/xminus.py @@ -43,7 +43,7 @@ class XMinusIE(InfoExtractor): r'minus_track\.dur_sec=\'([0-9]*?)\'', webpage, 'duration', fatal=False)) filesize_approx = parse_filesize(self._html_search_regex( - r'<div class="filesize[^"]*"></div>\s*([0-9.]+\s*[a-zA-Z][bB])', + r'<div id="finfo"[^>]*>\s*↓\s*([0-9.]+\s*[a-zA-Z][bB])', webpage, 'approximate filesize', fatal=False)) tbr = int_or_none(self._html_search_regex( r'<div class="quality[^"]*"></div>\s*([0-9]+)\s*kbps', @@ -58,7 +58,7 @@ class XMinusIE(InfoExtractor): description = re.sub(' *\r *', '\n', description) enc_token = self._html_search_regex( - r'minus_track\.tkn="(.+?)"', webpage, 'enc_token') + r'minus_track\.s?tkn="(.+?)"', webpage, 'enc_token') token = ''.join( c if pos == 3 else compat_chr(compat_ord(c) - 1) for pos, c in enumerate(reversed(enc_token))) diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index bf4e659ac..f9afbdbab 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -15,6 +15,7 @@ from ..utils import ( unescapeHTML, ExtractorError, int_or_none, + mimetype2ext, ) from .nbc import NBCSportsVPlayerIE @@ -236,6 +237,22 @@ class YahooIE(InfoExtractor): self._sort_formats(formats) + closed_captions = self._html_search_regex( + r'"closedcaptions":(\[[^\]]+\])', webpage, 'closed captions', + default='[]') + + cc_json = self._parse_json(closed_captions, video_id, fatal=False) + subtitles = {} + if cc_json: + for closed_caption in cc_json: + lang = closed_caption['lang'] + if lang not in subtitles: + subtitles[lang] = [] + subtitles[lang].append({ + 'url': closed_caption['url'], + 'ext': mimetype2ext(closed_caption['content_type']), + }) + return { 'id': video_id, 'display_id': display_id, @@ -244,6 +261,7 @@ class YahooIE(InfoExtractor): 'description': clean_html(meta['description']), 'thumbnail': meta['thumbnail'] if meta.get('thumbnail') else self._og_search_thumbnail(webpage), 'duration': int_or_none(meta.get('duration')), + 'subtitles': subtitles, } |