diff options
Diffstat (limited to 'youtube_dl/extractor')
| -rw-r--r-- | youtube_dl/extractor/arte.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/cloudy.py | 4 | ||||
| -rw-r--r-- | youtube_dl/extractor/crunchyroll.py | 31 | ||||
| -rw-r--r-- | youtube_dl/extractor/cwtv.py | 5 | ||||
| -rw-r--r-- | youtube_dl/extractor/extractors.py | 5 | ||||
| -rw-r--r-- | youtube_dl/extractor/malemotion.py | 46 | ||||
| -rw-r--r-- | youtube_dl/extractor/mwave.py | 26 | ||||
| -rw-r--r-- | youtube_dl/extractor/nuvid.py | 44 | ||||
| -rw-r--r-- | youtube_dl/extractor/ooyala.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/orf.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/scivee.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/theplatform.py | 6 | ||||
| -rw-r--r-- | youtube_dl/extractor/twentymin.py | 23 | ||||
| -rw-r--r-- | youtube_dl/extractor/viewster.py | 144 | ||||
| -rw-r--r-- | youtube_dl/extractor/watchindianporn.py (renamed from youtube_dl/extractor/sexykarma.py) | 63 | ||||
| -rw-r--r-- | youtube_dl/extractor/yandexmusic.py | 26 | ||||
| -rw-r--r-- | youtube_dl/extractor/youtube.py | 29 |
17 files changed, 222 insertions, 236 deletions
diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index a9e3266dc..881cacfab 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -63,7 +63,7 @@ class ArteTvIE(InfoExtractor): class ArteTVPlus7IE(InfoExtractor): IE_NAME = 'arte.tv:+7' - _VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/(?:(?:sendungen|emissions|embed)/)?(?P<id>[^/]+)/(?P<name>[^/?#&+])' + _VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/(?:(?:sendungen|emissions|embed)/)?(?P<id>[^/]+)/(?P<name>[^/?#&]+)' @classmethod def _extract_url_info(cls, url): diff --git a/youtube_dl/extractor/cloudy.py b/youtube_dl/extractor/cloudy.py index 9e267e6c0..9a28ef354 100644 --- a/youtube_dl/extractor/cloudy.py +++ b/youtube_dl/extractor/cloudy.py @@ -19,7 +19,7 @@ from ..utils import ( class CloudyIE(InfoExtractor): _IE_DESC = 'cloudy.ec and videoraj.ch' _VALID_URL = r'''(?x) - https?://(?:www\.)?(?P<host>cloudy\.ec|videoraj\.ch)/ + https?://(?:www\.)?(?P<host>cloudy\.ec|videoraj\.(?:ch|to))/ (?:v/|embed\.php\?id=) (?P<id>[A-Za-z0-9]+) ''' @@ -37,7 +37,7 @@ class CloudyIE(InfoExtractor): } }, { - 'url': 'http://www.videoraj.ch/v/47f399fd8bb60', + 'url': 'http://www.videoraj.to/v/47f399fd8bb60', 'md5': '7d0f8799d91efd4eda26587421c3c3b0', 'info_dict': { 'id': '47f399fd8bb60', diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 8ae3f2890..dd753c7c3 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -11,7 +11,6 @@ from math import pow, sqrt, floor from .common import InfoExtractor from ..compat import ( compat_etree_fromstring, - compat_urllib_parse_unquote, compat_urllib_parse_urlencode, compat_urllib_request, compat_urlparse, @@ -306,28 +305,24 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', webpage, 'video_uploader', fatal=False) - playerdata_url = compat_urllib_parse_unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url')) - playerdata_req = sanitized_Request(playerdata_url) - playerdata_req.data = urlencode_postdata({'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') - - stream_id = self._search_regex(r'<media_id>([^<]+)', playerdata, 'stream_id') - video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, 'thumbnail', fatal=False) - formats = [] - for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage): + video_encode_ids = [] + for fmt in re.findall(r'token="showmedia\.([0-9]{3,4})p"', webpage): stream_quality, stream_format = self._FORMAT_IDS[fmt] video_format = fmt + 'p' 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), + % (video_id, stream_format, stream_quality), compat_urllib_parse_urlencode({'current_page': url}).encode('utf-8')) streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded') streamdata = self._download_xml( streamdata_req, video_id, note='Downloading media info for %s' % video_format) stream_info = streamdata.find('./{default}preload/stream_info') + video_encode_id = xpath_text(stream_info, './video_encode_id') + if video_encode_id in video_encode_ids: + continue + video_encode_ids.append(video_encode_id) video_url = xpath_text(stream_info, './host') video_play_path = xpath_text(stream_info, './file') if not video_url or not video_play_path: @@ -360,15 +355,25 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text }) formats.append(format_info) + metadata = self._download_xml( + 'http://www.crunchyroll.com/xml', video_id, + note='Downloading media info', query={ + 'req': 'RpcApiVideoPlayer_GetMediaMetadata', + 'media_id': video_id, + }) + subtitles = self.extract_subtitles(video_id, webpage) return { 'id': video_id, 'title': video_title, 'description': video_description, - 'thumbnail': video_thumbnail, + 'thumbnail': xpath_text(metadata, 'episode_image_url'), 'uploader': video_uploader, 'upload_date': video_upload_date, + 'series': xpath_text(metadata, 'series_title'), + 'episode': xpath_text(metadata, 'episode_title'), + 'episode_number': int_or_none(xpath_text(metadata, 'episode_number')), 'subtitles': subtitles, 'formats': formats, } diff --git a/youtube_dl/extractor/cwtv.py b/youtube_dl/extractor/cwtv.py index f5cefd966..ebd14cb16 100644 --- a/youtube_dl/extractor/cwtv.py +++ b/youtube_dl/extractor/cwtv.py @@ -9,7 +9,7 @@ from ..utils import ( class CWTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?cw(?:tv|seed)\.com/shows/(?:[^/]+/){2}\?play=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})' + _VALID_URL = r'https?://(?:www\.)?cw(?:tv|seed)\.com/(?:shows/)?(?:[^/]+/){2}\?.*\bplay=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})' _TESTS = [{ 'url': 'http://cwtv.com/shows/arrow/legends-of-yesterday/?play=6b15e985-9345-4f60-baf8-56e96be57c63', 'info_dict': { @@ -48,6 +48,9 @@ class CWTVIE(InfoExtractor): # m3u8 download 'skip_download': True, } + }, { + 'url': 'http://cwtv.com/thecw/chroniclesofcisco/?play=8adebe35-f447-465f-ab52-e863506ff6d6', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 8b215c5ab..3adcd41c4 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -400,7 +400,6 @@ from .macgamestore import MacGameStoreIE from .mailru import MailRuIE from .makerschannel import MakersChannelIE from .makertv import MakerTVIE -from .malemotion import MalemotionIE from .matchtv import MatchTVIE from .mdr import MDRIE from .metacafe import MetacafeIE @@ -439,7 +438,7 @@ from .mtv import ( ) from .muenchentv import MuenchenTVIE from .musicplayon import MusicPlayOnIE -from .mwave import MwaveIE +from .mwave import MwaveIE, MwaveMeetGreetIE from .myspace import MySpaceIE, MySpaceAlbumIE from .myspass import MySpassIE from .myvi import MyviIE @@ -658,7 +657,6 @@ from .screenwavemedia import ScreenwaveMediaIE, TeamFourIE from .senateisvp import SenateISVPIE from .servingsys import ServingSysIE from .sexu import SexuIE -from .sexykarma import SexyKarmaIE from .shahid import ShahidIE from .shared import SharedIE from .sharesix import ShareSixIE @@ -919,6 +917,7 @@ from .vulture import VultureIE from .walla import WallaIE from .washingtonpost import WashingtonPostIE from .wat import WatIE +from .watchindianporn import WatchIndianPornIE from .wdr import ( WDRIE, WDRMobileIE, diff --git a/youtube_dl/extractor/malemotion.py b/youtube_dl/extractor/malemotion.py deleted file mode 100644 index 92511a671..000000000 --- a/youtube_dl/extractor/malemotion.py +++ /dev/null @@ -1,46 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..compat import compat_urllib_parse_unquote - - -class MalemotionIE(InfoExtractor): - _VALID_URL = r'https?://malemotion\.com/video/(.+?)\.(?P<id>.+?)(#|$)' - _TEST = { - 'url': 'http://malemotion.com/video/bete-de-concours.ltc', - 'md5': '3013e53a0afbde2878bc39998c33e8a5', - 'info_dict': { - 'id': 'ltc', - 'ext': 'mp4', - 'title': 'Bête de Concours', - 'age_limit': 18, - }, - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - video_url = compat_urllib_parse_unquote(self._search_regex( - r'<source type="video/mp4" src="(.+?)"', webpage, 'video URL')) - video_title = self._html_search_regex( - r'<title>(.*?)</title', webpage, 'title') - video_thumbnail = self._search_regex( - r'<video .+?poster="(.+?)"', webpage, 'thumbnail', fatal=False) - - formats = [{ - 'url': video_url, - 'ext': 'mp4', - 'format_id': 'mp4', - 'preference': 1, - }] - self._sort_formats(formats) - - return { - 'id': video_id, - 'formats': formats, - 'title': video_title, - 'thumbnail': video_thumbnail, - 'age_limit': 18, - } diff --git a/youtube_dl/extractor/mwave.py b/youtube_dl/extractor/mwave.py index 5c3c8d464..a103e0323 100644 --- a/youtube_dl/extractor/mwave.py +++ b/youtube_dl/extractor/mwave.py @@ -10,6 +10,7 @@ from ..utils import ( class MwaveIE(InfoExtractor): _VALID_URL = r'https?://mwave\.interest\.me/mnettv/videodetail\.m\?searchVideoDetailVO\.clip_id=(?P<id>[0-9]+)' + _URL_TEMPLATE = 'http://mwave.interest.me/mnettv/videodetail.m?searchVideoDetailVO.clip_id=%s' _TEST = { 'url': 'http://mwave.interest.me/mnettv/videodetail.m?searchVideoDetailVO.clip_id=168859', # md5 is unstable @@ -56,3 +57,28 @@ class MwaveIE(InfoExtractor): 'view_count': int_or_none(vod_info.get('hit')), 'formats': formats, } + + +class MwaveMeetGreetIE(InfoExtractor): + _VALID_URL = r'https?://mwave\.interest\.me/meetgreet/view/(?P<id>\d+)' + _TEST = { + 'url': 'http://mwave.interest.me/meetgreet/view/256', + 'info_dict': { + 'id': '173294', + 'ext': 'flv', + 'title': '[MEET&GREET] Park BoRam', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': 'Mwave', + 'duration': 3634, + 'view_count': int, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + clip_id = self._html_search_regex( + r'<iframe[^>]+src="/mnettv/ifr_clip\.m\?searchVideoDetailVO\.clip_id=(\d+)', + webpage, 'clip ID') + clip_url = MwaveIE._URL_TEMPLATE % clip_id + return self.url_result(clip_url, 'Mwave', clip_id) diff --git a/youtube_dl/extractor/nuvid.py b/youtube_dl/extractor/nuvid.py index 9fa7cefad..ab6bfcd7f 100644 --- a/youtube_dl/extractor/nuvid.py +++ b/youtube_dl/extractor/nuvid.py @@ -5,8 +5,6 @@ import re from .common import InfoExtractor from ..utils import ( parse_duration, - sanitized_Request, - unified_strdate, ) @@ -20,7 +18,6 @@ class NuvidIE(InfoExtractor): 'ext': 'mp4', 'title': 'Horny babes show their awesome bodeis and', 'duration': 129, - 'upload_date': '20140508', 'age_limit': 18, } } @@ -28,28 +25,31 @@ class NuvidIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - formats = [] + page_url = 'http://m.nuvid.com/video/%s' % video_id + webpage = self._download_webpage( + page_url, video_id, 'Downloading video page') + # When dwnld_speed exists and has a value larger than the MP4 file's + # bitrate, Nuvid returns the MP4 URL + # It's unit is 100bytes/millisecond, see mobile-nuvid-min.js for the algorithm + self._set_cookie('nuvid.com', 'dwnld_speed', '10.0') + mp4_webpage = self._download_webpage( + page_url, video_id, 'Downloading video page for MP4 format') - for dwnld_speed, format_id in [(0, '3gp'), (5, 'mp4')]: - 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( - request, video_id, 'Downloading %s page' % format_id) - video_url = self._html_search_regex( - r'<a\s+href="([^"]+)"\s+class="b_link">', webpage, '%s video URL' % format_id, fatal=False) - if not video_url: - continue + html5_video_re = r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', + video_url = self._html_search_regex(html5_video_re, webpage, video_id) + mp4_video_url = self._html_search_regex(html5_video_re, mp4_webpage, video_id) + formats = [{ + 'url': video_url, + }] + if mp4_video_url != video_url: formats.append({ - 'url': video_url, - 'format_id': format_id, + 'url': mp4_video_url, }) - webpage = self._download_webpage( - 'http://m.nuvid.com/video/%s' % video_id, video_id, 'Downloading video page') title = self._html_search_regex( [r'<span title="([^"]+)">', - r'<div class="thumb-holder video">\s*<h5[^>]*>([^<]+)</h5>'], webpage, 'title').strip() + r'<div class="thumb-holder video">\s*<h5[^>]*>([^<]+)</h5>', + r'<span[^>]+class="title_thumb">([^<]+)</span>'], webpage, 'title').strip() thumbnails = [ { 'url': thumb_url, @@ -57,9 +57,8 @@ class NuvidIE(InfoExtractor): ] thumbnail = thumbnails[0]['url'] if thumbnails else None duration = parse_duration(self._html_search_regex( - r'<i class="fa fa-clock-o"></i>\s*(\d{2}:\d{2})', webpage, 'duration', fatal=False)) - upload_date = unified_strdate(self._html_search_regex( - r'<i class="fa fa-user"></i>\s*(\d{4}-\d{2}-\d{2})', webpage, 'upload date', fatal=False)) + [r'<i class="fa fa-clock-o"></i>\s*(\d{2}:\d{2})', + r'<span[^>]+class="view_time">([^<]+)</span>'], webpage, 'duration', fatal=False)) return { 'id': video_id, @@ -67,7 +66,6 @@ class NuvidIE(InfoExtractor): 'thumbnails': thumbnails, 'thumbnail': thumbnail, 'duration': duration, - 'upload_date': upload_date, 'age_limit': 18, 'formats': formats, } diff --git a/youtube_dl/extractor/ooyala.py b/youtube_dl/extractor/ooyala.py index 16f040191..95e982897 100644 --- a/youtube_dl/extractor/ooyala.py +++ b/youtube_dl/extractor/ooyala.py @@ -96,6 +96,8 @@ class OoyalaIE(OoyalaBaseIE): 'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.', 'duration': 853.386, }, + # The video in the original webpage now uses PlayWire + 'skip': 'Ooyala said: movie expired', }, { # Only available for ipad 'url': 'http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0', diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index 66c75f8b3..4e3864f0d 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -185,6 +185,7 @@ class ORFFM4IE(InfoExtractor): 'timestamp': 1452456073, 'upload_date': '20160110', }, + 'skip': 'Live streams on FM4 got deleted soon', } def _real_extract(self, url): diff --git a/youtube_dl/extractor/scivee.py b/youtube_dl/extractor/scivee.py index 3bf93c870..b1ca12fde 100644 --- a/youtube_dl/extractor/scivee.py +++ b/youtube_dl/extractor/scivee.py @@ -18,6 +18,7 @@ class SciVeeIE(InfoExtractor): 'title': 'Adam Arkin at the 2014 DOE JGI Genomics of Energy & Environment Meeting', 'description': 'md5:81f1710638e11a481358fab1b11059d7', }, + 'skip': 'Not accessible from Travis CI server', } def _real_extract(self, url): diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index 8272dd969..a25417f94 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -159,11 +159,11 @@ class ThePlatformIE(ThePlatformBaseIE): def str_to_hex(str): return binascii.b2a_hex(str.encode('ascii')).decode('ascii') - def hex_to_str(hex): - return binascii.a2b_hex(hex) + def hex_to_bytes(hex): + return binascii.a2b_hex(hex.encode('ascii')) relative_path = re.match(r'https?://link.theplatform.com/s/([^?]+)', url).group(1) - clear_text = hex_to_str(flags + expiration_date + str_to_hex(relative_path)) + clear_text = hex_to_bytes(flags + expiration_date + str_to_hex(relative_path)) checksum = hmac.new(sig_key.encode('ascii'), clear_text, hashlib.sha1).hexdigest() sig = flags + expiration_date + checksum + str_to_hex(sig_secret) return '%s&sig=%s' % (url, sig) diff --git a/youtube_dl/extractor/twentymin.py b/youtube_dl/extractor/twentymin.py index ca7d953b8..b721ecb0a 100644 --- a/youtube_dl/extractor/twentymin.py +++ b/youtube_dl/extractor/twentymin.py @@ -32,7 +32,22 @@ class TwentyMinutenIE(InfoExtractor): 'title': '«Wir müssen mutig nach vorne schauen»', 'description': 'Kein Land sei innovativer als die Schweiz, sagte Johann Schneider-Ammann in seiner Neujahrsansprache. Das Land müsse aber seine Hausaufgaben machen.', 'thumbnail': 'http://www.20min.ch/images/content/2/2/0/22050469/10/teaserbreit.jpg' - } + }, + 'skip': '"This video is no longer available" is shown both on the web page and in the downloaded file.', + }, { + # YouTube embed + 'url': 'http://www.20min.ch/ro/sports/football/story/Il-marque-une-bicyclette-de-plus-de-30-metres--21115184', + 'md5': 'cec64d59aa01c0ed9dbba9cf639dd82f', + 'info_dict': { + 'id': 'ivM7A7SpDOs', + 'ext': 'mp4', + 'title': 'GOLAZO DE CHILENA DE JAVI GÓMEZ, FINALISTA AL BALÓN DE CLM 2016', + 'description': 'md5:903c92fbf2b2f66c09de514bc25e9f5a', + 'upload_date': '20160424', + 'uploader': 'RTVCM Castilla-La Mancha', + 'uploader_id': 'RTVCM', + }, + 'add_ie': ['Youtube'], }, { 'url': 'http://www.20min.ch/videotv/?cid=44&vid=468738', 'only_matching': True, @@ -48,6 +63,12 @@ class TwentyMinutenIE(InfoExtractor): webpage = self._download_webpage(url, display_id) + youtube_url = self._html_search_regex( + r'<iframe[^>]+src="((?:https?:)?//www\.youtube\.com/embed/[^"]+)"', + webpage, 'YouTube embed URL', default=None) + if youtube_url is not None: + return self.url_result(youtube_url, 'Youtube') + title = self._html_search_regex( r'<h1>.*?<span>(.+?)</span></h1>', webpage, 'title', default=None) diff --git a/youtube_dl/extractor/viewster.py b/youtube_dl/extractor/viewster.py index 6edc2c44e..a93196a07 100644 --- a/youtube_dl/extractor/viewster.py +++ b/youtube_dl/extractor/viewster.py @@ -6,7 +6,6 @@ import re from .common import InfoExtractor from ..compat import ( compat_HTTPError, - compat_urllib_parse, compat_urllib_parse_unquote, ) from ..utils import ( @@ -78,11 +77,11 @@ 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): + def _download_json(self, url, video_id, note='Downloading JSON metadata', fatal=True, query={}): 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) + return super(ViewsterIE, self)._download_json(request, video_id, note, fatal=fatal, query=query) def _real_extract(self, url): video_id = self._match_id(url) @@ -117,72 +116,85 @@ class ViewsterIE(InfoExtractor): return self.playlist_result(entries, video_id, title, description) formats = [] - manifest_url = None - m3u8_formats = [] - for media_type in ('application/f4m+xml', 'application/x-mpegURL', 'video/mp4'): - media = self._download_json( - 'https://public-api.viewster.com/movies/%s/video?mediaType=%s' - % (entry_id, compat_urllib_parse.quote(media_type)), - video_id, 'Downloading %s JSON' % media_type, fatal=False) - if not media: - continue - video_url = media.get('Uri') - if not video_url: - continue - ext = determine_ext(video_url) - if ext == 'f4m': - manifest_url = video_url - video_url += '&' if '?' in video_url else '?' - video_url += 'hdcore=3.2.0&plugin=flowplayer-3.2.0.1' - formats.extend(self._extract_f4m_formats( - video_url, video_id, f4m_id='hds')) - elif ext == 'm3u8': - manifest_url = video_url - m3u8_formats = self._extract_m3u8_formats( - video_url, video_id, 'mp4', m3u8_id='hls', - fatal=False) # m3u8 sometimes fail - if m3u8_formats: - formats.extend(m3u8_formats) - else: - qualities_basename = self._search_regex( - '/([^/]+)\.csmil/', - manifest_url, 'qualities basename', default=None) - if not qualities_basename: + for language_set in info.get('LanguageSets', []): + manifest_url = None + m3u8_formats = [] + audio = language_set.get('Audio') or '' + subtitle = language_set.get('Subtitle') or '' + base_format_id = audio + if subtitle: + base_format_id += '-%s' % subtitle + + def concat(suffix, sep='-'): + return (base_format_id + '%s%s' % (sep, suffix)) if base_format_id else suffix + + for media_type in ('application/f4m+xml', 'application/x-mpegURL', 'video/mp4'): + media = self._download_json( + 'https://public-api.viewster.com/movies/%s/video' % entry_id, + video_id, 'Downloading %s JSON' % concat(media_type, ' '), fatal=False, query={ + 'mediaType': media_type, + 'language': audio, + 'subtitle': subtitle, + }) + if not media: continue - QUALITIES_RE = r'((,\d+k)+,?)' - qualities = self._search_regex( - QUALITIES_RE, qualities_basename, - 'qualities', default=None) - if not qualities: + video_url = media.get('Uri') + if not video_url: continue - qualities = list(map(lambda q: int(q[:-1]), qualities.strip(',').split(','))) - qualities.sort() - http_template = re.sub(QUALITIES_RE, r'%dk', qualities_basename) - http_url_basename = url_basename(video_url) - if m3u8_formats: - self._sort_formats(m3u8_formats) - m3u8_formats = list(filter( - lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple', - m3u8_formats)) - if len(qualities) == len(m3u8_formats): - for q, m3u8_format in zip(qualities, m3u8_formats): - f = m3u8_format.copy() - f.update({ - 'url': video_url.replace(http_url_basename, http_template % q), - 'format_id': f['format_id'].replace('hls', 'http'), - 'protocol': 'http', - }) - formats.append(f) + ext = determine_ext(video_url) + if ext == 'f4m': + manifest_url = video_url + video_url += '&' if '?' in video_url else '?' + video_url += 'hdcore=3.2.0&plugin=flowplayer-3.2.0.1' + formats.extend(self._extract_f4m_formats( + video_url, video_id, f4m_id=concat('hds'))) + elif ext == 'm3u8': + manifest_url = video_url + m3u8_formats = self._extract_m3u8_formats( + video_url, video_id, 'mp4', m3u8_id=concat('hls'), + fatal=False) # m3u8 sometimes fail + if m3u8_formats: + formats.extend(m3u8_formats) else: - for q in qualities: - formats.append({ - 'url': video_url.replace(http_url_basename, http_template % q), - 'ext': 'mp4', - 'format_id': 'http-%d' % q, - 'tbr': q, - }) - - if not formats and not info.get('LanguageSets') and not info.get('VODSettings'): + qualities_basename = self._search_regex( + '/([^/]+)\.csmil/', + manifest_url, 'qualities basename', default=None) + if not qualities_basename: + continue + QUALITIES_RE = r'((,\d+k)+,?)' + qualities = self._search_regex( + QUALITIES_RE, qualities_basename, + 'qualities', default=None) + if not qualities: + continue + qualities = list(map(lambda q: int(q[:-1]), qualities.strip(',').split(','))) + qualities.sort() + http_template = re.sub(QUALITIES_RE, r'%dk', qualities_basename) + http_url_basename = url_basename(video_url) + if m3u8_formats: + self._sort_formats(m3u8_formats) + m3u8_formats = list(filter( + lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple', + m3u8_formats)) + if len(qualities) == len(m3u8_formats): + for q, m3u8_format in zip(qualities, m3u8_formats): + f = m3u8_format.copy() + f.update({ + 'url': video_url.replace(http_url_basename, http_template % q), + 'format_id': f['format_id'].replace('hls', 'http'), + 'protocol': 'http', + }) + formats.append(f) + else: + for q in qualities: + formats.append({ + 'url': video_url.replace(http_url_basename, http_template % q), + 'ext': 'mp4', + 'format_id': 'http-%d' % q, + 'tbr': q, + }) + + if not formats and not info.get('VODSettings'): self.raise_geo_restricted() self._sort_formats(formats) diff --git a/youtube_dl/extractor/sexykarma.py b/youtube_dl/extractor/watchindianporn.py index e33483674..5d3b5bdb4 100644 --- a/youtube_dl/extractor/sexykarma.py +++ b/youtube_dl/extractor/watchindianporn.py @@ -11,61 +11,27 @@ from ..utils import ( ) -class SexyKarmaIE(InfoExtractor): - IE_DESC = 'Sexy Karma and Watch Indian Porn' - _VALID_URL = r'https?://(?:www\.)?(?:sexykarma\.com|watchindianporn\.net)/(?:[^/]+/)*video/(?P<display_id>[^/]+)-(?P<id>[a-zA-Z0-9]+)\.html' - _TESTS = [{ - 'url': 'http://www.sexykarma.com/gonewild/video/taking-a-quick-pee-yHI70cOyIHt.html', - 'md5': 'b9798e7d1ef1765116a8f516c8091dbd', +class WatchIndianPornIE(InfoExtractor): + IE_DESC = 'Watch Indian Porn' + _VALID_URL = r'https?://(?:www\.)?watchindianporn\.net/(?:[^/]+/)*video/(?P<display_id>[^/]+)-(?P<id>[a-zA-Z0-9]+)\.html' + _TEST = { + 'url': 'http://www.watchindianporn.net/video/hot-milf-from-kerala-shows-off-her-gorgeous-large-breasts-on-camera-RZa2avywNPa.html', + 'md5': '249589a164dde236ec65832bfce17440', 'info_dict': { - 'id': 'yHI70cOyIHt', - 'display_id': 'taking-a-quick-pee', + 'id': 'RZa2avywNPa', + 'display_id': 'hot-milf-from-kerala-shows-off-her-gorgeous-large-breasts-on-camera', 'ext': 'mp4', - 'title': 'Taking a quick pee.', + 'title': 'Hot milf from kerala shows off her gorgeous large breasts on camera', 'thumbnail': 're:^https?://.*\.jpg$', - 'uploader': 'wildginger7', - 'upload_date': '20141008', - 'duration': 22, + 'uploader': 'LoveJay', + 'upload_date': '20160428', + 'duration': 226, 'view_count': int, 'comment_count': int, 'categories': list, 'age_limit': 18, } - }, { - 'url': 'http://www.sexykarma.com/gonewild/video/pot-pixie-tribute-8Id6EZPbuHf.html', - 'md5': 'dd216c68d29b49b12842b9babe762a5d', - 'info_dict': { - 'id': '8Id6EZPbuHf', - 'display_id': 'pot-pixie-tribute', - 'ext': 'mp4', - 'title': 'pot_pixie tribute', - 'thumbnail': 're:^https?://.*\.jpg$', - 'uploader': 'banffite', - 'upload_date': '20141013', - 'duration': 16, - 'view_count': int, - 'comment_count': int, - 'categories': list, - 'age_limit': 18, - } - }, { - 'url': 'http://www.watchindianporn.net/video/desi-dancer-namrata-stripping-completely-nude-and-dancing-on-a-hot-number-dW2mtctxJfs.html', - 'md5': '9afb80675550406ed9a63ac2819ef69d', - 'info_dict': { - 'id': 'dW2mtctxJfs', - 'display_id': 'desi-dancer-namrata-stripping-completely-nude-and-dancing-on-a-hot-number', - 'ext': 'mp4', - 'title': 'Desi dancer namrata stripping completely nude and dancing on a hot number', - 'thumbnail': 're:^https?://.*\.jpg$', - 'uploader': 'Don', - 'upload_date': '20140213', - 'duration': 83, - 'view_count': int, - 'comment_count': int, - 'categories': list, - 'age_limit': 18, - } - }] + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -109,6 +75,9 @@ class SexyKarmaIE(InfoExtractor): 'id': video_id, 'display_id': display_id, 'url': video_url, + 'http_headers': { + 'Referer': url, + }, 'title': title, 'thumbnail': thumbnail, 'uploader': uploader, diff --git a/youtube_dl/extractor/yandexmusic.py b/youtube_dl/extractor/yandexmusic.py index 7a90cc60c..ce3723b55 100644 --- a/youtube_dl/extractor/yandexmusic.py +++ b/youtube_dl/extractor/yandexmusic.py @@ -18,9 +18,23 @@ from ..utils import ( class YandexMusicBaseIE(InfoExtractor): @staticmethod def _handle_error(response): - error = response.get('error') - if error: - raise ExtractorError(error, expected=True) + if isinstance(response, dict): + error = response.get('error') + if error: + raise ExtractorError(error, expected=True) + + def _download_webpage(self, *args, **kwargs): + webpage = super(YandexMusicBaseIE, self)._download_webpage(*args, **kwargs) + if 'Нам очень жаль, но запросы, поступившие с вашего IP-адреса, похожи на автоматические.' in webpage: + raise ExtractorError( + 'YandexMusic has considered youtube-dl requests automated and ' + 'asks you to solve a CAPTCHA. You can either wait for some ' + 'time until unblocked and optionally use --sleep-interval ' + 'in future or alternatively you can go to https://music.yandex.ru/ ' + 'solve CAPTCHA, then export cookies and pass cookie file to ' + 'youtube-dl with --cookies', + expected=True) + return webpage def _download_json(self, *args, **kwargs): response = super(YandexMusicBaseIE, self)._download_json(*args, **kwargs) @@ -47,7 +61,8 @@ class YandexMusicTrackIE(YandexMusicBaseIE): 'album_artist': 'Carlo Ambrosio', 'artist': 'Carlo Ambrosio & Fabio Di Bari, Carlo Ambrosio', 'release_year': '2009', - } + }, + 'skip': 'Travis CI servers blocked by YandexMusic', } def _get_track_url(self, storage_dir, track_id): @@ -139,6 +154,7 @@ class YandexMusicAlbumIE(YandexMusicPlaylistBaseIE): 'title': 'Carlo Ambrosio - Gypsy Soul (2009)', }, 'playlist_count': 50, + 'skip': 'Travis CI servers blocked by YandexMusic', } def _real_extract(self, url): @@ -171,6 +187,7 @@ class YandexMusicPlaylistIE(YandexMusicPlaylistBaseIE): 'description': 'md5:3b9f27b0efbe53f2ee1e844d07155cc9', }, 'playlist_count': 6, + 'skip': 'Travis CI servers blocked by YandexMusic', }, { # playlist exceeding the limit of 150 tracks shipped with webpage (see # https://github.com/rg3/youtube-dl/issues/6666) @@ -180,6 +197,7 @@ class YandexMusicPlaylistIE(YandexMusicPlaylistBaseIE): 'title': 'Музыка 90-х', }, 'playlist_count': 310, + 'skip': 'Travis CI servers blocked by YandexMusic', }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 44f98d294..b7c3cb63f 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -2139,10 +2139,11 @@ class YoutubeSearchDateIE(YoutubeSearchIE): _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'} -class YoutubeSearchURLIE(InfoExtractor): +class YoutubeSearchURLIE(YoutubePlaylistBaseInfoExtractor): IE_DESC = 'YouTube.com search URLs' IE_NAME = 'youtube:search_url' _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)' + _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?' _TESTS = [{ 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', 'playlist_mincount': 5, @@ -2157,32 +2158,8 @@ class YoutubeSearchURLIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) query = compat_urllib_parse_unquote_plus(mobj.group('query')) - webpage = self._download_webpage(url, query) - result_code = self._search_regex( - r'(?s)<ol[^>]+class="item-section"(.*?)</ol>', webpage, 'result HTML') - - part_codes = re.findall( - r'(?s)<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*>(.*?)</h3>', result_code) - entries = [] - for part_code in part_codes: - part_title = self._html_search_regex( - [r'(?s)title="([^"]+)"', r'>([^<]+)</a>'], part_code, 'item title', fatal=False) - part_url_snippet = self._html_search_regex( - r'(?s)href="([^"]+)"', part_code, 'item URL') - part_url = compat_urlparse.urljoin( - 'https://www.youtube.com/', part_url_snippet) - entries.append({ - '_type': 'url', - 'url': part_url, - 'title': part_title, - }) - - return { - '_type': 'playlist', - 'entries': entries, - 'title': query, - } + return self.playlist_result(self._process_page(webpage), playlist_title=query) class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor): |