diff options
Diffstat (limited to 'youtube_dl/extractor')
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 10 | ||||
| -rw-r--r-- | youtube_dl/extractor/adultswim.py | 44 | ||||
| -rw-r--r-- | youtube_dl/extractor/breakcom.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/common.py | 13 | ||||
| -rw-r--r-- | youtube_dl/extractor/dailymotion.py | 10 | ||||
| -rw-r--r-- | youtube_dl/extractor/eagleplatform.py | 98 | ||||
| -rw-r--r-- | youtube_dl/extractor/funnyordie.py | 9 | ||||
| -rw-r--r-- | youtube_dl/extractor/gazeta.py | 38 | ||||
| -rw-r--r-- | youtube_dl/extractor/generic.py | 57 | ||||
| -rw-r--r-- | youtube_dl/extractor/niconico.py | 5 | ||||
| -rw-r--r-- | youtube_dl/extractor/npo.py | 4 | ||||
| -rw-r--r-- | youtube_dl/extractor/orf.py | 94 | ||||
| -rw-r--r-- | youtube_dl/extractor/pladform.py | 90 | ||||
| -rw-r--r-- | youtube_dl/extractor/ssa.py | 58 | ||||
| -rw-r--r-- | youtube_dl/extractor/teamcoco.py | 6 | ||||
| -rw-r--r-- | youtube_dl/extractor/twitch.py | 7 | ||||
| -rw-r--r-- | youtube_dl/extractor/vidme.py | 6 | ||||
| -rw-r--r-- | youtube_dl/extractor/vimeo.py | 38 | ||||
| -rw-r--r-- | youtube_dl/extractor/yandexmusic.py | 127 | ||||
| -rw-r--r-- | youtube_dl/extractor/youtube.py | 2 |
20 files changed, 654 insertions, 64 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 5ca534cdf..7adcc4dbf 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -116,6 +116,7 @@ from .defense import DefenseGouvFrIE from .discovery import DiscoveryIE from .divxstage import DivxStageIE from .dropbox import DropboxIE +from .eagleplatform import EaglePlatformIE from .ebaumsworld import EbaumsWorldIE from .echomsk import EchoMskIE from .ehow import EHowIE @@ -174,6 +175,7 @@ from .gameone import ( from .gamespot import GameSpotIE from .gamestar import GameStarIE from .gametrailers import GametrailersIE +from .gazeta import GazetaIE from .gdcvault import GDCVaultIE from .generic import GenericIE from .giantbomb import GiantBombIE @@ -354,6 +356,7 @@ from .orf import ( ORFTVthekIE, ORFOE1IE, ORFFM4IE, + ORFIPTVIE, ) from .parliamentliveuk import ParliamentLiveUKIE from .patreon import PatreonIE @@ -361,6 +364,7 @@ from .pbs import PBSIE from .phoenix import PhoenixIE from .photobucket import PhotobucketIE from .planetaplay import PlanetaPlayIE +from .pladform import PladformIE from .played import PlayedIE from .playfm import PlayFMIE from .playvid import PlayvidIE @@ -456,6 +460,7 @@ from .sport5 import Sport5IE from .sportbox import SportBoxIE from .sportdeutschland import SportDeutschlandIE from .srmediathek import SRMediathekIE +from .ssa import SSAIE from .stanfordoc import StanfordOpenClassroomIE from .steam import SteamIE from .streamcloud import StreamcloudIE @@ -607,6 +612,11 @@ from .yahoo import ( YahooSearchIE, ) from .yam import YamIE +from .yandexmusic import ( + YandexMusicTrackIE, + YandexMusicAlbumIE, + YandexMusicPlaylistIE, +) from .yesjapan import YesJapanIE from .ynet import YnetIE from .youjizz import YouJizzIE diff --git a/youtube_dl/extractor/adultswim.py b/youtube_dl/extractor/adultswim.py index 34b8b0115..39335b827 100644 --- a/youtube_dl/extractor/adultswim.py +++ b/youtube_dl/extractor/adultswim.py @@ -2,13 +2,12 @@ from __future__ import unicode_literals import re -import json from .common import InfoExtractor from ..utils import ( ExtractorError, - xpath_text, float_or_none, + xpath_text, ) @@ -60,6 +59,24 @@ class AdultSwimIE(InfoExtractor): 'title': 'American Dad - Putting Francine Out of Business', 'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].' }, + }, { + 'url': 'http://www.adultswim.com/videos/tim-and-eric-awesome-show-great-job/dr-steve-brule-for-your-wine/', + 'playlist': [ + { + 'md5': '3e346a2ab0087d687a05e1e7f3b3e529', + 'info_dict': { + 'id': 'sY3cMUR_TbuE4YmdjzbIcQ-0', + 'ext': 'flv', + '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', + }, + } + ], + 'info_dict': { + 'id': 'sY3cMUR_TbuE4YmdjzbIcQ', + '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', + }, }] @staticmethod @@ -80,6 +97,7 @@ class AdultSwimIE(InfoExtractor): for video in collection.get('videos'): if video.get('slug') == slug: return collection, video + return None, None def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -90,28 +108,30 @@ class AdultSwimIE(InfoExtractor): webpage = self._download_webpage(url, episode_path) # Extract the value of `bootstrappedData` from the Javascript in the page. - bootstrappedDataJS = self._search_regex(r'var bootstrappedData = ({.*});', webpage, episode_path) - - try: - bootstrappedData = json.loads(bootstrappedDataJS) - except ValueError as ve: - errmsg = '%s: Failed to parse JSON ' % episode_path - raise ExtractorError(errmsg, cause=ve) + bootstrapped_data = self._parse_json(self._search_regex( + r'var bootstrappedData = ({.*});', webpage, 'bootstraped data'), episode_path) # Downloading videos from a /videos/playlist/ URL needs to be handled differently. # NOTE: We are only downloading one video (the current one) not the playlist if is_playlist: - collections = bootstrappedData['playlists']['collections'] + collections = bootstrapped_data['playlists']['collections'] collection = self.find_collection_by_linkURL(collections, show_path) video_info = self.find_video_info(collection, episode_path) show_title = video_info['showTitle'] segment_ids = [video_info['videoPlaybackID']] else: - collections = bootstrappedData['show']['collections'] + collections = bootstrapped_data['show']['collections'] collection, video_info = self.find_collection_containing_video(collections, episode_path) - show = bootstrappedData['show'] + # Video wasn't found in the collections, let's try `slugged_video`. + if video_info is None: + if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path: + video_info = bootstrapped_data['slugged_video'] + else: + raise ExtractorError('Unable to find video info') + + show = bootstrapped_data['show'] show_title = show['title'] segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']] diff --git a/youtube_dl/extractor/breakcom.py b/youtube_dl/extractor/breakcom.py index 4bcc897c9..809287d14 100644 --- a/youtube_dl/extractor/breakcom.py +++ b/youtube_dl/extractor/breakcom.py @@ -41,7 +41,7 @@ class BreakIE(InfoExtractor): 'tbr': media['bitRate'], 'width': media['width'], 'height': media['height'], - } for media in info['media']] + } for media in info['media'] if media.get('mediaPurpose') == 'play'] if not formats: formats.append({ diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 8ff76342f..f9e8e2bad 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -839,7 +839,7 @@ class InfoExtractor(object): m3u8_id=None): formats = [{ - 'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-meta'])), + 'format_id': '-'.join(filter(None, [m3u8_id, 'meta'])), 'url': m3u8_url, 'ext': ext, 'protocol': 'm3u8', @@ -883,12 +883,13 @@ class InfoExtractor(object): formats.append({'url': format_url(line)}) continue tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000) - format_id = last_media.get('NAME') - if not format_id: - format_id = '-'.join(filter(None, [ - m3u8_id, 'm3u8-%d' % (tbr if tbr else len(formats))])) + format_id = [] + if m3u8_id: + format_id.append(m3u8_id) + last_media_name = last_media.get('NAME') if last_media else None + format_id.append(last_media_name if last_media_name else '%d' % (tbr if tbr else len(formats))) f = { - 'format_id': format_id, + 'format_id': '-'.join(format_id), 'url': format_url(line.strip()), 'tbr': tbr, 'ext': ext, diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 42b20a46d..4f67c3aac 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -46,13 +46,13 @@ class DailymotionIE(DailymotionBaseInfoExtractor): _TESTS = [ { - 'url': 'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech', - 'md5': '392c4b85a60a90dc4792da41ce3144eb', + 'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames', + 'md5': '2137c41a8e78554bb09225b8eb322406', 'info_dict': { - 'id': 'x33vw9', + 'id': 'x2iuewm', 'ext': 'mp4', - 'uploader': 'Amphora Alex and Van .', - 'title': 'Tutoriel de Youtubeur"DL DES VIDEO DE YOUTUBE"', + 'uploader': 'IGN', + 'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News', } }, # Vevo video diff --git a/youtube_dl/extractor/eagleplatform.py b/youtube_dl/extractor/eagleplatform.py new file mode 100644 index 000000000..7173371ee --- /dev/null +++ b/youtube_dl/extractor/eagleplatform.py @@ -0,0 +1,98 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + int_or_none, +) + + +class EaglePlatformIE(InfoExtractor): + _VALID_URL = r'''(?x) + (?: + eagleplatform:(?P<custom_host>[^/]+):| + https?://(?P<host>.+?\.media\.eagleplatform\.com)/index/player\?.*\brecord_id= + ) + (?P<id>\d+) + ''' + _TESTS = [{ + # http://lenta.ru/news/2015/03/06/navalny/ + 'url': 'http://lentaru.media.eagleplatform.com/index/player?player=new&record_id=227304&player_template_id=5201', + 'md5': '0b7994faa2bd5c0f69a3db6db28d078d', + 'info_dict': { + 'id': '227304', + 'ext': 'mp4', + 'title': 'Навальный вышел на свободу', + 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 87, + 'view_count': int, + 'age_limit': 0, + }, + }, { + # http://muz-tv.ru/play/7129/ + # http://media.clipyou.ru/index/player?record_id=12820&width=730&height=415&autoplay=true + 'url': 'eagleplatform:media.clipyou.ru:12820', + 'md5': '6c2ebeab03b739597ce8d86339d5a905', + 'info_dict': { + 'id': '12820', + 'ext': 'mp4', + 'title': "'O Sole Mio", + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 216, + 'view_count': int, + }, + }] + + def _handle_error(self, response): + status = int_or_none(response.get('status', 200)) + if status != 200: + raise ExtractorError(' '.join(response['errors']), expected=True) + + def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata'): + response = super(EaglePlatformIE, self)._download_json(url_or_request, video_id, note) + self._handle_error(response) + return response + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + host, video_id = mobj.group('custom_host') or mobj.group('host'), mobj.group('id') + + player_data = self._download_json( + 'http://%s/api/player_data?id=%s' % (host, video_id), video_id) + + media = player_data['data']['playlist']['viewports'][0]['medialist'][0] + + title = media['title'] + description = media.get('description') + thumbnail = media.get('snapshot') + duration = int_or_none(media.get('duration')) + view_count = int_or_none(media.get('views')) + + age_restriction = media.get('age_restriction') + age_limit = None + if age_restriction: + age_limit = 0 if age_restriction == 'allow_all' else 18 + + m3u8_data = self._download_json( + media['sources']['secure_m3u8']['auto'], + video_id, 'Downloading m3u8 JSON') + + formats = self._extract_m3u8_formats( + m3u8_data['data'][0], video_id, + 'mp4', entry_protocol='m3u8_native') + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'view_count': view_count, + 'age_limit': age_limit, + 'formats': formats, + } diff --git a/youtube_dl/extractor/funnyordie.py b/youtube_dl/extractor/funnyordie.py index a49fc1151..dd87257c4 100644 --- a/youtube_dl/extractor/funnyordie.py +++ b/youtube_dl/extractor/funnyordie.py @@ -50,7 +50,6 @@ class FunnyOrDieIE(InfoExtractor): bitrates.sort() formats = [] - for bitrate in bitrates: for link in links: formats.append({ @@ -59,6 +58,13 @@ class FunnyOrDieIE(InfoExtractor): 'vbr': bitrate, }) + subtitles = {} + for src, src_lang in re.findall(r'<track kind="captions" src="([^"]+)" srclang="([^"]+)"', webpage): + subtitles[src_lang] = [{ + 'ext': src.split('/')[-1], + 'url': 'http://www.funnyordie.com%s' % src, + }] + post_json = self._search_regex( r'fb_post\s*=\s*(\{.*?\});', webpage, 'post details') post = json.loads(post_json) @@ -69,4 +75,5 @@ class FunnyOrDieIE(InfoExtractor): 'description': post.get('description'), 'thumbnail': post.get('picture'), 'formats': formats, + 'subtitles': subtitles, } diff --git a/youtube_dl/extractor/gazeta.py b/youtube_dl/extractor/gazeta.py new file mode 100644 index 000000000..ea32b621c --- /dev/null +++ b/youtube_dl/extractor/gazeta.py @@ -0,0 +1,38 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class GazetaIE(InfoExtractor): + _VALID_URL = r'(?P<url>https?://(?:www\.)?gazeta\.ru/(?:[^/]+/)?video/(?:(?:main|\d{4}/\d{2}/\d{2})/)?(?P<id>[A-Za-z0-9-_.]+)\.s?html)' + _TESTS = [{ + 'url': 'http://www.gazeta.ru/video/main/zadaite_vopros_vladislavu_yurevichu.shtml', + 'md5': 'd49c9bdc6e5a7888f27475dc215ee789', + 'info_dict': { + 'id': '205566', + 'ext': 'mp4', + 'title': '«70–80 процентов гражданских в Донецке на грани голода»', + 'description': 'md5:38617526050bd17b234728e7f9620a71', + 'thumbnail': 're:^https?://.*\.jpg', + }, + }, { + 'url': 'http://www.gazeta.ru/lifestyle/video/2015/03/08/master-klass_krasivoi_byt._delaem_vesennii_makiyazh.shtml', + 'only_matching': True, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + + display_id = mobj.group('id') + embed_url = '%s?p=embed' % mobj.group('url') + embed_page = self._download_webpage( + embed_url, display_id, 'Downloading embed page') + + video_id = self._search_regex( + r'<div[^>]*?class="eagleplayer"[^>]*?data-id="([^"]+)"', embed_page, 'video id') + + return self.url_result( + 'eagleplatform:gazeta.media.eagleplatform.com:%s' % video_id, 'EaglePlatform') diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 5dc53685c..4e6927b08 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -570,6 +570,45 @@ class GenericIE(InfoExtractor): 'title': 'John Carlson Postgame 2/25/15', }, }, + # Eagle.Platform embed (generic URL) + { + 'url': 'http://lenta.ru/news/2015/03/06/navalny/', + 'info_dict': { + 'id': '227304', + 'ext': 'mp4', + 'title': 'Навальный вышел на свободу', + 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 87, + 'view_count': int, + 'age_limit': 0, + }, + }, + # ClipYou (Eagle.Platform) embed (custom URL) + { + 'url': 'http://muz-tv.ru/play/7129/', + 'info_dict': { + 'id': '12820', + 'ext': 'mp4', + 'title': "'O Sole Mio", + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 216, + 'view_count': int, + }, + }, + # Pladform embed + { + 'url': 'http://muz-tv.ru/kinozal/view/7400/', + 'info_dict': { + 'id': '100183293', + 'ext': 'mp4', + 'title': 'Тайны перевала Дятлова • Тайна перевала Дятлова 1 серия 2 часть', + 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 694, + 'age_limit': 0, + }, + }, # RSS feed with enclosure { 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml', @@ -1155,6 +1194,24 @@ class GenericIE(InfoExtractor): if mobj is not None: return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura') + # Look for Eagle.Platform embeds + mobj = re.search( + r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'EaglePlatform') + + # Look for ClipYou (uses Eagle.Platform) embeds + mobj = re.search( + r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage) + if mobj is not None: + 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') + def check_video(vurl): if YoutubeIE.suitable(vurl): return True diff --git a/youtube_dl/extractor/niconico.py b/youtube_dl/extractor/niconico.py index 4c1890416..7fb4e57df 100644 --- a/youtube_dl/extractor/niconico.py +++ b/youtube_dl/extractor/niconico.py @@ -41,7 +41,7 @@ class NiconicoIE(InfoExtractor): }, } - _VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/((?:[a-z]{2})?[0-9]+)' + _VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/(?P<id>(?:[a-z]{2})?[0-9]+)' _NETRC_MACHINE = 'niconico' # Determine whether the downloader used authentication to download video _AUTHENTICATED = False @@ -76,8 +76,7 @@ class NiconicoIE(InfoExtractor): return True def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) + video_id = self._match_id(url) # Get video webpage. We are not actually interested in it, but need # the cookies in order to be able to download the info webpage diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py index 9c01eb0af..557dffa46 100644 --- a/youtube_dl/extractor/npo.py +++ b/youtube_dl/extractor/npo.py @@ -219,7 +219,8 @@ class NPOLiveIE(NPOBaseIE): if streams: for stream in streams: stream_type = stream.get('type').lower() - if stream_type == 'ss': + # smooth streaming is not supported + if stream_type in ['ss', 'ms']: continue stream_info = self._download_json( 'http://ida.omroep.nl/aapi/?stream=%s&token=%s&type=jsonp' @@ -242,6 +243,7 @@ class NPOLiveIE(NPOBaseIE): else: formats.append({ 'url': stream_url, + 'preference': -10, }) self._sort_formats(formats) diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index 4e293392b..ca1a5bb3c 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -11,6 +11,11 @@ from ..utils import ( HEADRequest, unified_strdate, ExtractorError, + strip_jsonp, + int_or_none, + float_or_none, + determine_ext, + remove_end, ) @@ -197,3 +202,92 @@ class ORFFM4IE(InfoExtractor): 'description': data['subtitle'], 'entries': entries } + + +class ORFIPTVIE(InfoExtractor): + IE_NAME = 'orf:iptv' + IE_DESC = 'iptv.ORF.at' + _VALID_URL = r'http://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)' + + _TEST = { + 'url': 'http://iptv.orf.at/stories/2267952', + 'md5': '26ffa4bab6dbce1eee78bbc7021016cd', + 'info_dict': { + 'id': '339775', + 'ext': 'flv', + 'title': 'Kreml-Kritiker Nawalny wieder frei', + 'description': 'md5:6f24e7f546d364dacd0e616a9e409236', + 'duration': 84.729, + 'thumbnail': 're:^https?://.*\.jpg$', + 'upload_date': '20150306', + }, + } + + def _real_extract(self, url): + story_id = self._match_id(url) + + webpage = self._download_webpage( + 'http://iptv.orf.at/stories/%s' % story_id, story_id) + + video_id = self._search_regex( + r'data-video(?:id)?="(\d+)"', webpage, 'video id') + + data = self._download_json( + 'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id, + video_id)[0] + + duration = float_or_none(data['duration'], 1000) + + video = data['sources']['default'] + load_balancer_url = video['loadBalancerUrl'] + abr = int_or_none(video.get('audioBitrate')) + vbr = int_or_none(video.get('bitrate')) + fps = int_or_none(video.get('videoFps')) + width = int_or_none(video.get('videoWidth')) + height = int_or_none(video.get('videoHeight')) + thumbnail = video.get('preview') + + rendition = self._download_json( + load_balancer_url, video_id, transform_source=strip_jsonp) + + f = { + 'abr': abr, + 'vbr': vbr, + 'fps': fps, + 'width': width, + 'height': height, + } + + formats = [] + for format_id, format_url in rendition['redirect'].items(): + if format_id == 'rtmp': + ff = f.copy() + ff.update({ + 'url': format_url, + 'format_id': format_id, + }) + formats.append(ff) + elif determine_ext(format_url) == 'f4m': + formats.extend(self._extract_f4m_formats( + format_url, video_id, f4m_id=format_id)) + elif determine_ext(format_url) == 'm3u8': + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', m3u8_id=format_id)) + else: + continue + self._sort_formats(formats) + + title = remove_end(self._og_search_title(webpage), ' - iptv.ORF.at') + description = self._og_search_description(webpage) + upload_date = unified_strdate(self._html_search_meta( + 'dc.date', webpage, 'upload date')) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'duration': duration, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'formats': formats, + } diff --git a/youtube_dl/extractor/pladform.py b/youtube_dl/extractor/pladform.py new file mode 100644 index 000000000..abde34b94 --- /dev/null +++ b/youtube_dl/extractor/pladform.py @@ -0,0 +1,90 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + int_or_none, + xpath_text, + qualities, +) + + +class PladformIE(InfoExtractor): + _VALID_URL = r'''(?x) + https?:// + (?: + (?: + out\.pladform\.ru/player| + static\.pladform\.ru/player\.swf + ) + \?.*\bvideoid=| + video\.pladform\.ru/catalog/video/videoid/ + ) + (?P<id>\d+) + ''' + _TESTS = [{ + # http://muz-tv.ru/kinozal/view/7400/ + 'url': 'http://out.pladform.ru/player?pl=24822&videoid=100183293', + 'md5': '61f37b575dd27f1bb2e1854777fe31f4', + 'info_dict': { + 'id': '100183293', + 'ext': 'mp4', + 'title': 'Тайны перевала Дятлова • Тайна перевала Дятлова 1 серия 2 часть', + 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 694, + 'age_limit': 0, + }, + }, { + 'url': 'http://static.pladform.ru/player.swf?pl=21469&videoid=100183293&vkcid=0', + 'only_matching': True, + }, { + 'url': 'http://video.pladform.ru/catalog/video/videoid/100183293/vkcid/0', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + video = self._download_xml( + 'http://out.pladform.ru/getVideo?pl=1&videoid=%s' % video_id, + video_id) + + if video.tag == 'error': + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, video.text), + expected=True) + + quality = qualities(('ld', 'sd', 'hd')) + + formats = [{ + 'url': src.text, + 'format_id': src.get('quality'), + 'quality': quality(src.get('quality')), + } for src in video.findall('./src')] + self._sort_formats(formats) + + webpage = self._download_webpage( + 'http://video.pladform.ru/catalog/video/videoid/%s' % video_id, + video_id) + + title = self._og_search_title(webpage, fatal=False) or xpath_text( + video, './/title', 'title', fatal=True) + description = self._search_regex( + r'</h3>\s*<p>([^<]+)</p>', webpage, 'description', fatal=False) + thumbnail = self._og_search_thumbnail(webpage) or xpath_text( + video, './/cover', 'cover') + + duration = int_or_none(xpath_text(video, './/time', 'duration')) + age_limit = int_or_none(xpath_text(video, './/age18', 'age limit')) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'age_limit': age_limit, + 'formats': formats, + } diff --git a/youtube_dl/extractor/ssa.py b/youtube_dl/extractor/ssa.py new file mode 100644 index 000000000..13101c714 --- /dev/null +++ b/youtube_dl/extractor/ssa.py @@ -0,0 +1,58 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + unescapeHTML, + parse_duration, +) + + +class SSAIE(InfoExtractor): + _VALID_URL = r'http://ssa\.nls\.uk/film/(?P<id>\d+)' + _TEST = { + 'url': 'http://ssa.nls.uk/film/3561', + 'info_dict': { + 'id': '3561', + 'ext': 'flv', + 'title': 'SHETLAND WOOL', + 'description': 'md5:c5afca6871ad59b4271e7704fe50ab04', + 'duration': 900, + 'thumbnail': 're:^https?://.*\.jpg$', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + streamer = self._search_regex( + r"'streamer'\s*,\S*'(rtmp[^']+)'", webpage, 'streamer') + play_path = self._search_regex( + r"'file'\s*,\s*'([^']+)'", webpage, 'file').rpartition('.')[0] + + def search_field(field_name, fatal=False): + return self._search_regex( + r'<span\s+class="field_title">%s:</span>\s*<span\s+class="field_content">([^<]+)</span>' % field_name, + webpage, 'title', fatal=fatal) + + title = unescapeHTML(search_field('Title', fatal=True)).strip('()[]') + description = unescapeHTML(search_field('Description')) + duration = parse_duration(search_field('Running time')) + thumbnail = self._search_regex( + r"'image'\s*,\s*'([^']+)'", webpage, 'thumbnails', fatal=False) + + return { + 'id': video_id, + 'url': streamer, + 'play_path': play_path, + 'ext': 'flv', + 'title': title, + 'description': description, + 'duration': duration, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py index 5793dbc10..7cb06f351 100644 --- a/youtube_dl/extractor/teamcoco.py +++ b/youtube_dl/extractor/teamcoco.py @@ -53,10 +53,10 @@ class TeamcocoIE(InfoExtractor): embed = self._download_webpage( embed_url, video_id, 'Downloading embed page') - encoded_data = self._search_regex( - r'"preload"\s*:\s*"([^"]+)"', embed, 'encoded data') + player_data = self._parse_json(self._search_regex( + r'Y\.Ginger\.Module\.Player\((\{.*?\})\);', embed, 'player data'), video_id) data = self._parse_json( - base64.b64decode(encoded_data.encode('ascii')).decode('utf-8'), video_id) + base64.b64decode(player_data['preload'].encode('ascii')).decode('utf-8'), video_id) formats = [] get_quality = qualities(['500k', '480p', '1000k', '720p', '1080p']) diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index b058891bd..cbdaf9c7a 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -358,13 +358,12 @@ class TwitchStreamIE(TwitchBaseIE): 'p': random.randint(1000000, 10000000), 'player': 'twitchweb', 'segment_preference': '4', - 'sig': access_token['sig'], - 'token': access_token['token'], + 'sig': access_token['sig'].encode('utf-8'), + 'token': access_token['token'].encode('utf-8'), } - formats = self._extract_m3u8_formats( '%s/api/channel/hls/%s.m3u8?%s' - % (self._USHER_BASE, channel_id, compat_urllib_parse.urlencode(query).encode('utf-8')), + % (self._USHER_BASE, channel_id, compat_urllib_parse.urlencode(query)), channel_id, 'mp4') self._prefer_source(formats) diff --git a/youtube_dl/extractor/vidme.py b/youtube_dl/extractor/vidme.py index 339c3d897..bd953fb4c 100644 --- a/youtube_dl/extractor/vidme.py +++ b/youtube_dl/extractor/vidme.py @@ -41,13 +41,10 @@ class VidmeIE(InfoExtractor): duration = float_or_none(self._html_search_regex( r'data-duration="([^"]+)"', webpage, 'duration', fatal=False)) view_count = str_to_int(self._html_search_regex( - r'<span class="video_views">\s*([\d,\.]+)\s*plays?', webpage, 'view count', fatal=False)) + r'<(?:li|span) class="video_views">\s*([\d,\.]+)\s*plays?', webpage, 'view count', fatal=False)) like_count = str_to_int(self._html_search_regex( r'class="score js-video-vote-score"[^>]+data-score="([\d,\.\s]+)">', webpage, 'like count', fatal=False)) - comment_count = str_to_int(self._html_search_regex( - r'class="js-comment-count"[^>]+data-count="([\d,\.\s]+)">', - webpage, 'comment count', fatal=False)) return { 'id': video_id, @@ -61,5 +58,4 @@ class VidmeIE(InfoExtractor): 'duration': duration, 'view_count': view_count, 'like_count': like_count, - 'comment_count': comment_count, } diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 8f540f578..b84a83ba6 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -4,7 +4,6 @@ from __future__ import unicode_literals import json import re import itertools -import hashlib from .common import InfoExtractor from ..compat import ( @@ -20,6 +19,7 @@ from ..utils import ( RegexNotFoundError, smuggle_url, std_headers, + unified_strdate, unsmuggle_url, urlencode_postdata, ) @@ -140,6 +140,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'description': 'md5:8678b246399b070816b12313e8b4eb5c', 'uploader_id': 'atencio', 'uploader': 'Peter Atencio', + 'upload_date': '20130927', 'duration': 187, }, }, @@ -176,17 +177,15 @@ 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', expected=True) - token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token') - data = compat_urllib_parse.urlencode({ + token = self._search_regex(r'xsrft = \'(.*?)\'', webpage, 'login token') + data = urlencode_postdata({ 'password': password, 'token': token, }) - # I didn't manage to use the password with https - if url.startswith('https'): - pass_url = url.replace('https', 'http') - else: - pass_url = url - password_request = compat_urllib_request.Request(pass_url + '/password', data) + 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.add_header('Content-Type', 'application/x-www-form-urlencoded') password_request.add_header('Cookie', 'xsrft=%s' % token) return self._download_webpage( @@ -223,12 +222,7 @@ class VimeoIE(VimeoBaseInfoExtractor): video_id = mobj.group('id') orig_url = url if mobj.group('pro') or mobj.group('player'): - url = 'http://player.vimeo.com/video/' + video_id - - password = self._downloader.params.get('videopassword', None) - if password: - headers['Cookie'] = '%s_password=%s' % ( - video_id, hashlib.md5(password.encode('utf-8')).hexdigest()) + url = 'https://player.vimeo.com/video/' + video_id # Retrieve video webpage to extract further information request = compat_urllib_request.Request(url, None, headers) @@ -323,9 +317,9 @@ class VimeoIE(VimeoBaseInfoExtractor): # Extract upload date video_upload_date = None - mobj = re.search(r'<meta itemprop="dateCreated" content="(\d{4})-(\d{2})-(\d{2})T', webpage) + mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage) if mobj is not None: - video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3) + video_upload_date = unified_strdate(mobj.group(1)) try: view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count')) @@ -435,10 +429,10 @@ class VimeoChannelIE(InfoExtractor): name="([^"]+)"\s+ value="([^"]*)" ''', login_form)) - token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token') + token = self._search_regex(r'xsrft = \'(.*?)\'', webpage, 'login token') fields['token'] = token fields['password'] = password - post = compat_urllib_parse.urlencode(fields) + post = urlencode_postdata(fields) password_path = self._search_regex( r'action="([^"]+)"', login_form, 'password URL') password_url = compat_urlparse.urljoin(page_url, password_path) @@ -500,10 +494,10 @@ class VimeoUserIE(VimeoChannelIE): class VimeoAlbumIE(VimeoChannelIE): IE_NAME = 'vimeo:album' - _VALID_URL = r'https?://vimeo\.com/album/(?P<id>\d+)' + _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)' _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>' _TESTS = [{ - 'url': 'http://vimeo.com/album/2632481', + 'url': 'https://vimeo.com/album/2632481', 'info_dict': { 'id': '2632481', 'title': 'Staff Favorites: November 2013', @@ -527,7 +521,7 @@ class VimeoAlbumIE(VimeoChannelIE): def _real_extract(self, url): album_id = self._match_id(url) - return self._extract_videos(album_id, 'http://vimeo.com/album/%s' % album_id) + return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id) class VimeoGroupsIE(VimeoAlbumIE): diff --git a/youtube_dl/extractor/yandexmusic.py b/youtube_dl/extractor/yandexmusic.py new file mode 100644 index 000000000..b47aecb15 --- /dev/null +++ b/youtube_dl/extractor/yandexmusic.py @@ -0,0 +1,127 @@ +# coding=utf-8 +from __future__ import unicode_literals + +import re +import hashlib + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + int_or_none, + float_or_none, +) + + +class YandexMusicBaseIE(InfoExtractor): + def _get_track_url(self, storage_dir, track_id): + data = self._download_json( + 'http://music.yandex.ru/api/v1.5/handlers/api-jsonp.jsx?action=getTrackSrc&p=download-info/%s' + % storage_dir, + track_id, 'Downloading track location JSON') + + key = hashlib.md5(('XGRlBW9FXlekgbPrRHuSiA' + data['path'][1:] + data['s']).encode('utf-8')).hexdigest() + storage = storage_dir.split('.') + + return ('http://%s/get-mp3/%s/%s?track-id=%s&from=service-10-track&similarities-experiment=default' + % (data['host'], key, data['ts'] + data['path'], storage[1])) + + def _get_track_info(self, track): + return { + 'id': track['id'], + 'ext': 'mp3', + 'url': self._get_track_url(track['storageDir'], track['id']), + 'title': '%s - %s' % (track['artists'][0]['name'], track['title']), + 'filesize': int_or_none(track.get('fileSize')), + 'duration': float_or_none(track.get('durationMs'), 1000), + } + + +class YandexMusicTrackIE(YandexMusicBaseIE): + IE_NAME = 'yandexmusic:track' + IE_DESC = 'Яндекс.Музыка - Трек' + _VALID_URL = r'https?://music\.yandex\.ru/album/(?P<album_id>\d+)/track/(?P<id>\d+)' + + _TEST = { + 'url': 'http://music.yandex.ru/album/540508/track/4878838', + 'md5': 'f496818aa2f60b6c0062980d2e00dc20', + 'info_dict': { + 'id': '4878838', + 'ext': 'mp3', + 'title': 'Carlo Ambrosio - Gypsy Eyes 1', + 'filesize': 4628061, + 'duration': 193.04, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + album_id, track_id = mobj.group('album_id'), mobj.group('id') + + track = self._download_json( + 'http://music.yandex.ru/handlers/track.jsx?track=%s:%s' % (track_id, album_id), + track_id, 'Downloading track JSON')['track'] + + return self._get_track_info(track) + + +class YandexMusicAlbumIE(YandexMusicBaseIE): + IE_NAME = 'yandexmusic:album' + IE_DESC = 'Яндекс.Музыка - Альбом' + _VALID_URL = r'https?://music\.yandex\.ru/album/(?P<id>\d+)/?(\?|$)' + + _TEST = { + 'url': 'http://music.yandex.ru/album/540508', + 'info_dict': { + 'id': '540508', + 'title': 'Carlo Ambrosio - Gypsy Soul (2009)', + }, + 'playlist_count': 50, + } + + def _real_extract(self, url): + album_id = self._match_id(url) + + album = self._download_json( + 'http://music.yandex.ru/handlers/album.jsx?album=%s' % album_id, + album_id, 'Downloading album JSON') + + entries = [self._get_track_info(track) for track in album['volumes'][0]] + + title = '%s - %s' % (album['artists'][0]['name'], album['title']) + year = album.get('year') + if year: + title += ' (%s)' % year + + return self.playlist_result(entries, compat_str(album['id']), title) + + +class YandexMusicPlaylistIE(YandexMusicBaseIE): + IE_NAME = 'yandexmusic:playlist' + IE_DESC = 'Яндекс.Музыка - Плейлист' + _VALID_URL = r'https?://music\.yandex\.ru/users/[^/]+/playlists/(?P<id>\d+)' + + _TEST = { + 'url': 'http://music.yandex.ru/users/music.partners/playlists/1245', + 'info_dict': { + 'id': '1245', + 'title': 'Что слушают Enter Shikari', + 'description': 'md5:3b9f27b0efbe53f2ee1e844d07155cc9', + }, + 'playlist_count': 6, + } + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + playlist = self._parse_json( + self._search_regex( + r'var\s+Mu\s*=\s*({.+?});\s*</script>', webpage, 'player'), + playlist_id)['pageData']['playlist'] + + entries = [self._get_track_info(track) for track in playlist['tracks']] + + return self.playlist_result( + entries, compat_str(playlist_id), + playlist['title'], playlist.get('description')) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 3690f8021..27c8c4453 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1532,7 +1532,7 @@ class YoutubeSearchURLIE(InfoExtractor): webpage = self._download_webpage(url, query) result_code = self._search_regex( - r'(?s)<ol class="item-section"(.*?)</ol>', webpage, 'result HTML') + r'(?s)<ol[^>]+class="item-section"(.*?)</ol>', webpage, 'result HTML') part_codes = re.findall( r'(?s)<h3 class="yt-lockup-title">(.*?)</h3>', result_code) |