diff options
Diffstat (limited to 'youtube_dl/extractor')
37 files changed, 1284 insertions, 147 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 5ca534cdf..bceed92e1 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -37,6 +37,7 @@ from .bandcamp import BandcampIE, BandcampAlbumIE from .bbccouk import BBCCoUkIE from .beeg import BeegIE from .behindkink import BehindKinkIE +from .beatportpro import BeatportProIE from .bet import BetIE from .bild import BildIE from .bilibili import BiliBiliIE @@ -116,6 +117,7 @@ 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 @@ -150,6 +152,7 @@ from .fktv import ( ) from .flickr import FlickrIE from .folketinget import FolketingetIE +from .footyroom import FootyRoomIE from .fourtube import FourTubeIE from .foxgay import FoxgayIE from .foxnews import FoxNewsIE @@ -174,6 +177,7 @@ 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 @@ -228,6 +232,7 @@ from .jove import JoveIE from .jukebox import JukeboxIE from .jpopsukitv import JpopsukiIE from .kaltura import KalturaIE +from .kanalplay import KanalPlayIE from .kankan import KankanIE from .karaoketv import KaraoketvIE from .keezmovies import KeezMoviesIE @@ -354,6 +359,7 @@ from .orf import ( ORFTVthekIE, ORFOE1IE, ORFFM4IE, + ORFIPTVIE, ) from .parliamentliveuk import ParliamentLiveUKIE from .patreon import PatreonIE @@ -361,6 +367,7 @@ 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 @@ -373,6 +380,7 @@ from .pornhub import ( ) from .pornotube import PornotubeIE from .pornoxo import PornoXOIE +from .primesharetv import PrimeShareTVIE from .promptfile import PromptFileIE from .prosiebensat1 import ProSiebenSat1IE from .puls4 import Puls4IE @@ -398,7 +406,7 @@ from .rtlnow import RTLnowIE from .rtl2 import RTL2IE from .rtp import RTPIE from .rts import RTSIE -from .rtve import RTVEALaCartaIE, RTVELiveIE +from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE from .ruhd import RUHDIE from .rutube import ( RutubeIE, @@ -456,6 +464,7 @@ 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 @@ -551,6 +560,7 @@ from .videoweed import VideoWeedIE from .vidme import VidmeIE from .vidzi import VidziIE from .vier import VierIE, VierVideosIE +from .viewster import ViewsterIE from .vimeo import ( VimeoIE, VimeoAlbumIE, @@ -607,6 +617,11 @@ 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/aftenposten.py b/youtube_dl/extractor/aftenposten.py index 2b257ede7..e15c015fb 100644 --- a/youtube_dl/extractor/aftenposten.py +++ b/youtube_dl/extractor/aftenposten.py @@ -14,10 +14,10 @@ from ..utils import ( class AftenpostenIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?aftenposten\.no/webtv/([^/]+/)*(?P<id>[^/]+)-\d+\.html' + _VALID_URL = r'https?://(?:www\.)?aftenposten\.no/webtv/(?:#!/)?video/(?P<id>\d+)' _TEST = { - 'url': 'http://www.aftenposten.no/webtv/serier-og-programmer/sweatshopenglish/TRAILER-SWEATSHOP---I-cant-take-any-more-7800835.html?paging=§ion=webtv_serierogprogrammer_sweatshop_sweatshopenglish', + 'url': 'http://www.aftenposten.no/webtv/#!/video/21039/trailer-sweatshop-i-can-t-take-any-more', 'md5': 'fd828cd29774a729bf4d4425fe192972', 'info_dict': { 'id': '21039', @@ -30,12 +30,7 @@ class AftenpostenIE(InfoExtractor): } def _real_extract(self, url): - display_id = self._match_id(url) - - webpage = self._download_webpage(url, display_id) - - video_id = self._html_search_regex( - r'data-xs-id="(\d+)"', webpage, 'video id') + video_id = self._match_id(url) data = self._download_xml( 'http://frontend.xstream.dk/ap/feed/video/?platform=web&id=%s' % video_id, video_id) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 783b53e23..6a35ea463 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -50,6 +50,9 @@ class ARDMediathekIE(InfoExtractor): if '>Der gewünschte Beitrag ist nicht mehr verfügbar.<' in webpage: raise ExtractorError('Video %s is no longer available' % video_id, expected=True) + if 'Diese Sendung ist für Jugendliche unter 12 Jahren nicht geeignet. Der Clip ist deshalb nur von 20 bis 6 Uhr verfügbar.' in webpage: + raise ExtractorError('This program is only suitable for those aged 12 and older. Video %s is therefore only available between 20 pm and 6 am.' % video_id, expected=True) + if re.search(r'[\?&]rss($|[=&])', url): doc = parse_xml(webpage) if doc.tag == 'rss': diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index 929dd3cc5..8273bd6c9 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -146,6 +146,7 @@ class ArteTVPlus7IE(InfoExtractor): formats.append(format) + self._check_formats(formats, video_id) self._sort_formats(formats) info_dict['formats'] = formats diff --git a/youtube_dl/extractor/beatportpro.py b/youtube_dl/extractor/beatportpro.py new file mode 100644 index 000000000..3c7775d3e --- /dev/null +++ b/youtube_dl/extractor/beatportpro.py @@ -0,0 +1,103 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import int_or_none + + +class BeatportProIE(InfoExtractor): + _VALID_URL = r'https?://pro\.beatport\.com/track/(?P<display_id>[^/]+)/(?P<id>[0-9]+)' + _TESTS = [{ + 'url': 'https://pro.beatport.com/track/synesthesia-original-mix/5379371', + 'md5': 'b3c34d8639a2f6a7f734382358478887', + 'info_dict': { + 'id': '5379371', + 'display_id': 'synesthesia-original-mix', + 'ext': 'mp4', + 'title': 'Froxic - Synesthesia (Original Mix)', + }, + }, { + 'url': 'https://pro.beatport.com/track/love-and-war-original-mix/3756896', + 'md5': 'e44c3025dfa38c6577fbaeb43da43514', + 'info_dict': { + 'id': '3756896', + 'display_id': 'love-and-war-original-mix', + 'ext': 'mp3', + 'title': 'Wolfgang Gartner - Love & War (Original Mix)', + }, + }, { + 'url': 'https://pro.beatport.com/track/birds-original-mix/4991738', + 'md5': 'a1fd8e8046de3950fd039304c186c05f', + 'info_dict': { + 'id': '4991738', + 'display_id': 'birds-original-mix', + 'ext': 'mp4', + 'title': "Tos, Middle Milk, Mumblin' Johnsson - Birds (Original Mix)", + } + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + track_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + playables = self._parse_json( + self._search_regex( + r'window\.Playables\s*=\s*({.+?});', webpage, + 'playables info', flags=re.DOTALL), + track_id) + + track = next(t for t in playables['tracks'] if t['id'] == int(track_id)) + + title = ', '.join((a['name'] for a in track['artists'])) + ' - ' + track['name'] + if track['mix']: + title += ' (' + track['mix'] + ')' + + formats = [] + for ext, info in track['preview'].items(): + if not info['url']: + continue + fmt = { + 'url': info['url'], + 'ext': ext, + 'format_id': ext, + 'vcodec': 'none', + } + if ext == 'mp3': + fmt['preference'] = 0 + fmt['acodec'] = 'mp3' + fmt['abr'] = 96 + fmt['asr'] = 44100 + elif ext == 'mp4': + fmt['preference'] = 1 + fmt['acodec'] = 'aac' + fmt['abr'] = 96 + fmt['asr'] = 44100 + formats.append(fmt) + self._sort_formats(formats) + + images = [] + for name, info in track['images'].items(): + image_url = info.get('url') + if name == 'dynamic' or not image_url: + continue + image = { + 'id': name, + 'url': image_url, + 'height': int_or_none(info.get('height')), + 'width': int_or_none(info.get('width')), + } + images.append(image) + + return { + 'id': compat_str(track.get('id')) or track_id, + 'display_id': track.get('slug') or display_id, + 'title': title, + 'formats': formats, + 'thumbnails': images, + } 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/cloudy.py b/youtube_dl/extractor/cloudy.py index abf8cc280..0fa720ee8 100644 --- a/youtube_dl/extractor/cloudy.py +++ b/youtube_dl/extractor/cloudy.py @@ -105,6 +105,7 @@ class CloudyIE(InfoExtractor): webpage = self._download_webpage(url, video_id) file_key = self._search_regex( - r'filekey\s*=\s*"([^"]+)"', webpage, 'file_key') + [r'key\s*:\s*"([^"]+)"', r'filekey\s*=\s*"([^"]+)"'], + webpage, 'file_key') return self._extract_video(video_host, video_id, file_key) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index cf39c0c21..e5245ec3f 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', @@ -883,8 +883,13 @@ class InfoExtractor(object): formats.append({'url': format_url(line)}) continue tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000) + 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': '-'.join(filter(None, [m3u8_id, 'm3u8-%d' % (tbr if tbr else len(formats))])), + 'format_id': '-'.join(format_id), 'url': format_url(line.strip()), 'tbr': tbr, 'ext': ext, @@ -1057,6 +1062,9 @@ class InfoExtractor(object): def _get_automatic_captions(self, *args, **kwargs): raise NotImplementedError("This method must be implemented by subclasses") + def _subtitles_timecode(self, seconds): + return '%02d:%02d:%02d.%03d' % (seconds / 3600, (seconds % 3600) / 60, seconds % 60, (seconds % 1) * 1000) + class SearchInfoExtractor(InfoExtractor): """ 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/eighttracks.py b/youtube_dl/extractor/eighttracks.py index fb5dbbe2b..0b61ea0ba 100644 --- a/youtube_dl/extractor/eighttracks.py +++ b/youtube_dl/extractor/eighttracks.py @@ -3,7 +3,6 @@ from __future__ import unicode_literals import json import random -import re from .common import InfoExtractor from ..compat import ( @@ -103,20 +102,23 @@ class EightTracksIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - playlist_id = mobj.group('id') + playlist_id = self._match_id(url) webpage = self._download_webpage(url, playlist_id) - json_like = self._search_regex( - r"(?s)PAGE.mix = (.*?);\n", webpage, 'trax information') - data = json.loads(json_like) + data = self._parse_json( + self._search_regex( + r"(?s)PAGE\.mix\s*=\s*({.+?});\n", webpage, 'trax information'), + playlist_id) session = str(random.randint(0, 1000000000)) mix_id = data['id'] track_count = data['tracks_count'] duration = data['duration'] avg_song_duration = float(duration) / track_count + # duration is sometimes negative, use predefined avg duration + if avg_song_duration <= 0: + avg_song_duration = 300 first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id) next_url = first_url entries = [] diff --git a/youtube_dl/extractor/footyroom.py b/youtube_dl/extractor/footyroom.py new file mode 100644 index 000000000..2b4691ae8 --- /dev/null +++ b/youtube_dl/extractor/footyroom.py @@ -0,0 +1,41 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class FootyRoomIE(InfoExtractor): + _VALID_URL = r'http://footyroom\.com/(?P<id>[^/]+)' + _TEST = { + 'url': 'http://footyroom.com/schalke-04-0-2-real-madrid-2015-02/', + 'info_dict': { + 'id': 'schalke-04-0-2-real-madrid-2015-02', + 'title': 'Schalke 04 0 – 2 Real Madrid', + }, + 'playlist_count': 3, + } + + 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'VideoSelector\.load\((\[.+?\])\);', webpage, 'video selector'), + playlist_id) + + playlist_title = self._og_search_title(webpage) + + entries = [] + for video in playlist: + payload = video.get('payload') + if not payload: + continue + playwire_url = self._search_regex( + r'data-config="([^"]+)"', payload, + 'playwire url', default=None) + if playwire_url: + entries.append(self.url_result(playwire_url, 'Playwire')) + + return self.playlist_result(entries, playlist_id, playlist_title) 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/globo.py b/youtube_dl/extractor/globo.py index 29638a194..8a95793ca 100644 --- a/youtube_dl/extractor/globo.py +++ b/youtube_dl/extractor/globo.py @@ -20,7 +20,7 @@ class GloboIE(InfoExtractor): _VALID_URL = 'https?://.+?\.globo\.com/(?P<id>.+)' _API_URL_TEMPLATE = 'http://api.globovideos.com/videos/%s/playlist' - _SECURITY_URL_TEMPLATE = 'http://security.video.globo.com/videos/%s/hash?player=flash&version=2.9.9.50&resource_id=%s' + _SECURITY_URL_TEMPLATE = 'http://security.video.globo.com/videos/%s/hash?player=flash&version=17.0.0.132&resource_id=%s' _VIDEOID_REGEXES = [ r'\bdata-video-id="(\d+)"', diff --git a/youtube_dl/extractor/jeuxvideo.py b/youtube_dl/extractor/jeuxvideo.py index 8094cc2e4..d0720ff56 100644 --- a/youtube_dl/extractor/jeuxvideo.py +++ b/youtube_dl/extractor/jeuxvideo.py @@ -2,7 +2,6 @@ from __future__ import unicode_literals -import json import re from .common import InfoExtractor @@ -15,10 +14,10 @@ class JeuxVideoIE(InfoExtractor): 'url': 'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm', 'md5': '046e491afb32a8aaac1f44dd4ddd54ee', 'info_dict': { - 'id': '5182', + 'id': '114765', 'ext': 'mp4', - 'title': 'GC 2013 : Tearaway nous présente ses papiers d\'identité', - 'description': 'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.\n', + 'title': 'Tearaway : GC 2013 : Tearaway nous présente ses papiers d\'identité', + 'description': 'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.', }, } @@ -26,26 +25,29 @@ class JeuxVideoIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) title = mobj.group(1) webpage = self._download_webpage(url, title) - xml_link = self._html_search_regex( - r'<param name="flashvars" value="config=(.*?)" />', + title = self._html_search_meta('name', webpage) + config_url = self._html_search_regex( + r'data-src="(/contenu/medias/video.php.*?)"', webpage, 'config URL') + config_url = 'http://www.jeuxvideo.com' + config_url video_id = self._search_regex( - r'http://www\.jeuxvideo\.com/config/\w+/\d+/(.*?)/\d+_player\.xml', - xml_link, 'video ID') + r'id=(\d+)', + config_url, 'video ID') - config = self._download_xml( - xml_link, title, 'Downloading XML config') - info_json = config.find('format.json').text - info = json.loads(info_json)['versions'][0] + config = self._download_json( + config_url, title, 'Downloading JSON config') - video_url = 'http://video720.jeuxvideo.com/' + info['file'] + formats = [{ + 'url': source['file'], + 'format_id': source['label'], + 'resolution': source['label'], + } for source in reversed(config['sources'])] return { 'id': video_id, - 'title': config.find('titre_video').text, - 'ext': 'mp4', - 'url': video_url, + 'title': title, + 'formats': formats, 'description': self._og_search_description(webpage), - 'thumbnail': config.find('image').text, + 'thumbnail': config.get('image'), } diff --git a/youtube_dl/extractor/kanalplay.py b/youtube_dl/extractor/kanalplay.py new file mode 100644 index 000000000..2bb078036 --- /dev/null +++ b/youtube_dl/extractor/kanalplay.py @@ -0,0 +1,96 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + float_or_none, +) + + +class KanalPlayIE(InfoExtractor): + IE_DESC = 'Kanal 5/9/11 Play' + _VALID_URL = r'https?://(?:www\.)?kanal(?P<channel_id>5|9|11)play\.se/(?:#!/)?(?:play/)?program/\d+/video/(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://www.kanal5play.se/#!/play/program/3060212363/video/3270012277', + 'info_dict': { + 'id': '3270012277', + 'ext': 'flv', + 'title': 'Saknar både dusch och avlopp', + 'description': 'md5:6023a95832a06059832ae93bc3c7efb7', + 'duration': 2636.36, + }, + 'params': { + # rtmp download + 'skip_download': True, + } + }, { + 'url': 'http://www.kanal9play.se/#!/play/program/335032/video/246042', + 'only_matching': True, + }, { + 'url': 'http://www.kanal11play.se/#!/play/program/232835958/video/367135199', + 'only_matching': True, + }] + + def _fix_subtitles(self, subs): + return '\r\n\r\n'.join( + '%s\r\n%s --> %s\r\n%s' + % ( + num, + self._subtitles_timecode(item['startMillis'] / 1000.0), + self._subtitles_timecode(item['endMillis'] / 1000.0), + item['text'], + ) for num, item in enumerate(subs, 1)) + + def _get_subtitles(self, channel_id, video_id): + subs = self._download_json( + 'http://www.kanal%splay.se/api/subtitles/%s' % (channel_id, video_id), + video_id, 'Downloading subtitles JSON', fatal=False) + return {'se': [{'ext': 'srt', 'data': self._fix_subtitles(subs)}]} if subs else {} + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + channel_id = mobj.group('channel_id') + + video = self._download_json( + 'http://www.kanal%splay.se/api/getVideo?format=FLASH&videoId=%s' % (channel_id, video_id), + video_id) + + reasons_for_no_streams = video.get('reasonsForNoStreams') + if reasons_for_no_streams: + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, '\n'.join(reasons_for_no_streams)), + expected=True) + + title = video['title'] + description = video.get('description') + duration = float_or_none(video.get('length'), 1000) + thumbnail = video.get('posterUrl') + + stream_base_url = video['streamBaseUrl'] + + formats = [{ + 'url': stream_base_url, + 'play_path': stream['source'], + 'ext': 'flv', + 'tbr': float_or_none(stream.get('bitrate'), 1000), + 'rtmp_real_time': True, + } for stream in video['streams']] + self._sort_formats(formats) + + subtitles = {} + if video.get('hasSubtitle'): + subtitles = self.extract_subtitles(channel_id, video_id) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'formats': formats, + 'subtitles': subtitles, + } diff --git a/youtube_dl/extractor/letv.py b/youtube_dl/extractor/letv.py index 85eee141b..1484ac0d2 100644 --- a/youtube_dl/extractor/letv.py +++ b/youtube_dl/extractor/letv.py @@ -88,12 +88,13 @@ class LetvIE(InfoExtractor): play_json_req = compat_urllib_request.Request( 'http://api.letv.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params) ) - play_json_req.add_header( - 'Ytdl-request-proxy', - self._downloader.params.get('cn_verification_proxy')) + cn_verification_proxy = self._downloader.params.get('cn_verification_proxy') + if cn_verification_proxy: + play_json_req.add_header('Ytdl-request-proxy', cn_verification_proxy) + play_json = self._download_json( play_json_req, - media_id, 'playJson data') + media_id, 'Downloading playJson data') # Check for errors playstatus = play_json['playstatus'] diff --git a/youtube_dl/extractor/livestream.py b/youtube_dl/extractor/livestream.py index 3642089f7..2467f8bdd 100644 --- a/youtube_dl/extractor/livestream.py +++ b/youtube_dl/extractor/livestream.py @@ -2,6 +2,7 @@ from __future__ import unicode_literals import re import json +import itertools from .common import InfoExtractor from ..compat import ( @@ -41,6 +42,13 @@ class LivestreamIE(InfoExtractor): }, 'playlist_mincount': 4, }, { + 'url': 'http://new.livestream.com/chess24/tatasteelchess', + 'info_dict': { + 'title': 'Tata Steel Chess', + 'id': '3705884', + }, + 'playlist_mincount': 60, + }, { 'url': 'https://new.livestream.com/accounts/362/events/3557232/videos/67864563/player?autoPlay=false&height=360&mute=false&width=640', 'only_matching': True, }] @@ -117,6 +125,30 @@ class LivestreamIE(InfoExtractor): 'view_count': video_data.get('views'), } + def _extract_event(self, info): + event_id = compat_str(info['id']) + account = compat_str(info['owner_account_id']) + root_url = ( + 'https://new.livestream.com/api/accounts/{account}/events/{event}/' + 'feed.json'.format(account=account, event=event_id)) + + def _extract_videos(): + last_video = None + for i in itertools.count(1): + if last_video is None: + info_url = root_url + else: + info_url = '{root}?&id={id}&newer=-1&type=video'.format( + root=root_url, id=last_video) + videos_info = self._download_json(info_url, event_id, 'Downloading page {0}'.format(i))['data'] + videos_info = [v['data'] for v in videos_info if v['type'] == 'video'] + if not videos_info: + break + for v in videos_info: + yield self._extract_video_info(v) + last_video = videos_info[-1]['id'] + return self.playlist_result(_extract_videos(), event_id, info['full_name']) + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') @@ -144,14 +176,13 @@ class LivestreamIE(InfoExtractor): result = result and compat_str(vdata['data']['id']) == vid return result - videos = [self._extract_video_info(video_data['data']) - for video_data in info['feed']['data'] - if is_relevant(video_data, video_id)] if video_id is None: # This is an event page: - return self.playlist_result( - videos, '%s' % info['id'], info['full_name']) + return self._extract_event(info) else: + videos = [self._extract_video_info(video_data['data']) + for video_data in info['feed']['data'] + if is_relevant(video_data, video_id)] if not videos: raise ExtractorError('Cannot find video %s' % video_id) return videos[0] 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/nrk.py b/youtube_dl/extractor/nrk.py index 1e4cfa2e7..bff36f9d3 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -149,9 +149,6 @@ class NRKTVIE(InfoExtractor): } ] - def _seconds2str(self, s): - return '%02d:%02d:%02d.%03d' % (s / 3600, (s % 3600) / 60, s % 60, (s % 1) * 1000) - def _debug_print(self, txt): if self._downloader.params.get('verbose', False): self.to_screen('[debug] %s' % txt) @@ -168,8 +165,8 @@ class NRKTVIE(InfoExtractor): for pos, p in enumerate(ps): begin = parse_duration(p.get('begin')) duration = parse_duration(p.get('dur')) - starttime = self._seconds2str(begin) - endtime = self._seconds2str(begin + duration) + starttime = self._subtitles_timecode(begin) + endtime = self._subtitles_timecode(begin + duration) srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (compat_str(pos), starttime, endtime, p.text) return {lang: [ {'ext': 'ttml', 'url': url}, 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/primesharetv.py b/youtube_dl/extractor/primesharetv.py new file mode 100644 index 000000000..01cc3d9ea --- /dev/null +++ b/youtube_dl/extractor/primesharetv.py @@ -0,0 +1,69 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse, + compat_urllib_request, +) +from ..utils import ExtractorError + + +class PrimeShareTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?primeshare\.tv/download/(?P<id>[\da-zA-Z]+)' + + _TEST = { + 'url': 'http://primeshare.tv/download/238790B611', + 'md5': 'b92d9bf5461137c36228009f31533fbc', + 'info_dict': { + 'id': '238790B611', + 'ext': 'mp4', + 'title': 'Public Domain - 1960s Commercial - Crest Toothpaste-YKsuFona', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + if '>File not exist<' in webpage: + raise ExtractorError('Video %s does not exist' % video_id, expected=True) + + fields = dict(re.findall(r'''(?x)<input\s+ + type="hidden"\s+ + name="([^"]+)"\s+ + (?:id="[^"]+"\s+)? + value="([^"]*)" + ''', webpage)) + + headers = { + 'Referer': url, + 'Content-Type': 'application/x-www-form-urlencoded', + } + + wait_time = int(self._search_regex( + r'var\s+cWaitTime\s*=\s*(\d+)', + webpage, 'wait time', default=7)) + 1 + self._sleep(wait_time, video_id) + + req = compat_urllib_request.Request( + url, compat_urllib_parse.urlencode(fields), headers) + video_page = self._download_webpage( + req, video_id, 'Downloading video page') + + video_url = self._search_regex( + r"url\s*:\s*'([^']+\.primeshare\.tv(?::443)?/file/[^']+)'", + video_page, 'video url') + + title = self._html_search_regex( + r'<h1>Watch\s*(?: )?\s*\((.+?)(?:\s*\[\.\.\.\])?\)\s*(?: )?\s*<strong>', + video_page, 'title') + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'ext': 'mp4', + } diff --git a/youtube_dl/extractor/rtve.py b/youtube_dl/extractor/rtve.py index b42442d12..13f071077 100644 --- a/youtube_dl/extractor/rtve.py +++ b/youtube_dl/extractor/rtve.py @@ -127,6 +127,47 @@ class RTVEALaCartaIE(InfoExtractor): for s in subs) +class RTVEInfantilIE(InfoExtractor): + IE_NAME = 'rtve.es:infantil' + IE_DESC = 'RTVE infantil' + _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/(?P<show>[^/]*)/video/(?P<short_title>[^/]*)/(?P<id>[0-9]+)/' + + _TESTS = [{ + 'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/', + 'md5': '915319587b33720b8e0357caaa6617e6', + 'info_dict': { + 'id': '3040283', + 'ext': 'mp4', + 'title': 'Maneras de vivir', + 'thumbnail': 'http://www.rtve.es/resources/jpg/6/5/1426182947956.JPG', + 'duration': 357.958, + }, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + info = self._download_json( + 'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id, + video_id)['page']['items'][0] + + webpage = self._download_webpage(url, video_id) + vidplayer_id = self._search_regex( + r' id="vidplayer([0-9]+)"', webpage, 'internal video ID') + + png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id + png = self._download_webpage(png_url, video_id, 'Downloading url information') + video_url = _decrypt_url(png) + + return { + 'id': video_id, + 'ext': 'mp4', + 'title': info['title'], + 'url': video_url, + 'thumbnail': info.get('image'), + 'duration': float_or_none(info.get('duration'), scale=1000), + } + + class RTVELiveIE(InfoExtractor): IE_NAME = 'rtve.es:live' IE_DESC = 'RTVE.es live streams' 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 8af136147..cbdaf9c7a 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -85,6 +85,14 @@ class TwitchBaseIE(InfoExtractor): raise ExtractorError( 'Unable to login: %s' % m.group('msg').strip(), expected=True) + def _prefer_source(self, formats): + try: + source = next(f for f in formats if f['format_id'] == 'Source') + source['preference'] = 10 + except StopIteration: + pass # No Source stream present + self._sort_formats(formats) + class TwitchItemBaseIE(TwitchBaseIE): def _download_info(self, item, item_id): @@ -209,6 +217,7 @@ class TwitchVodIE(TwitchItemBaseIE): '%s/vod/%s?nauth=%s&nauthsig=%s' % (self._USHER_BASE, item_id, access_token['token'], access_token['sig']), item_id, 'mp4') + self._prefer_source(formats) info['formats'] = formats return info @@ -349,21 +358,14 @@ 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') - - # prefer the 'source' stream, the others are limited to 30 fps - def _sort_source(f): - if f.get('m3u8_media') is not None and f['m3u8_media'].get('NAME') == 'Source': - return 1 - return 0 - formats = sorted(formats, key=_sort_source) + self._prefer_source(formats) view_count = stream.get('viewers') timestamp = parse_iso8601(stream.get('created_at')) diff --git a/youtube_dl/extractor/vidme.py b/youtube_dl/extractor/vidme.py index 5c89824c1..bd953fb4c 100644 --- a/youtube_dl/extractor/vidme.py +++ b/youtube_dl/extractor/vidme.py @@ -1,7 +1,5 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( int_or_none, @@ -28,12 +26,11 @@ class VidmeIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - video_url = self._html_search_regex(r'<source src="([^"]+)"', webpage, 'video URL') + video_url = self._html_search_regex( + r'<source src="([^"]+)"', webpage, 'video URL') title = self._og_search_title(webpage) description = self._og_search_description(webpage, default='') @@ -44,13 +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, @@ -64,5 +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/viewster.py b/youtube_dl/extractor/viewster.py new file mode 100644 index 000000000..1742e66f4 --- /dev/null +++ b/youtube_dl/extractor/viewster.py @@ -0,0 +1,129 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_urllib_request + + +class ViewsterIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?viewster\.com/movie/(?P<id>\d+-\d+-\d+)' + _TESTS = [{ + # movielink, paymethod=fre + 'url': 'http://www.viewster.com/movie/1293-19341-000/hout-wood/', + 'playlist': [{ + 'md5': '8f9d94b282d80c42b378dffdbb11caf3', + 'info_dict': { + 'id': '1293-19341-000-movie', + 'ext': 'flv', + 'title': "'Hout' (Wood) - Movie", + }, + }], + 'info_dict': { + 'id': '1293-19341-000', + 'title': "'Hout' (Wood)", + 'description': 'md5:925733185a9242ef96f436937683f33b', + } + }, { + # movielink, paymethod=adv + 'url': 'http://www.viewster.com/movie/1140-11855-000/the-listening-project/', + 'playlist': [{ + 'md5': '77a005453ca7396cbe3d35c9bea30aef', + 'info_dict': { + 'id': '1140-11855-000-movie', + 'ext': 'flv', + 'title': "THE LISTENING PROJECT - Movie", + }, + }], + 'info_dict': { + 'id': '1140-11855-000', + 'title': "THE LISTENING PROJECT", + 'description': 'md5:714421ae9957e112e672551094bf3b08', + } + }, { + # direct links, no movielink + 'url': 'http://www.viewster.com/movie/1198-56411-000/sinister/', + 'playlist': [{ + 'md5': '0307b7eac6bfb21ab0577a71f6eebd8f', + 'info_dict': { + 'id': '1198-56411-000-trailer', + 'ext': 'mp4', + 'title': "Sinister - Trailer", + }, + }, { + 'md5': '80b9ee3ad69fb368f104cb5d9732ae95', + 'info_dict': { + 'id': '1198-56411-000-behind-scenes', + 'ext': 'mp4', + 'title': "Sinister - Behind Scenes", + }, + }, { + 'md5': '3b3ea897ecaa91fca57a8a94ac1b15c5', + 'info_dict': { + 'id': '1198-56411-000-scene-from-movie', + 'ext': 'mp4', + 'title': "Sinister - Scene from movie", + }, + }], + 'info_dict': { + 'id': '1198-56411-000', + 'title': "Sinister", + 'description': 'md5:014c40b0488848de9683566a42e33372', + } + }] + + _ACCEPT_HEADER = 'application/json, text/javascript, */*; q=0.01' + + def _real_extract(self, url): + video_id = self._match_id(url) + + request = compat_urllib_request.Request( + 'http://api.live.viewster.com/api/v1/movie/%s' % video_id) + request.add_header('Accept', self._ACCEPT_HEADER) + + movie = self._download_json( + request, video_id, 'Downloading movie metadata JSON') + + title = movie.get('title') or movie['original_title'] + description = movie.get('synopsis') + thumbnail = movie.get('large_artwork') or movie.get('artwork') + + entries = [] + for clip in movie['play_list']: + entry = None + + # movielink api + link_request = clip.get('link_request') + if link_request: + request = compat_urllib_request.Request( + 'http://api.live.viewster.com/api/v1/movielink?movieid=%(movieid)s&action=%(action)s&paymethod=%(paymethod)s&price=%(price)s¤cy=%(currency)s&language=%(language)s&subtitlelanguage=%(subtitlelanguage)s&ischromecast=%(ischromecast)s' + % link_request) + request.add_header('Accept', self._ACCEPT_HEADER) + + movie_link = self._download_json( + request, video_id, 'Downloading movie link JSON', fatal=False) + + if movie_link: + formats = self._extract_f4m_formats( + movie_link['url'] + '&hdcore=3.2.0&plugin=flowplayer-3.2.0.1', video_id) + self._sort_formats(formats) + entry = { + 'formats': formats, + } + + # direct link + clip_url = clip.get('clip_data', {}).get('url') + if clip_url: + entry = { + 'url': clip_url, + 'ext': 'mp4', + } + + if entry: + entry.update({ + 'id': '%s-%s' % (video_id, clip['canonical_title']), + 'title': '%s - %s' % (title, clip['title']), + }) + entries.append(entry) + + playlist = self.playlist_result(entries, video_id, title, description) + playlist['thumbnail'] = thumbnail + return playlist diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 8f540f578..bd09652cd 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, ) @@ -38,7 +38,7 @@ class VimeoBaseInfoExtractor(InfoExtractor): self.report_login() login_url = 'https://vimeo.com/log_in' webpage = self._download_webpage(login_url, None, False) - token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token') + token = self._search_regex(r'xsrft = \'(.*?)\'', webpage, 'login token') data = urlencode_postdata({ 'email': username, 'password': password, @@ -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')) @@ -379,7 +373,7 @@ class VimeoIE(VimeoBaseInfoExtractor): for tt in text_tracks: subtitles[tt['lang']] = [{ 'ext': 'vtt', - 'url': 'http://vimeo.com' + tt['url'], + 'url': 'https://vimeo.com' + tt['url'], }] return { @@ -402,11 +396,11 @@ class VimeoIE(VimeoBaseInfoExtractor): class VimeoChannelIE(InfoExtractor): IE_NAME = 'vimeo:channel' - _VALID_URL = r'https?://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])' + _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])' _MORE_PAGES_INDICATOR = r'<a.+?rel="next"' _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"' _TESTS = [{ - 'url': 'http://vimeo.com/channels/tributes', + 'url': 'https://vimeo.com/channels/tributes', 'info_dict': { 'id': 'tributes', 'title': 'Vimeo Tributes', @@ -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) @@ -465,7 +459,7 @@ class VimeoChannelIE(InfoExtractor): if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None: break - entries = [self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo') + entries = [self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo') for video_id in video_ids] return {'_type': 'playlist', 'id': list_id, @@ -476,15 +470,15 @@ class VimeoChannelIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) channel_id = mobj.group('id') - return self._extract_videos(channel_id, 'http://vimeo.com/channels/%s' % channel_id) + return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id) class VimeoUserIE(VimeoChannelIE): IE_NAME = 'vimeo:user' - _VALID_URL = r'https?://vimeo\.com/(?![0-9]+(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)' + _VALID_URL = r'https://vimeo\.com/(?![0-9]+(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)' _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>' _TESTS = [{ - 'url': 'http://vimeo.com/nkistudio/videos', + 'url': 'https://vimeo.com/nkistudio/videos', 'info_dict': { 'title': 'Nki', 'id': 'nkistudio', @@ -495,15 +489,15 @@ class VimeoUserIE(VimeoChannelIE): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) name = mobj.group('name') - return self._extract_videos(name, 'http://vimeo.com/%s' % name) + return self._extract_videos(name, 'https://vimeo.com/%s' % name) 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', @@ -527,14 +521,14 @@ 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): IE_NAME = 'vimeo:group' - _VALID_URL = r'(?:https?://)?vimeo\.com/groups/(?P<name>[^/]+)' + _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)' _TESTS = [{ - 'url': 'http://vimeo.com/groups/rolexawards', + 'url': 'https://vimeo.com/groups/rolexawards', 'info_dict': { 'id': 'rolexawards', 'title': 'Rolex Awards for Enterprise', @@ -548,13 +542,13 @@ class VimeoGroupsIE(VimeoAlbumIE): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) name = mobj.group('name') - return self._extract_videos(name, 'http://vimeo.com/groups/%s' % name) + return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name) class VimeoReviewIE(InfoExtractor): IE_NAME = 'vimeo:review' IE_DESC = 'Review pages on vimeo' - _VALID_URL = r'https?://vimeo\.com/[^/]+/review/(?P<id>[^/]+)' + _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)' _TESTS = [{ 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d', 'md5': 'c507a72f780cacc12b2248bb4006d253', @@ -566,7 +560,7 @@ class VimeoReviewIE(InfoExtractor): } }, { 'note': 'video player needs Referer', - 'url': 'http://vimeo.com/user22258446/review/91613211/13f927e053', + 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053', 'md5': '6295fdab8f4bf6a002d058b2c6dce276', 'info_dict': { 'id': '91613211', @@ -588,11 +582,11 @@ class VimeoReviewIE(InfoExtractor): class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE): IE_NAME = 'vimeo:watchlater' IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)' - _VALID_URL = r'https?://vimeo\.com/home/watchlater|:vimeowatchlater' + _VALID_URL = r'https://vimeo\.com/home/watchlater|:vimeowatchlater' _LOGIN_REQUIRED = True _TITLE_RE = r'href="/home/watchlater".*?>(.*?)<' _TESTS = [{ - 'url': 'http://vimeo.com/home/watchlater', + 'url': 'https://vimeo.com/home/watchlater', 'only_matching': True, }] @@ -612,7 +606,7 @@ class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE): class VimeoLikesIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)' + _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)' IE_NAME = 'vimeo:likes' IE_DESC = 'Vimeo user likes' _TEST = { @@ -640,8 +634,8 @@ class VimeoLikesIE(InfoExtractor): description = self._html_search_meta('description', webpage) def _get_page(idx): - page_url = '%s//vimeo.com/user%s/likes/page:%d/sort:date' % ( - self.http_scheme(), user_id, idx + 1) + page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % ( + user_id, idx + 1) webpage = self._download_webpage( page_url, user_id, note='Downloading page %d/%d' % (idx + 1, page_count)) diff --git a/youtube_dl/extractor/yam.py b/youtube_dl/extractor/yam.py index b294767c5..19f8762ae 100644 --- a/youtube_dl/extractor/yam.py +++ b/youtube_dl/extractor/yam.py @@ -8,6 +8,7 @@ from ..compat import compat_urlparse from ..utils import ( float_or_none, month_by_abbreviation, + ExtractorError, ) @@ -28,23 +29,45 @@ class YamIE(InfoExtractor): } }, { # An external video hosted on YouTube - 'url': 'http://mymedia.yam.com/m/3598173', - 'md5': '0238ceec479c654e8c2f1223755bf3e9', + 'url': 'http://mymedia.yam.com/m/3599430', + 'md5': '03127cf10d8f35d120a9e8e52e3b17c6', 'info_dict': { - 'id': 'pJ2Deys283c', + 'id': 'CNpEoQlrIgA', 'ext': 'mp4', - 'upload_date': '20150202', + 'upload_date': '20150306', 'uploader': '新莊社大瑜伽社', - 'description': 'md5:f5cc72f0baf259a70fb731654b0d2eff', + 'description': 'md5:11e2e405311633ace874f2e6226c8b17', 'uploader_id': '2323agoy', - 'title': '外婆的澎湖灣KTV-潘安邦', - } + 'title': '20090412陽明山二子坪-1', + }, + 'skip': 'Video does not exist', + }, { + 'url': 'http://mymedia.yam.com/m/3598173', + 'info_dict': { + 'id': '3598173', + 'ext': 'mp4', + }, + 'skip': 'cause Yam system error', + }, { + 'url': 'http://mymedia.yam.com/m/3599437', + 'info_dict': { + 'id': '3599437', + 'ext': 'mp4', + }, + 'skip': 'invalid YouTube URL', }] def _real_extract(self, url): video_id = self._match_id(url) page = self._download_webpage(url, video_id) + # Check for errors + system_msg = self._html_search_regex( + r'系統訊息(?:<br>|\n|\r)*([^<>]+)<br>', page, 'system message', + default=None) + if system_msg: + raise ExtractorError(system_msg, expected=True) + # Is it hosted externally on YouTube? youtube_url = self._html_search_regex( r'<embed src="(http://www.youtube.com/[^"]+)"', diff --git a/youtube_dl/extractor/yandexmusic.py b/youtube_dl/extractor/yandexmusic.py new file mode 100644 index 000000000..f4c0f5702 --- /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|kz|ua|by)/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|kz|ua|by)/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|kz|ua|by)/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) |