diff options
Diffstat (limited to 'youtube_dl/extractor')
151 files changed, 6124 insertions, 1395 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 3503c76b7..da9606f24 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -1,8 +1,11 @@ +from .abc import ABCIE from .academicearth import AcademicEarthCourseIE from .addanime import AddAnimeIE +from .adultswim import AdultSwimIE from .aftonbladet import AftonbladetIE from .anitube import AnitubeIE from .aol import AolIE +from .allocine import AllocineIE from .aparat import AparatIE from .appletrailers import AppleTrailersIE from .archiveorg import ArchiveOrgIE @@ -51,6 +54,7 @@ from .cnn import ( from .collegehumor import CollegeHumorIE from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE from .condenast import CondeNastIE +from .cracked import CrackedIE from .criterion import CriterionIE from .crunchyroll import CrunchyrollIE from .cspan import CSpanIE @@ -61,8 +65,11 @@ from .dailymotion import ( DailymotionUserIE, ) from .daum import DaumIE +from .dfb import DFBIE from .dotsub import DotsubIE from .dreisat import DreiSatIE +from .drtv import DRTVIE +from .dump import DumpIE from .defense import DefenseGouvFrIE from .discovery import DiscoveryIE from .divxstage import DivxStageIE @@ -71,6 +78,10 @@ from .ebaumsworld import EbaumsWorldIE from .ehow import EHowIE from .eighttracks import EightTracksIE from .eitb import EitbIE +from .ellentv import ( + EllenTVIE, + EllenTVClipsIE, +) from .elpais import ElPaisIE from .empflix import EmpflixIE from .engadget import EngadgetIE @@ -81,6 +92,7 @@ from .extremetube import ExtremeTubeIE from .facebook import FacebookIE from .faz import FazIE from .fc2 import FC2IE +from .firedrive import FiredriveIE from .firstpost import FirstpostIE from .firsttv import FirstTVIE from .fivemin import FiveMinIE @@ -103,17 +115,23 @@ from .freesound import FreesoundIE from .freespeech import FreespeechIE from .funnyordie import FunnyOrDieIE from .gamekings import GamekingsIE +from .gameone import GameOneIE from .gamespot import GameSpotIE +from .gamestar import GameStarIE from .gametrailers import GametrailersIE from .gdcvault import GDCVaultIE from .generic import GenericIE +from .godtube import GodTubeIE from .googleplus import GooglePlusIE from .googlesearch import GoogleSearchIE +from .gorillavid import GorillaVidIE +from .goshgay import GoshgayIE from .hark import HarkIE from .helsinki import HelsinkiIE from .hentaistigma import HentaiStigmaIE from .hotnewhiphop import HotNewHipHopIE from .howcast import HowcastIE +from .howstuffworks import HowStuffWorksIE from .huffpost import HuffPostIE from .hypem import HypemIE from .iconosquare import IconosquareIE @@ -131,8 +149,10 @@ from .ivi import ( IviIE, IviCompilationIE ) +from .izlesene import IzleseneIE from .jadorecettepub import JadoreCettePubIE from .jeuxvideo import JeuxVideoIE +from .jove import JoveIE from .jukebox import JukeboxIE from .justintv import JustinTVIE from .jpopsukitv import JpopsukiIE @@ -142,10 +162,16 @@ from .khanacademy import KhanAcademyIE from .kickstarter import KickStarterIE from .keek import KeekIE from .kontrtube import KontrTubeIE +from .krasview import KrasViewIE +from .ku6 import Ku6IE from .la7 import LA7IE from .lifenews import LifeNewsIE from .liveleak import LiveLeakIE -from .livestream import LivestreamIE, LivestreamOriginalIE +from .livestream import ( + LivestreamIE, + LivestreamOriginalIE, + LivestreamShortenerIE, +) from .lynda import ( LyndaIE, LyndaCourseIE @@ -158,16 +184,21 @@ from .mdr import MDRIE from .metacafe import MetacafeIE from .metacritic import MetacriticIE from .mit import TechTVMITIE, MITIE, OCWMITIE +from .mitele import MiTeleIE from .mixcloud import MixcloudIE +from .mlb import MLBIE from .mpora import MporaIE from .mofosex import MofosexIE +from .mojvideo import MojvideoIE from .mooshare import MooshareIE from .morningstar import MorningstarIE +from .motherless import MotherlessIE from .motorsport import MotorsportIE from .moviezine import MoviezineIE from .movshare import MovShareIE from .mtv import ( MTVIE, + MTVServicesEmbeddedIE, MTVIggyIE, ) from .musicplayon import MusicPlayOnIE @@ -194,16 +225,25 @@ from .normalboots import NormalbootsIE from .novamov import NovaMovIE from .nowness import NownessIE from .nowvideo import NowVideoIE -from .nrk import NRKIE +from .npo import NPOIE +from .nrk import ( + NRKIE, + NRKTVIE, +) from .ntv import NTVIE from .nytimes import NYTimesIE from .nuvid import NuvidIE -from .oe1 import OE1IE from .ooyala import OoyalaIE -from .orf import ORFIE +from .orf import ( + ORFTVthekIE, + ORFOE1IE, + ORFFM4IE, +) from .parliamentliveuk import ParliamentLiveUKIE +from .patreon import PatreonIE from .pbs import PBSIE from .photobucket import PhotobucketIE +from .playfm import PlayFMIE from .playvid import PlayvidIE from .podomatic import PodomaticIE from .pornhd import PornHdIE @@ -212,16 +252,20 @@ from .pornotube import PornotubeIE from .prosiebensat1 import ProSiebenSat1IE from .pyvideo import PyvideoIE from .radiofrance import RadioFranceIE +from .rai import RaiIE from .rbmaradio import RBMARadioIE from .redtube import RedTubeIE +from .reverbnation import ReverbNationIE from .ringtv import RingTVIE from .ro220 import Ro220IE from .rottentomatoes import RottenTomatoesIE from .roxwel import RoxwelIE from .rtbf import RTBFIE +from .rtlnl import RtlXlIE from .rtlnow import RTLnowIE from .rts import RTSIE from .rtve import RTVEALaCartaIE +from .ruhd import RUHDIE from .rutube import ( RutubeIE, RutubeChannelIE, @@ -229,9 +273,12 @@ from .rutube import ( RutubePersonIE, ) from .rutv import RUTVIE +from .sapo import SapoIE from .savefrom import SaveFromIE from .scivee import SciVeeIE +from .screencast import ScreencastIE from .servingsys import ServingSysIE +from .shared import SharedIE from .sina import SinaIE from .slideshare import SlideshareIE from .slutload import SlutloadIE @@ -241,6 +288,8 @@ from .smotri import ( SmotriUserIE, SmotriBroadcastIE, ) +from .snotr import SnotrIE +from .sockshare import SockshareIE from .sohu import SohuIE from .soundcloud import ( SoundcloudIE, @@ -248,23 +297,33 @@ from .soundcloud import ( SoundcloudUserIE, SoundcloudPlaylistIE ) -from .southparkstudios import ( - SouthParkStudiosIE, +from .soundgasm import SoundgasmIE +from .southpark import ( + SouthParkIE, SouthparkDeIE, ) from .space import SpaceIE from .spankwire import SpankwireIE from .spiegel import SpiegelIE +from .spiegeltv import SpiegeltvIE from .spike import SpikeIE from .stanfordoc import StanfordOpenClassroomIE from .steam import SteamIE from .streamcloud import StreamcloudIE from .streamcz import StreamCZIE +from .swrmediathek import SWRMediathekIE from .syfy import SyfyIE from .sztvhu import SztvHuIE +from .tagesschau import TagesschauIE +from .teachertube import ( + TeacherTubeIE, + TeacherTubeUserIE, +) +from .teachingchannel import TeachingChannelIE from .teamcoco import TeamcocoIE from .techtalks import TechTalksIE from .ted import TEDIE +from .tenplay import TenPlayIE from .testurl import TestURLIE from .tf1 import TF1IE from .theplatform import ThePlatformIE @@ -282,6 +341,8 @@ from .tumblr import TumblrIE from .tutv import TutvIE from .tvigle import TvigleIE from .tvp import TvpIE +from .tvplay import TVPlayIE +from .ubu import UbuIE from .udemy import ( UdemyIE, UdemyCourseIE @@ -294,6 +355,7 @@ from .veehd import VeeHDIE from .veoh import VeohIE from .vesti import VestiIE from .vevo import VevoIE +from .vh1 import VH1IE from .viddler import ViddlerIE from .videobam import VideoBamIE from .videodetective import VideoDetectiveIE @@ -302,6 +364,7 @@ from .videofyme import VideofyMeIE from .videopremium import VideoPremiumIE from .videott import VideoTtIE from .videoweed import VideoWeedIE +from .vidme import VidmeIE from .vimeo import ( VimeoIE, VimeoChannelIE, @@ -311,14 +374,17 @@ from .vimeo import ( VimeoReviewIE, VimeoWatchLaterIE, ) +from .vimple import VimpleIE from .vine import ( VineIE, VineUserIE, ) from .viki import VikiIE from .vk import VKIE +from .vodlocker import VodlockerIE from .vube import VubeIE from .vuclip import VuClipIE +from .vulture import VultureIE from .washingtonpost import WashingtonPostIE from .wat import WatIE from .wdr import ( @@ -330,7 +396,9 @@ from .weibo import WeiboIE from .wimp import WimpIE from .wistia import WistiaIE from .worldstarhiphop import WorldStarHipHopIE +from .wrzuta import WrzutaIE from .xbef import XBefIE +from .xboxclips import XboxClipsIE from .xhamster import XHamsterIE from .xnxx import XNXXIE from .xvideos import XVideosIE @@ -360,6 +428,7 @@ from .youtube import ( YoutubeUserIE, YoutubeWatchLaterIE, ) + from .zdf import ZDFIE diff --git a/youtube_dl/extractor/abc.py b/youtube_dl/extractor/abc.py new file mode 100644 index 000000000..7d89f44ee --- /dev/null +++ b/youtube_dl/extractor/abc.py @@ -0,0 +1,48 @@ +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor + + +class ABCIE(InfoExtractor): + IE_NAME = 'abc.net.au' + _VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P<id>\d+)' + + _TEST = { + 'url': 'http://www.abc.net.au/news/2014-07-25/bringing-asylum-seekers-to-australia-would-give/5624716', + 'md5': 'dad6f8ad011a70d9ddf887ce6d5d0742', + 'info_dict': { + 'id': '5624716', + 'ext': 'mp4', + 'title': 'Bringing asylum seekers to Australia would give them right to asylum claims: professor', + 'description': 'md5:ba36fa5e27e5c9251fd929d339aea4af', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + + urls_info_json = self._search_regex( + r'inlineVideoData\.push\((.*?)\);', webpage, 'video urls', + flags=re.DOTALL) + urls_info = json.loads(urls_info_json.replace('\'', '"')) + formats = [{ + 'url': url_info['url'], + 'width': int(url_info['width']), + 'height': int(url_info['height']), + 'tbr': int(url_info['bitrate']), + 'filesize': int(url_info['filesize']), + } for url_info in urls_info] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': self._og_search_title(webpage), + 'formats': formats, + 'description': self._og_search_description(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + } diff --git a/youtube_dl/extractor/adultswim.py b/youtube_dl/extractor/adultswim.py new file mode 100644 index 000000000..a00bfcb35 --- /dev/null +++ b/youtube_dl/extractor/adultswim.py @@ -0,0 +1,139 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + +class AdultSwimIE(InfoExtractor): + _VALID_URL = r'https?://video\.adultswim\.com/(?P<path>.+?)(?:\.html)?(?:\?.*)?(?:#.*)?$' + _TEST = { + 'url': 'http://video.adultswim.com/rick-and-morty/close-rick-counters-of-the-rick-kind.html?x=y#title', + 'playlist': [ + { + 'md5': '4da359ec73b58df4575cd01a610ba5dc', + 'info_dict': { + 'id': '8a250ba1450996e901453d7f02ca02f5', + 'ext': 'flv', + 'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 1', + 'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?', + 'uploader': 'Rick and Morty', + 'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg' + } + }, + { + 'md5': 'ffbdf55af9331c509d95350bd0cc1819', + 'info_dict': { + 'id': '8a250ba1450996e901453d7f4bd102f6', + 'ext': 'flv', + 'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 2', + 'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?', + 'uploader': 'Rick and Morty', + 'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg' + } + }, + { + 'md5': 'b92409635540304280b4b6c36bd14a0a', + 'info_dict': { + 'id': '8a250ba1450996e901453d7fa73c02f7', + 'ext': 'flv', + 'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 3', + 'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?', + 'uploader': 'Rick and Morty', + 'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg' + } + }, + { + 'md5': 'e8818891d60e47b29cd89d7b0278156d', + 'info_dict': { + 'id': '8a250ba1450996e901453d7fc8ba02f8', + 'ext': 'flv', + 'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 4', + 'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?', + 'uploader': 'Rick and Morty', + 'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg' + } + } + ] + } + + _video_extensions = { + '3500': 'flv', + '640': 'mp4', + '150': 'mp4', + 'ipad': 'm3u8', + 'iphone': 'm3u8' + } + _video_dimensions = { + '3500': (1280, 720), + '640': (480, 270), + '150': (320, 180) + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_path = mobj.group('path') + + webpage = self._download_webpage(url, video_path) + episode_id = self._html_search_regex(r'<link rel="video_src" href="http://i\.adultswim\.com/adultswim/adultswimtv/tools/swf/viralplayer.swf\?id=([0-9a-f]+?)"\s*/?\s*>', webpage, 'episode_id') + title = self._og_search_title(webpage) + + index_url = 'http://asfix.adultswim.com/asfix-svc/episodeSearch/getEpisodesByIDs?networkName=AS&ids=%s' % episode_id + idoc = self._download_xml(index_url, title, 'Downloading episode index', 'Unable to download episode index') + + episode_el = idoc.find('.//episode') + show_title = episode_el.attrib.get('collectionTitle') + episode_title = episode_el.attrib.get('title') + thumbnail = episode_el.attrib.get('thumbnailUrl') + description = episode_el.find('./description').text.strip() + + entries = [] + segment_els = episode_el.findall('./segments/segment') + + for part_num, segment_el in enumerate(segment_els): + segment_id = segment_el.attrib.get('id') + segment_title = '%s %s part %d' % (show_title, episode_title, part_num + 1) + thumbnail = segment_el.attrib.get('thumbnailUrl') + duration = segment_el.attrib.get('duration') + + segment_url = 'http://asfix.adultswim.com/asfix-svc/episodeservices/getCvpPlaylist?networkName=AS&id=%s' % segment_id + idoc = self._download_xml(segment_url, segment_title, 'Downloading segment information', 'Unable to download segment information') + + formats = [] + file_els = idoc.findall('.//files/file') + + for file_el in file_els: + bitrate = file_el.attrib.get('bitrate') + type = file_el.attrib.get('type') + width, height = self._video_dimensions.get(bitrate, (None, None)) + formats.append({ + 'format_id': '%s-%s' % (bitrate, type), + 'url': file_el.text, + 'ext': self._video_extensions.get(bitrate, 'mp4'), + # The bitrate may not be a number (for example: 'iphone') + 'tbr': int(bitrate) if bitrate.isdigit() else None, + 'height': height, + 'width': width + }) + + self._sort_formats(formats) + + entries.append({ + 'id': segment_id, + 'title': segment_title, + 'formats': formats, + 'uploader': show_title, + 'thumbnail': thumbnail, + 'duration': duration, + 'description': description + }) + + return { + '_type': 'playlist', + 'id': episode_id, + 'display_id': video_path, + 'entries': entries, + 'title': '%s %s' % (show_title, episode_title), + 'description': description, + 'thumbnail': thumbnail + } diff --git a/youtube_dl/extractor/aftonbladet.py b/youtube_dl/extractor/aftonbladet.py index 6a8cd14c9..cfc7370ae 100644 --- a/youtube_dl/extractor/aftonbladet.py +++ b/youtube_dl/extractor/aftonbladet.py @@ -1,7 +1,6 @@ # encoding: utf-8 from __future__ import unicode_literals -import datetime import re from .common import InfoExtractor @@ -16,6 +15,7 @@ class AftonbladetIE(InfoExtractor): 'ext': 'mp4', 'title': 'Vulkanutbrott i rymden - nu släpper NASA bilderna', 'description': 'Jupiters måne mest aktiv av alla himlakroppar', + 'timestamp': 1394142732, 'upload_date': '20140306', }, } @@ -27,17 +27,17 @@ class AftonbladetIE(InfoExtractor): webpage = self._download_webpage(url, video_id) # find internal video meta data - META_URL = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json' + meta_url = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json' internal_meta_id = self._html_search_regex( r'data-aptomaId="([\w\d]+)"', webpage, 'internal_meta_id') - internal_meta_url = META_URL % internal_meta_id + internal_meta_url = meta_url % internal_meta_id internal_meta_json = self._download_json( internal_meta_url, video_id, 'Downloading video meta data') # find internal video formats - FORMATS_URL = 'http://aftonbladet-play.videodata.drvideo.aptoma.no/actions/video/?id=%s' + format_url = 'http://aftonbladet-play.videodata.drvideo.aptoma.no/actions/video/?id=%s' internal_video_id = internal_meta_json['videoId'] - internal_formats_url = FORMATS_URL % internal_video_id + internal_formats_url = format_url % internal_video_id internal_formats_json = self._download_json( internal_formats_url, video_id, 'Downloading video formats') @@ -54,16 +54,13 @@ class AftonbladetIE(InfoExtractor): }) self._sort_formats(formats) - timestamp = datetime.datetime.fromtimestamp(internal_meta_json['timePublished']) - upload_date = timestamp.strftime('%Y%m%d') - return { 'id': video_id, 'title': internal_meta_json['title'], 'formats': formats, 'thumbnail': internal_meta_json['imageUrl'], 'description': internal_meta_json['shortPreamble'], - 'upload_date': upload_date, + 'timestamp': internal_meta_json['timePublished'], 'duration': internal_meta_json['duration'], 'view_count': internal_meta_json['views'], } diff --git a/youtube_dl/extractor/allocine.py b/youtube_dl/extractor/allocine.py new file mode 100644 index 000000000..7bd797884 --- /dev/null +++ b/youtube_dl/extractor/allocine.py @@ -0,0 +1,89 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor +from ..utils import ( + compat_str, + qualities, + determine_ext, +) + + +class AllocineIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?P<typ>article|video|film)/(fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=)(?P<id>[0-9]+)(?:\.html)?' + + _TESTS = [{ + 'url': 'http://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html', + 'md5': '0c9fcf59a841f65635fa300ac43d8269', + 'info_dict': { + 'id': '19546517', + 'ext': 'mp4', + 'title': 'Astérix - Le Domaine des Dieux Teaser VF', + 'description': 'md5:4a754271d9c6f16c72629a8a993ee884', + 'thumbnail': 're:http://.*\.jpg', + }, + }, { + 'url': 'http://www.allocine.fr/video/player_gen_cmedia=19540403&cfilm=222257.html', + 'md5': 'd0cdce5d2b9522ce279fdfec07ff16e0', + 'info_dict': { + 'id': '19540403', + 'ext': 'mp4', + 'title': 'Planes 2 Bande-annonce VF', + 'description': 'md5:eeaffe7c2d634525e21159b93acf3b1e', + 'thumbnail': 're:http://.*\.jpg', + }, + }, { + 'url': 'http://www.allocine.fr/film/fichefilm_gen_cfilm=181290.html', + 'md5': '101250fb127ef9ca3d73186ff22a47ce', + 'info_dict': { + 'id': '19544709', + 'ext': 'mp4', + 'title': 'Dragons 2 - Bande annonce finale VF', + 'description': 'md5:71742e3a74b0d692c7fce0dd2017a4ac', + 'thumbnail': 're:http://.*\.jpg', + }, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + typ = mobj.group('typ') + display_id = mobj.group('id') + + webpage = self._download_webpage(url, display_id) + + if typ == 'film': + video_id = self._search_regex(r'href="/video/player_gen_cmedia=([0-9]+).+"', webpage, 'video id') + else: + player = self._search_regex(r'data-player=\'([^\']+)\'>', webpage, 'data player') + + player_data = json.loads(player) + video_id = compat_str(player_data['refMedia']) + + xml = self._download_xml('http://www.allocine.fr/ws/AcVisiondataV4.ashx?media=%s' % video_id, display_id) + + video = xml.find('.//AcVisionVideo').attrib + quality = qualities(['ld', 'md', 'hd']) + + formats = [] + for k, v in video.items(): + if re.match(r'.+_path', k): + format_id = k.split('_')[0] + formats.append({ + 'format_id': format_id, + 'quality': quality(format_id), + 'url': v, + 'ext': determine_ext(v), + }) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': video['videoTitle'], + 'thumbnail': self._og_search_thumbnail(webpage), + 'formats': formats, + 'description': self._og_search_description(webpage), + } diff --git a/youtube_dl/extractor/anitube.py b/youtube_dl/extractor/anitube.py index 2b019daa9..31f0d417c 100644 --- a/youtube_dl/extractor/anitube.py +++ b/youtube_dl/extractor/anitube.py @@ -1,22 +1,24 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor class AnitubeIE(InfoExtractor): - IE_NAME = u'anitube.se' + IE_NAME = 'anitube.se' _VALID_URL = r'https?://(?:www\.)?anitube\.se/video/(?P<id>\d+)' _TEST = { - u'url': u'http://www.anitube.se/video/36621', - u'md5': u'59d0eeae28ea0bc8c05e7af429998d43', - u'file': u'36621.mp4', - u'info_dict': { - u'id': u'36621', - u'ext': u'mp4', - u'title': u'Recorder to Randoseru 01', + 'url': 'http://www.anitube.se/video/36621', + 'md5': '59d0eeae28ea0bc8c05e7af429998d43', + 'info_dict': { + 'id': '36621', + 'ext': 'mp4', + 'title': 'Recorder to Randoseru 01', + 'duration': 180.19, }, - u'skip': u'Blocked in the US', + 'skip': 'Blocked in the US', } def _real_extract(self, url): @@ -24,13 +26,15 @@ class AnitubeIE(InfoExtractor): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - key = self._html_search_regex(r'http://www\.anitube\.se/embed/([A-Za-z0-9_-]*)', - webpage, u'key') + key = self._html_search_regex( + r'http://www\.anitube\.se/embed/([A-Za-z0-9_-]*)', webpage, 'key') - config_xml = self._download_xml('http://www.anitube.se/nuevo/econfig.php?key=%s' % key, - key) + config_xml = self._download_xml( + 'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, key) video_title = config_xml.find('title').text + thumbnail = config_xml.find('image').text + duration = float(config_xml.find('duration').text) formats = [] video_url = config_xml.find('file') @@ -49,5 +53,7 @@ class AnitubeIE(InfoExtractor): return { 'id': video_id, 'title': video_title, + 'thumbnail': thumbnail, + 'duration': duration, 'formats': formats } diff --git a/youtube_dl/extractor/aparat.py b/youtube_dl/extractor/aparat.py index 7e93bc4df..748608826 100644 --- a/youtube_dl/extractor/aparat.py +++ b/youtube_dl/extractor/aparat.py @@ -1,5 +1,7 @@ #coding: utf-8 +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -13,13 +15,14 @@ class AparatIE(InfoExtractor): _VALID_URL = r'^https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)' _TEST = { - u'url': u'http://www.aparat.com/v/wP8On', - u'file': u'wP8On.mp4', - u'md5': u'6714e0af7e0d875c5a39c4dc4ab46ad1', - u'info_dict': { - u"title": u"تیم گلکسی 11 - زومیت", + 'url': 'http://www.aparat.com/v/wP8On', + 'md5': '6714e0af7e0d875c5a39c4dc4ab46ad1', + 'info_dict': { + 'id': 'wP8On', + 'ext': 'mp4', + 'title': 'تیم گلکسی 11 - زومیت', }, - #u'skip': u'Extremely unreliable', + # 'skip': 'Extremely unreliable', } def _real_extract(self, url): @@ -29,8 +32,8 @@ class AparatIE(InfoExtractor): # Note: There is an easier-to-parse configuration at # http://www.aparat.com/video/video/config/videohash/%video_id # but the URL in there does not work - embed_url = (u'http://www.aparat.com/video/video/embed/videohash/' + - video_id + u'/vt/frame') + embed_url = ('http://www.aparat.com/video/video/embed/videohash/' + + video_id + '/vt/frame') webpage = self._download_webpage(embed_url, video_id) video_urls = re.findall(r'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage) diff --git a/youtube_dl/extractor/appletrailers.py b/youtube_dl/extractor/appletrailers.py index dc8657b67..4359b88d1 100644 --- a/youtube_dl/extractor/appletrailers.py +++ b/youtube_dl/extractor/appletrailers.py @@ -6,6 +6,7 @@ import json from .common import InfoExtractor from ..utils import ( compat_urlparse, + int_or_none, ) @@ -110,8 +111,8 @@ class AppleTrailersIE(InfoExtractor): formats.append({ 'url': format_url, 'format': format['type'], - 'width': format['width'], - 'height': int(format['height']), + 'width': int_or_none(format['width']), + 'height': int_or_none(format['height']), }) self._sort_formats(formats) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index b88f71bc4..7f0da8ab6 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -7,23 +7,34 @@ from .common import InfoExtractor from ..utils import ( determine_ext, ExtractorError, + qualities, + compat_urllib_parse_urlparse, + compat_urllib_parse, ) class ARDIE(InfoExtractor): - _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?' + _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?' - _TEST = { - 'url': 'http://www.ardmediathek.de/das-erste/guenther-jauch/edward-snowden-im-interview-held-oder-verraeter?documentId=19288786', - 'file': '19288786.mp4', - 'md5': '515bf47ce209fb3f5a61b7aad364634c', + _TESTS = [{ + 'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht', + 'file': '22429276.mp4', + 'md5': '469751912f1de0816a9fc9df8336476c', 'info_dict': { - 'title': 'Edward Snowden im Interview - Held oder Verräter?', - 'description': 'Edward Snowden hat alles aufs Spiel gesetzt, um die weltweite \xdcberwachung durch die Geheimdienste zu enttarnen. Nun stellt sich der ehemalige NSA-Mitarbeiter erstmals weltweit in einem TV-Interview den Fragen eines NDR-Journalisten. Die Sendung vom Sonntagabend.', - 'thumbnail': 'http://www.ardmediathek.de/ard/servlet/contentblob/19/28/87/90/19288790/bild/2250037', + 'title': 'Vertrauen ist gut, Spionieren ist besser - Geht so deutsch-amerikanische Freundschaft?', + 'description': 'Das Erste Mediathek [ARD]: Vertrauen ist gut, Spionieren ist besser - Geht so deutsch-amerikanische Freundschaft?, Anne Will, Über die Spionage-Affäre diskutieren Clemens Binninger, Katrin Göring-Eckardt, Georg Mascolo, Andrew B. Denison und Constanze Kurz.. Das Video zur Sendung Anne Will am Mittwoch, 16.07.2014', }, 'skip': 'Blocked outside of Germany', - } + }, { + 'url': 'http://www.ardmediathek.de/tv/Tatort/Das-Wunder-von-Wolbeck-Video-tgl-ab-20/Das-Erste/Video?documentId=22490580&bcastId=602916', + 'info_dict': { + 'id': '22490580', + 'ext': 'mp4', + 'title': 'Das Wunder von Wolbeck (Video tgl. ab 20 Uhr)', + 'description': 'Auf einem restaurierten Hof bei Wolbeck wird der Heilpraktiker Raffael Lembeck eines morgens von seiner Frau Stella tot aufgefunden. Das Opfer war offensichtlich in seiner Praxis zu Fall gekommen und ist dann verblutet, erklärt Prof. Boerne am Tatort.', + }, + 'skip': 'Blocked outside of Germany', + }] def _real_extract(self, url): # determine video id from url @@ -35,42 +46,78 @@ class ARDIE(InfoExtractor): else: video_id = m.group('video_id') + urlp = compat_urllib_parse_urlparse(url) + url = urlp._replace(path=compat_urllib_parse.quote(urlp.path.encode('utf-8'))).geturl() + webpage = self._download_webpage(url, video_id) + if '>Der gewünschte Beitrag ist nicht mehr verfügbar.<' in webpage: + raise ExtractorError('Video %s is no longer available' % video_id, expected=True) + title = self._html_search_regex( - r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>', webpage, 'title') + [r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>', + r'<meta name="dcterms.title" content="(.*?)"/>', + r'<h4 class="headline">(.*?)</h4>'], + webpage, 'title') description = self._html_search_meta( - 'dcterms.abstract', webpage, 'description') - thumbnail = self._og_search_thumbnail(webpage) - - streams = [ - mo.groupdict() - for mo in re.finditer( - r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)', webpage)] - if not streams: - if '"fsk"' in webpage: - raise ExtractorError('This video is only available after 20:00') - - formats = [] - for s in streams: - format = { - 'quality': int(s['quality']), - } - if s.get('rtmp_url'): - format['protocol'] = 'rtmp' - format['url'] = s['rtmp_url'] - format['playpath'] = s['video_url'] - else: - format['url'] = s['video_url'] - - quality_name = self._search_regex( - r'[,.]([a-zA-Z0-9_-]+),?\.mp4', format['url'], - 'quality name', default='NA') - format['format_id'] = '%s-%s-%s-%s' % ( - determine_ext(format['url']), quality_name, s['media_type'], - s['quality']) - - formats.append(format) + 'dcterms.abstract', webpage, 'description', default=None) + if description is None: + description = self._html_search_meta( + 'description', webpage, 'meta description') + + # Thumbnail is sometimes not present. + # It is in the mobile version, but that seems to use a different URL + # structure altogether. + thumbnail = self._og_search_thumbnail(webpage, default=None) + + media_streams = re.findall(r'''(?x) + mediaCollection\.addMediaStream\([0-9]+,\s*[0-9]+,\s*"[^"]*",\s* + "([^"]+)"''', webpage) + + if media_streams: + QUALITIES = qualities(['lo', 'hi', 'hq']) + formats = [] + for furl in set(media_streams): + if furl.endswith('.f4m'): + fid = 'f4m' + else: + fid_m = re.match(r'.*\.([^.]+)\.[^.]+$', furl) + fid = fid_m.group(1) if fid_m else None + formats.append({ + 'quality': QUALITIES(fid), + 'format_id': fid, + 'url': furl, + }) + else: # request JSON file + media_info = self._download_json( + 'http://www.ardmediathek.de/play/media/%s' % video_id, video_id) + # The second element of the _mediaArray contains the standard http urls + streams = media_info['_mediaArray'][1]['_mediaStreamArray'] + if not streams: + if '"fsk"' in webpage: + raise ExtractorError('This video is only available after 20:00') + + formats = [] + for s in streams: + if type(s['_stream']) == list: + for index, url in enumerate(s['_stream'][::-1]): + quality = s['_quality'] + index + formats.append({ + 'quality': quality, + 'url': url, + 'format_id': '%s-%s' % (determine_ext(url), quality) + }) + continue + + format = { + 'quality': s['_quality'], + 'url': s['_stream'], + } + + format['format_id'] = '%s-%s' % ( + determine_ext(format['url']), format['quality']) + + formats.append(format) self._sort_formats(formats) diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index b528a9ec5..d86dbba8e 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -39,7 +39,10 @@ class ArteTvIE(InfoExtractor): formats = [{ 'forma_id': q.attrib['quality'], - 'url': q.text, + # The playpath starts at 'mp4:', if we don't manually + # split the url, rtmpdump will incorrectly parse them + 'url': q.text.split('mp4:', 1)[0], + 'play_path': 'mp4:' + q.text.split('mp4:', 1)[1], 'ext': 'flv', 'quality': 2 if q.attrib['quality'] == 'hd' else 1, } for q in config.findall('./urls/url')] @@ -106,15 +109,19 @@ class ArteTVPlus7IE(InfoExtractor): regexes = [r'VO?%s' % l, r'VO?.-ST%s' % l] return any(re.match(r, f['versionCode']) for r in regexes) # Some formats may not be in the same language as the url + # TODO: Might want not to drop videos that does not match requested language + # but to process those formats with lower precedence formats = filter(_match_lang, all_formats) - formats = list(formats) # in python3 filter returns an iterator + formats = list(formats) # in python3 filter returns an iterator if not formats: # Some videos are only available in the 'Originalversion' # they aren't tagged as being in French or German - if all(f['versionCode'] == 'VO' for f in all_formats): - formats = all_formats - else: - raise ExtractorError(u'The formats list is empty') + # Sometimes there are neither videos of requested lang code + # nor original version videos available + # For such cases we just take all_formats as is + formats = all_formats + if not formats: + raise ExtractorError('The formats list is empty') if re.match(r'[A-Z]Q', formats[0]['quality']) is not None: def sort_key(f): @@ -189,9 +196,10 @@ class ArteTVFutureIE(ArteTVPlus7IE): _TEST = { 'url': 'http://future.arte.tv/fr/sujet/info-sciences#article-anchor-7081', 'info_dict': { - 'id': '050940-003', + 'id': '5201', 'ext': 'mp4', 'title': 'Les champignons au secours de la planète', + 'upload_date': '20131101', }, } diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py index 929aafdff..dcbbdef43 100644 --- a/youtube_dl/extractor/bandcamp.py +++ b/youtube_dl/extractor/bandcamp.py @@ -19,7 +19,7 @@ class BandcampIE(InfoExtractor): 'md5': 'c557841d5e50261777a6585648adf439', 'info_dict': { "title": "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad", - "duration": 10, + "duration": 9.8485, }, '_skip': 'There is a limit of 200 free downloads / month for the test song' }] @@ -28,36 +28,32 @@ class BandcampIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) title = mobj.group('title') webpage = self._download_webpage(url, title) - # We get the link to the free download page m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage) - if m_download is None: + if not m_download: m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage) if m_trackinfo: json_code = m_trackinfo.group(1) - data = json.loads(json_code) - d = data[0] + data = json.loads(json_code)[0] - duration = int(round(d['duration'])) formats = [] - for format_id, format_url in d['file'].items(): - ext, _, abr_str = format_id.partition('-') - + for format_id, format_url in data['file'].items(): + ext, abr_str = format_id.split('-', 1) formats.append({ 'format_id': format_id, 'url': format_url, - 'ext': format_id.partition('-')[0], + 'ext': ext, 'vcodec': 'none', - 'acodec': format_id.partition('-')[0], - 'abr': int(format_id.partition('-')[2]), + 'acodec': ext, + 'abr': int(abr_str), }) self._sort_formats(formats) return { - 'id': compat_str(d['id']), - 'title': d['title'], + 'id': compat_str(data['id']), + 'title': data['title'], 'formats': formats, - 'duration': duration, + 'duration': float(data['duration']), } else: raise ExtractorError('No free songs found') @@ -67,11 +63,9 @@ class BandcampIE(InfoExtractor): r'var TralbumData = {(.*?)id: (?P<id>\d*?)$', webpage, re.MULTILINE | re.DOTALL).group('id') - download_webpage = self._download_webpage(download_link, video_id, - 'Downloading free downloads page') - # We get the dictionary of the track from some javascrip code - info = re.search(r'items: (.*?),$', - download_webpage, re.MULTILINE).group(1) + download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page') + # We get the dictionary of the track from some javascript code + info = re.search(r'items: (.*?),$', download_webpage, re.MULTILINE).group(1) info = json.loads(info)[0] # We pick mp3-320 for now, until format selection can be easily implemented. mp3_info = info['downloads']['mp3-320'] @@ -100,7 +94,7 @@ class BandcampIE(InfoExtractor): class BandcampAlbumIE(InfoExtractor): IE_NAME = 'Bandcamp:album' - _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))?' + _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))' _TEST = { 'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1', @@ -123,7 +117,7 @@ class BandcampAlbumIE(InfoExtractor): 'params': { 'playlistend': 2 }, - 'skip': 'Bancamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test' + 'skip': 'Bandcamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test' } def _real_extract(self, url): diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py index 45067b944..0d5889f5d 100644 --- a/youtube_dl/extractor/bilibili.py +++ b/youtube_dl/extractor/bilibili.py @@ -13,7 +13,7 @@ from ..utils import ( class BiliBiliIE(InfoExtractor): - _VALID_URL = r'http://www\.bilibili\.tv/video/av(?P<id>[0-9]+)/' + _VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>[0-9]+)/' _TEST = { 'url': 'http://www.bilibili.tv/video/av1074402/', @@ -56,7 +56,7 @@ class BiliBiliIE(InfoExtractor): 'thumbnailUrl', video_code, 'thumbnail', fatal=False) player_params = compat_parse_qs(self._html_search_regex( - r'<iframe .*?class="player" src="https://secure.bilibili.tv/secure,([^"]+)"', + r'<iframe .*?class="player" src="https://secure\.bilibili\.(?:tv|com)/secure,([^"]+)"', webpage, 'player params')) if 'cid' in player_params: diff --git a/youtube_dl/extractor/blinkx.py b/youtube_dl/extractor/blinkx.py index 96408e4e0..3e461e715 100644 --- a/youtube_dl/extractor/blinkx.py +++ b/youtube_dl/extractor/blinkx.py @@ -1,13 +1,10 @@ from __future__ import unicode_literals -import datetime import json import re from .common import InfoExtractor -from ..utils import ( - remove_start, -) +from ..utils import remove_start class BlinkxIE(InfoExtractor): @@ -16,18 +13,21 @@ class BlinkxIE(InfoExtractor): _TEST = { 'url': 'http://www.blinkx.com/ce/8aQUy7GVFYgFzpKhT0oqsilwOGFRVXk3R1ZGWWdGenBLaFQwb3FzaWx3OGFRVXk3R1ZGWWdGenB', - 'file': '8aQUy7GV.mp4', 'md5': '2e9a07364af40163a908edbf10bb2492', 'info_dict': { - "title": "Police Car Rolls Away", - "uploader": "stupidvideos.com", - "upload_date": "20131215", - "description": "A police car gently rolls away from a fight. Maybe it felt weird being around a confrontation and just had to get out of there!", - "duration": 14.886, - "thumbnails": [{ - "width": 100, - "height": 76, - "url": "http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg", + 'id': '8aQUy7GV', + 'ext': 'mp4', + 'title': 'Police Car Rolls Away', + 'uploader': 'stupidvideos.com', + 'upload_date': '20131215', + 'timestamp': 1387068000, + 'description': 'A police car gently rolls away from a fight. Maybe it felt weird being around a confrontation and just had to get out of there!', + 'duration': 14.886, + 'thumbnails': [{ + 'width': 100, + 'height': 76, + 'resolution': '100x76', + 'url': 'http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg', }], }, } @@ -37,13 +37,10 @@ class BlinkxIE(InfoExtractor): video_id = m.group('id') display_id = video_id[:8] - api_url = (u'https://apib4.blinkx.com/api.php?action=play_video&' + + api_url = ('https://apib4.blinkx.com/api.php?action=play_video&' + 'video=%s' % video_id) data_json = self._download_webpage(api_url, display_id) data = json.loads(data_json)['api']['results'][0] - dt = datetime.datetime.fromtimestamp(data['pubdate_epoch']) - pload_date = dt.strftime('%Y%m%d') - duration = None thumbnails = [] formats = [] @@ -55,19 +52,16 @@ class BlinkxIE(InfoExtractor): 'height': int(m['h']), }) elif m['type'] == 'original': - duration = m['d'] + duration = float(m['d']) elif m['type'] == 'youtube': yt_id = m['link'] - self.to_screen(u'Youtube video detected: %s' % yt_id) + self.to_screen('Youtube video detected: %s' % yt_id) return self.url_result(yt_id, 'Youtube', video_id=yt_id) elif m['type'] in ('flv', 'mp4'): vcodec = remove_start(m['vcodec'], 'ff') acodec = remove_start(m['acodec'], 'ff') tbr = (int(m['vbr']) + int(m['abr'])) // 1000 - format_id = (u'%s-%sk-%s' % - (vcodec, - tbr, - m['w'])) + format_id = '%s-%sk-%s' % (vcodec, tbr, m['w']) formats.append({ 'format_id': format_id, 'url': m['link'], @@ -88,7 +82,7 @@ class BlinkxIE(InfoExtractor): 'title': data['title'], 'formats': formats, 'uploader': data['channel_name'], - 'upload_date': pload_date, + 'timestamp': data['pubdate_epoch'], 'description': data.get('description'), 'thumbnails': thumbnails, 'duration': duration, diff --git a/youtube_dl/extractor/bliptv.py b/youtube_dl/extractor/bliptv.py index d4da08991..acfc4ad73 100644 --- a/youtube_dl/extractor/bliptv.py +++ b/youtube_dl/extractor/bliptv.py @@ -15,7 +15,7 @@ from ..utils import ( class BlipTVIE(SubtitlesInfoExtractor): - _VALID_URL = r'https?://(?:\w+\.)?blip\.tv/(?:(?:.+-|rss/flash/)(?P<id>\d+)|((?:play/|api\.swf#)(?P<lookup_id>[\da-zA-Z]+)))' + _VALID_URL = r'https?://(?:\w+\.)?blip\.tv/(?:(?:.+-|rss/flash/)(?P<id>\d+)|((?:play/|api\.swf#)(?P<lookup_id>[\da-zA-Z+]+)))' _TESTS = [ { diff --git a/youtube_dl/extractor/bloomberg.py b/youtube_dl/extractor/bloomberg.py index 25fb79e14..c51a97ce4 100644 --- a/youtube_dl/extractor/bloomberg.py +++ b/youtube_dl/extractor/bloomberg.py @@ -10,7 +10,7 @@ class BloombergIE(InfoExtractor): _TEST = { 'url': 'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html', - 'md5': '7bf08858ff7c203c870e8a6190e221e5', + # The md5 checksum changes 'info_dict': { 'id': 'qurhIVlJSB6hzkVi229d8g', 'ext': 'flv', @@ -31,8 +31,7 @@ class BloombergIE(InfoExtractor): return { 'id': name.split('-')[-1], 'title': title, - 'url': f4m_url, - 'ext': 'flv', + 'formats': self._extract_f4m_formats(f4m_url, name), 'description': self._og_search_description(webpage), 'thumbnail': self._og_search_thumbnail(webpage), } diff --git a/youtube_dl/extractor/br.py b/youtube_dl/extractor/br.py index b5b56ff00..86f0c2861 100644 --- a/youtube_dl/extractor/br.py +++ b/youtube_dl/extractor/br.py @@ -7,25 +7,25 @@ from .common import InfoExtractor from ..utils import ( ExtractorError, int_or_none, + parse_duration, ) class BRIE(InfoExtractor): IE_DESC = 'Bayerischer Rundfunk Mediathek' - _VALID_URL = r'https?://(?:www\.)?br\.de/(?:[a-z0-9\-]+/)+(?P<id>[a-z0-9\-]+)\.html' + _VALID_URL = r'https?://(?:www\.)?br\.de/(?:[a-z0-9\-_]+/)+(?P<id>[a-z0-9\-_]+)\.html' _BASE_URL = 'http://www.br.de' _TESTS = [ { - 'url': 'http://www.br.de/mediathek/video/anselm-gruen-114.html', - 'md5': 'c4f83cf0f023ba5875aba0bf46860df2', + 'url': 'http://www.br.de/mediathek/video/sendungen/heimatsound/heimatsound-festival-2014-trailer-100.html', + 'md5': '93556dd2bcb2948d9259f8670c516d59', 'info_dict': { - 'id': '2c8d81c5-6fb7-4a74-88d4-e768e5856532', + 'id': '25e279aa-1ffd-40fd-9955-5325bd48a53a', 'ext': 'mp4', - 'title': 'Feiern und Verzichten', - 'description': 'Anselm Grün: Feiern und Verzichten', - 'uploader': 'BR/Birgit Baier', - 'upload_date': '20140301', + 'title': 'Wenn das Traditions-Theater wackelt', + 'description': 'Heimatsound-Festival 2014: Wenn das Traditions-Theater wackelt', + 'duration': 34, } }, { @@ -36,6 +36,7 @@ class BRIE(InfoExtractor): 'ext': 'mp4', 'title': 'Über den Pass', 'description': 'Die Eroberung der Alpen: Über den Pass', + 'duration': 2588, } }, { @@ -46,6 +47,7 @@ class BRIE(InfoExtractor): 'ext': 'aac', 'title': '"Keine neuen Schulden im nächsten Jahr"', 'description': 'Haushaltsentwurf: "Keine neuen Schulden im nächsten Jahr"', + 'duration': 64, } }, { @@ -56,6 +58,7 @@ class BRIE(InfoExtractor): 'ext': 'mp4', 'title': 'Umweltbewusster Häuslebauer', 'description': 'Uwe Erdelt: Umweltbewusster Häuslebauer', + 'duration': 116, } }, { @@ -66,6 +69,7 @@ class BRIE(InfoExtractor): 'ext': 'mp4', 'title': 'Folge 1 - Metaphysik', 'description': 'Kant für Anfänger: Folge 1 - Metaphysik', + 'duration': 893, 'uploader': 'Eva Maria Steimle', 'upload_date': '20140117', } @@ -86,6 +90,7 @@ class BRIE(InfoExtractor): media = { 'id': xml_media.get('externalId'), 'title': xml_media.find('title').text, + 'duration': parse_duration(xml_media.find('duration').text), 'formats': self._extract_formats(xml_media.find('assets')), 'thumbnails': self._extract_thumbnails(xml_media.find('teaserImage/variants')), 'description': ' '.join(xml_media.find('shareTitle').text.splitlines()), diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 3c02c297a..419951b62 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -15,6 +15,7 @@ from ..utils import ( compat_urllib_request, compat_parse_qs, + determine_ext, ExtractorError, unsmuggle_url, unescapeHTML, @@ -29,10 +30,11 @@ class BrightcoveIE(InfoExtractor): { # From http://www.8tv.cat/8aldia/videos/xavier-sala-i-martin-aquesta-tarda-a-8-al-dia/ 'url': 'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1654948606001&flashID=myExperience&%40videoPlayer=2371591881001', - 'file': '2371591881001.mp4', 'md5': '5423e113865d26e40624dce2e4b45d95', 'note': 'Test Brightcove downloads and detection in GenericIE', 'info_dict': { + 'id': '2371591881001', + 'ext': 'mp4', 'title': 'Xavier Sala i Martín: “Un banc que no presta és un banc zombi que no serveix per a res”', 'uploader': '8TV', 'description': 'md5:a950cc4285c43e44d763d036710cd9cd', @@ -41,8 +43,9 @@ class BrightcoveIE(InfoExtractor): { # From http://medianetwork.oracle.com/video/player/1785452137001 'url': 'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1217746023001&flashID=myPlayer&%40videoPlayer=1785452137001', - 'file': '1785452137001.flv', 'info_dict': { + 'id': '1785452137001', + 'ext': 'flv', 'title': 'JVMLS 2012: Arrays 2.0 - Opportunities and Challenges', 'description': 'John Rose speaks at the JVM Language Summit, August 1, 2012.', 'uploader': 'Oracle', @@ -70,7 +73,20 @@ class BrightcoveIE(InfoExtractor): 'description': 'md5:363109c02998fee92ec02211bd8000df', 'uploader': 'National Ballet of Canada', }, - } + }, + { + # test flv videos served by akamaihd.net + # From http://www.redbull.com/en/bike/stories/1331655643987/replay-uci-dh-world-cup-2014-from-fort-william + 'url': 'http://c.brightcove.com/services/viewer/htmlFederated?%40videoPlayer=ref%3ABC2996102916001&linkBaseURL=http%3A%2F%2Fwww.redbull.com%2Fen%2Fbike%2Fvideos%2F1331655630249%2Freplay-uci-fort-william-2014-dh&playerKey=AQ%7E%7E%2CAAAApYJ7UqE%7E%2Cxqr_zXk0I-zzNndy8NlHogrCb5QdyZRf&playerID=1398061561001#__youtubedl_smuggle=%7B%22Referer%22%3A+%22http%3A%2F%2Fwww.redbull.com%2Fen%2Fbike%2Fstories%2F1331655643987%2Freplay-uci-dh-world-cup-2014-from-fort-william%22%7D', + # The md5 checksum changes on each download + 'info_dict': { + 'id': '2996102916001', + 'ext': 'flv', + 'title': 'UCI MTB World Cup 2014: Fort William, UK - Downhill Finals', + 'uploader': 'Red Bull TV', + 'description': 'UCI MTB World Cup 2014: Fort William, UK - Downhill Finals', + }, + }, ] @classmethod @@ -187,7 +203,7 @@ class BrightcoveIE(InfoExtractor): webpage = self._download_webpage(req, video_id) self.report_extraction(video_id) - info = self._search_regex(r'var experienceJSON = ({.*?});', webpage, 'json') + info = self._search_regex(r'var experienceJSON = ({.*});', webpage, 'json') info = json.loads(info)['data'] video_info = info['programmedContent']['videoPlayer']['mediaDTO'] video_info['_youtubedl_adServerURL'] = info.get('adServerURL') @@ -219,12 +235,26 @@ class BrightcoveIE(InfoExtractor): renditions = video_info.get('renditions') if renditions: - renditions = sorted(renditions, key=lambda r: r['size']) - info['formats'] = [{ - 'url': rend['defaultURL'], - 'height': rend.get('frameHeight'), - 'width': rend.get('frameWidth'), - } for rend in renditions] + formats = [] + for rend in renditions: + url = rend['defaultURL'] + if rend['remote']: + # This type of renditions are served through akamaihd.net, + # but they don't use f4m manifests + url = url.replace('control/', '') + '?&v=3.3.0&fp=13&r=FEEFJ&g=RTSJIMBMPFPB' + ext = 'flv' + else: + ext = determine_ext(url) + size = rend.get('size') + formats.append({ + 'url': url, + 'ext': ext, + 'height': rend.get('frameHeight'), + 'width': rend.get('frameWidth'), + 'filesize': size if size != 0 else None, + }) + self._sort_formats(formats) + info['formats'] = formats elif video_info.get('FLVFullLengthURL') is not None: info.update({ 'url': video_info['FLVFullLengthURL'], diff --git a/youtube_dl/extractor/cbs.py b/youtube_dl/extractor/cbs.py index ac0315853..822f9a7be 100644 --- a/youtube_dl/extractor/cbs.py +++ b/youtube_dl/extractor/cbs.py @@ -1,24 +1,42 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor class CBSIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?cbs\.com/shows/[^/]+/video/(?P<id>[^/]+)/.*' + _VALID_URL = r'https?://(?:www\.)?cbs\.com/shows/[^/]+/(?:video|artist)/(?P<id>[^/]+)/.*' - _TEST = { - u'url': u'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/', - u'file': u'4JUVEwq3wUT7.flv', - u'info_dict': { - u'title': u'Connect Chat feat. Garth Brooks', - u'description': u'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!', - u'duration': 1495, + _TESTS = [{ + 'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/', + 'info_dict': { + 'id': '4JUVEwq3wUT7', + 'ext': 'flv', + 'title': 'Connect Chat feat. Garth Brooks', + 'description': 'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!', + 'duration': 1495, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + '_skip': 'Blocked outside the US', + }, { + 'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/', + 'info_dict': { + 'id': 'P9gjWjelt6iP', + 'ext': 'flv', + 'title': 'Live on Letterman - St. Vincent', + 'description': 'Live On Letterman: St. Vincent in concert from New York\'s Ed Sullivan Theater on Tuesday, July 16, 2014.', + 'duration': 3221, }, - u'params': { + 'params': { # rtmp download - u'skip_download': True, + 'skip_download': True, }, - } + '_skip': 'Blocked outside the US', + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -26,5 +44,5 @@ class CBSIE(InfoExtractor): webpage = self._download_webpage(url, video_id) real_id = self._search_regex( r"video\.settings\.pid\s*=\s*'([^']+)';", - webpage, u'real video ID') + webpage, 'real video ID') return self.url_result(u'theplatform:%s' % real_id) diff --git a/youtube_dl/extractor/chilloutzone.py b/youtube_dl/extractor/chilloutzone.py index 02d5ba527..a62395d4b 100644 --- a/youtube_dl/extractor/chilloutzone.py +++ b/youtube_dl/extractor/chilloutzone.py @@ -42,7 +42,7 @@ class ChilloutzoneIE(InfoExtractor): 'id': '85523671', 'ext': 'mp4', 'title': 'The Sunday Times - Icons', - 'description': 'md5:3e1c0dc6047498d6728dcdaad0891762', + 'description': 'md5:a5f7ff82e2f7a9ed77473fe666954e84', 'uploader': 'Us', 'uploader_id': 'usfilms', 'upload_date': '20140131' diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py index 2301f61b6..496271be4 100644 --- a/youtube_dl/extractor/cinemassacre.py +++ b/youtube_dl/extractor/cinemassacre.py @@ -1,10 +1,12 @@ # encoding: utf-8 from __future__ import unicode_literals + import re from .common import InfoExtractor from ..utils import ( ExtractorError, + int_or_none, ) @@ -13,9 +15,10 @@ class CinemassacreIE(InfoExtractor): _TESTS = [ { 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', - 'file': '19911.mp4', - 'md5': '782f8504ca95a0eba8fc9177c373eec7', + 'md5': 'fde81fbafaee331785f58cd6c0d46190', 'info_dict': { + 'id': '19911', + 'ext': 'mp4', 'upload_date': '20121110', 'title': '“Angry Video Game Nerd: The Movie” – Trailer', 'description': 'md5:fb87405fcb42a331742a0dce2708560b', @@ -23,9 +26,10 @@ class CinemassacreIE(InfoExtractor): }, { 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940', - 'file': '521be8ef82b16.mp4', - 'md5': 'dec39ee5118f8d9cc067f45f9cbe3a35', + 'md5': 'd72f10cd39eac4215048f62ab477a511', 'info_dict': { + 'id': '521be8ef82b16', + 'ext': 'mp4', 'upload_date': '20131002', 'title': 'The Mummy’s Hand (1940)', }, @@ -50,29 +54,40 @@ class CinemassacreIE(InfoExtractor): r'<div class="entry-content">(?P<description>.+?)</div>', webpage, 'description', flags=re.DOTALL, fatal=False) - playerdata = self._download_webpage(playerdata_url, video_id) + playerdata = self._download_webpage(playerdata_url, video_id, 'Downloading player webpage') + video_thumbnail = self._search_regex( + r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False) + sd_url = self._search_regex(r'file: \'([^\']+)\', label: \'SD\'', playerdata, 'sd_file') + videolist_url = self._search_regex(r'file: \'([^\']+\.smil)\'}', playerdata, 'videolist_url') - sd_url = self._html_search_regex(r'file: \'([^\']+)\', label: \'SD\'', playerdata, 'sd_file') - hd_url = self._html_search_regex( - r'file: \'([^\']+)\', label: \'HD\'', playerdata, 'hd_file', - default=None) - video_thumbnail = self._html_search_regex(r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False) + videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML') - formats = [{ - 'url': sd_url, - 'ext': 'mp4', - 'format': 'sd', - 'format_id': 'sd', - 'quality': 1, - }] - if hd_url: - formats.append({ - 'url': hd_url, - 'ext': 'mp4', - 'format': 'hd', - 'format_id': 'hd', - 'quality': 2, - }) + formats = [] + baseurl = sd_url[:sd_url.rfind('/')+1] + for video in videolist.findall('.//video'): + src = video.get('src') + if not src: + continue + file_ = src.partition(':')[-1] + width = int_or_none(video.get('width')) + height = int_or_none(video.get('height')) + bitrate = int_or_none(video.get('system-bitrate')) + format = { + 'url': baseurl + file_, + 'format_id': src.rpartition('.')[0].rpartition('_')[-1], + } + if width or height: + format.update({ + 'tbr': bitrate // 1000 if bitrate else None, + 'width': width, + 'height': height, + }) + else: + format.update({ + 'abr': bitrate // 1000 if bitrate else None, + 'vcodec': 'none', + }) + formats.append(format) self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/cmt.py b/youtube_dl/extractor/cmt.py index 88e0e9aba..e96c59f71 100644 --- a/youtube_dl/extractor/cmt.py +++ b/youtube_dl/extractor/cmt.py @@ -1,19 +1,19 @@ +from __future__ import unicode_literals from .mtv import MTVIE + class CMTIE(MTVIE): - IE_NAME = u'cmt.com' + IE_NAME = 'cmt.com' _VALID_URL = r'https?://www\.cmt\.com/videos/.+?/(?P<videoid>[^/]+)\.jhtml' _FEED_URL = 'http://www.cmt.com/sitewide/apps/player/embed/rss/' - _TESTS = [ - { - u'url': u'http://www.cmt.com/videos/garth-brooks/989124/the-call-featuring-trisha-yearwood.jhtml#artist=30061', - u'md5': u'e6b7ef3c4c45bbfae88061799bbba6c2', - u'info_dict': { - u'id': u'989124', - u'ext': u'mp4', - u'title': u'Garth Brooks - "The Call (featuring Trisha Yearwood)"', - u'description': u'Blame It All On My Roots', - }, + _TESTS = [{ + 'url': 'http://www.cmt.com/videos/garth-brooks/989124/the-call-featuring-trisha-yearwood.jhtml#artist=30061', + 'md5': 'e6b7ef3c4c45bbfae88061799bbba6c2', + 'info_dict': { + 'id': '989124', + 'ext': 'mp4', + 'title': 'Garth Brooks - "The Call (featuring Trisha Yearwood)"', + 'description': 'Blame It All On My Roots', }, - ] + }] diff --git a/youtube_dl/extractor/cnet.py b/youtube_dl/extractor/cnet.py index a94f42571..710d5009b 100644 --- a/youtube_dl/extractor/cnet.py +++ b/youtube_dl/extractor/cnet.py @@ -43,7 +43,11 @@ class CNETIE(InfoExtractor): raise ExtractorError('Cannot find video data') video_id = vdata['id'] - title = vdata['headline'] + title = vdata.get('headline') + if title is None: + title = vdata.get('title') + if title is None: + raise ExtractorError('Cannot find title!') description = vdata.get('dek') thumbnail = vdata.get('image', {}).get('path') author = vdata.get('author') diff --git a/youtube_dl/extractor/cnn.py b/youtube_dl/extractor/cnn.py index b32cb8980..dae40c136 100644 --- a/youtube_dl/extractor/cnn.py +++ b/youtube_dl/extractor/cnn.py @@ -79,8 +79,11 @@ class CNNIE(InfoExtractor): self._sort_formats(formats) - thumbnails = sorted([((int(t.attrib['height']),int(t.attrib['width'])), t.text) for t in info.findall('images/image')]) - thumbs_dict = [{'resolution': res, 'url': t_url} for (res, t_url) in thumbnails] + thumbnails = [{ + 'height': int(t.attrib['height']), + 'width': int(t.attrib['width']), + 'url': t.text, + } for t in info.findall('images/image')] metas_el = info.find('metas') upload_date = ( @@ -93,8 +96,7 @@ class CNNIE(InfoExtractor): 'id': info.attrib['id'], 'title': info.find('headline').text, 'formats': formats, - 'thumbnail': thumbnails[-1][1], - 'thumbnails': thumbs_dict, + 'thumbnails': thumbnails, 'description': info.find('description').text, 'duration': duration, 'upload_date': upload_date, diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py index 6e3a316c6..c81ce5a96 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -14,13 +14,13 @@ from ..utils import ( class ComedyCentralIE(MTVServicesInfoExtractor): - _VALID_URL = r'''(?x)https?://(?:www\.)?(comedycentral|cc)\.com/ - (video-clips|episodes|cc-studios|video-collections) + _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/ + (video-clips|episodes|cc-studios|video-collections|full-episodes) /(?P<title>.*)''' _FEED_URL = 'http://comedycentral.com/feeds/mrss/' _TEST = { - 'url': 'http://www.comedycentral.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother', + 'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother', 'md5': 'c4f48e9eda1b16dd10add0744344b6d8', 'info_dict': { 'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354', @@ -130,7 +130,7 @@ class ComedyCentralShowsIE(InfoExtractor): raise ExtractorError('Invalid redirected URL: ' + url) if mobj.group('episode') == '': raise ExtractorError('Redirected URL is still not specific: ' + url) - epTitle = mobj.group('episode').rpartition('/')[-1] + epTitle = (mobj.group('episode') or mobj.group('videotitle')).rpartition('/')[-1] mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage) if len(mMovieParams) == 0: @@ -188,7 +188,7 @@ class ComedyCentralShowsIE(InfoExtractor): }) formats.append({ 'format_id': 'rtmp-%s' % format, - 'url': rtmp_video_url, + 'url': rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm'), 'ext': self._video_extensions.get(format, 'mp4'), 'height': h, 'width': w, diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index db472aace..2e6eeac08 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1,11 +1,12 @@ import base64 import hashlib import json +import netrc import os import re import socket import sys -import netrc +import time import xml.etree.ElementTree from ..utils import ( @@ -17,6 +18,7 @@ from ..utils import ( clean_html, compiled_regex_type, ExtractorError, + int_or_none, RegexNotFoundError, sanitize_filename, unescapeHTML, @@ -68,6 +70,7 @@ class InfoExtractor(object): * vcodec Name of the video codec in use * container Name of the container format * filesize The number of bytes, if known in advance + * filesize_approx An estimate for the number of bytes * player_url SWF Player URL (used for rtmpdump). * protocol The protocol that will be used for the actual download, lower-case. @@ -92,8 +95,12 @@ class InfoExtractor(object): unique, but available before title. Typically, id is something like "4234987", title "Dancing naked mole rats", and display_id "dancing-naked-mole-rats" - thumbnails: A list of dictionaries (with the entries "resolution" and - "url") for the varying thumbnails + thumbnails: A list of dictionaries, with the following entries: + * "url" + * "width" (optional, int) + * "height" (optional, int) + * "resolution" (optional, string "{width}x{height"}, + deprecated) thumbnail: Full URL to a video thumbnail image. description: One-line video description. uploader: Full name of the video uploader. @@ -295,8 +302,12 @@ class InfoExtractor(object): def _download_json(self, url_or_request, video_id, note=u'Downloading JSON metadata', errnote=u'Unable to download JSON metadata', - transform_source=None): - json_string = self._download_webpage(url_or_request, video_id, note, errnote) + transform_source=None, + fatal=True): + json_string = self._download_webpage( + url_or_request, video_id, note, errnote, fatal=fatal) + if (not fatal) and json_string is False: + return None if transform_source: json_string = transform_source(json_string) try: @@ -363,7 +374,8 @@ class InfoExtractor(object): else: for p in pattern: mobj = re.search(p, string, flags) - if mobj: break + if mobj: + break if os.name != 'nt' and sys.stderr.isatty(): _name = u'\033[0;34m%s\033[0m' % name @@ -451,18 +463,22 @@ class InfoExtractor(object): return self._og_search_property('title', html, **kargs) def _og_search_video_url(self, html, name='video url', secure=True, **kargs): - regexes = self._og_regexes('video') - if secure: regexes = self._og_regexes('video:secure_url') + regexes + regexes = self._og_regexes('video') + self._og_regexes('video:url') + if secure: + regexes = self._og_regexes('video:secure_url') + regexes return self._html_search_regex(regexes, html, name, **kargs) - def _html_search_meta(self, name, html, display_name=None, fatal=False): + def _og_search_url(self, html, **kargs): + return self._og_search_property('url', html, **kargs) + + def _html_search_meta(self, name, html, display_name=None, fatal=False, **kwargs): if display_name is None: display_name = name return self._html_search_regex( r'''(?ix)<meta - (?=[^>]+(?:itemprop|name|property)=["\']%s["\']) + (?=[^>]+(?:itemprop|name|property)=["\']?%s["\']?) [^>]+content=["\']([^"\']+)["\']''' % re.escape(name), - html, display_name, fatal=fatal) + html, display_name, fatal=fatal, **kwargs) def _dc_search_uploader(self, html): return self._html_search_meta('dc.creator', html, 'uploader') @@ -547,6 +563,7 @@ class InfoExtractor(object): f.get('abr') if f.get('abr') is not None else -1, audio_ext_preference, f.get('filesize') if f.get('filesize') is not None else -1, + f.get('filesize_approx') if f.get('filesize_approx') is not None else -1, f.get('format_id'), ) formats.sort(key=_formats_key) @@ -568,6 +585,31 @@ class InfoExtractor(object): else: return url + def _sleep(self, timeout, video_id, msg_template=None): + if msg_template is None: + msg_template = u'%(video_id)s: Waiting for %(timeout)s seconds' + msg = msg_template % {'video_id': video_id, 'timeout': timeout} + self.to_screen(msg) + time.sleep(timeout) + + def _extract_f4m_formats(self, manifest_url, video_id): + manifest = self._download_xml( + manifest_url, video_id, 'Downloading f4m manifest', + 'Unable to download f4m manifest') + + formats = [] + for media_el in manifest.findall('{http://ns.adobe.com/f4m/1.0}media'): + formats.append({ + 'url': manifest_url, + 'ext': 'flv', + 'tbr': int_or_none(media_el.attrib.get('bitrate')), + 'width': int_or_none(media_el.attrib.get('width')), + 'height': int_or_none(media_el.attrib.get('height')), + }) + self._sort_formats(formats) + + return formats + class SearchInfoExtractor(InfoExtractor): """ @@ -611,4 +653,3 @@ class SearchInfoExtractor(InfoExtractor): @property def SEARCH_KEY(self): return self._SEARCH_KEY - diff --git a/youtube_dl/extractor/cracked.py b/youtube_dl/extractor/cracked.py new file mode 100644 index 000000000..74b880ffc --- /dev/null +++ b/youtube_dl/extractor/cracked.py @@ -0,0 +1,65 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_iso8601, + str_to_int, +) + + +class CrackedIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?cracked\.com/video_(?P<id>\d+)_[\da-z-]+\.html' + _TEST = { + 'url': 'http://www.cracked.com/video_19006_4-plot-holes-you-didnt-notice-in-your-favorite-movies.html', + 'md5': '4b29a5eeec292cd5eca6388c7558db9e', + 'info_dict': { + 'id': '19006', + 'ext': 'mp4', + 'title': '4 Plot Holes You Didn\'t Notice in Your Favorite Movies', + 'description': 'md5:3b909e752661db86007d10e5ec2df769', + 'timestamp': 1405659600, + 'upload_date': '20140718', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex( + [r'var\s+CK_vidSrc\s*=\s*"([^"]+)"', r'<video\s+src="([^"]+)"'], webpage, 'video URL') + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + + timestamp = self._html_search_regex(r'<time datetime="([^"]+)"', webpage, 'upload date', fatal=False) + if timestamp: + timestamp = parse_iso8601(timestamp[:-6]) + + view_count = str_to_int(self._html_search_regex( + r'<span class="views" id="viewCounts">([\d,\.]+) Views</span>', webpage, 'view count', fatal=False)) + comment_count = str_to_int(self._html_search_regex( + r'<span id="commentCounts">([\d,\.]+)</span>', webpage, 'comment count', fatal=False)) + + m = re.search(r'_(?P<width>\d+)X(?P<height>\d+)\.mp4$', video_url) + if m: + width = int(m.group('width')) + height = int(m.group('height')) + else: + width = height = None + + return { + 'id': video_id, + 'url':video_url, + 'title': title, + 'description': description, + 'timestamp': timestamp, + 'view_count': view_count, + 'comment_count': comment_count, + 'height': height, + 'width': width, + }
\ No newline at end of file diff --git a/youtube_dl/extractor/criterion.py b/youtube_dl/extractor/criterion.py index 31fe3d57b..4fb178165 100644 --- a/youtube_dl/extractor/criterion.py +++ b/youtube_dl/extractor/criterion.py @@ -1,40 +1,43 @@ # -*- coding: utf-8 -*- +from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import determine_ext + class CriterionIE(InfoExtractor): - _VALID_URL = r'https?://www\.criterion\.com/films/(\d*)-.+' + _VALID_URL = r'https?://www\.criterion\.com/films/(?P<id>[0-9]+)-.+' _TEST = { - u'url': u'http://www.criterion.com/films/184-le-samourai', - u'file': u'184.mp4', - u'md5': u'bc51beba55685509883a9a7830919ec3', - u'info_dict': { - u"title": u"Le Samouraï", - u"description" : u'md5:a2b4b116326558149bef81f76dcbb93f', + 'url': 'http://www.criterion.com/films/184-le-samourai', + 'md5': 'bc51beba55685509883a9a7830919ec3', + 'info_dict': { + 'id': '184', + 'ext': 'mp4', + 'title': 'Le Samouraï', + 'description': 'md5:a2b4b116326558149bef81f76dcbb93f', } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) + video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - final_url = self._search_regex(r'so.addVariable\("videoURL", "(.+?)"\)\;', - webpage, 'video url') - title = self._html_search_regex(r'<meta content="(.+?)" property="og:title" />', - webpage, 'video title') - description = self._html_search_regex(r'<meta name="description" content="(.+?)" />', - webpage, 'video description') - thumbnail = self._search_regex(r'so.addVariable\("thumbnailURL", "(.+?)"\)\;', - webpage, 'thumbnail url') + final_url = self._search_regex( + r'so.addVariable\("videoURL", "(.+?)"\)\;', webpage, 'video url') + title = self._og_search_title(webpage) + description = self._html_search_regex( + r'<meta name="description" content="(.+?)" />', + webpage, 'video description') + thumbnail = self._search_regex( + r'so.addVariable\("thumbnailURL", "(.+?)"\)\;', + webpage, 'thumbnail url') - return {'id': video_id, - 'url' : final_url, - 'title': title, - 'ext': determine_ext(final_url), - 'description': description, - 'thumbnail': thumbnail, - } + return { + 'id': video_id, + 'url': final_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 55216201f..5d0bfe454 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -150,7 +150,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): return { 'id': video_id, 'formats': formats, - 'uploader': info['owner_screenname'], + 'uploader': info['owner.screenname'], 'upload_date': video_upload_date, 'title': self._og_search_title(webpage), 'subtitles': video_subtitles, diff --git a/youtube_dl/extractor/dfb.py b/youtube_dl/extractor/dfb.py new file mode 100644 index 000000000..8049779b0 --- /dev/null +++ b/youtube_dl/extractor/dfb.py @@ -0,0 +1,44 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class DFBIE(InfoExtractor): + IE_NAME = 'tv.dfb.de' + _VALID_URL = r'https?://tv\.dfb\.de/video/[^/]+/(?P<id>\d+)' + + _TEST = { + 'url': 'http://tv.dfb.de/video/highlights-des-empfangs-in-berlin/9070/', + # The md5 is different each time + 'info_dict': { + 'id': '9070', + 'ext': 'flv', + 'title': 'Highlights des Empfangs in Berlin', + 'upload_date': '20140716', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + player_info = self._download_xml( + 'http://tv.dfb.de/server/hd_video.php?play=%s' % video_id, + video_id) + video_info = player_info.find('video') + + f4m_info = self._download_xml(self._proto_relative_url(video_info.find('url').text.strip()), video_id) + token_el = f4m_info.find('token') + manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + '&hdcore=3.2.0' + + return { + 'id': video_id, + 'title': video_info.find('title').text, + 'url': manifest_url, + 'ext': 'flv', + 'thumbnail': self._og_search_thumbnail(webpage), + 'upload_date': ''.join(video_info.find('time_date').text.split('.')[::-1]), + } diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py index 2ae6ecc12..554df6735 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -7,9 +7,9 @@ from .common import InfoExtractor class DiscoveryIE(InfoExtractor): - _VALID_URL = r'http://dsc\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?' + _VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?' _TEST = { - 'url': 'http://dsc.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm', + 'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm', 'md5': 'e12614f9ee303a6ccef415cb0793eba2', 'info_dict': { 'id': '614784', diff --git a/youtube_dl/extractor/dreisat.py b/youtube_dl/extractor/dreisat.py index 0b11d1f10..69ca75423 100644 --- a/youtube_dl/extractor/dreisat.py +++ b/youtube_dl/extractor/dreisat.py @@ -1,39 +1,37 @@ -# coding: utf-8 +from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - unified_strdate, -) +from ..utils import unified_strdate class DreiSatIE(InfoExtractor): IE_NAME = '3sat' _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$' _TEST = { - u"url": u"http://www.3sat.de/mediathek/index.php?obj=36983", - u'file': u'36983.mp4', - u'md5': u'9dcfe344732808dbfcc901537973c922', - u'info_dict': { - u"title": u"Kaffeeland Schweiz", - u"description": u"Über 80 Kaffeeröstereien liefern in der Schweiz das Getränk, in das das Land so vernarrt ist: Mehr als 1000 Tassen trinkt ein Schweizer pro Jahr. SCHWEIZWEIT nimmt die Kaffeekultur unter die...", - u"uploader": u"3sat", - u"upload_date": u"20130622" + 'url': 'http://www.3sat.de/mediathek/index.php?obj=36983', + 'md5': '9dcfe344732808dbfcc901537973c922', + 'info_dict': { + 'id': '36983', + 'ext': 'mp4', + 'title': 'Kaffeeland Schweiz', + 'description': 'md5:cc4424b18b75ae9948b13929a0814033', + 'uploader': '3sat', + 'upload_date': '20130622' } } - def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id - details_doc = self._download_xml(details_url, video_id, note=u'Downloading video details') + details_doc = self._download_xml(details_url, video_id, 'Downloading video details') thumbnail_els = details_doc.findall('.//teaserimage') thumbnails = [{ - 'width': te.attrib['key'].partition('x')[0], - 'height': te.attrib['key'].partition('x')[2], + 'width': int(te.attrib['key'].partition('x')[0]), + 'height': int(te.attrib['key'].partition('x')[2]), 'url': te.text, } for te in thumbnail_els] diff --git a/youtube_dl/extractor/dropbox.py b/youtube_dl/extractor/dropbox.py index 41208c976..9f569aa93 100644 --- a/youtube_dl/extractor/dropbox.py +++ b/youtube_dl/extractor/dropbox.py @@ -5,24 +5,26 @@ import os.path import re from .common import InfoExtractor +from ..utils import compat_urllib_parse_unquote class DropboxIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?dropbox[.]com/s/(?P<id>[a-zA-Z0-9]{15})/(?P<title>[^?#]*)' _TEST = { - 'url': 'https://www.dropbox.com/s/0qr9sai2veej4f8/THE_DOCTOR_GAMES.mp4', - 'md5': '8ae17c51172fb7f93bdd6a214cc8c896', + 'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4', + 'md5': '8a3d905427a6951ccb9eb292f154530b', 'info_dict': { - 'id': '0qr9sai2veej4f8', + 'id': 'nelirfsxnmcfbfh', 'ext': 'mp4', - 'title': 'THE_DOCTOR_GAMES' + 'title': 'youtube-dl test video \'ä"BaW_jenozKc' } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - title = os.path.splitext(mobj.group('title'))[0] + fn = compat_urllib_parse_unquote(mobj.group('title')) + title = os.path.splitext(fn)[0] video_url = url + '?dl=1' return { diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py new file mode 100644 index 000000000..cdccfd376 --- /dev/null +++ b/youtube_dl/extractor/drtv.py @@ -0,0 +1,91 @@ +from __future__ import unicode_literals + +import re + +from .subtitles import SubtitlesInfoExtractor +from .common import ExtractorError +from ..utils import parse_iso8601 + + +class DRTVIE(SubtitlesInfoExtractor): + _VALID_URL = r'http://(?:www\.)?dr\.dk/tv/se/[^/]+/(?P<id>[\da-z-]+)' + + _TEST = { + 'url': 'http://www.dr.dk/tv/se/partiets-mand/partiets-mand-7-8', + 'md5': '4a7e1dd65cdb2643500a3f753c942f25', + 'info_dict': { + 'id': 'partiets-mand-7-8', + 'ext': 'mp4', + 'title': 'Partiets mand (7:8)', + 'description': 'md5:a684b90a8f9336cd4aab94b7647d7862', + 'timestamp': 1403047940, + 'upload_date': '20140617', + 'duration': 1299.040, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + programcard = self._download_json( + 'http://www.dr.dk/mu/programcard/expanded/%s' % video_id, video_id, 'Downloading video JSON') + + data = programcard['Data'][0] + + title = data['Title'] + description = data['Description'] + timestamp = parse_iso8601(data['CreatedTime'][:-5]) + + thumbnail = None + duration = None + + restricted_to_denmark = False + + formats = [] + subtitles = {} + + for asset in data['Assets']: + if asset['Kind'] == 'Image': + thumbnail = asset['Uri'] + elif asset['Kind'] == 'VideoResource': + duration = asset['DurationInMilliseconds'] / 1000.0 + restricted_to_denmark = asset['RestrictedToDenmark'] + for link in asset['Links']: + target = link['Target'] + uri = link['Uri'] + formats.append({ + 'url': uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43' if target == 'HDS' else uri, + 'format_id': target, + 'ext': link['FileFormat'], + 'preference': -1 if target == 'HDS' else -2, + }) + subtitles_list = asset.get('SubtitlesList') + if isinstance(subtitles_list, list): + LANGS = { + 'Danish': 'dk', + } + for subs in subtitles_list: + lang = subs['Language'] + subtitles[LANGS.get(lang, lang)] = subs['Uri'] + + if not formats and restricted_to_denmark: + raise ExtractorError( + 'Unfortunately, DR is not allowed to show this program outside Denmark.', expected=True) + + self._sort_formats(formats) + + if self._downloader.params.get('listsubtitles', False): + self._list_available_subtitles(video_id, subtitles) + return + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'formats': formats, + 'subtitles': self.extract_subtitles(video_id, subtitles), + } diff --git a/youtube_dl/extractor/dump.py b/youtube_dl/extractor/dump.py new file mode 100644 index 000000000..6b651778a --- /dev/null +++ b/youtube_dl/extractor/dump.py @@ -0,0 +1,39 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class DumpIE(InfoExtractor): + _VALID_URL = r'^https?://(?:www\.)?dump\.com/(?P<id>[a-zA-Z0-9]+)/' + + _TEST = { + 'url': 'http://www.dump.com/oneus/', + 'md5': 'ad71704d1e67dfd9e81e3e8b42d69d99', + 'info_dict': { + 'id': 'oneus', + 'ext': 'flv', + 'title': "He's one of us.", + 'thumbnail': 're:^https?://.*\.jpg$', + }, + } + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url) + video_id = m.group('id') + + webpage = self._download_webpage(url, video_id) + video_url = self._search_regex( + r's1.addVariable\("file",\s*"([^"]+)"', webpage, 'video URL') + + thumb = self._og_search_thumbnail(webpage) + title = self._search_regex(r'<b>([^"]+)</b>', webpage, 'title') + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'thumbnail': thumb, + } diff --git a/youtube_dl/extractor/ellentv.py b/youtube_dl/extractor/ellentv.py new file mode 100644 index 000000000..3e7923648 --- /dev/null +++ b/youtube_dl/extractor/ellentv.py @@ -0,0 +1,79 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + parse_iso8601, +) + + +class EllenTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?ellentv\.com/videos/(?P<id>[a-z0-9_-]+)' + _TEST = { + 'url': 'http://www.ellentv.com/videos/0-7jqrsr18/', + 'md5': 'e4af06f3bf0d5f471921a18db5764642', + 'info_dict': { + 'id': '0-7jqrsr18', + 'ext': 'mp4', + 'title': 'What\'s Wrong with These Photos? A Whole Lot', + 'timestamp': 1406876400, + 'upload_date': '20140801', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + timestamp = parse_iso8601(self._search_regex( + r'<span class="publish-date"><time datetime="([^"]+)">', + webpage, 'timestamp')) + + return { + 'id': video_id, + 'title': self._og_search_title(webpage), + 'url': self._html_search_meta('VideoURL', webpage, 'url'), + 'timestamp': timestamp, + } + + +class EllenTVClipsIE(InfoExtractor): + IE_NAME = 'EllenTV:clips' + _VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)' + _TEST = { + 'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/', + 'info_dict': { + 'id': 'meryl-streep-vanessa-hudgens', + 'title': 'Meryl Streep, Vanessa Hudgens', + }, + 'playlist_mincount': 9, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + playlist_id = mobj.group('id') + + webpage = self._download_webpage(url, playlist_id) + playlist = self._extract_playlist(webpage) + + return { + '_type': 'playlist', + 'id': playlist_id, + 'title': self._og_search_title(webpage), + 'entries': self._extract_entries(playlist) + } + + def _extract_playlist(self, webpage): + json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json') + try: + return json.loads("[{" + json_string + "}]") + except ValueError as ve: + raise ExtractorError('Failed to download JSON', cause=ve) + + def _extract_entries(self, playlist): + return [self.url_result(item['url'], 'EllenTV') for item in playlist] diff --git a/youtube_dl/extractor/empflix.py b/youtube_dl/extractor/empflix.py index eaeee5a51..e6952588f 100644 --- a/youtube_dl/extractor/empflix.py +++ b/youtube_dl/extractor/empflix.py @@ -3,20 +3,18 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - ExtractorError, -) class EmpflixIE(InfoExtractor): _VALID_URL = r'^https?://www\.empflix\.com/videos/.*?-(?P<id>[0-9]+)\.html' _TEST = { 'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html', - 'md5': '5e5cc160f38ca9857f318eb97146e13e', + 'md5': 'b1bc15b6412d33902d6e5952035fcabc', 'info_dict': { 'id': '33051', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Amateur Finger Fuck', + 'description': 'Amateur solo finger fucking.', 'age_limit': 18, } } @@ -30,6 +28,8 @@ class EmpflixIE(InfoExtractor): video_title = self._html_search_regex( r'name="title" value="(?P<title>[^"]*)"', webpage, 'title') + video_description = self._html_search_regex( + r'name="description" value="([^"]*)"', webpage, 'description', fatal=False) cfg_url = self._html_search_regex( r'flashvars\.config = escape\("([^"]+)"', @@ -37,12 +37,18 @@ class EmpflixIE(InfoExtractor): cfg_xml = self._download_xml( cfg_url, video_id, note='Downloading metadata') - video_url = cfg_xml.find('videoLink').text + + formats = [ + { + 'url': item.find('videoLink').text, + 'format_id': item.find('res').text, + } for item in cfg_xml.findall('./quality/item') + ] return { 'id': video_id, - 'url': video_url, - 'ext': 'flv', 'title': video_title, + 'description': video_description, + 'formats': formats, 'age_limit': age_limit, } diff --git a/youtube_dl/extractor/escapist.py b/youtube_dl/extractor/escapist.py index 272dfe1f6..476fc22b9 100644 --- a/youtube_dl/extractor/escapist.py +++ b/youtube_dl/extractor/escapist.py @@ -36,7 +36,7 @@ class EscapistIE(InfoExtractor): r'<meta name="description" content="([^"]*)"', webpage, 'description', fatal=False) - playerUrl = self._og_search_video_url(webpage, name=u'player URL') + playerUrl = self._og_search_video_url(webpage, name='player URL') title = self._html_search_regex( r'<meta name="title" content="([^"]*)"', diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py index ff7c0cd3e..14a196ffc 100644 --- a/youtube_dl/extractor/extremetube.py +++ b/youtube_dl/extractor/extremetube.py @@ -37,7 +37,7 @@ class ExtremeTubeIE(InfoExtractor): webpage = self._download_webpage(req, video_id) video_title = self._html_search_regex( - r'<h1 [^>]*?title="([^"]+)"[^>]*>\1<', webpage, 'title') + r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title') uploader = self._html_search_regex( r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, 'uploader', fatal=False) diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index f0cd8f156..f7cf700b5 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -20,7 +20,7 @@ from ..utils import ( class FacebookIE(InfoExtractor): _VALID_URL = r'''(?x) https?://(?:\w+\.)?facebook\.com/ - (?:[^#?]*\#!/)? + (?:[^#]*?\#!/)? (?:video/video\.php|photo\.php|video/embed)\?(?:.*?) (?:v|video_id)=(?P<id>[0-9]+) (?:.*)''' diff --git a/youtube_dl/extractor/fc2.py b/youtube_dl/extractor/fc2.py index ca8993241..c663a0f81 100644 --- a/youtube_dl/extractor/fc2.py +++ b/youtube_dl/extractor/fc2.py @@ -13,7 +13,7 @@ from ..utils import ( class FC2IE(InfoExtractor): - _VALID_URL = r'^http://video\.fc2\.com/(?P<lang>[^/]+)/content/(?P<id>[^/]+)' + _VALID_URL = r'^http://video\.fc2\.com/((?P<lang>[^/]+)/)?content/(?P<id>[^/]+)' IE_NAME = 'fc2' _TEST = { 'url': 'http://video.fc2.com/en/content/20121103kUan1KHs', @@ -36,7 +36,7 @@ class FC2IE(InfoExtractor): thumbnail = self._og_search_thumbnail(webpage) refer = url.replace('/content/', '/a/content/') - mimi = hashlib.md5(video_id + '_gGddgPfeaf_gzyr').hexdigest() + mimi = hashlib.md5((video_id + '_gGddgPfeaf_gzyr').encode('utf-8')).hexdigest() info_url = ( "http://video.fc2.com/ginfo.php?mimi={1:s}&href={2:s}&v={0:s}&fversion=WIN%2011%2C6%2C602%2C180&from=2&otag=0&upid={0:s}&tk=null&". @@ -50,10 +50,13 @@ class FC2IE(InfoExtractor): raise ExtractorError('Error code: %s' % info['err_code'][0]) video_url = info['filepath'][0] + '?mid=' + info['mid'][0] + title_info = info.get('title') + if title_info: + title = title_info[0] return { 'id': video_id, - 'title': info['title'][0], + 'title': title, 'url': video_url, 'ext': 'flv', 'thumbnail': thumbnail, diff --git a/youtube_dl/extractor/firedrive.py b/youtube_dl/extractor/firedrive.py new file mode 100644 index 000000000..af439ccfe --- /dev/null +++ b/youtube_dl/extractor/firedrive.py @@ -0,0 +1,81 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_urllib_parse, + compat_urllib_request, +) + + +class FiredriveIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?firedrive\.com/' + \ + '(?:file|embed)/(?P<id>[0-9a-zA-Z]+)' + _FILE_DELETED_REGEX = r'<div class="removed_file_image">' + + _TESTS = [{ + 'url': 'https://www.firedrive.com/file/FEB892FA160EBD01', + 'md5': 'd5d4252f80ebeab4dc2d5ceaed1b7970', + 'info_dict': { + 'id': 'FEB892FA160EBD01', + 'ext': 'flv', + 'title': 'bbb_theora_486kbit.flv', + 'thumbnail': 're:^http://.*\.jpg$', + }, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + url = 'http://firedrive.com/file/%s' % video_id + + webpage = self._download_webpage(url, video_id) + + if re.search(self._FILE_DELETED_REGEX, webpage) is not None: + raise ExtractorError('Video %s does not exist' % video_id, + expected=True) + + fields = dict(re.findall(r'''(?x)<input\s+ + type="hidden"\s+ + name="([^"]+)"\s+ + value="([^"]*)" + ''', webpage)) + + post = compat_urllib_parse.urlencode(fields) + req = compat_urllib_request.Request(url, post) + req.add_header('Content-type', 'application/x-www-form-urlencoded') + + # Apparently, this header is required for confirmation to work. + req.add_header('Host', 'www.firedrive.com') + + webpage = self._download_webpage(req, video_id, + 'Downloading video page') + + title = self._search_regex(r'class="external_title_left">(.+)</div>', + webpage, 'title') + thumbnail = self._search_regex(r'image:\s?"(//[^\"]+)', webpage, + 'thumbnail', fatal=False) + if thumbnail is not None: + thumbnail = 'http:' + thumbnail + + ext = self._search_regex(r'type:\s?\'([^\']+)\',', + webpage, 'extension', fatal=False) + video_url = self._search_regex( + r'file:\s?loadURL\(\'(http[^\']+)\'\),', webpage, 'file url') + + formats = [{ + 'format_id': 'sd', + 'url': video_url, + 'ext': ext, + }] + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/firstpost.py b/youtube_dl/extractor/firstpost.py index eccd8dde9..0993af1c9 100644 --- a/youtube_dl/extractor/firstpost.py +++ b/youtube_dl/extractor/firstpost.py @@ -15,6 +15,7 @@ class FirstpostIE(InfoExtractor): 'id': '1025403', 'ext': 'mp4', 'title': 'India to launch indigenous aircraft carrier INS Vikrant today', + 'description': 'md5:feef3041cb09724e0bdc02843348f5f4', } } @@ -22,13 +23,16 @@ class FirstpostIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + page = self._download_webpage(url, video_id) + title = self._html_search_meta('twitter:title', page, 'title') + description = self._html_search_meta('twitter:description', page, 'title') + data = self._download_xml( 'http://www.firstpost.com/getvideoxml-%s.xml' % video_id, video_id, 'Downloading video XML') item = data.find('./playlist/item') thumbnail = item.find('./image').text - title = item.find('./title').text formats = [ { @@ -42,6 +46,7 @@ class FirstpostIE(InfoExtractor): return { 'id': video_id, 'title': title, + 'description': description, 'thumbnail': thumbnail, 'formats': formats, } diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index f3e0f38b7..1b0e8e5d5 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -19,17 +19,35 @@ class FranceTVBaseInfoExtractor(InfoExtractor): + video_id, video_id, 'Downloading XML config') manifest_url = info.find('videos/video/url').text - video_url = manifest_url.replace('manifest.f4m', 'index_2_av.m3u8') - video_url = video_url.replace('/z/', '/i/') + manifest_url = manifest_url.replace('/z/', '/i/') + + if manifest_url.startswith('rtmp'): + formats = [{'url': manifest_url, 'ext': 'flv'}] + else: + formats = [] + available_formats = self._search_regex(r'/[^,]*,(.*?),k\.mp4', manifest_url, 'available formats') + for index, format_descr in enumerate(available_formats.split(',')): + format_info = { + 'url': manifest_url.replace('manifest.f4m', 'index_%d_av.m3u8' % index), + 'ext': 'mp4', + } + m_resolution = re.search(r'(?P<width>\d+)x(?P<height>\d+)', format_descr) + if m_resolution is not None: + format_info.update({ + 'width': int(m_resolution.group('width')), + 'height': int(m_resolution.group('height')), + }) + formats.append(format_info) + thumbnail_path = info.find('image').text - return {'id': video_id, - 'ext': 'flv' if video_url.startswith('rtmp') else 'mp4', - 'url': video_url, - 'title': info.find('titre').text, - 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path), - 'description': info.find('synopsis').text, - } + return { + 'id': video_id, + 'title': info.find('titre').text, + 'formats': formats, + 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path), + 'description': info.find('synopsis').text, + } class PluzzIE(FranceTVBaseInfoExtractor): @@ -48,7 +66,7 @@ class PluzzIE(FranceTVBaseInfoExtractor): class FranceTvInfoIE(FranceTVBaseInfoExtractor): IE_NAME = 'francetvinfo.fr' - _VALID_URL = r'https?://www\.francetvinfo\.fr/.*/(?P<title>.+)\.html' + _VALID_URL = r'https?://(?:www|mobile)\.francetvinfo\.fr/.*/(?P<title>.+)\.html' _TESTS = [{ 'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html', @@ -211,7 +229,7 @@ class GenerationQuoiIE(InfoExtractor): class CultureboxIE(FranceTVBaseInfoExtractor): IE_NAME = 'culturebox.francetvinfo.fr' - _VALID_URL = r'https?://culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)' + _VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)' _TEST = { 'url': 'http://culturebox.francetvinfo.fr/einstein-on-the-beach-au-theatre-du-chatelet-146813', diff --git a/youtube_dl/extractor/funnyordie.py b/youtube_dl/extractor/funnyordie.py index 6e6b66660..721e5fce0 100644 --- a/youtube_dl/extractor/funnyordie.py +++ b/youtube_dl/extractor/funnyordie.py @@ -26,7 +26,7 @@ class FunnyOrDieIE(InfoExtractor): 'id': 'e402820827', 'ext': 'mp4', 'title': 'Please Use This Song (Jon Lajoie)', - 'description': 'md5:2ed27d364f5a805a6dba199faaf6681d', + 'description': 'Please use this to sell something. www.jonlajoie.com', 'thumbnail': 're:^http:.*\.jpg$', }, }] diff --git a/youtube_dl/extractor/gamekings.py b/youtube_dl/extractor/gamekings.py index 233398966..11fee3d31 100644 --- a/youtube_dl/extractor/gamekings.py +++ b/youtube_dl/extractor/gamekings.py @@ -15,7 +15,7 @@ class GamekingsIE(InfoExtractor): 'id': '20130811', 'ext': 'mp4', 'title': 'Phoenix Wright: Ace Attorney \u2013 Dual Destinies Review', - 'description': 'md5:632e61a9f97d700e83f43d77ddafb6a4', + 'description': 'md5:36fd701e57e8c15ac8682a2374c99731', } } diff --git a/youtube_dl/extractor/gameone.py b/youtube_dl/extractor/gameone.py new file mode 100644 index 000000000..b580f52fb --- /dev/null +++ b/youtube_dl/extractor/gameone.py @@ -0,0 +1,90 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + xpath_with_ns, + parse_iso8601 +) + +NAMESPACE_MAP = { + 'media': 'http://search.yahoo.com/mrss/', +} + +# URL prefix to download the mp4 files directly instead of streaming via rtmp +# Credits go to XBox-Maniac +# http://board.jdownloader.org/showpost.php?p=185835&postcount=31 +RAW_MP4_URL = 'http://cdn.riptide-mtvn.com/' + + +class GameOneIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?gameone\.de/tv/(?P<id>\d+)' + _TEST = { + 'url': 'http://www.gameone.de/tv/288', + 'md5': '136656b7fb4c9cb4a8e2d500651c499b', + 'info_dict': { + 'id': '288', + 'ext': 'mp4', + 'title': 'Game One - Folge 288', + 'duration': 1238, + 'thumbnail': 'http://s3.gameone.de/gameone/assets/video_metas/teaser_images/000/643/636/big/640x360.jpg', + 'description': 'FIFA-Pressepokal 2014, Star Citizen, Kingdom Come: Deliverance, Project Cars, Schöner Trants Nerdquiz Folge 2 Runde 1', + 'age_limit': 16, + 'upload_date': '20140513', + 'timestamp': 1399980122, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + og_video = self._og_search_video_url(webpage, secure=False) + description = self._html_search_meta('description', webpage) + age_limit = int( + self._search_regex( + r'age=(\d+)', + self._html_search_meta( + 'age-de-meta-label', + webpage), + 'age_limit', + '0')) + mrss_url = self._search_regex(r'mrss=([^&]+)', og_video, 'mrss') + + mrss = self._download_xml(mrss_url, video_id, 'Downloading mrss') + title = mrss.find('.//item/title').text + thumbnail = mrss.find('.//item/image').get('url') + timestamp = parse_iso8601(mrss.find('.//pubDate').text, delimiter=' ') + content = mrss.find(xpath_with_ns('.//media:content', NAMESPACE_MAP)) + content_url = content.get('url') + + content = self._download_xml( + content_url, + video_id, + 'Downloading media:content') + rendition_items = content.findall('.//rendition') + duration = int(rendition_items[0].get('duration')) + formats = [ + { + 'url': re.sub(r'.*/(r2)', RAW_MP4_URL + r'\1', r.find('./src').text), + 'width': int(r.get('width')), + 'height': int(r.get('height')), + 'tbr': int(r.get('bitrate')), + } + for r in rendition_items + ] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'duration': duration, + 'formats': formats, + 'description': description, + 'age_limit': age_limit, + 'timestamp': timestamp, + } diff --git a/youtube_dl/extractor/gamestar.py b/youtube_dl/extractor/gamestar.py new file mode 100644 index 000000000..50f8fc7e7 --- /dev/null +++ b/youtube_dl/extractor/gamestar.py @@ -0,0 +1,74 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_duration, + str_to_int, + unified_strdate, +) + + +class GameStarIE(InfoExtractor): + _VALID_URL = r'http://www\.gamestar\.de/videos/.*,(?P<id>[0-9]+)\.html' + _TEST = { + 'url': 'http://www.gamestar.de/videos/trailer,3/hobbit-3-die-schlacht-der-fuenf-heere,76110.html', + 'md5': '96974ecbb7fd8d0d20fca5a00810cea7', + 'info_dict': { + 'id': '76110', + 'ext': 'mp4', + 'title': 'Hobbit 3: Die Schlacht der Fünf Heere - Teaser-Trailer zum dritten Teil', + 'description': 'Der Teaser-Trailer zu Hobbit 3: Die Schlacht der Fünf Heere zeigt einige Szenen aus dem dritten Teil der Saga und kündigt den vollständigen Trailer an.', + 'thumbnail': 'http://images.gamestar.de/images/idgwpgsgp/bdb/2494525/600x.jpg', + 'upload_date': '20140728', + 'duration': 17 + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + og_title = self._og_search_title(webpage) + title = og_title.replace(' - Video bei GameStar.de', '').strip() + + url = 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id + + description = self._og_search_description(webpage).strip() + + thumbnail = self._proto_relative_url( + self._og_search_thumbnail(webpage), scheme='http:') + + upload_date = unified_strdate(self._html_search_regex( + r'<span style="float:left;font-size:11px;">Datum: ([0-9]+\.[0-9]+\.[0-9]+) ', + webpage, 'upload_date', fatal=False)) + + duration = parse_duration(self._html_search_regex( + r' Länge: ([0-9]+:[0-9]+)</span>', webpage, 'duration', + fatal=False)) + + view_count = str_to_int(self._html_search_regex( + r' Zuschauer: ([0-9\.]+) ', webpage, + 'view_count', fatal=False)) + + comment_count = int_or_none(self._html_search_regex( + r'>Kommentieren \(([0-9]+)\)</a>', webpage, 'comment_count', + fatal=False)) + + return { + 'id': video_id, + 'title': title, + 'url': url, + 'ext': 'mp4', + 'thumbnail': thumbnail, + 'description': description, + 'upload_date': upload_date, + 'duration': duration, + 'view_count': view_count, + 'comment_count': comment_count + } diff --git a/youtube_dl/extractor/gdcvault.py b/youtube_dl/extractor/gdcvault.py index 89d5994ee..de14ae1fb 100644 --- a/youtube_dl/extractor/gdcvault.py +++ b/youtube_dl/extractor/gdcvault.py @@ -8,6 +8,7 @@ from ..utils import ( compat_urllib_request, ) + class GDCVaultIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)/(?P<name>(\w|-)+)' _TESTS = [ @@ -31,6 +32,15 @@ class GDCVaultIE(InfoExtractor): 'skip_download': True, # Requires rtmpdump } }, + { + 'url': 'http://www.gdcvault.com/play/1015301/Thexder-Meets-Windows-95-or', + 'md5': 'a5eb77996ef82118afbbe8e48731b98e', + 'info_dict': { + 'id': '1015301', + 'ext': 'flv', + 'title': 'Thexder Meets Windows 95, or Writing Great Games in the Windows 95 Environment', + } + } ] def _parse_mp4(self, xml_description): @@ -103,18 +113,40 @@ class GDCVaultIE(InfoExtractor): webpage_url = 'http://www.gdcvault.com/play/' + video_id start_page = self._download_webpage(webpage_url, video_id) - xml_root = self._html_search_regex(r'<iframe src="(?P<xml_root>.*?)player.html.*?".*?</iframe>', start_page, 'xml root', None, False) + direct_url = self._search_regex( + r's1\.addVariable\("file",\s*encodeURIComponent\("(/[^"]+)"\)\);', + start_page, 'url', default=None) + if direct_url: + video_url = 'http://www.gdcvault.com/' + direct_url + title = self._html_search_regex( + r'<td><strong>Session Name</strong></td>\s*<td>(.*?)</td>', + start_page, 'title') + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'flv', + 'title': title, + } + xml_root = self._html_search_regex( + r'<iframe src="(?P<xml_root>.*?)player.html.*?".*?</iframe>', + start_page, 'xml root', default=None) if xml_root is None: # Probably need to authenticate - start_page = self._login(webpage_url, video_id) - if start_page is None: + login_res = self._login(webpage_url, video_id) + if login_res is None: self.report_warning('Could not login.') else: + start_page = login_res # Grab the url from the authenticated page - xml_root = self._html_search_regex(r'<iframe src="(?P<xml_root>.*?)player.html.*?".*?</iframe>', start_page, 'xml root') + xml_root = self._html_search_regex( + r'<iframe src="(.*?)player.html.*?".*?</iframe>', + start_page, 'xml root') - xml_name = self._html_search_regex(r'<iframe src=".*?\?xml=(?P<xml_file>.+?\.xml).*?".*?</iframe>', start_page, 'xml filename', None, False) + xml_name = self._html_search_regex( + r'<iframe src=".*?\?xml=(.+?\.xml).*?".*?</iframe>', + start_page, 'xml filename', default=None) if xml_name is None: # Fallback to the older format xml_name = self._html_search_regex(r'<iframe src=".*?\?xmlURL=xml/(?P<xml_file>.+?\.xml).*?".*?</iframe>', start_page, 'xml filename') diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index dfa8d6153..7246ea7fc 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -261,6 +261,34 @@ class GenericIE(InfoExtractor): }, 'add_ie': ['Dailymotion'], }, + # YouTube embed + { + 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html', + 'info_dict': { + 'id': 'FXRb4ykk4S0', + 'ext': 'mp4', + 'title': 'The NBL Auction 2014', + 'uploader': 'BADMINTON England', + 'uploader_id': 'BADMINTONEvents', + 'upload_date': '20140603', + 'description': 'md5:9ef128a69f1e262a700ed83edb163a73', + }, + 'add_ie': ['Youtube'], + 'params': { + 'skip_download': True, + } + }, + # MTVSercices embed + { + 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too', + 'md5': '35727f82f58c76d996fc188f9755b0d5', + 'info_dict': { + 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9', + 'ext': 'mp4', + 'title': 'Review', + 'description': 'Mario\'s life in the fast lane has never looked so good.', + }, + }, # YouTube embed via <data-embed-url=""> { 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM', @@ -369,17 +397,28 @@ class GenericIE(InfoExtractor): if not parsed_url.scheme: default_search = self._downloader.params.get('default_search') if default_search is None: - default_search = 'auto_warning' + default_search = 'fixup_error' - if default_search in ('auto', 'auto_warning'): + if default_search in ('auto', 'auto_warning', 'fixup_error'): if '/' in url: self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http') return self.url_result('http://' + url) - else: + elif default_search != 'fixup_error': if default_search == 'auto_warning': - self._downloader.report_warning( - 'Falling back to youtube search for %s . Set --default-search to "auto" to suppress this warning.' % url) + if re.match(r'^(?:url|URL)$', url): + raise ExtractorError( + 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url, + expected=True) + else: + self._downloader.report_warning( + 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url) return self.url_result('ytsearch:' + url) + + if default_search in ('error', 'fixup_error'): + raise ExtractorError( + ('%r is not a valid URL. ' + 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube' + ) % (url, url), expected=True) else: assert ':' in default_search return self.url_result(default_search + url) @@ -487,8 +526,14 @@ class GenericIE(InfoExtractor): # Look for embedded YouTube player matches = re.findall(r'''(?x) - (?:<iframe[^>]+?src=|data-video-url=|embedSWF\(\s*) - (["\'])(?P<url>(?:https?:)?//(?:www\.)?youtube\.com/ + (?: + <iframe[^>]+?src=| + data-video-url=| + <embed[^>]+?src=| + embedSWF\(?:\s* + ) + (["\']) + (?P<url>(?:https?:)?//(?:www\.)?youtube\.com/ (?:embed|v)/.+?) \1''', webpage) if matches: @@ -612,6 +657,11 @@ class GenericIE(InfoExtractor): if mobj is not None: return self.url_result(mobj.group('url'), 'VK') + # Look for embedded ivi player + mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'Ivi') + # Look for embedded Huffington Post player mobj = re.search( r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage) @@ -679,6 +729,29 @@ class GenericIE(InfoExtractor): url = unescapeHTML(mobj.group('url')) return self.url_result(url) + # Look for embedded vulture.com player + mobj = re.search( + r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"', + webpage) + if mobj is not None: + url = unescapeHTML(mobj.group('url')) + return self.url_result(url, ie='Vulture') + + # Look for embedded mtvservices player + mobj = re.search( + r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"', + webpage) + if mobj is not None: + url = unescapeHTML(mobj.group('url')) + return self.url_result(url, ie='MTVServicesEmbedded') + + # Look for embedded yahoo player + mobj = re.search( + r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1', + webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'Yahoo') + # Start with something easy: JW Player in SWFObject found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) if not found: diff --git a/youtube_dl/extractor/godtube.py b/youtube_dl/extractor/godtube.py new file mode 100644 index 000000000..73bd6d890 --- /dev/null +++ b/youtube_dl/extractor/godtube.py @@ -0,0 +1,58 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + parse_iso8601, +) + + +class GodTubeIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?godtube\.com/watch/\?v=(?P<id>[\da-zA-Z]+)' + _TESTS = [ + { + 'url': 'https://www.godtube.com/watch/?v=0C0CNNNU', + 'md5': '77108c1e4ab58f48031101a1a2119789', + 'info_dict': { + 'id': '0C0CNNNU', + 'ext': 'mp4', + 'title': 'Woman at the well.', + 'duration': 159, + 'timestamp': 1205712000, + 'uploader': 'beverlybmusic', + 'upload_date': '20080317', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + config = self._download_xml( + 'http://www.godtube.com/resource/mediaplayer/%s.xml' % video_id.lower(), + video_id, 'Downloading player config XML') + + video_url = config.find('.//file').text + uploader = config.find('.//author').text + timestamp = parse_iso8601(config.find('.//date').text) + duration = parse_duration(config.find('.//duration').text) + thumbnail = config.find('.//image').text + + media = self._download_xml( + 'http://www.godtube.com/media/xml/?v=%s' % video_id, video_id, 'Downloading media XML') + + title = media.find('.//title').text + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'uploader': uploader, + 'duration': duration, + } diff --git a/youtube_dl/extractor/googleplus.py b/youtube_dl/extractor/googleplus.py index cc29a7e5d..07d994b44 100644 --- a/youtube_dl/extractor/googleplus.py +++ b/youtube_dl/extractor/googleplus.py @@ -52,8 +52,7 @@ class GooglePlusIE(InfoExtractor): # Extract title # Get the first line for title - video_title = self._html_search_regex(r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]', - webpage, 'title', default='NA') + video_title = self._og_search_description(webpage).splitlines()[0] # Step 2, Simulate clicking the image box to launch video DOMAIN = 'https://plus.google.com/' diff --git a/youtube_dl/extractor/gorillavid.py b/youtube_dl/extractor/gorillavid.py new file mode 100644 index 000000000..ca5f7c417 --- /dev/null +++ b/youtube_dl/extractor/gorillavid.py @@ -0,0 +1,88 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + compat_urllib_parse, + compat_urllib_request, +) + + +class GorillaVidIE(InfoExtractor): + IE_DESC = 'GorillaVid.in and daclips.in' + _VALID_URL = r'''(?x) + https?://(?P<host>(?:www\.)? + (?:daclips\.in|gorillavid\.in))/ + (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)? + ''' + + _TESTS = [{ + 'url': 'http://gorillavid.in/06y9juieqpmi', + 'md5': '5ae4a3580620380619678ee4875893ba', + 'info_dict': { + 'id': '06y9juieqpmi', + 'ext': 'flv', + 'title': 'Rebecca Black My Moment Official Music Video Reaction', + 'thumbnail': 're:http://.*\.jpg', + }, + }, { + 'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html', + 'md5': 'c9e293ca74d46cad638e199c3f3fe604', + 'info_dict': { + 'id': 'z08zf8le23c6', + 'ext': 'mp4', + 'title': 'Say something nice', + 'thumbnail': 're:http://.*\.jpg', + }, + }, { + 'url': 'http://daclips.in/3rso4kdn6f9m', + 'md5': '1ad8fd39bb976eeb66004d3a4895f106', + 'info_dict': { + 'id': '3rso4kdn6f9m', + 'ext': 'mp4', + 'title': 'Micro Pig piglets ready on 16th July 2009', + 'thumbnail': 're:http://.*\.jpg', + }, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage('http://%s/%s' % (mobj.group('host'), video_id), video_id) + + fields = dict(re.findall(r'''(?x)<input\s+ + type="hidden"\s+ + name="([^"]+)"\s+ + (?:id="[^"]+"\s+)? + value="([^"]*)" + ''', webpage)) + + if fields['op'] == 'download1': + post = compat_urllib_parse.urlencode(fields) + + req = compat_urllib_request.Request(url, post) + req.add_header('Content-type', 'application/x-www-form-urlencoded') + + webpage = self._download_webpage(req, video_id, 'Downloading video page') + + title = self._search_regex(r'style="z-index: [0-9]+;">([0-9a-zA-Z ]+)(?:-.+)?</span>', webpage, 'title') + thumbnail = self._search_regex(r'image:\'(http[^\']+)\',', webpage, 'thumbnail') + url = self._search_regex(r'file: \'(http[^\']+)\',', webpage, 'file url') + + formats = [{ + 'format_id': 'sd', + 'url': url, + 'ext': determine_ext(url), + 'quality': 1, + }] + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/goshgay.py b/youtube_dl/extractor/goshgay.py new file mode 100644 index 000000000..7bca21ad0 --- /dev/null +++ b/youtube_dl/extractor/goshgay.py @@ -0,0 +1,73 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urlparse, + str_to_int, + ExtractorError, +) +import json + + +class GoshgayIE(InfoExtractor): + _VALID_URL = r'^(?:https?://)www.goshgay.com/video(?P<id>\d+?)($|/)' + _TEST = { + 'url': 'http://www.goshgay.com/video4116282', + 'md5': '268b9f3c3229105c57859e166dd72b03', + 'info_dict': { + 'id': '4116282', + 'ext': 'flv', + 'title': 'md5:089833a4790b5e103285a07337f245bf', + 'thumbnail': 're:http://.*\.jpg', + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + title = self._search_regex(r'class="video-title"><h1>(.+?)<', webpage, 'title') + + player_config = self._search_regex( + r'(?s)jwplayer\("player"\)\.setup\(({.+?})\)', webpage, 'config settings') + player_vars = json.loads(player_config.replace("'", '"')) + width = str_to_int(player_vars.get('width')) + height = str_to_int(player_vars.get('height')) + config_uri = player_vars.get('config') + + if config_uri is None: + raise ExtractorError('Missing config URI') + node = self._download_xml(config_uri, video_id, 'Downloading player config XML', + errnote='Unable to download XML') + if node is None: + raise ExtractorError('Missing config XML') + if node.tag != 'config': + raise ExtractorError('Missing config attribute') + fns = node.findall('file') + imgs = node.findall('image') + if len(fns) != 1: + raise ExtractorError('Missing media URI') + video_url = fns[0].text + if len(imgs) < 1: + thumbnail = None + else: + thumbnail = imgs[0].text + + url_comp = compat_urlparse.urlparse(url) + ref = "%s://%s%s" % (url_comp[0], url_comp[1], url_comp[2]) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'width': width, + 'height': height, + 'thumbnail': thumbnail, + 'http_referer': ref, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/howstuffworks.py b/youtube_dl/extractor/howstuffworks.py new file mode 100644 index 000000000..68684b997 --- /dev/null +++ b/youtube_dl/extractor/howstuffworks.py @@ -0,0 +1,134 @@ +from __future__ import unicode_literals + +import re +import json +import random +import string + +from .common import InfoExtractor +from ..utils import find_xpath_attr + + +class HowStuffWorksIE(InfoExtractor): + _VALID_URL = r'https?://[\da-z-]+\.howstuffworks\.com/(?:[^/]+/)*\d+-(?P<id>.+?)-video\.htm' + _TESTS = [ + { + 'url': 'http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm', + 'info_dict': { + 'id': '450221', + 'display_id': 'cool-jobs-iditarod-musher', + 'ext': 'flv', + 'title': 'Cool Jobs - Iditarod Musher', + 'description': 'md5:82bb58438a88027b8186a1fccb365f90', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + 'params': { + # md5 is not consistent + 'skip_download': True + } + }, + { + 'url': 'http://adventure.howstuffworks.com/39516-deadliest-catch-jakes-farewell-pots-video.htm', + 'info_dict': { + 'id': '553470', + 'display_id': 'deadliest-catch-jakes-farewell-pots', + 'ext': 'mp4', + 'title': 'Deadliest Catch: Jake\'s Farewell Pots', + 'description': 'md5:9632c346d5e43ee238028c9cefd8dbbc', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + 'params': { + # md5 is not consistent + 'skip_download': True + } + }, + { + 'url': 'http://entertainment.howstuffworks.com/arts/2706-sword-swallowing-1-by-dan-meyer-video.htm', + 'info_dict': { + 'id': '440011', + 'display_id': 'sword-swallowing-1-by-dan-meyer', + 'ext': 'flv', + 'title': 'Sword Swallowing #1 by Dan Meyer', + 'description': 'md5:b2409e88172913e2e7d3d1159b0ef735', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + 'params': { + # md5 is not consistent + 'skip_download': True + } + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('id') + webpage = self._download_webpage(url, display_id) + + content_id = self._search_regex(r'var siteSectionId="(\d+)";', webpage, 'content id') + + mp4 = self._search_regex( + r'''(?xs)var\s+clip\s*=\s*{\s* + .+?\s* + content_id\s*:\s*%s\s*,\s* + .+?\s* + mp4\s*:\s*\[(.*?),?\]\s* + };\s* + videoData\.push\(clip\);''' % content_id, + webpage, 'mp4', fatal=False, default=None) + + smil = self._download_xml( + 'http://services.media.howstuffworks.com/videos/%s/smil-service.smil' % content_id, + content_id, 'Downloading video SMIL') + + http_base = find_xpath_attr( + smil, + './{0}head/{0}meta'.format('{http://www.w3.org/2001/SMIL20/Language}'), + 'name', + 'httpBase').get('content') + + def random_string(str_len=0): + return ''.join([random.choice(string.ascii_uppercase) for _ in range(str_len)]) + + URL_SUFFIX = '?v=2.11.3&fp=LNX 11,2,202,356&r=%s&g=%s' % (random_string(5), random_string(12)) + + formats = [] + + if mp4: + for video in json.loads('[%s]' % mp4): + bitrate = video['bitrate'] + fmt = { + 'url': video['src'].replace('http://pmd.video.howstuffworks.com', http_base) + URL_SUFFIX, + 'format_id': bitrate, + } + m = re.search(r'(?P<vbr>\d+)[Kk]', bitrate) + if m: + fmt['vbr'] = int(m.group('vbr')) + formats.append(fmt) + else: + for video in smil.findall( + './/{0}body/{0}switch/{0}video'.format('{http://www.w3.org/2001/SMIL20/Language}')): + vbr = int(video.attrib['system-bitrate']) / 1000 + formats.append({ + 'url': '%s/%s%s' % (http_base, video.attrib['src'], URL_SUFFIX), + 'format_id': '%dk' % vbr, + 'vbr': vbr, + }) + + self._sort_formats(formats) + + title = self._og_search_title(webpage) + TITLE_SUFFIX = ' : HowStuffWorks' + if title.endswith(TITLE_SUFFIX): + title = title[:-len(TITLE_SUFFIX)] + + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail(webpage) + + return { + 'id': content_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/hypem.py b/youtube_dl/extractor/hypem.py index 9bd06e7c7..6d0d847c6 100644 --- a/youtube_dl/extractor/hypem.py +++ b/youtube_dl/extractor/hypem.py @@ -1,10 +1,11 @@ +from __future__ import unicode_literals + import json import re import time from .common import InfoExtractor from ..utils import ( - compat_str, compat_urllib_parse, compat_urllib_request, @@ -13,59 +14,55 @@ from ..utils import ( class HypemIE(InfoExtractor): - """Information Extractor for hypem""" - _VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)' + _VALID_URL = r'http://(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)' _TEST = { - u'url': u'http://hypem.com/track/1v6ga/BODYWORK+-+TAME', - u'file': u'1v6ga.mp3', - u'md5': u'b9cc91b5af8995e9f0c1cee04c575828', - u'info_dict': { - u"title": u"Tame" + 'url': 'http://hypem.com/track/1v6ga/BODYWORK+-+TAME', + 'md5': 'b9cc91b5af8995e9f0c1cee04c575828', + 'info_dict': { + 'id': '1v6ga', + 'ext': 'mp3', + 'title': 'Tame', + 'uploader': 'BODYWORK', } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) track_id = mobj.group(1) data = {'ax': 1, 'ts': time.time()} data_encoded = compat_urllib_parse.urlencode(data) complete_url = url + "?" + data_encoded request = compat_urllib_request.Request(complete_url) - response, urlh = self._download_webpage_handle(request, track_id, u'Downloading webpage with the url') + response, urlh = self._download_webpage_handle( + request, track_id, 'Downloading webpage with the url') cookie = urlh.headers.get('Set-Cookie', '') - self.report_extraction(track_id) - - html_tracks = self._html_search_regex(r'<script type="application/json" id="displayList-data">(.*?)</script>', - response, u'tracks', flags=re.MULTILINE|re.DOTALL).strip() + html_tracks = self._html_search_regex( + r'(?ms)<script type="application/json" id="displayList-data">\s*(.*?)\s*</script>', + response, 'tracks') try: track_list = json.loads(html_tracks) - track = track_list[u'tracks'][0] + track = track_list['tracks'][0] except ValueError: - raise ExtractorError(u'Hypemachine contained invalid JSON.') + raise ExtractorError('Hypemachine contained invalid JSON.') - key = track[u"key"] - track_id = track[u"id"] - artist = track[u"artist"] - title = track[u"song"] + key = track['key'] + track_id = track['id'] + artist = track['artist'] + title = track['song'] - serve_url = "http://hypem.com/serve/source/%s/%s" % (compat_str(track_id), compat_str(key)) - request = compat_urllib_request.Request(serve_url, "" , {'Content-Type': 'application/json'}) + serve_url = "http://hypem.com/serve/source/%s/%s" % (track_id, key) + request = compat_urllib_request.Request( + serve_url, '', {'Content-Type': 'application/json'}) request.add_header('cookie', cookie) - song_data_json = self._download_webpage(request, track_id, u'Downloading metadata') - try: - song_data = json.loads(song_data_json) - except ValueError: - raise ExtractorError(u'Hypemachine contained invalid JSON.') - final_url = song_data[u"url"] + song_data = self._download_json(request, track_id, 'Downloading metadata') + final_url = song_data["url"] - return [{ - 'id': track_id, - 'url': final_url, - 'ext': "mp3", - 'title': title, - 'artist': artist, - }] + return { + 'id': track_id, + 'url': final_url, + 'ext': 'mp3', + 'title': title, + 'uploader': artist, + } diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index 1ba4966c7..4027deb70 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -14,7 +14,7 @@ from ..utils import ( class IviIE(InfoExtractor): IE_DESC = 'ivi.ru' IE_NAME = 'ivi' - _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch(?:/(?P<compilationid>[^/]+))?/(?P<videoid>\d+)' + _VALID_URL = r'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<videoid>\d+)' _TESTS = [ # Single movie @@ -33,14 +33,14 @@ class IviIE(InfoExtractor): }, # Serial's serie { - 'url': 'http://www.ivi.ru/watch/dezhurnyi_angel/74791', - 'md5': '3e6cc9a848c1d2ebcc6476444967baa9', + 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/9549', + 'md5': '221f56b35e3ed815fde2df71032f4b3e', 'info_dict': { - 'id': '74791', + 'id': '9549', 'ext': 'mp4', - 'title': 'Дежурный ангел - 1 серия', - 'duration': 2490, - 'thumbnail': 'http://thumbs.ivi.ru/f7.vcp.digitalaccess.ru/contents/8/e/bc2f6c2b6e5d291152fdd32c059141.jpg', + 'title': 'Двое из ларца - Серия 1', + 'duration': 2655, + 'thumbnail': 'http://thumbs.ivi.ru/f15.vcp.digitalaccess.ru/contents/8/4/0068dc0677041f3336b7c2baad8fc0.jpg', }, 'skip': 'Only works from Russia', } diff --git a/youtube_dl/extractor/izlesene.py b/youtube_dl/extractor/izlesene.py new file mode 100644 index 000000000..79e8430b5 --- /dev/null +++ b/youtube_dl/extractor/izlesene.py @@ -0,0 +1,97 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + get_element_by_id, + parse_iso8601, + determine_ext, + int_or_none, + str_to_int, +) + + +class IzleseneIE(InfoExtractor): + _VALID_URL = r'https?://(?:(?:www|m)\.)?izlesene\.com/(?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)' + _STREAM_URL = 'http://panel.izlesene.com/api/streamurl/{id:}/{format:}' + _TEST = { + 'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694', + 'md5': '4384f9f0ea65086734b881085ee05ac2', + 'info_dict': { + 'id': '7599694', + 'ext': 'mp4', + 'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi', + 'description': 'Annesi oğluna doğum günü hediyesi olarak minecraft cd si alıyor, ve çocuk hunharca seviniyor', + 'thumbnail': 're:^http://.*\.jpg', + 'uploader_id': 'pelikzzle', + 'timestamp': 1404298698, + 'upload_date': '20140702', + 'duration': 95.395, + 'age_limit': 0, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + url = 'http://www.izlesene.com/video/%s' % video_id + + webpage = self._download_webpage(url, video_id) + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail(webpage) + + uploader = self._html_search_regex( + r"adduserUsername\s*=\s*'([^']+)';", webpage, 'uploader', fatal=False, default='') + timestamp = parse_iso8601(self._html_search_meta( + 'uploadDate', webpage, 'upload date', fatal=False)) + + duration = int_or_none(self._html_search_regex( + r'"videoduration"\s*:\s*"([^"]+)"', webpage, 'duration', fatal=False)) + if duration: + duration /= 1000.0 + + view_count = str_to_int(get_element_by_id('videoViewCount', webpage)) + comment_count = self._html_search_regex( + r'comment_count\s*=\s*\'([^\']+)\';', webpage, 'uploader', fatal=False) + + family_friendly = self._html_search_meta( + 'isFamilyFriendly', webpage, 'age limit', fatal=False) + + content_url = self._html_search_meta( + 'contentURL', webpage, 'content URL', fatal=False) + ext = determine_ext(content_url, 'mp4') + + # Might be empty for some videos. + qualities = self._html_search_regex( + r'"quality"\s*:\s*"([^"]+)"', webpage, 'qualities', fatal=False, default='') + + formats = [] + for quality in qualities.split('|'): + json = self._download_json( + self._STREAM_URL.format(id=video_id, format=quality), video_id, + note='Getting video URL for "%s" quality' % quality, + errnote='Failed to get video URL for "%s" quality' % quality + ) + formats.append({ + 'url': json.get('streamurl'), + 'ext': ext, + 'format_id': '%sp' % quality if quality else 'sd', + }) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'uploader_id': uploader, + 'timestamp': timestamp, + 'duration': duration, + 'view_count': int_or_none(view_count), + 'comment_count': int_or_none(comment_count), + 'age_limit': 18 if family_friendly == 'False' else 0, + 'formats': formats, + } diff --git a/youtube_dl/extractor/jove.py b/youtube_dl/extractor/jove.py new file mode 100644 index 000000000..cf73cd753 --- /dev/null +++ b/youtube_dl/extractor/jove.py @@ -0,0 +1,80 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + unified_strdate +) + + +class JoveIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?jove\.com/video/(?P<id>[0-9]+)' + _CHAPTERS_URL = 'http://www.jove.com/video-chapters?videoid={video_id:}' + _TESTS = [ + { + 'url': 'http://www.jove.com/video/2744/electrode-positioning-montage-transcranial-direct-current', + 'md5': '93723888d82dbd6ba8b3d7d0cd65dd2b', + 'info_dict': { + 'id': '2744', + 'ext': 'mp4', + 'title': 'Electrode Positioning and Montage in Transcranial Direct Current Stimulation', + 'description': 'md5:015dd4509649c0908bc27f049e0262c6', + 'thumbnail': 're:^https?://.*\.png$', + 'upload_date': '20110523', + } + }, + { + 'url': 'http://www.jove.com/video/51796/culturing-caenorhabditis-elegans-axenic-liquid-media-creation', + 'md5': '914aeb356f416811d911996434811beb', + 'info_dict': { + 'id': '51796', + 'ext': 'mp4', + 'title': 'Culturing Caenorhabditis elegans in Axenic Liquid Media and Creation of Transgenic Worms by Microparticle Bombardment', + 'description': 'md5:35ff029261900583970c4023b70f1dc9', + 'thumbnail': 're:^https?://.*\.png$', + 'upload_date': '20140802', + } + }, + + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + chapters_id = self._html_search_regex( + r'/video-chapters\?videoid=([0-9]+)', webpage, 'chapters id') + + chapters_xml = self._download_xml( + self._CHAPTERS_URL.format(video_id=chapters_id), + video_id, note='Downloading chapters XML', + errnote='Failed to download chapters XML') + + video_url = chapters_xml.attrib.get('video') + if not video_url: + raise ExtractorError('Failed to get the video URL') + + title = self._html_search_meta('citation_title', webpage, 'title') + thumbnail = self._og_search_thumbnail(webpage) + description = self._html_search_regex( + r'<div id="section_body_summary"><p class="jove_content">(.+?)</p>', + webpage, 'description', fatal=False) + publish_date = unified_strdate(self._html_search_meta( + 'citation_publication_date', webpage, 'publish date', fatal=False)) + comment_count = self._html_search_regex( + r'<meta name="num_comments" content="(\d+) Comments?"', + webpage, 'comment count', fatal=False) + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'thumbnail': thumbnail, + 'description': description, + 'upload_date': publish_date, + 'comment_count': comment_count, + } diff --git a/youtube_dl/extractor/justintv.py b/youtube_dl/extractor/justintv.py index 7083db12e..27017e89f 100644 --- a/youtube_dl/extractor/justintv.py +++ b/youtube_dl/extractor/justintv.py @@ -1,5 +1,6 @@ from __future__ import unicode_literals +import itertools import json import os import re @@ -43,10 +44,11 @@ class JustinTVIE(InfoExtractor): } # Return count of items, list of *valid* items - def _parse_page(self, url, video_id): - info_json = self._download_webpage(url, video_id, - 'Downloading video info JSON', - 'unable to download video info JSON') + def _parse_page(self, url, video_id, counter): + info_json = self._download_webpage( + url, video_id, + 'Downloading video info JSON on page %d' % counter, + 'Unable to download video info JSON %d' % counter) response = json.loads(info_json) if type(response) != list: @@ -138,11 +140,10 @@ class JustinTVIE(InfoExtractor): entries = [] offset = 0 limit = self._JUSTIN_PAGE_LIMIT - while True: - if paged: - self.report_download_page(video_id, offset) + for counter in itertools.count(1): page_url = api + ('?offset=%d&limit=%d' % (offset, limit)) - page_count, page_info = self._parse_page(page_url, video_id) + page_count, page_info = self._parse_page( + page_url, video_id, counter) entries.extend(page_info) if not paged or page_count != limit: break diff --git a/youtube_dl/extractor/kickstarter.py b/youtube_dl/extractor/kickstarter.py index 961dd1aa6..56a76380c 100644 --- a/youtube_dl/extractor/kickstarter.py +++ b/youtube_dl/extractor/kickstarter.py @@ -8,7 +8,7 @@ from .common import InfoExtractor class KickStarterIE(InfoExtractor): _VALID_URL = r'https?://www\.kickstarter\.com/projects/(?P<id>[^/]*)/.*' - _TEST = { + _TESTS = [{ 'url': 'https://www.kickstarter.com/projects/1404461844/intersection-the-story-of-josh-grant?ref=home_location', 'md5': 'c81addca81327ffa66c642b5d8b08cab', 'info_dict': { @@ -18,22 +18,45 @@ class KickStarterIE(InfoExtractor): 'description': 'A unique motocross documentary that examines the ' 'life and mind of one of sports most elite athletes: Josh Grant.', }, - } + }, { + 'note': 'Embedded video (not using the native kickstarter video service)', + 'url': 'https://www.kickstarter.com/projects/597507018/pebble-e-paper-watch-for-iphone-and-android/posts/659178', + 'playlist': [ + { + 'info_dict': { + 'id': '78704821', + 'ext': 'mp4', + 'uploader_id': 'pebble', + 'uploader': 'Pebble Technology', + 'title': 'Pebble iOS Notifications', + } + } + ], + }] def _real_extract(self, url): m = re.match(self._VALID_URL, url) video_id = m.group('id') webpage = self._download_webpage(url, video_id) - video_url = self._search_regex(r'data-video-url="(.*?)"', - webpage, 'video URL') - video_title = self._html_search_regex(r'<title>(.*?)</title>', - webpage, 'title').rpartition('— Kickstarter')[0].strip() + title = self._html_search_regex( + r'<title>\s*(.*?)(?:\s*— Kickstarter)?\s*</title>', + webpage, 'title') + video_url = self._search_regex( + r'data-video-url="(.*?)"', + webpage, 'video URL', default=None) + if video_url is None: # No native kickstarter, look for embedded videos + return { + '_type': 'url_transparent', + 'ie_key': 'Generic', + 'url': url, + 'title': title, + } return { 'id': video_id, 'url': video_url, - 'title': video_title, + 'title': title, 'description': self._og_search_description(webpage), 'thumbnail': self._og_search_thumbnail(webpage), } diff --git a/youtube_dl/extractor/krasview.py b/youtube_dl/extractor/krasview.py new file mode 100644 index 000000000..6f3d2345b --- /dev/null +++ b/youtube_dl/extractor/krasview.py @@ -0,0 +1,59 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + unescapeHTML, +) + + +class KrasViewIE(InfoExtractor): + IE_DESC = 'Красвью' + _VALID_URL = r'https?://krasview\.ru/video/(?P<id>\d+)' + + _TEST = { + 'url': 'http://krasview.ru/video/512228', + 'md5': '3b91003cf85fc5db277870c8ebd98eae', + 'info_dict': { + 'id': '512228', + 'ext': 'mp4', + 'title': 'Снег, лёд, заносы', + 'description': 'Снято в городе Нягань, в Ханты-Мансийском автономном округе.', + 'duration': 27, + 'thumbnail': 're:^https?://.*\.jpg', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + flashvars = json.loads(self._search_regex( + r'flashvars\s*:\s*({.+?})\s*}\);', webpage, 'flashvars')) + + video_url = flashvars['url'] + title = unescapeHTML(flashvars['title']) + description = unescapeHTML(flashvars.get('subtitle') or self._og_search_description(webpage, default=None)) + thumbnail = flashvars['image'] + duration = int(flashvars['duration']) + filesize = int(flashvars['size']) + width = int_or_none(self._og_search_property('video:width', webpage, 'video width')) + height = int_or_none(self._og_search_property('video:height', webpage, 'video height')) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'filesize': filesize, + 'width': width, + 'height': height, + } diff --git a/youtube_dl/extractor/ku6.py b/youtube_dl/extractor/ku6.py new file mode 100644 index 000000000..484239b19 --- /dev/null +++ b/youtube_dl/extractor/ku6.py @@ -0,0 +1,35 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class Ku6IE(InfoExtractor): + _VALID_URL = r'http://v\.ku6\.com/show/(?P<id>[a-zA-Z0-9\-\_]+)(?:\.)*html' + _TEST = { + 'url': 'http://v.ku6.com/show/JG-8yS14xzBr4bCn1pu0xw...html', + 'md5': '01203549b9efbb45f4b87d55bdea1ed1', + 'info_dict': { + 'id': 'JG-8yS14xzBr4bCn1pu0xw', + 'ext': 'f4v', + 'title': 'techniques test', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + title = self._search_regex(r'<h1 title=.*>(.*?)</h1>', webpage, 'title') + dataUrl = 'http://v.ku6.com/fetchVideo4Player/%s.html' % video_id + jsonData = self._download_json(dataUrl, video_id) + downloadUrl = jsonData['data']['f'] + + return { + 'id': video_id, + 'title': title, + 'url': downloadUrl + } + diff --git a/youtube_dl/extractor/lifenews.py b/youtube_dl/extractor/lifenews.py index 7a431a274..8d9491f23 100644 --- a/youtube_dl/extractor/lifenews.py +++ b/youtube_dl/extractor/lifenews.py @@ -24,7 +24,7 @@ class LifeNewsIE(InfoExtractor): 'ext': 'mp4', 'title': 'МВД разыскивает мужчин, оставивших в IKEA сумку с автоматом', 'description': 'Камеры наблюдения гипермаркета зафиксировали троих мужчин, спрятавших оружейный арсенал в камере хранения.', - 'thumbnail': 'http://lifenews.ru/static/posts/2014/1/126342/.video.jpg', + 'thumbnail': 're:http://.*\.jpg', 'upload_date': '20140130', } } diff --git a/youtube_dl/extractor/livestream.py b/youtube_dl/extractor/livestream.py index 1dcd1fb2d..281a0ce40 100644 --- a/youtube_dl/extractor/livestream.py +++ b/youtube_dl/extractor/livestream.py @@ -1,36 +1,109 @@ +from __future__ import unicode_literals + import re import json from .common import InfoExtractor from ..utils import ( + compat_str, compat_urllib_parse_urlparse, compat_urlparse, + ExtractorError, + find_xpath_attr, + int_or_none, + orderedSet, xpath_with_ns, ) class LivestreamIE(InfoExtractor): - IE_NAME = u'livestream' + IE_NAME = 'livestream' _VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$' _TEST = { - u'url': u'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370', - u'file': u'4719370.mp4', - u'md5': u'0d2186e3187d185a04b3cdd02b828836', - u'info_dict': { - u'title': u'Live from Webster Hall NYC', - u'upload_date': u'20121012', + 'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370', + 'md5': '53274c76ba7754fb0e8d072716f2292b', + 'info_dict': { + 'id': '4719370', + 'ext': 'mp4', + 'title': 'Live from Webster Hall NYC', + 'upload_date': '20121012', + 'like_count': int, + 'view_count': int, + 'thumbnail': 're:^http://.*\.jpg$' } } + def _parse_smil(self, video_id, smil_url): + formats = [] + _SWITCH_XPATH = ( + './/{http://www.w3.org/2001/SMIL20/Language}body/' + '{http://www.w3.org/2001/SMIL20/Language}switch') + smil_doc = self._download_xml( + smil_url, video_id, + note='Downloading SMIL information', + errnote='Unable to download SMIL information', + fatal=False) + if smil_doc is False: # Download failed + return formats + title_node = find_xpath_attr( + smil_doc, './/{http://www.w3.org/2001/SMIL20/Language}meta', + 'name', 'title') + if title_node is None: + self.report_warning('Cannot find SMIL id') + switch_node = smil_doc.find(_SWITCH_XPATH) + else: + title_id = title_node.attrib['content'] + switch_node = find_xpath_attr( + smil_doc, _SWITCH_XPATH, 'id', title_id) + if switch_node is None: + raise ExtractorError('Cannot find switch node') + video_nodes = switch_node.findall( + '{http://www.w3.org/2001/SMIL20/Language}video') + + for vn in video_nodes: + tbr = int_or_none(vn.attrib.get('system-bitrate')) + furl = ( + 'http://livestream-f.akamaihd.net/%s?v=3.0.3&fp=WIN%%2014,0,0,145' % + (vn.attrib['src'])) + if 'clipBegin' in vn.attrib: + furl += '&ssek=' + vn.attrib['clipBegin'] + formats.append({ + 'url': furl, + 'format_id': 'smil_%d' % tbr, + 'ext': 'flv', + 'tbr': tbr, + 'preference': -1000, + }) + return formats + def _extract_video_info(self, video_data): - video_url = video_data.get('progressive_url_hd') or video_data.get('progressive_url') - return {'id': video_data['id'], - 'url': video_url, - 'ext': 'mp4', - 'title': video_data['caption'], - 'thumbnail': video_data['thumbnail_url'], - 'upload_date': video_data['updated_at'].replace('-','')[:8], - } + video_id = compat_str(video_data['id']) + + FORMAT_KEYS = ( + ('sd', 'progressive_url'), + ('hd', 'progressive_url_hd'), + ) + formats = [{ + 'format_id': format_id, + 'url': video_data[key], + 'quality': i + 1, + } for i, (format_id, key) in enumerate(FORMAT_KEYS) + if video_data.get(key)] + + smil_url = video_data.get('smil_url') + if smil_url: + formats.extend(self._parse_smil(video_id, smil_url)) + self._sort_formats(formats) + + return { + 'id': video_id, + 'formats': formats, + 'title': video_data['caption'], + 'thumbnail': video_data.get('thumbnail_url'), + 'upload_date': video_data['updated_at'].replace('-', '')[:8], + 'like_count': video_data.get('likes', {}).get('total'), + 'view_count': video_data.get('views'), + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -38,45 +111,57 @@ class LivestreamIE(InfoExtractor): event_name = mobj.group('event_name') webpage = self._download_webpage(url, video_id or event_name) - if video_id is None: - # This is an event page: - config_json = self._search_regex(r'window.config = ({.*?});', - webpage, u'window config') + og_video = self._og_search_video_url(webpage, 'player url', fatal=False, default=None) + if og_video is None: + config_json = self._search_regex( + r'window.config = ({.*?});', webpage, 'window config') info = json.loads(config_json)['event'] + + def is_relevant(vdata, vid): + result = vdata['type'] == 'video' + if video_id is not None: + 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 video_data['type'] == u'video'] - return self.playlist_result(videos, info['id'], info['full_name']) + 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, info['id'], info['full_name']) + else: + if videos: + return videos[0] else: - og_video = self._og_search_video_url(webpage, name=u'player url') query_str = compat_urllib_parse_urlparse(og_video).query query = compat_urlparse.parse_qs(query_str) api_url = query['play_url'][0].replace('.smil', '') - info = json.loads(self._download_webpage(api_url, video_id, - u'Downloading video info')) + info = json.loads(self._download_webpage( + api_url, video_id, 'Downloading video info')) return self._extract_video_info(info) # The original version of Livestream uses a different system class LivestreamOriginalIE(InfoExtractor): - IE_NAME = u'livestream:original' - _VALID_URL = r'https?://www\.livestream\.com/(?P<user>[^/]+)/video\?.*?clipId=(?P<id>.*?)(&|$)' + IE_NAME = 'livestream:original' + _VALID_URL = r'''(?x)https?://www\.livestream\.com/ + (?P<user>[^/]+)/(?P<type>video|folder) + (?:\?.*?Id=|/)(?P<id>.*?)(&|$) + ''' _TEST = { - u'url': u'http://www.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb', - u'info_dict': { - u'id': u'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb', - u'ext': u'flv', - u'title': u'Spark 1 (BitCoin) with Cameron Winklevoss & Tyler Winklevoss of Winklevoss Capital', + 'url': 'http://www.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb', + 'info_dict': { + 'id': 'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb', + 'ext': 'flv', + 'title': 'Spark 1 (BitCoin) with Cameron Winklevoss & Tyler Winklevoss of Winklevoss Capital', }, - u'params': { + 'params': { # rtmp - u'skip_download': True, + 'skip_download': True, }, } - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - user = mobj.group('user') + def _extract_video(self, user, video_id): api_url = 'http://x{0}x.api.channel.livestream.com/2.0/clipdetails?extendedInfo=true&id={1}'.format(user, video_id) info = self._download_xml(api_url, video_id) @@ -84,7 +169,7 @@ class LivestreamOriginalIE(InfoExtractor): ns = {'media': 'http://search.yahoo.com/mrss'} thumbnail_url = item.find(xpath_with_ns('media:thumbnail', ns)).attrib['url'] # Remove the extension and number from the path (like 1.jpg) - path = self._search_regex(r'(user-files/.+)_.*?\.jpg$', thumbnail_url, u'path') + path = self._search_regex(r'(user-files/.+)_.*?\.jpg$', thumbnail_url, 'path') return { 'id': video_id, @@ -94,3 +179,44 @@ class LivestreamOriginalIE(InfoExtractor): 'ext': 'flv', 'thumbnail': thumbnail_url, } + + def _extract_folder(self, url, folder_id): + webpage = self._download_webpage(url, folder_id) + urls = orderedSet(re.findall(r'<a href="(https?://livestre\.am/.*?)"', webpage)) + + return { + '_type': 'playlist', + 'id': folder_id, + 'entries': [{ + '_type': 'url', + 'url': video_url, + } for video_url in urls], + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + id = mobj.group('id') + user = mobj.group('user') + url_type = mobj.group('type') + if url_type == 'folder': + return self._extract_folder(url, id) + else: + return self._extract_video(user, id) + + +# The server doesn't support HEAD request, the generic extractor can't detect +# the redirection +class LivestreamShortenerIE(InfoExtractor): + IE_NAME = 'livestream:shortener' + IE_DESC = False # Do not list + _VALID_URL = r'https?://livestre\.am/(?P<id>.+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + id = mobj.group('id') + webpage = self._download_webpage(url, id) + + return { + '_type': 'url', + 'url': self._og_search_url(webpage), + } diff --git a/youtube_dl/extractor/mailru.py b/youtube_dl/extractor/mailru.py index f819c09b3..7460d81cd 100644 --- a/youtube_dl/extractor/mailru.py +++ b/youtube_dl/extractor/mailru.py @@ -2,7 +2,6 @@ from __future__ import unicode_literals import re -import datetime from .common import InfoExtractor @@ -10,28 +9,48 @@ from .common import InfoExtractor class MailRuIE(InfoExtractor): IE_NAME = 'mailru' IE_DESC = 'Видео@Mail.Ru' - _VALID_URL = r'http://(?:www\.)?my\.mail\.ru/video/.*#video=/?(?P<id>[^/]+/[^/]+/[^/]+/\d+)' + _VALID_URL = r'http://(?:www\.)?my\.mail\.ru/(?:video/.*#video=/?(?P<idv1>(?:[^/]+/){3}\d+)|(?:(?P<idv2prefix>(?:[^/]+/){2})video/(?P<idv2suffix>[^/]+/\d+))\.html)' - _TEST = { - 'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76', - 'md5': 'dea205f03120046894db4ebb6159879a', - 'info_dict': { - 'id': '46301138', - 'ext': 'mp4', - 'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро', - 'upload_date': '20140224', - 'uploader': 'sonypicturesrus', - 'uploader_id': 'sonypicturesrus@mail.ru', - 'duration': 184, - } - } + _TESTS = [ + { + 'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76', + 'md5': 'dea205f03120046894db4ebb6159879a', + 'info_dict': { + 'id': '46301138', + 'ext': 'mp4', + 'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро', + 'timestamp': 1393232740, + 'upload_date': '20140224', + 'uploader': 'sonypicturesrus', + 'uploader_id': 'sonypicturesrus@mail.ru', + 'duration': 184, + }, + }, + { + 'url': 'http://my.mail.ru/corp/hitech/video/news_hi-tech_mail_ru/1263.html', + 'md5': '00a91a58c3402204dcced523777b475f', + 'info_dict': { + 'id': '46843144', + 'ext': 'mp4', + 'title': 'Samsung Galaxy S5 Hammer Smash Fail Battery Explosion', + 'timestamp': 1397217632, + 'upload_date': '20140411', + 'uploader': 'hitech', + 'uploader_id': 'hitech@corp.mail.ru', + 'duration': 245, + }, + }, + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = mobj.group('idv1') + + if not video_id: + video_id = mobj.group('idv2prefix') + mobj.group('idv2suffix') video_data = self._download_json( - 'http://videoapi.my.mail.ru/videos/%s.json?new=1' % video_id, video_id, 'Downloading video JSON') + 'http://api.video.mail.ru/videos/%s.json?new=1' % video_id, video_id, 'Downloading video JSON') author = video_data['author'] uploader = author['name'] @@ -40,10 +59,11 @@ class MailRuIE(InfoExtractor): movie = video_data['movie'] content_id = str(movie['contentId']) title = movie['title'] + if title.endswith('.mp4'): + title = title[:-4] thumbnail = movie['poster'] duration = movie['duration'] - upload_date = datetime.datetime.fromtimestamp(video_data['timestamp']).strftime('%Y%m%d') view_count = video_data['views_count'] formats = [ @@ -57,7 +77,7 @@ class MailRuIE(InfoExtractor): 'id': content_id, 'title': title, 'thumbnail': thumbnail, - 'upload_date': upload_date, + 'timestamp': video_data['timestamp'], 'uploader': uploader, 'uploader_id': uploader_id, 'duration': duration, diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py index 6436c05a3..1a896b536 100644 --- a/youtube_dl/extractor/metacafe.py +++ b/youtube_dl/extractor/metacafe.py @@ -9,6 +9,7 @@ from ..utils import ( compat_urllib_request, determine_ext, ExtractorError, + int_or_none, ) @@ -83,6 +84,21 @@ class MetacafeIE(InfoExtractor): 'skip_download': True, }, }, + # Movieclips.com video + { + 'url': 'http://www.metacafe.com/watch/mv-Wy7ZU/my_week_with_marilyn_do_you_love_me/', + 'info_dict': { + 'id': 'mv-Wy7ZU', + 'ext': 'mp4', + 'title': 'My Week with Marilyn - Do You Love Me?', + 'description': 'From the movie My Week with Marilyn - Colin (Eddie Redmayne) professes his love to Marilyn (Michelle Williams) and gets her to promise to return to set and finish the movie.', + 'uploader': 'movie_trailers', + 'duration': 176, + }, + 'params': { + 'skip_download': 'requires rtmpdump', + } + } ] def report_disclaimer(self): @@ -134,6 +150,7 @@ class MetacafeIE(InfoExtractor): # Extract URL, uploader and title from webpage self.report_extraction(video_id) + video_url = None mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) if mobj is not None: mediaURL = compat_urllib_parse.unquote(mobj.group(1)) @@ -146,16 +163,17 @@ class MetacafeIE(InfoExtractor): else: gdaKey = mobj.group(1) video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) - else: + if video_url is None: mobj = re.search(r'<video src="([^"]+)"', webpage) if mobj: video_url = mobj.group(1) video_ext = 'mp4' - else: - mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) - if mobj is None: - raise ExtractorError('Unable to extract media URL') - vardict = compat_parse_qs(mobj.group(1)) + if video_url is None: + flashvars = self._search_regex( + r' name="flashvars" value="(.*?)"', webpage, 'flashvars', + default=None) + if flashvars: + vardict = compat_parse_qs(flashvars) if 'mediaData' not in vardict: raise ExtractorError('Unable to extract media URL') mobj = re.search( @@ -165,26 +183,68 @@ class MetacafeIE(InfoExtractor): mediaURL = mobj.group('mediaURL').replace('\\/', '/') video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key')) video_ext = determine_ext(video_url) - - video_title = self._html_search_regex(r'(?im)<title>(.*) - Video</title>', webpage, 'title') + if video_url is None: + player_url = self._search_regex( + r"swfobject\.embedSWF\('([^']+)'", + webpage, 'config URL', default=None) + if player_url: + config_url = self._search_regex( + r'config=(.+)$', player_url, 'config URL') + config_doc = self._download_xml( + config_url, video_id, + note='Downloading video config') + smil_url = config_doc.find('.//properties').attrib['smil_file'] + smil_doc = self._download_xml( + smil_url, video_id, + note='Downloading SMIL document') + base_url = smil_doc.find('./head/meta').attrib['base'] + video_url = [] + for vn in smil_doc.findall('.//video'): + br = int(vn.attrib['system-bitrate']) + play_path = vn.attrib['src'] + video_url.append({ + 'format_id': 'smil-%d' % br, + 'url': base_url, + 'play_path': play_path, + 'page_url': url, + 'player_url': player_url, + 'ext': play_path.partition(':')[0], + }) + + if video_url is None: + raise ExtractorError('Unsupported video type') + + video_title = self._html_search_regex( + r'(?im)<title>(.*) - Video</title>', webpage, 'title') description = self._og_search_description(webpage) thumbnail = self._og_search_thumbnail(webpage) video_uploader = self._html_search_regex( r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);', webpage, 'uploader nickname', fatal=False) + duration = int_or_none( + self._html_search_meta('video:duration', webpage)) + + age_limit = ( + 18 + if re.search(r'"contentRating":"restricted"', webpage) + else 0) - if re.search(r'"contentRating":"restricted"', webpage) is not None: - age_limit = 18 + if isinstance(video_url, list): + formats = video_url else: - age_limit = 0 + formats = [{ + 'url': video_url, + 'ext': video_ext, + }] + self._sort_formats(formats) return { 'id': video_id, - 'url': video_url, 'description': description, 'uploader': video_uploader, 'title': video_title, - 'thumbnail':thumbnail, - 'ext': video_ext, + 'thumbnail': thumbnail, 'age_limit': age_limit, + 'formats': formats, + 'duration': duration, } diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py new file mode 100644 index 000000000..979f3d692 --- /dev/null +++ b/youtube_dl/extractor/mitele.py @@ -0,0 +1,60 @@ +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + get_element_by_attribute, + parse_duration, + strip_jsonp, +) + + +class MiTeleIE(InfoExtractor): + IE_NAME = 'mitele.es' + _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<episode>[^/]+)/' + + _TEST = { + 'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/', + 'md5': '6a75fe9d0d3275bead0cb683c616fddb', + 'info_dict': { + 'id': '0fce117d', + 'ext': 'mp4', + 'title': 'Programa 144 - Tor, la web invisible', + 'description': 'md5:3b6fce7eaa41b2d97358726378d9369f', + 'display_id': 'programa-144', + 'duration': 2913, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + episode = mobj.group('episode') + webpage = self._download_webpage(url, episode) + embed_data_json = self._search_regex( + r'MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data', + flags=re.DOTALL + ).replace('\'', '"') + embed_data = json.loads(embed_data_json) + + info_url = embed_data['flashvars']['host'] + info_el = self._download_xml(info_url, episode).find('./video/info') + + video_link = info_el.find('videoUrl/link').text + token_query = compat_urllib_parse.urlencode({'id': video_link}) + token_info = self._download_json( + 'http://token.mitele.es/?' + token_query, episode, + transform_source=strip_jsonp + ) + + return { + 'id': embed_data['videoId'], + 'display_id': episode, + 'title': info_el.find('title').text, + 'url': token_info['tokenizedUrl'], + 'description': get_element_by_attribute('class', 'text', webpage), + 'thumbnail': info_el.find('thumb').text, + 'duration': parse_duration(info_el.find('duration').text), + } diff --git a/youtube_dl/extractor/mlb.py b/youtube_dl/extractor/mlb.py new file mode 100644 index 000000000..37c72bc53 --- /dev/null +++ b/youtube_dl/extractor/mlb.py @@ -0,0 +1,116 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + parse_iso8601, + find_xpath_attr, +) + + +class MLBIE(InfoExtractor): + _VALID_URL = r'https?://m\.mlb\.com/(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v(?P<id>n?\d+)' + _TESTS = [ + { + 'url': 'http://m.mlb.com/sea/video/topic/51231442/v34698933/nymsea-ackley-robs-a-home-run-with-an-amazing-catch/?c_id=sea', + 'md5': 'ff56a598c2cf411a9a38a69709e97079', + 'info_dict': { + 'id': '34698933', + 'ext': 'mp4', + 'title': "Ackley's spectacular catch", + 'description': 'md5:7f5a981eb4f3cbc8daf2aeffa2215bf0', + 'duration': 66, + 'timestamp': 1405980600, + 'upload_date': '20140721', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, + { + 'url': 'http://m.mlb.com/video/topic/81536970/v34496663/mianym-stanton-practices-for-the-home-run-derby', + 'md5': 'd9c022c10d21f849f49c05ae12a8a7e9', + 'info_dict': { + 'id': '34496663', + 'ext': 'mp4', + 'title': 'Stanton prepares for Derby', + 'description': 'md5:d00ce1e5fd9c9069e9c13ab4faedfa57', + 'duration': 46, + 'timestamp': 1405105800, + 'upload_date': '20140711', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, + { + 'url': 'http://m.mlb.com/video/topic/vtp_hrd_sponsor/v34578115/hrd-cespedes-wins-2014-gillette-home-run-derby', + 'md5': '0e6e73d509321e142409b695eadd541f', + 'info_dict': { + 'id': '34578115', + 'ext': 'mp4', + 'title': 'Cespedes repeats as Derby champ', + 'description': 'md5:08df253ce265d4cf6fb09f581fafad07', + 'duration': 488, + 'timestamp': 1405399936, + 'upload_date': '20140715', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, + { + 'url': 'http://m.mlb.com/video/v34577915/bautista-on-derby-captaining-duties-his-performance', + 'md5': 'b8fd237347b844365d74ea61d4245967', + 'info_dict': { + 'id': '34577915', + 'ext': 'mp4', + 'title': 'Bautista on Home Run Derby', + 'description': 'md5:b80b34031143d0986dddc64a8839f0fb', + 'duration': 52, + 'timestamp': 1405390722, + 'upload_date': '20140715', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + detail = self._download_xml( + 'http://m.mlb.com/gen/multimedia/detail/%s/%s/%s/%s.xml' + % (video_id[-3], video_id[-2], video_id[-1], video_id), video_id) + + title = detail.find('./headline').text + description = detail.find('./big-blurb').text + duration = parse_duration(detail.find('./duration').text) + timestamp = parse_iso8601(detail.attrib['date'][:-5]) + + thumbnail = find_xpath_attr( + detail, './thumbnailScenarios/thumbnailScenario', 'type', '45').text + + formats = [] + for media_url in detail.findall('./url'): + playback_scenario = media_url.attrib['playback_scenario'] + fmt = { + 'url': media_url.text, + 'format_id': playback_scenario, + } + m = re.search(r'(?P<vbr>\d+)K_(?P<width>\d+)X(?P<height>\d+)', playback_scenario) + if m: + fmt.update({ + 'vbr': int(m.group('vbr')) * 1000, + 'width': int(m.group('width')), + 'height': int(m.group('height')), + }) + formats.append(fmt) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'duration': duration, + 'timestamp': timestamp, + 'formats': formats, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/mojvideo.py b/youtube_dl/extractor/mojvideo.py new file mode 100644 index 000000000..90b460d65 --- /dev/null +++ b/youtube_dl/extractor/mojvideo.py @@ -0,0 +1,58 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + parse_duration, +) + + +class MojvideoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?mojvideo\.com/video-(?P<display_id>[^/]+)/(?P<id>[a-f0-9]+)' + _TEST = { + 'url': 'http://www.mojvideo.com/video-v-avtu-pred-mano-rdecelaska-alfi-nipic/3d1ed4497707730b2906', + 'md5': 'f7fd662cc8ce2be107b0d4f2c0483ae7', + 'info_dict': { + 'id': '3d1ed4497707730b2906', + 'display_id': 'v-avtu-pred-mano-rdecelaska-alfi-nipic', + 'ext': 'mp4', + 'title': 'V avtu pred mano rdečelaska - Alfi Nipič', + 'thumbnail': 're:^http://.*\.jpg$', + 'duration': 242, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + # XML is malformed + playerapi = self._download_webpage( + 'http://www.mojvideo.com/playerapi.php?v=%s&t=1' % video_id, display_id) + + if '<error>true</error>' in playerapi: + error_desc = self._html_search_regex( + r'<errordesc>([^<]*)</errordesc>', playerapi, 'error description', fatal=False) + raise ExtractorError('%s said: %s' % (self.IE_NAME, error_desc), expected=True) + + title = self._html_search_regex( + r'<title>([^<]+)</title>', playerapi, 'title') + video_url = self._html_search_regex( + r'<file>([^<]+)</file>', playerapi, 'video URL') + thumbnail = self._html_search_regex( + r'<preview>([^<]+)</preview>', playerapi, 'thumbnail', fatal=False) + duration = parse_duration(self._html_search_regex( + r'<duration>([^<]+)</duration>', playerapi, 'duration', fatal=False)) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'duration': duration, + }
\ No newline at end of file diff --git a/youtube_dl/extractor/motherless.py b/youtube_dl/extractor/motherless.py new file mode 100644 index 000000000..6229b2173 --- /dev/null +++ b/youtube_dl/extractor/motherless.py @@ -0,0 +1,87 @@ +from __future__ import unicode_literals + +import datetime +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + unified_strdate, +) + + +class MotherlessIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?motherless\.com/(?P<id>[A-Z0-9]+)' + _TESTS = [ + { + 'url': 'http://motherless.com/AC3FFE1', + 'md5': '5527fef81d2e529215dad3c2d744a7d9', + 'info_dict': { + 'id': 'AC3FFE1', + 'ext': 'flv', + 'title': 'Fucked in the ass while playing PS3', + 'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'], + 'upload_date': '20100913', + 'uploader_id': 'famouslyfuckedup', + 'thumbnail': 're:http://.*\.jpg', + 'age_limit': 18, + } + }, + { + 'url': 'http://motherless.com/532291B', + 'md5': 'bc59a6b47d1f958e61fbd38a4d31b131', + 'info_dict': { + 'id': '532291B', + 'ext': 'mp4', + 'title': 'Amazing girl playing the omegle game, PERFECT!', + 'categories': ['Amateur', 'webcam', 'omegle', 'pink', 'young', 'masturbate', 'teen', 'game', 'hairy'], + 'upload_date': '20140622', + 'uploader_id': 'Sulivana7x', + 'thumbnail': 're:http://.*\.jpg', + 'age_limit': 18, + } + } + ] + + def _real_extract(self,url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex(r'id="view-upload-title">\s+([^<]+)<', webpage, 'title') + + video_url = self._html_search_regex(r'setup\(\{\s+"file".+: "([^"]+)",', webpage, 'video_url') + age_limit = self._rta_search(webpage) + + view_count = self._html_search_regex(r'<strong>Views</strong>\s+([^<]+)<', webpage, 'view_count') + + upload_date = self._html_search_regex(r'<strong>Uploaded</strong>\s+([^<]+)<', webpage, 'upload_date') + if 'Ago' in upload_date: + days = int(re.search(r'([0-9]+)', upload_date).group(1)) + upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d') + else: + upload_date = unified_strdate(upload_date) + + like_count = self._html_search_regex(r'<strong>Favorited</strong>\s+([^<]+)<', webpage, 'like_count') + + comment_count = webpage.count('class="media-comment-contents"') + uploader_id = self._html_search_regex(r'"thumb-member-username">\s+<a href="/m/([^"]+)"', webpage, 'uploader_id') + + categories = self._html_search_meta('keywords', webpage) + if categories: + categories = [cat.strip() for cat in categories.split(',')] + + return { + 'id': video_id, + 'title': title, + 'upload_date': upload_date, + 'uploader_id': uploader_id, + 'thumbnail': self._og_search_thumbnail(webpage), + 'categories': categories, + 'view_count': int_or_none(view_count.replace(',', '')), + 'like_count': int_or_none(like_count.replace(',', '')), + 'comment_count': comment_count, + 'age_limit': age_limit, + 'url': video_url, + } diff --git a/youtube_dl/extractor/mpora.py b/youtube_dl/extractor/mpora.py index 39d6feb98..387935d4d 100644 --- a/youtube_dl/extractor/mpora.py +++ b/youtube_dl/extractor/mpora.py @@ -28,7 +28,7 @@ class MporaIE(InfoExtractor): webpage = self._download_webpage(url, video_id) data_json = self._search_regex( - r"new FM\.Player\('[^']+',\s*(\{.*?)\);\n", webpage, 'json') + r"new FM\.Player\('[^']+',\s*(\{.*?)\).player;", webpage, 'json') data = json.loads(data_json) diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index d75241d3f..228b42d2b 100644 --- a/youtube_dl/extractor/mtv.py +++ b/youtube_dl/extractor/mtv.py @@ -22,6 +22,7 @@ def _media_xml_tag(tag): class MTVServicesInfoExtractor(InfoExtractor): _MOBILE_TEMPLATE = None + @staticmethod def _id_from_uri(uri): return uri.split(':')[-1] @@ -35,6 +36,9 @@ class MTVServicesInfoExtractor(InfoExtractor): base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/' return base + m.group('finalid') + def _get_feed_url(self, uri): + return self._FEED_URL + def _get_thumbnail_url(self, uri, itemdoc): search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail')) thumb_node = itemdoc.find(search_path) @@ -80,6 +84,7 @@ class MTVServicesInfoExtractor(InfoExtractor): }) except (KeyError, TypeError): raise ExtractorError('Invalid rendition field.') + self._sort_formats(formats) return formats def _get_video_info(self, itemdoc): @@ -135,10 +140,10 @@ class MTVServicesInfoExtractor(InfoExtractor): def _get_videos_info(self, uri): video_id = self._id_from_uri(uri) + feed_url = self._get_feed_url(uri) data = compat_urllib_parse.urlencode({'uri': uri}) - idoc = self._download_xml( - self._FEED_URL + '?' + data, video_id, + feed_url + '?' + data, video_id, 'Downloading info', transform_source=fix_xml_ampersands) return [self._get_video_info(item) for item in idoc.findall('.//item')] @@ -153,12 +158,46 @@ class MTVServicesInfoExtractor(InfoExtractor): if mgid.endswith('.swf'): mgid = mgid[:-4] except RegexNotFoundError: + mgid = None + + if mgid is None or ':' not in mgid: mgid = self._search_regex( [r'data-mgid="(.*?)"', r'swfobject.embedSWF\(".*?(mgid:.*?)"'], webpage, u'mgid') return self._get_videos_info(mgid) +class MTVServicesEmbeddedIE(MTVServicesInfoExtractor): + IE_NAME = 'mtvservices:embedded' + _VALID_URL = r'https?://media\.mtvnservices\.com/embed/(?P<mgid>.+?)(\?|/|$)' + + _TEST = { + # From http://www.thewrap.com/peter-dinklage-sums-up-game-of-thrones-in-45-seconds-video/ + 'url': 'http://media.mtvnservices.com/embed/mgid:uma:video:mtv.com:1043906/cp~vid%3D1043906%26uri%3Dmgid%3Auma%3Avideo%3Amtv.com%3A1043906', + 'md5': 'cb349b21a7897164cede95bd7bf3fbb9', + 'info_dict': { + 'id': '1043906', + 'ext': 'mp4', + 'title': 'Peter Dinklage Sums Up \'Game Of Thrones\' In 45 Seconds', + 'description': '"Sexy sexy sexy, stabby stabby stabby, beautiful language," says Peter Dinklage as he tries summarizing "Game of Thrones" in under a minute.', + }, + } + + def _get_feed_url(self, uri): + video_id = self._id_from_uri(uri) + site_id = uri.replace(video_id, '') + config_url = 'http://media.mtvnservices.com/pmt/e1/players/{0}/config.xml'.format(site_id) + config_doc = self._download_xml(config_url, video_id) + feed_node = config_doc.find('.//feed') + feed_url = feed_node.text.strip().split('?')[0] + return feed_url + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + mgid = mobj.group('mgid') + return self._get_videos_info(mgid) + + class MTVIE(MTVServicesInfoExtractor): _VALID_URL = r'''(?x)^https?:// (?:(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$| diff --git a/youtube_dl/extractor/naver.py b/youtube_dl/extractor/naver.py index 4cab30631..c0231c197 100644 --- a/youtube_dl/extractor/naver.py +++ b/youtube_dl/extractor/naver.py @@ -1,4 +1,6 @@ # encoding: utf-8 +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -12,12 +14,13 @@ class NaverIE(InfoExtractor): _VALID_URL = r'https?://(?:m\.)?tvcast\.naver\.com/v/(?P<id>\d+)' _TEST = { - u'url': u'http://tvcast.naver.com/v/81652', - u'file': u'81652.mp4', - u'info_dict': { - u'title': u'[9월 모의고사 해설강의][수학_김상희] 수학 A형 16~20번', - u'description': u'합격불변의 법칙 메가스터디 | 메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.', - u'upload_date': u'20130903', + 'url': 'http://tvcast.naver.com/v/81652', + 'info_dict': { + 'id': '81652', + 'ext': 'mp4', + 'title': '[9월 모의고사 해설강의][수학_김상희] 수학 A형 16~20번', + 'description': '합격불변의 법칙 메가스터디 | 메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.', + 'upload_date': '20130903', }, } @@ -28,7 +31,7 @@ class NaverIE(InfoExtractor): m_id = re.search(r'var rmcPlayer = new nhn.rmcnmv.RMCVideoPlayer\("(.+?)", "(.+?)"', webpage) if m_id is None: - raise ExtractorError(u'couldn\'t extract vid and key') + raise ExtractorError('couldn\'t extract vid and key') vid = m_id.group(1) key = m_id.group(2) query = compat_urllib_parse.urlencode({'vid': vid, 'inKey': key,}) @@ -39,22 +42,27 @@ class NaverIE(InfoExtractor): }) info = self._download_xml( 'http://serviceapi.rmcnmv.naver.com/flash/videoInfo.nhn?' + query, - video_id, u'Downloading video info') + video_id, 'Downloading video info') urls = self._download_xml( 'http://serviceapi.rmcnmv.naver.com/flash/playableEncodingOption.nhn?' + query_urls, - video_id, u'Downloading video formats info') + video_id, 'Downloading video formats info') formats = [] for format_el in urls.findall('EncodingOptions/EncodingOption'): domain = format_el.find('Domain').text - if domain.startswith('rtmp'): - continue - formats.append({ + f = { 'url': domain + format_el.find('uri').text, 'ext': 'mp4', 'width': int(format_el.find('width').text), 'height': int(format_el.find('height').text), - }) + } + if domain.startswith('rtmp'): + f.update({ + 'ext': 'flv', + 'rtmp_protocol': '1', # rtmpt + }) + formats.append(f) + self._sort_formats(formats) return { 'id': video_id, diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index 1a63ab56a..d2e4acbad 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -1,9 +1,14 @@ from __future__ import unicode_literals import re +import json from .common import InfoExtractor -from ..utils import find_xpath_attr, compat_str +from ..utils import ( + compat_str, + ExtractorError, + find_xpath_attr, +) class NBCIE(InfoExtractor): @@ -31,30 +36,82 @@ class NBCIE(InfoExtractor): class NBCNewsIE(InfoExtractor): - _VALID_URL = r'https?://www\.nbcnews\.com/video/.+?/(?P<id>\d+)' + _VALID_URL = r'''(?x)https?://www\.nbcnews\.com/ + ((video/.+?/(?P<id>\d+))| + (feature/[^/]+/(?P<title>.+))) + ''' - _TEST = { - 'url': 'http://www.nbcnews.com/video/nbc-news/52753292', - 'md5': '47abaac93c6eaf9ad37ee6c4463a5179', - 'info_dict': { - 'id': '52753292', - 'ext': 'flv', - 'title': 'Crew emerges after four-month Mars food study', - 'description': 'md5:24e632ffac72b35f8b67a12d1b6ddfc1', + _TESTS = [ + { + 'url': 'http://www.nbcnews.com/video/nbc-news/52753292', + 'md5': '47abaac93c6eaf9ad37ee6c4463a5179', + 'info_dict': { + 'id': '52753292', + 'ext': 'flv', + 'title': 'Crew emerges after four-month Mars food study', + 'description': 'md5:24e632ffac72b35f8b67a12d1b6ddfc1', + }, }, - } + { + 'url': 'http://www.nbcnews.com/feature/edward-snowden-interview/how-twitter-reacted-snowden-interview-n117236', + 'md5': 'b2421750c9f260783721d898f4c42063', + 'info_dict': { + 'id': 'I1wpAI_zmhsQ', + 'ext': 'flv', + 'title': 'How Twitter Reacted To The Snowden Interview', + 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64', + }, + 'add_ie': ['ThePlatform'], + }, + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id) - info = all_info.find('video') + if video_id is not None: + all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id) + info = all_info.find('video') - return { - 'id': video_id, - 'title': info.find('headline').text, - 'ext': 'flv', - 'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text, - 'description': compat_str(info.find('caption').text), - 'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text, - } + return { + 'id': video_id, + 'title': info.find('headline').text, + 'ext': 'flv', + 'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text, + 'description': compat_str(info.find('caption').text), + 'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text, + } + else: + # "feature" pages use theplatform.com + title = mobj.group('title') + webpage = self._download_webpage(url, title) + bootstrap_json = self._search_regex( + r'var bootstrapJson = ({.+})\s*$', webpage, 'bootstrap json', + flags=re.MULTILINE) + bootstrap = json.loads(bootstrap_json) + info = bootstrap['results'][0]['video'] + mpxid = info['mpxId'] + + base_urls = [ + info['fallbackPlaylistUrl'], + info['associatedPlaylistUrl'], + ] + + for base_url in base_urls: + playlist_url = base_url + '?form=MPXNBCNewsAPI' + all_videos = self._download_json(playlist_url, title)['videos'] + + try: + info = next(v for v in all_videos if v['mpxId'] == mpxid) + break + except StopIteration: + continue + + if info is None: + raise ExtractorError('Could not find video in playlists') + + return { + '_type': 'url', + # We get the best quality video + 'url': info['videoAssets'][-1]['publicUrl'], + 'ie_key': 'ThePlatform', + } diff --git a/youtube_dl/extractor/ndr.py b/youtube_dl/extractor/ndr.py index 53b34f5e6..94d5ba982 100644 --- a/youtube_dl/extractor/ndr.py +++ b/youtube_dl/extractor/ndr.py @@ -7,6 +7,7 @@ from .common import InfoExtractor from ..utils import ( ExtractorError, int_or_none, + qualities, ) @@ -17,15 +18,15 @@ class NDRIE(InfoExtractor): _TESTS = [ { - 'url': 'http://www.ndr.de/fernsehen/sendungen/markt/markt7959.html', - 'md5': 'e7a6079ca39d3568f4996cb858dd6708', + 'url': 'http://www.ndr.de/fernsehen/media/dienordreportage325.html', + 'md5': '4a4eeafd17c3058b65f0c8f091355855', 'note': 'Video file', 'info_dict': { - 'id': '7959', + 'id': '325', 'ext': 'mp4', - 'title': 'Markt - die ganze Sendung', - 'description': 'md5:af9179cf07f67c5c12dc6d9997e05725', - 'duration': 2655, + 'title': 'Blaue Bohnen aus Blocken', + 'description': 'md5:190d71ba2ccddc805ed01547718963bc', + 'duration': 1715, }, }, { @@ -57,7 +58,7 @@ class NDRIE(InfoExtractor): formats = [] - mp3_url = re.search(r'''{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page) + mp3_url = re.search(r'''\{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page) if mp3_url: formats.append({ 'url': mp3_url.group('audio'), @@ -66,15 +67,15 @@ class NDRIE(InfoExtractor): thumbnail = None - video_url = re.search(r'''3: {src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page) + video_url = re.search(r'''3: \{src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page) if video_url: - thumbnails = re.findall(r'''\d+: {src: "([^"]+)"(?: \|\| '[^']+')?, quality: '([^']+)'}''', page) + thumbnails = re.findall(r'''\d+: \{src: "([^"]+)"(?: \|\| '[^']+')?, quality: '([^']+)'}''', page) if thumbnails: - QUALITIES = ['xs', 's', 'm', 'l', 'xl'] - thumbnails.sort(key=lambda thumb: QUALITIES.index(thumb[1]) if thumb[1] in QUALITIES else -1) - thumbnail = 'http://www.ndr.de' + thumbnails[-1][0] + quality_key = qualities(['xs', 's', 'm', 'l', 'xl']) + largest = max(thumbnails, key=lambda thumb: quality_key(thumb[1])) + thumbnail = 'http://www.ndr.de' + largest[0] - for format_id in ['lo', 'hi', 'hq']: + for format_id in 'lo', 'hi', 'hq': formats.append({ 'url': '%s.%s.mp4' % (video_url.group('video'), format_id), 'format_id': format_id, diff --git a/youtube_dl/extractor/ndtv.py b/youtube_dl/extractor/ndtv.py index d81df3c10..95e7d63aa 100644 --- a/youtube_dl/extractor/ndtv.py +++ b/youtube_dl/extractor/ndtv.py @@ -1,22 +1,28 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor -from ..utils import month_by_name +from ..utils import ( + month_by_name, + int_or_none, +) class NDTVIE(InfoExtractor): _VALID_URL = r'^https?://(?:www\.)?ndtv\.com/video/player/[^/]*/[^/]*/(?P<id>[a-z0-9]+)' _TEST = { - u"url": u"http://www.ndtv.com/video/player/news/ndtv-exclusive-don-t-need-character-certificate-from-rahul-gandhi-says-arvind-kejriwal/300710", - u"file": u"300710.mp4", - u"md5": u"39f992dbe5fb531c395d8bbedb1e5e88", - u"info_dict": { - u"title": u"NDTV exclusive: Don't need character certificate from Rahul Gandhi, says Arvind Kejriwal", - u"description": u"In an exclusive interview to NDTV, Aam Aadmi Party's Arvind Kejriwal says it makes no difference to him that Rahul Gandhi said the Congress needs to learn from his party.", - u"upload_date": u"20131208", - u"duration": 1327, - u"thumbnail": u"http://i.ndtvimg.com/video/images/vod/medium/2013-12/big_300710_1386518307.jpg", + 'url': 'http://www.ndtv.com/video/player/news/ndtv-exclusive-don-t-need-character-certificate-from-rahul-gandhi-says-arvind-kejriwal/300710', + 'md5': '39f992dbe5fb531c395d8bbedb1e5e88', + 'info_dict': { + 'id': '300710', + 'ext': 'mp4', + 'title': "NDTV exclusive: Don't need character certificate from Rahul Gandhi, says Arvind Kejriwal", + 'description': 'md5:ab2d4b4a6056c5cb4caa6d729deabf02', + 'upload_date': '20131208', + 'duration': 1327, + 'thumbnail': 'http://i.ndtvimg.com/video/images/vod/medium/2013-12/big_300710_1386518307.jpg', }, } @@ -27,13 +33,12 @@ class NDTVIE(InfoExtractor): webpage = self._download_webpage(url, video_id) filename = self._search_regex( - r"__filename='([^']+)'", webpage, u'video filename') - video_url = (u'http://bitcast-b.bitgravity.com/ndtvod/23372/ndtv/%s' % + r"__filename='([^']+)'", webpage, 'video filename') + video_url = ('http://bitcast-b.bitgravity.com/ndtvod/23372/ndtv/%s' % filename) - duration_str = filename = self._search_regex( - r"__duration='([^']+)'", webpage, u'duration', fatal=False) - duration = None if duration_str is None else int(duration_str) + duration = int_or_none(self._search_regex( + r"__duration='([^']+)'", webpage, 'duration', fatal=False)) date_m = re.search(r'''(?x) <p\s+class="vod_dateline">\s* @@ -41,7 +46,7 @@ class NDTVIE(InfoExtractor): (?P<monthname>[A-Za-z]+)\s+(?P<day>[0-9]+),\s*(?P<year>[0-9]+) ''', webpage) upload_date = None - assert date_m + if date_m is not None: month = month_by_name(date_m.group('monthname')) if month is not None: @@ -49,14 +54,19 @@ class NDTVIE(InfoExtractor): date_m.group('year'), month, int(date_m.group('day'))) description = self._og_search_description(webpage) - READ_MORE = u' (Read more)' + READ_MORE = ' (Read more)' if description.endswith(READ_MORE): description = description[:-len(READ_MORE)] + title = self._og_search_title(webpage) + TITLE_SUFFIX = ' - NDTV' + if title.endswith(TITLE_SUFFIX): + title = title[:-len(TITLE_SUFFIX)] + return { 'id': video_id, 'url': video_url, - 'title': self._og_search_title(webpage), + 'title': title, 'description': description, 'thumbnail': self._og_search_thumbnail(webpage), 'duration': duration, diff --git a/youtube_dl/extractor/newstube.py b/youtube_dl/extractor/newstube.py index 2fd5b8f04..551bd4d7a 100644 --- a/youtube_dl/extractor/newstube.py +++ b/youtube_dl/extractor/newstube.py @@ -4,18 +4,19 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import ExtractorError class NewstubeIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?newstube\.ru/media/(?P<id>.+)' _TEST = { - 'url': 'http://newstube.ru/media/na-korable-progress-prodolzhaetsya-testirovanie-sistemy-kurs', + 'url': 'http://www.newstube.ru/media/telekanal-cnn-peremestil-gorod-slavyansk-v-krym', 'info_dict': { - 'id': 'd156a237-a6e9-4111-a682-039995f721f1', + 'id': '728e0ef2-e187-4012-bac0-5a081fdcb1f6', 'ext': 'flv', - 'title': 'На корабле «Прогресс» продолжается тестирование системы «Курс»', - 'description': 'md5:d0cbe7b4a6f600552617e48548d5dc77', - 'duration': 20.04, + 'title': 'Телеканал CNN переместил город Славянск в Крым', + 'description': 'md5:419a8c9f03442bc0b0a794d689360335', + 'duration': 31.05, }, 'params': { # rtmp download @@ -40,6 +41,10 @@ class NewstubeIE(InfoExtractor): def ns(s): return s.replace('/', '/%(ns)s') % {'ns': '{http://app1.newstube.ru/N2SiteWS/player.asmx}'} + error_message = player.find(ns('./ErrorMessage')) + if error_message is not None: + raise ExtractorError('%s returned error: %s' % (self.IE_NAME, error_message.text), expected=True) + session_id = player.find(ns('./SessionId')).text media_info = player.find(ns('./Medias/MediaInfo')) title = media_info.find(ns('./Name')).text diff --git a/youtube_dl/extractor/niconico.py b/youtube_dl/extractor/niconico.py index 517a72561..c0c139b5d 100644 --- a/youtube_dl/extractor/niconico.py +++ b/youtube_dl/extractor/niconico.py @@ -8,10 +8,9 @@ from ..utils import ( compat_urllib_parse, compat_urllib_request, compat_urlparse, - compat_str, - - ExtractorError, unified_strdate, + parse_duration, + int_or_none, ) @@ -30,6 +29,7 @@ class NiconicoIE(InfoExtractor): 'uploader_id': '2698420', 'upload_date': '20131123', 'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org', + 'duration': 33, }, 'params': { 'username': 'ydl.niconico@gmail.com', @@ -37,17 +37,20 @@ class NiconicoIE(InfoExtractor): }, } - _VALID_URL = r'^https?://(?:www\.|secure\.)?nicovideo\.jp/watch/([a-z][a-z][0-9]+)(?:.*)$' + _VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/((?:[a-z]{2})?[0-9]+)' _NETRC_MACHINE = 'niconico' + # Determine whether the downloader uses authentication to download video + _AUTHENTICATE = False def _real_initialize(self): - self._login() + if self._downloader.params.get('username', None) is not None: + self._AUTHENTICATE = True + + if self._AUTHENTICATE: + self._login() def _login(self): (username, password) = self._get_login_info() - if username is None: - # Login is required - raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) # Log in login_form_strs = { @@ -79,44 +82,66 @@ class NiconicoIE(InfoExtractor): 'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id, note='Downloading video info page') - # Get flv info - flv_info_webpage = self._download_webpage( - 'http://flapi.nicovideo.jp/api/getflv?v=' + video_id, - video_id, 'Downloading flv info') + if self._AUTHENTICATE: + # Get flv info + flv_info_webpage = self._download_webpage( + 'http://flapi.nicovideo.jp/api/getflv?v=' + video_id, + video_id, 'Downloading flv info') + else: + # Get external player info + ext_player_info = self._download_webpage( + 'http://ext.nicovideo.jp/thumb_watch/' + video_id, video_id) + thumb_play_key = self._search_regex( + r'\'thumbPlayKey\'\s*:\s*\'(.*?)\'', ext_player_info, 'thumbPlayKey') + + # Get flv info + flv_info_data = compat_urllib_parse.urlencode({ + 'k': thumb_play_key, + 'v': video_id + }) + flv_info_request = compat_urllib_request.Request( + 'http://ext.nicovideo.jp/thumb_watch', flv_info_data, + {'Content-Type': 'application/x-www-form-urlencoded'}) + flv_info_webpage = self._download_webpage( + flv_info_request, video_id, + note='Downloading flv info', errnote='Unable to download flv info') + video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0] # Start extracting information - video_title = video_info.find('.//title').text - video_extension = video_info.find('.//movie_type').text - video_format = video_extension.upper() - video_thumbnail = video_info.find('.//thumbnail_url').text - video_description = video_info.find('.//description').text - video_uploader_id = video_info.find('.//user_id').text - video_upload_date = unified_strdate(video_info.find('.//first_retrieve').text.split('+')[0]) - video_view_count = video_info.find('.//view_counter').text - video_webpage_url = video_info.find('.//watch_url').text - - # uploader - video_uploader = video_uploader_id - url = 'http://seiga.nicovideo.jp/api/user/info?id=' + video_uploader_id - try: - user_info = self._download_xml( - url, video_id, note='Downloading user information') - video_uploader = user_info.find('.//nickname').text - except ExtractorError as err: - self._downloader.report_warning('Unable to download user info webpage: %s' % compat_str(err)) + title = video_info.find('.//title').text + extension = video_info.find('.//movie_type').text + video_format = extension.upper() + thumbnail = video_info.find('.//thumbnail_url').text + description = video_info.find('.//description').text + upload_date = unified_strdate(video_info.find('.//first_retrieve').text.split('+')[0]) + view_count = int_or_none(video_info.find('.//view_counter').text) + comment_count = int_or_none(video_info.find('.//comment_num').text) + duration = parse_duration(video_info.find('.//length').text) + webpage_url = video_info.find('.//watch_url').text + + if video_info.find('.//ch_id') is not None: + uploader_id = video_info.find('.//ch_id').text + uploader = video_info.find('.//ch_name').text + elif video_info.find('.//user_id') is not None: + uploader_id = video_info.find('.//user_id').text + uploader = video_info.find('.//user_nickname').text + else: + uploader_id = uploader = None return { 'id': video_id, 'url': video_real_url, - 'title': video_title, - 'ext': video_extension, + 'title': title, + 'ext': extension, 'format': video_format, - 'thumbnail': video_thumbnail, - 'description': video_description, - 'uploader': video_uploader, - 'upload_date': video_upload_date, - 'uploader_id': video_uploader_id, - 'view_count': video_view_count, - 'webpage_url': video_webpage_url, + 'thumbnail': thumbnail, + 'description': description, + 'uploader': uploader, + 'upload_date': upload_date, + 'uploader_id': uploader_id, + 'view_count': view_count, + 'comment_count': comment_count, + 'duration': duration, + 'webpage_url': webpage_url, } diff --git a/youtube_dl/extractor/ninegag.py b/youtube_dl/extractor/ninegag.py index c2e7b67c7..33daa0dec 100644 --- a/youtube_dl/extractor/ninegag.py +++ b/youtube_dl/extractor/ninegag.py @@ -47,7 +47,7 @@ class NineGagIE(InfoExtractor): webpage = self._download_webpage(url, display_id) post_view = json.loads(self._html_search_regex( - r'var postView = new app\.PostView\({\s*post:\s*({.+?}),', webpage, 'post view')) + r'var postView = new app\.PostView\({\s*post:\s*({.+?}),\s*posts:\s*prefetchedCurrentPost', webpage, 'post view')) youtube_id = post_view['videoExternalId'] title = post_view['title'] diff --git a/youtube_dl/extractor/noco.py b/youtube_dl/extractor/noco.py index d451cd1bf..da203538d 100644 --- a/youtube_dl/extractor/noco.py +++ b/youtube_dl/extractor/noco.py @@ -35,7 +35,7 @@ class NocoIE(InfoExtractor): video_id = mobj.group('id') medias = self._download_json( - 'http://api.noco.tv/1.0/video/medias/%s' % video_id, video_id, 'Downloading video JSON') + 'https://api.noco.tv/1.0/video/medias/%s' % video_id, video_id, 'Downloading video JSON') formats = [] @@ -43,7 +43,7 @@ class NocoIE(InfoExtractor): format_id = fmt['quality_key'] file = self._download_json( - 'http://api.noco.tv/1.0/video/file/%s/fr/%s' % (format_id.lower(), video_id), + 'https://api.noco.tv/1.0/video/file/%s/fr/%s' % (format_id.lower(), video_id), video_id, 'Downloading %s video JSON' % format_id) file_url = file['file'] @@ -71,7 +71,7 @@ class NocoIE(InfoExtractor): self._sort_formats(formats) show = self._download_json( - 'http://api.noco.tv/1.0/shows/show/%s' % video_id, video_id, 'Downloading show JSON')[0] + 'https://api.noco.tv/1.0/shows/show/%s' % video_id, video_id, 'Downloading show JSON')[0] upload_date = unified_strdate(show['indexed']) uploader = show['partner_name'] diff --git a/youtube_dl/extractor/nowness.py b/youtube_dl/extractor/nowness.py index b1bcb7e54..6b2f3f55a 100644 --- a/youtube_dl/extractor/nowness.py +++ b/youtube_dl/extractor/nowness.py @@ -1,27 +1,42 @@ +# encoding: utf-8 from __future__ import unicode_literals import re from .brightcove import BrightcoveIE from .common import InfoExtractor -from ..utils import ( - ExtractorError, -) +from ..utils import ExtractorError class NownessIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?nowness\.com/[^?#]*?/(?P<id>[0-9]+)/(?P<slug>[^/]+?)(?:$|[?#])' - - _TEST = { - 'url': 'http://www.nowness.com/day/2013/6/27/3131/candor--the-art-of-gesticulation', - 'file': '2520295746001.mp4', - 'md5': '0ece2f70a7bd252c7b00f3070182d418', - 'info_dict': { - 'description': 'Candor: The Art of Gesticulation', - 'uploader': 'Nowness', - 'title': 'Candor: The Art of Gesticulation', - } - } + _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/[^?#]*?/(?P<id>[0-9]+)/(?P<slug>[^/]+?)(?:$|[?#])' + + _TESTS = [ + { + 'url': 'http://www.nowness.com/day/2013/6/27/3131/candor--the-art-of-gesticulation', + 'md5': '068bc0202558c2e391924cb8cc470676', + 'info_dict': { + 'id': '2520295746001', + 'ext': 'mp4', + 'title': 'Candor: The Art of Gesticulation', + 'description': 'Candor: The Art of Gesticulation', + 'thumbnail': 're:^https?://.*\.jpg', + 'uploader': 'Nowness', + } + }, + { + 'url': 'http://cn.nowness.com/day/2014/8/7/4069/kasper-bj-rke-ft-jaakko-eino-kalevi--tnr', + 'md5': 'e79cf125e387216f86b2e0a5b5c63aa3', + 'info_dict': { + 'id': '3716354522001', + 'ext': 'mp4', + 'title': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR', + 'description': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR', + 'thumbnail': 're:^https?://.*\.jpg', + 'uploader': 'Nowness', + } + }, + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py new file mode 100644 index 000000000..12e85a716 --- /dev/null +++ b/youtube_dl/extractor/npo.py @@ -0,0 +1,62 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + unified_strdate, +) + + +class NPOIE(InfoExtractor): + IE_NAME = 'npo.nl' + _VALID_URL = r'https?://www\.npo\.nl/[^/]+/[^/]+/(?P<id>[^/?]+)' + + _TEST = { + 'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719', + 'md5': '4b3f9c429157ec4775f2c9cb7b911016', + 'info_dict': { + 'id': 'VPWON_1220719', + 'ext': 'mp4', + 'title': 'Nieuwsuur', + 'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.', + 'upload_date': '20140622', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + metadata = self._download_json( + 'http://e.omroep.nl/metadata/aflevering/%s' % video_id, + video_id, + # We have to remove the javascript callback + transform_source=lambda j: re.sub(r'parseMetadata\((.*?)\);\n//.*$', r'\1', j) + ) + token_page = self._download_webpage( + 'http://ida.omroep.nl/npoplayer/i.js', + video_id, + note='Downloading token' + ) + token = self._search_regex(r'npoplayer.token = "(.+?)"', token_page, 'token') + streams_info = self._download_json( + 'http://ida.omroep.nl/odi/?prid=%s&puboptions=h264_std&adaptive=yes&token=%s' % (video_id, token), + video_id + ) + + stream_info = self._download_json( + streams_info['streams'][0] + '&type=json', + video_id, + 'Downloading stream info' + ) + + return { + 'id': video_id, + 'title': metadata['titel'], + 'ext': 'mp4', + 'url': stream_info['url'], + 'description': metadata['info'], + 'thumbnail': metadata['images'][-1]['url'], + 'upload_date': unified_strdate(metadata['gidsdatum']), + } diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index e6d68b836..96f0ae1eb 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -4,7 +4,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ExtractorError +from ..utils import ( + ExtractorError, + float_or_none, + unified_strdate, +) class NRKIE(InfoExtractor): @@ -64,4 +68,77 @@ class NRKIE(InfoExtractor): 'title': data['title'], 'description': data['description'], 'thumbnail': thumbnail, - }
\ No newline at end of file + } + + +class NRKTVIE(InfoExtractor): + _VALID_URL = r'http://tv\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})' + + _TESTS = [ + { + 'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014', + 'md5': '7b96112fbae1faf09a6f9ae1aff6cb84', + 'info_dict': { + 'id': 'MUHH48000314', + 'ext': 'flv', + 'title': '20 spørsmål', + 'description': 'md5:bdea103bc35494c143c6a9acdd84887a', + 'upload_date': '20140523', + 'duration': 1741.52, + } + }, + { + 'url': 'http://tv.nrk.no/program/mdfp15000514', + 'md5': 'af01795a31f1cf7265c8657534d8077b', + 'info_dict': { + 'id': 'mdfp15000514', + 'ext': 'flv', + 'title': 'Kunnskapskanalen: Grunnlovsjubiléet - Stor ståhei for ingenting', + 'description': 'md5:654c12511f035aed1e42bdf5db3b206a', + 'upload_date': '20140524', + 'duration': 4605.0, + } + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + page = self._download_webpage(url, video_id) + + title = self._html_search_meta('title', page, 'title') + description = self._html_search_meta('description', page, 'description') + thumbnail = self._html_search_regex(r'data-posterimage="([^"]+)"', page, 'thumbnail', fatal=False) + upload_date = unified_strdate(self._html_search_meta('rightsfrom', page, 'upload date', fatal=False)) + duration = float_or_none( + self._html_search_regex(r'data-duration="([^"]+)"', page, 'duration', fatal=False)) + + formats = [] + + f4m_url = re.search(r'data-media="([^"]+)"', page) + if f4m_url: + formats.append({ + 'url': f4m_url.group(1) + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', + 'format_id': 'f4m', + 'ext': 'flv', + }) + + m3u8_url = re.search(r'data-hls-media="([^"]+)"', page) + if m3u8_url: + formats.append({ + 'url': m3u8_url.group(1), + 'format_id': 'm3u8', + }) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/ntv.py b/youtube_dl/extractor/ntv.py index 733ed6c26..ed60314ec 100644 --- a/youtube_dl/extractor/ntv.py +++ b/youtube_dl/extractor/ntv.py @@ -5,7 +5,6 @@ import re from .common import InfoExtractor from ..utils import ( - ExtractorError, unescapeHTML ) diff --git a/youtube_dl/extractor/nuvid.py b/youtube_dl/extractor/nuvid.py index f0befa116..58ec81f91 100644 --- a/youtube_dl/extractor/nuvid.py +++ b/youtube_dl/extractor/nuvid.py @@ -3,6 +3,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import ( + parse_duration, + unified_strdate, + compat_urllib_request, +) class NuvidIE(InfoExtractor): @@ -13,8 +18,10 @@ class NuvidIE(InfoExtractor): 'info_dict': { 'id': '1310741', 'ext': 'mp4', - "title": "Horny babes show their awesome bodeis and", - "age_limit": 18, + 'title': 'Horny babes show their awesome bodeis and', + 'duration': 129, + 'upload_date': '20140508', + 'age_limit': 18, } } @@ -22,27 +29,46 @@ class NuvidIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - murl = url.replace('://www.', '://m.') - webpage = self._download_webpage(murl, video_id) - - title = self._html_search_regex( - r'<div class="title">\s+<h2[^>]*>([^<]+)</h2>', - webpage, 'title').strip() + formats = [] - url_end = self._html_search_regex( - r'href="(/mp4/[^"]+)"[^>]*data-link_type="mp4"', - webpage, 'video_url') - video_url = 'http://m.nuvid.com' + url_end + for dwnld_speed, format_id in [(0, '3gp'), (5, 'mp4')]: + request = compat_urllib_request.Request( + 'http://m.nuvid.com/play/%s' % video_id) + request.add_header('Cookie', 'skip_download_page=1; dwnld_speed=%d; adv_show=1' % dwnld_speed) + webpage = self._download_webpage( + request, video_id, 'Downloading %s page' % format_id) + video_url = self._html_search_regex( + r'<a\s+href="([^"]+)"\s+class="b_link">', webpage, '%s video URL' % format_id, fatal=False) + if not video_url: + continue + formats.append({ + 'url': video_url, + 'format_id': format_id, + }) - thumbnail = self._html_search_regex( - r'href="(/thumbs/[^"]+)"[^>]*data-link_type="thumbs"', - webpage, 'thumbnail URL', fatal=False) + webpage = self._download_webpage( + 'http://m.nuvid.com/video/%s' % video_id, video_id, 'Downloading video page') + title = self._html_search_regex( + [r'<span title="([^"]+)">', + r'<div class="thumb-holder video">\s*<h5[^>]*>([^<]+)</h5>'], webpage, 'title').strip() + thumbnails = [ + { + 'url': thumb_url, + } for thumb_url in re.findall(r'<img src="([^"]+)" alt="" />', webpage) + ] + thumbnail = thumbnails[0]['url'] if thumbnails else None + duration = parse_duration(self._html_search_regex( + r'<i class="fa fa-clock-o"></i>\s*(\d{2}:\d{2})', webpage, 'duration', fatal=False)) + upload_date = unified_strdate(self._html_search_regex( + r'<i class="fa fa-user"></i>\s*(\d{4}-\d{2}-\d{2})', webpage, 'upload date', fatal=False)) return { 'id': video_id, - 'url': video_url, - 'ext': 'mp4', 'title': title, + 'thumbnails': thumbnails, 'thumbnail': thumbnail, + 'duration': duration, + 'upload_date': upload_date, 'age_limit': 18, - } + 'formats': formats, + }
\ No newline at end of file diff --git a/youtube_dl/extractor/oe1.py b/youtube_dl/extractor/oe1.py deleted file mode 100644 index 38971ab4d..000000000 --- a/youtube_dl/extractor/oe1.py +++ /dev/null @@ -1,40 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import calendar -import datetime -import re - -from .common import InfoExtractor - -# audios on oe1.orf.at are only available for 7 days, so we can't -# add tests. - - -class OE1IE(InfoExtractor): - IE_DESC = 'oe1.orf.at' - _VALID_URL = r'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)' - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - show_id = mobj.group('id') - - data = self._download_json( - 'http://oe1.orf.at/programm/%s/konsole' % show_id, - show_id - ) - - timestamp = datetime.datetime.strptime('%s %s' % ( - data['item']['day_label'], - data['item']['time'] - ), '%d.%m.%Y %H:%M') - unix_timestamp = calendar.timegm(timestamp.utctimetuple()) - - return { - 'id': show_id, - 'title': data['item']['title'], - 'url': data['item']['url_stream'], - 'ext': 'mp3', - 'description': data['item'].get('info'), - 'timestamp': unix_timestamp - } diff --git a/youtube_dl/extractor/ooyala.py b/youtube_dl/extractor/ooyala.py index 13f12824c..2044e107e 100644 --- a/youtube_dl/extractor/ooyala.py +++ b/youtube_dl/extractor/ooyala.py @@ -3,23 +3,38 @@ import re import json from .common import InfoExtractor -from ..utils import unescapeHTML +from ..utils import ( + unescapeHTML, + ExtractorError, +) class OoyalaIE(InfoExtractor): _VALID_URL = r'(?:ooyala:|https?://.+?\.ooyala\.com/.*?(?:embedCode|ec)=)(?P<id>.+?)(&|$)' - _TEST = { - # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video - 'url': 'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', - 'md5': '3f5cceb3a7bf461d6c29dc466cf8033c', - 'info_dict': { - 'id': 'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', - 'ext': 'mp4', - 'title': 'Explaining Data Recovery from Hard Drives and SSDs', - 'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.', + _TESTS = [ + { + # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video + 'url': 'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', + 'md5': '3f5cceb3a7bf461d6c29dc466cf8033c', + 'info_dict': { + 'id': 'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', + 'ext': 'mp4', + 'title': 'Explaining Data Recovery from Hard Drives and SSDs', + 'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.', + }, + }, { + # Only available for ipad + 'url': 'http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0', + 'md5': '4b9754921fddb68106e48c142e2a01e6', + 'info_dict': { + 'id': 'x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0', + 'ext': 'mp4', + 'title': 'Simulation Overview - Levels of Simulation', + 'description': '', + }, }, - } + ] @staticmethod def _url_for_embed_code(embed_code): @@ -47,13 +62,30 @@ class OoyalaIE(InfoExtractor): player = self._download_webpage(player_url, embedCode) mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="', player, 'mobile player url') - mobile_player = self._download_webpage(mobile_url, embedCode) - videos_info = self._search_regex( - r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);', - mobile_player, 'info').replace('\\"','"') - videos_more_info = self._search_regex(r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"','"') + # Looks like some videos are only available for particular devices + # (e.g. http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0 + # is only available for ipad) + # Working around with fetching URLs for all the devices found starting with 'unknown' + # until we succeed or eventually fail for each device. + devices = re.findall(r'device\s*=\s*"([^"]+)";', player) + devices.remove('unknown') + devices.insert(0, 'unknown') + for device in devices: + mobile_player = self._download_webpage( + '%s&device=%s' % (mobile_url, device), embedCode, + 'Downloading mobile player JS for %s device' % device) + videos_info = self._search_regex( + r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);', + mobile_player, 'info', fatal=False, default=None) + if videos_info: + break + if not videos_info: + raise ExtractorError('Unable to extract info') + videos_info = videos_info.replace('\\"', '"') + videos_more_info = self._search_regex( + r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"', '"') videos_info = json.loads(videos_info) - videos_more_info =json.loads(videos_more_info) + videos_more_info = json.loads(videos_more_info) if videos_more_info.get('lineup'): videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])] diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index 03421d1d5..011e6be13 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -3,6 +3,8 @@ from __future__ import unicode_literals import json import re +import calendar +import datetime from .common import InfoExtractor from ..utils import ( @@ -12,7 +14,9 @@ from ..utils import ( ) -class ORFIE(InfoExtractor): +class ORFTVthekIE(InfoExtractor): + IE_NAME = 'orf:tvthek' + IE_DESC = 'ORF TVthek' _VALID_URL = r'https?://tvthek\.orf\.at/(?:programs/.+?/episodes|topics/.+?|program/[^/]+)/(?P<id>\d+)' _TEST = { @@ -105,3 +109,73 @@ class ORFIE(InfoExtractor): 'entries': entries, 'id': playlist_id, } + + +# Audios on ORF radio are only available for 7 days, so we can't add tests. + + +class ORFOE1IE(InfoExtractor): + IE_NAME = 'orf:oe1' + IE_DESC = 'Radio Österreich 1' + _VALID_URL = r'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + show_id = mobj.group('id') + + data = self._download_json( + 'http://oe1.orf.at/programm/%s/konsole' % show_id, + show_id + ) + + timestamp = datetime.datetime.strptime('%s %s' % ( + data['item']['day_label'], + data['item']['time'] + ), '%d.%m.%Y %H:%M') + unix_timestamp = calendar.timegm(timestamp.utctimetuple()) + + return { + 'id': show_id, + 'title': data['item']['title'], + 'url': data['item']['url_stream'], + 'ext': 'mp3', + 'description': data['item'].get('info'), + 'timestamp': unix_timestamp + } + + +class ORFFM4IE(InfoExtractor): + IE_DESC = 'orf:fm4' + IE_DESC = 'radio FM4' + _VALID_URL = r'http://fm4\.orf\.at/7tage/?#(?P<date>[0-9]+)/(?P<show>\w+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + show_date = mobj.group('date') + show_id = mobj.group('show') + + data = self._download_json( + 'http://audioapi.orf.at/fm4/json/2.0/broadcasts/%s/4%s' % (show_date, show_id), + show_id + ) + + def extract_entry_dict(info, title, subtitle): + return { + 'id': info['loopStreamId'].replace('.mp3', ''), + 'url': 'http://loopstream01.apa.at/?channel=fm4&id=%s' % info['loopStreamId'], + 'title': title, + 'description': subtitle, + 'duration': (info['end'] - info['start']) / 1000, + 'timestamp': info['start'] / 1000, + 'ext': 'mp3' + } + + entries = [extract_entry_dict(t, data['title'], data['subtitle']) for t in data['streams']] + + return { + '_type': 'playlist', + 'id': show_id, + 'title': data['title'], + 'description': data['subtitle'], + 'entries': entries + }
\ No newline at end of file diff --git a/youtube_dl/extractor/patreon.py b/youtube_dl/extractor/patreon.py new file mode 100644 index 000000000..707a54e3a --- /dev/null +++ b/youtube_dl/extractor/patreon.py @@ -0,0 +1,101 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urlparse, + js_to_json, +) + + +class PatreonIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?patreon\.com/creation\?hid=(.+)' + _TESTS = [ + { + 'url': 'http://www.patreon.com/creation?hid=743933', + 'md5': 'e25505eec1053a6e6813b8ed369875cc', + 'info_dict': { + 'id': '743933', + 'ext': 'mp3', + 'title': 'Episode 166: David Smalley of Dogma Debate', + 'uploader': 'Cognitive Dissonance Podcast', + 'thumbnail': 're:^https?://.*$', + }, + }, + { + 'url': 'http://www.patreon.com/creation?hid=754133', + 'md5': '3eb09345bf44bf60451b8b0b81759d0a', + 'info_dict': { + 'id': '754133', + 'ext': 'mp3', + 'title': 'CD 167 Extra', + 'uploader': 'Cognitive Dissonance Podcast', + 'thumbnail': 're:^https?://.*$', + }, + }, + ] + + # Currently Patreon exposes download URL via hidden CSS, so login is not + # needed. Keeping this commented for when this inevitably changes. + ''' + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + + login_form = { + 'redirectUrl': 'http://www.patreon.com/', + 'email': username, + 'password': password, + } + + request = compat_urllib_request.Request( + 'https://www.patreon.com/processLogin', + compat_urllib_parse.urlencode(login_form).encode('utf-8') + ) + login_page = self._download_webpage(request, None, note='Logging in as %s' % username) + + if re.search(r'onLoginFailed', login_page): + raise ExtractorError('Unable to login, incorrect username and/or password', expected=True) + + def _real_initialize(self): + self._login() + ''' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group(1) + + webpage = self._download_webpage(url, video_id) + title = self._og_search_title(webpage).strip() + + attach_fn = self._html_search_regex( + r'<div class="attach"><a target="_blank" href="([^"]+)">', + webpage, 'attachment URL', default=None) + if attach_fn is not None: + video_url = 'http://www.patreon.com' + attach_fn + thumbnail = self._og_search_thumbnail(webpage) + uploader = self._html_search_regex( + r'<strong>(.*?)</strong> is creating', webpage, 'uploader') + else: + playlist_js = self._search_regex( + r'(?s)new\s+jPlayerPlaylist\(\s*\{\s*[^}]*},\s*(\[.*?,?\s*\])', + webpage, 'playlist JSON') + playlist_json = js_to_json(playlist_js) + playlist = json.loads(playlist_json) + data = playlist[0] + video_url = self._proto_relative_url(data['mp3']) + thumbnail = self._proto_relative_url(data.get('cover')) + uploader = data.get('artist') + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp3', + 'title': title, + 'uploader': uploader, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index 64cded707..2adfde909 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -20,27 +20,74 @@ class PBSIE(InfoExtractor): ) ''' - _TEST = { - 'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/', - 'md5': 'ce1888486f0908d555a8093cac9a7362', - 'info_dict': { - 'id': '2365006249', - 'ext': 'mp4', - 'title': 'A More Perfect Union', - 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a', - 'duration': 3190, + _TESTS = [ + { + 'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/', + 'md5': 'ce1888486f0908d555a8093cac9a7362', + 'info_dict': { + 'id': '2365006249', + 'ext': 'mp4', + 'title': 'A More Perfect Union', + 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a', + 'duration': 3190, + }, + }, + { + 'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/', + 'md5': '143c98aa54a346738a3d78f54c925321', + 'info_dict': { + 'id': '2365297690', + 'ext': 'mp4', + 'title': 'Losing Iraq', + 'description': 'md5:f5bfbefadf421e8bb8647602011caf8e', + 'duration': 5050, + }, + }, + { + 'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/', + 'md5': 'b19856d7f5351b17a5ab1dc6a64be633', + 'info_dict': { + 'id': '2201174722', + 'ext': 'mp4', + 'title': 'Cyber Schools Gain Popularity, but Quality Questions Persist', + 'description': 'md5:5871c15cba347c1b3d28ac47a73c7c28', + 'duration': 801, + }, }, - } + { + 'url': 'http://www.pbs.org/wnet/gperf/dudamel-conducts-verdi-requiem-hollywood-bowl-full-episode/3374/', + 'md5': 'c62859342be2a0358d6c9eb306595978', + 'info_dict': { + 'id': '2365297708', + 'ext': 'mp4', + 'description': 'md5:68d87ef760660eb564455eb30ca464fe', + 'title': 'Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full', + 'duration': 6559, + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + ] - def _real_extract(self, url): + def _extract_ids(self, url): mobj = re.match(self._VALID_URL, url) presumptive_id = mobj.group('presumptive_id') display_id = presumptive_id if presumptive_id: webpage = self._download_webpage(url, display_id) + + MEDIA_ID_REGEXES = [ + r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed + r'class="coveplayerid">([^<]+)<', # coveplayer + ] + + media_id = self._search_regex( + MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None) + if media_id: + return media_id, presumptive_id + url = self._search_regex( - r'<iframe\s+id=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>', + r'<iframe\s+(?:class|id)=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>', webpage, 'player URL') mobj = re.match(self._VALID_URL, url) @@ -57,6 +104,11 @@ class PBSIE(InfoExtractor): video_id = mobj.group('id') display_id = video_id + return video_id, display_id + + def _real_extract(self, url): + video_id, display_id = self._extract_ids(url) + info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id info = self._download_json(info_url, display_id) diff --git a/youtube_dl/extractor/playfm.py b/youtube_dl/extractor/playfm.py new file mode 100644 index 000000000..72df4d842 --- /dev/null +++ b/youtube_dl/extractor/playfm.py @@ -0,0 +1,82 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + compat_urllib_request, + ExtractorError, + float_or_none, + int_or_none, +) + + +class PlayFMIE(InfoExtractor): + IE_NAME = 'play.fm' + _VALID_URL = r'https?://(?:www\.)?play\.fm/[^?#]*(?P<upload_date>[0-9]{8})(?P<id>[0-9]{6})(?:$|[?#])' + + _TEST = { + 'url': 'http://www.play.fm/recording/leipzigelectronicmusicbatofarparis_fr20140712137220', + 'md5': 'c505f8307825a245d0c7ad1850001f22', + 'info_dict': { + 'id': '137220', + 'ext': 'mp3', + 'title': 'LEIPZIG ELECTRONIC MUSIC @ Batofar (Paris,FR) - 2014-07-12', + 'uploader': 'Sven Tasnadi', + 'uploader_id': 'sventasnadi', + 'duration': 5627.428, + 'upload_date': '20140712', + 'view_count': int, + 'thumbnail': 're:^https?://.*\.jpg$', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + upload_date = mobj.group('upload_date') + + rec_data = compat_urllib_parse.urlencode({'rec_id': video_id}) + req = compat_urllib_request.Request( + 'http://www.play.fm/flexRead/recording', data=rec_data) + req.add_header('Content-Type', 'application/x-www-form-urlencoded') + rec_doc = self._download_xml(req, video_id) + + error_node = rec_doc.find('./error') + if error_node is not None: + raise ExtractorError('An error occured: %s (code %s)' % ( + error_node.text, rec_doc.find('./status').text)) + + recording = rec_doc.find('./recording') + title = recording.find('./title').text + view_count = int_or_none(recording.find('./stats/playcount').text) + duration = float_or_none(recording.find('./duration').text, scale=1000) + thumbnail = recording.find('./image').text + + artist = recording.find('./artists/artist') + uploader = artist.find('./name').text + uploader_id = artist.find('./slug').text + + video_url = '%s//%s/%s/%s/offset/0/sh/%s/rec/%s/jingle/%s/loc/%s' % ( + 'http:', recording.find('./url').text, + recording.find('./_class').text, recording.find('./file_id').text, + rec_doc.find('./uuid').text, video_id, + rec_doc.find('./jingle/file_id').text, + 'http%3A%2F%2Fwww.play.fm%2Fplayer', + ) + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp3', + 'filesize': int_or_none(recording.find('./size').text), + 'title': title, + 'upload_date': upload_date, + 'view_count': view_count, + 'duration': duration, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'uploader_id': uploader_id, + } diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 7dd3dca0d..4118ee956 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -45,7 +45,7 @@ class PornHubIE(InfoExtractor): video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title') video_uploader = self._html_search_regex( - r'(?s)<div class="video-info-row">\s*From: .+?<(?:a href="/users/|<span class="username)[^>]+>(.+?)<', + r'(?s)From: .+?<(?:a href="/users/|<span class="username)[^>]+>(.+?)<', webpage, 'uploader', fatal=False) thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False) if thumbnail: diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py index e4c4ad714..da64a1a7b 100644 --- a/youtube_dl/extractor/prosiebensat1.py +++ b/youtube_dl/extractor/prosiebensat1.py @@ -158,19 +158,19 @@ class ProSiebenSat1IE(InfoExtractor): _CLIPID_REGEXES = [ r'"clip_id"\s*:\s+"(\d+)"', r'clipid: "(\d+)"', - r'clipId=(\d+)', + r'clip[iI]d=(\d+)', ] _TITLE_REGEXES = [ r'<h2 class="subtitle" itemprop="name">\s*(.+?)</h2>', r'<header class="clearfix">\s*<h3>(.+?)</h3>', r'<!-- start video -->\s*<h1>(.+?)</h1>', - r'<div class="ep-femvideos-pi4-video-txt">\s*<h2>(.+?)</h2>', + r'<h1 class="att-name">\s*(.+?)</h1>', ] _DESCRIPTION_REGEXES = [ r'<p itemprop="description">\s*(.+?)</p>', r'<div class="videoDecription">\s*<p><strong>Beschreibung</strong>: (.+?)</p>', r'<div class="g-plusone" data-size="medium"></div>\s*</div>\s*</header>\s*(.+?)\s*<footer>', - r'<p>(.+?)</p>\s*<div class="ep-femvideos-pi4-video-footer">', + r'<p class="att-description">\s*(.+?)\s*</p>', ] _UPLOAD_DATE_REGEXES = [ r'<meta property="og:published_time" content="(.+?)">', diff --git a/youtube_dl/extractor/pyvideo.py b/youtube_dl/extractor/pyvideo.py index 0bc0859b4..6d5732d45 100644 --- a/youtube_dl/extractor/pyvideo.py +++ b/youtube_dl/extractor/pyvideo.py @@ -46,7 +46,7 @@ class PyvideoIE(InfoExtractor): return self.url_result(m_youtube.group(1), 'Youtube') title = self._html_search_regex( - r'<div class="section">.*?<h3(?:\s+class="[^"]*")?>([^>]+?)</h3>', + r'<div class="section">\s*<h3(?:\s+class="[^"]*"[^>]*)?>([^>]+?)</h3>', webpage, 'title', flags=re.DOTALL) video_url = self._search_regex( [r'<source src="(.*?)"', r'<dt>Download</dt>.*?<a href="(.+?)"'], diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py new file mode 100644 index 000000000..ba3dd707f --- /dev/null +++ b/youtube_dl/extractor/rai.py @@ -0,0 +1,122 @@ +from __future__ import unicode_literals + +import re + +from .subtitles import SubtitlesInfoExtractor +from ..utils import ( + parse_duration, + unified_strdate, + compat_urllib_parse, +) + + +class RaiIE(SubtitlesInfoExtractor): + _VALID_URL = r'(?P<url>http://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html)' + _TESTS = [ + { + 'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html', + 'md5': 'c064c0b2d09c278fb293116ef5d0a32d', + 'info_dict': { + 'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391', + 'ext': 'mp4', + 'title': 'Report del 07/04/2014', + 'description': 'md5:f27c544694cacb46a078db84ec35d2d9', + 'upload_date': '20140407', + 'duration': 6160, + } + }, + { + 'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html', + 'md5': '8bb9c151924ce241b74dd52ef29ceafa', + 'info_dict': { + 'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9', + 'ext': 'mp4', + 'title': 'TG PRIMO TEMPO', + 'description': '', + 'upload_date': '20140612', + 'duration': 1758, + }, + 'skip': 'Error 404', + }, + { + 'url': 'http://www.rainews.it/dl/rainews/media/state-of-the-net-Antonella-La-Carpia-regole-virali-7aafdea9-0e5d-49d5-88a6-7e65da67ae13.html', + 'md5': '35cf7c229f22eeef43e48b5cf923bef0', + 'info_dict': { + 'id': '7aafdea9-0e5d-49d5-88a6-7e65da67ae13', + 'ext': 'mp4', + 'title': 'State of the Net, Antonella La Carpia: regole virali', + 'description': 'md5:b0ba04a324126903e3da7763272ae63c', + 'upload_date': '20140613', + }, + 'skip': 'Error 404', + }, + { + 'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-b4a49761-e0cc-4b14-8736-2729f6f73132-tg2.html', + 'md5': '35694f062977fe6619943f08ed935730', + 'info_dict': { + 'id': 'b4a49761-e0cc-4b14-8736-2729f6f73132', + 'ext': 'mp4', + 'title': 'Alluvione in Sardegna e dissesto idrogeologico', + 'description': 'Edizione delle ore 20:30 ', + } + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + media = self._download_json('%s?json' % mobj.group('url'), video_id, 'Downloading video JSON') + + title = media.get('name') + description = media.get('desc') + thumbnail = media.get('image_300') or media.get('image_medium') or media.get('image') + duration = parse_duration(media.get('length')) + uploader = media.get('author') + upload_date = unified_strdate(media.get('date')) + + formats = [] + + for format_id in ['wmv', 'm3u8', 'mediaUri', 'h264']: + media_url = media.get(format_id) + if not media_url: + continue + formats.append({ + 'url': media_url, + 'format_id': format_id, + 'ext': 'mp4', + }) + + if self._downloader.params.get('listsubtitles', False): + page = self._download_webpage(url, video_id) + self._list_available_subtitles(video_id, page) + return + + subtitles = {} + if self._have_to_download_any_subtitles: + page = self._download_webpage(url, video_id) + subtitles = self.extract_subtitles(video_id, page) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'upload_date': upload_date, + 'duration': duration, + 'formats': formats, + 'subtitles': subtitles, + } + + def _get_available_subtitles(self, video_id, webpage): + subtitles = {} + m = re.search(r'<meta name="closedcaption" content="(?P<captions>[^"]+)"', webpage) + if m: + captions = m.group('captions') + STL_EXT = '.stl' + SRT_EXT = '.srt' + if captions.endswith(STL_EXT): + captions = captions[:-len(STL_EXT)] + SRT_EXT + subtitles['it'] = 'http://www.rai.tv%s' % compat_urllib_parse.quote(captions) + return subtitles
\ No newline at end of file diff --git a/youtube_dl/extractor/redtube.py b/youtube_dl/extractor/redtube.py index 4295cf93a..d1e12dd8d 100644 --- a/youtube_dl/extractor/redtube.py +++ b/youtube_dl/extractor/redtube.py @@ -35,9 +35,7 @@ class RedTubeIE(InfoExtractor): r'<h1 class="videoTitle[^"]*">(.+?)</h1>', webpage, u'title') - video_thumbnail = self._html_search_regex( - r'playerInnerHTML.+?<img\s+src="(.+?)"', - webpage, u'thumbnail', fatal=False) + video_thumbnail = self._og_search_thumbnail(webpage) # No self-labeling, but they describe themselves as # "Home of Videos Porno" diff --git a/youtube_dl/extractor/reverbnation.py b/youtube_dl/extractor/reverbnation.py new file mode 100644 index 000000000..ec7e7df7b --- /dev/null +++ b/youtube_dl/extractor/reverbnation.py @@ -0,0 +1,44 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import str_or_none + + +class ReverbNationIE(InfoExtractor): + _VALID_URL = r'^https?://(?:www\.)?reverbnation\.com/.*?/song/(?P<id>\d+).*?$' + _TESTS = [{ + 'url': 'http://www.reverbnation.com/alkilados/song/16965047-mona-lisa', + 'md5': '3da12ebca28c67c111a7f8b262d3f7a7', + 'info_dict': { + "id": "16965047", + "ext": "mp3", + "title": "MONA LISA", + "uploader": "ALKILADOS", + "uploader_id": "216429", + "thumbnail": "re:^https://gp1\.wac\.edgecastcdn\.net/.*?\.jpg$" + }, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + song_id = mobj.group('id') + + api_res = self._download_json( + 'https://api.reverbnation.com/song/%s' % song_id, + song_id, + note='Downloading information of song %s' % song_id + ) + + return { + 'id': song_id, + 'title': api_res.get('name'), + 'url': api_res.get('url'), + 'uploader': api_res.get('artist', {}).get('name'), + 'uploader_id': str_or_none(api_res.get('artist', {}).get('id')), + 'thumbnail': self._proto_relative_url( + api_res.get('image', api_res.get('thumbnail'))), + 'ext': 'mp3', + 'vcodec': 'none', + } diff --git a/youtube_dl/extractor/rtbf.py b/youtube_dl/extractor/rtbf.py index 205f8a167..dce64e151 100644 --- a/youtube_dl/extractor/rtbf.py +++ b/youtube_dl/extractor/rtbf.py @@ -30,7 +30,7 @@ class RTBFIE(InfoExtractor): page = self._download_webpage('https://www.rtbf.be/video/embed?id=%s' % video_id, video_id) data = json.loads(self._html_search_regex( - r'<div class="js-player-embed" data-video="([^"]+)"', page, 'data video'))['data'] + r'<div class="js-player-embed(?: player-embed)?" data-video="([^"]+)"', page, 'data video'))['data'] video_url = data.get('downloadUrl') or data.get('url') diff --git a/youtube_dl/extractor/rtlnl.py b/youtube_dl/extractor/rtlnl.py new file mode 100644 index 000000000..14928cd62 --- /dev/null +++ b/youtube_dl/extractor/rtlnl.py @@ -0,0 +1,52 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class RtlXlIE(InfoExtractor): + IE_NAME = 'rtlxl.nl' + _VALID_URL = r'https?://www\.rtlxl\.nl/#!/[^/]+/(?P<uuid>[^/?]+)' + + _TEST = { + 'url': 'http://www.rtlxl.nl/#!/rtl-nieuws-132237/6e4203a6-0a5e-3596-8424-c599a59e0677', + 'info_dict': { + 'id': '6e4203a6-0a5e-3596-8424-c599a59e0677', + 'ext': 'flv', + 'title': 'RTL Nieuws - Laat', + 'description': 'Dagelijks het laatste nieuws uit binnen- en ' + 'buitenland. Voor nog meer nieuws kunt u ook gebruikmaken van ' + 'onze mobiele apps.', + 'timestamp': 1408051800, + 'upload_date': '20140814', + }, + 'params': { + # We download the first bytes of the first fragment, it can't be + # processed by the f4m downloader beacuse it isn't complete + 'skip_download': True, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + uuid = mobj.group('uuid') + + info = self._download_json( + 'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=flash/' % uuid, + uuid) + meta = info['meta'] + material = info['material'][0] + episode_info = info['episodes'][0] + + f4m_url = 'http://manifest.us.rtl.nl' + material['videopath'] + progname = info['abstracts'][0]['name'] + subtitle = material['title'] or info['episodes'][0]['name'] + + return { + 'id': uuid, + 'title': '%s - %s' % (progname, subtitle), + 'formats': self._extract_f4m_formats(f4m_url, uuid), + 'timestamp': material['original_date'], + 'description': episode_info['synopsis'], + } diff --git a/youtube_dl/extractor/rtlnow.py b/youtube_dl/extractor/rtlnow.py index 4835ec5ec..a45884b25 100644 --- a/youtube_dl/extractor/rtlnow.py +++ b/youtube_dl/extractor/rtlnow.py @@ -92,16 +92,7 @@ class RTLnowIE(InfoExtractor): }, { 'url': 'http://www.n-tvnow.de/deluxe-alles-was-spass-macht/thema-ua-luxushotel-fuer-vierbeiner.php?container_id=153819&player=1&season=0', - 'info_dict': { - 'id': '153819', - 'ext': 'flv', - 'title': 'Deluxe - Alles was Spaß macht - Thema u.a.: Luxushotel für Vierbeiner', - 'description': 'md5:c3705e1bb32e1a5b2bcd634fc065c631', - 'thumbnail': 'http://autoimg.static-fra.de/ntvnow/383157/1500x1500/image2.jpg', - 'upload_date': '20140221', - 'duration': 2429, - }, - 'skip': 'Only works from Germany', + 'only_matching': True, }, ] diff --git a/youtube_dl/extractor/rtve.py b/youtube_dl/extractor/rtve.py index 77fd08dde..c2228b2f0 100644 --- a/youtube_dl/extractor/rtve.py +++ b/youtube_dl/extractor/rtve.py @@ -17,7 +17,7 @@ class RTVEALaCartaIE(InfoExtractor): _TEST = { 'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/', - 'md5': '18fcd45965bdd076efdb12cd7f6d7b9e', + 'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43', 'info_dict': { 'id': '2491869', 'ext': 'mp4', diff --git a/youtube_dl/extractor/ruhd.py b/youtube_dl/extractor/ruhd.py new file mode 100644 index 000000000..55b58e5e6 --- /dev/null +++ b/youtube_dl/extractor/ruhd.py @@ -0,0 +1,46 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class RUHDIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?ruhd\.ru/play\.php\?vid=(?P<id>\d+)' + _TEST = { + 'url': 'http://www.ruhd.ru/play.php?vid=207', + 'md5': 'd1a9ec4edf8598e3fbd92bb16072ba83', + 'info_dict': { + 'id': '207', + 'ext': 'divx', + 'title': 'КОТ бааааам', + 'description': 'классный кот)', + 'thumbnail': 're:^http://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex( + r'<param name="src" value="([^"]+)"', webpage, 'video url') + title = self._html_search_regex( + r'<title>([^<]+) RUHD.ru - Видео Высокого качества №1 в России!</title>', webpage, 'title') + description = self._html_search_regex( + r'(?s)<div id="longdesc">(.+?)<span id="showlink">', webpage, 'description', fatal=False) + thumbnail = self._html_search_regex( + r'<param name="previewImage" value="([^"]+)"', webpage, 'thumbnail', fatal=False) + if thumbnail: + thumbnail = 'http://www.ruhd.ru' + thumbnail + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/sapo.py b/youtube_dl/extractor/sapo.py new file mode 100644 index 000000000..172cc1275 --- /dev/null +++ b/youtube_dl/extractor/sapo.py @@ -0,0 +1,119 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + unified_strdate, +) + + +class SapoIE(InfoExtractor): + IE_DESC = 'SAPO Vídeos' + _VALID_URL = r'https?://(?:(?:v2|www)\.)?videos\.sapo\.(?:pt|cv|ao|mz|tl)/(?P<id>[\da-zA-Z]{20})' + + _TESTS = [ + { + 'url': 'http://videos.sapo.pt/UBz95kOtiWYUMTA5Ghfi', + 'md5': '79ee523f6ecb9233ac25075dee0eda83', + 'note': 'SD video', + 'info_dict': { + 'id': 'UBz95kOtiWYUMTA5Ghfi', + 'ext': 'mp4', + 'title': 'Benfica - Marcas na Hitória', + 'description': 'md5:c9082000a128c3fd57bf0299e1367f22', + 'duration': 264, + 'uploader': 'tiago_1988', + 'upload_date': '20080229', + 'categories': ['benfica', 'cabral', 'desporto', 'futebol', 'geovanni', 'hooijdonk', 'joao', 'karel', 'lisboa', 'miccoli'], + }, + }, + { + 'url': 'http://videos.sapo.pt/IyusNAZ791ZdoCY5H5IF', + 'md5': '90a2f283cfb49193fe06e861613a72aa', + 'note': 'HD video', + 'info_dict': { + 'id': 'IyusNAZ791ZdoCY5H5IF', + 'ext': 'mp4', + 'title': 'Codebits VII - Report', + 'description': 'md5:6448d6fd81ce86feac05321f354dbdc8', + 'duration': 144, + 'uploader': 'codebits', + 'upload_date': '20140427', + 'categories': ['codebits', 'codebits2014'], + }, + }, + { + 'url': 'http://v2.videos.sapo.pt/yLqjzPtbTimsn2wWBKHz', + 'md5': 'e5aa7cc0bdc6db9b33df1a48e49a15ac', + 'note': 'v2 video', + 'info_dict': { + 'id': 'yLqjzPtbTimsn2wWBKHz', + 'ext': 'mp4', + 'title': 'Hipnose Condicionativa 4', + 'description': 'md5:ef0481abf8fb4ae6f525088a6dadbc40', + 'duration': 692, + 'uploader': 'sapozen', + 'upload_date': '20090609', + 'categories': ['condicionativa', 'heloisa', 'hipnose', 'miranda', 'sapo', 'zen'], + }, + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + item = self._download_xml( + 'http://rd3.videos.sapo.pt/%s/rss2' % video_id, video_id).find('./channel/item') + + title = item.find('./title').text + description = item.find('./{http://videos.sapo.pt/mrss/}synopse').text + thumbnail = item.find('./{http://search.yahoo.com/mrss/}content').get('url') + duration = parse_duration(item.find('./{http://videos.sapo.pt/mrss/}time').text) + uploader = item.find('./{http://videos.sapo.pt/mrss/}author').text + upload_date = unified_strdate(item.find('./pubDate').text) + view_count = int(item.find('./{http://videos.sapo.pt/mrss/}views').text) + comment_count = int(item.find('./{http://videos.sapo.pt/mrss/}comment_count').text) + tags = item.find('./{http://videos.sapo.pt/mrss/}tags').text + categories = tags.split() if tags else [] + age_limit = 18 if item.find('./{http://videos.sapo.pt/mrss/}m18').text == 'true' else 0 + + video_url = item.find('./{http://videos.sapo.pt/mrss/}videoFile').text + video_size = item.find('./{http://videos.sapo.pt/mrss/}videoSize').text.split('x') + + formats = [{ + 'url': video_url, + 'ext': 'mp4', + 'format_id': 'sd', + 'width': int(video_size[0]), + 'height': int(video_size[1]), + }] + + if item.find('./{http://videos.sapo.pt/mrss/}HD').text == 'true': + formats.append({ + 'url': re.sub(r'/mov/1$', '/mov/39', video_url), + 'ext': 'mp4', + 'format_id': 'hd', + 'width': 1280, + 'height': 720, + }) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'uploader': uploader, + 'upload_date': upload_date, + 'view_count': view_count, + 'comment_count': comment_count, + 'categories': categories, + 'age_limit': age_limit, + 'formats': formats, + } diff --git a/youtube_dl/extractor/savefrom.py b/youtube_dl/extractor/savefrom.py index 198a08c1c..5b7367b94 100644 --- a/youtube_dl/extractor/savefrom.py +++ b/youtube_dl/extractor/savefrom.py @@ -20,7 +20,7 @@ class SaveFromIE(InfoExtractor): 'upload_date': '20120816', 'uploader': 'Howcast', 'uploader_id': 'Howcast', - 'description': 'md5:4f0aac94361a12e1ce57d74f85265175', + 'description': 're:(?s).* Hi, my name is Rene Dreifuss\. And I\'m here to show you some MMA.*', }, 'params': { 'skip_download': True diff --git a/youtube_dl/extractor/screencast.py b/youtube_dl/extractor/screencast.py new file mode 100644 index 000000000..306869e6a --- /dev/null +++ b/youtube_dl/extractor/screencast.py @@ -0,0 +1,112 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_parse_qs, + compat_urllib_request, +) + + +class ScreencastIE(InfoExtractor): + _VALID_URL = r'https?://www\.screencast\.com/t/(?P<id>[a-zA-Z0-9]+)' + _TESTS = [{ + 'url': 'http://www.screencast.com/t/3ZEjQXlT', + 'md5': '917df1c13798a3e96211dd1561fded83', + 'info_dict': { + 'id': '3ZEjQXlT', + 'ext': 'm4v', + 'title': 'Color Measurement with Ocean Optics Spectrometers', + 'description': 'md5:240369cde69d8bed61349a199c5fb153', + 'thumbnail': 're:^https?://.*\.(?:gif|jpg)$', + } + }, { + 'url': 'http://www.screencast.com/t/V2uXehPJa1ZI', + 'md5': 'e8e4b375a7660a9e7e35c33973410d34', + 'info_dict': { + 'id': 'V2uXehPJa1ZI', + 'ext': 'mov', + 'title': 'The Amadeus Spectrometer', + 'description': 're:^In this video, our friends at.*To learn more about Amadeus, visit', + 'thumbnail': 're:^https?://.*\.(?:gif|jpg)$', + } + }, { + 'url': 'http://www.screencast.com/t/aAB3iowa', + 'md5': 'dedb2734ed00c9755761ccaee88527cd', + 'info_dict': { + 'id': 'aAB3iowa', + 'ext': 'mp4', + 'title': 'Google Earth Export', + 'description': 'Provides a demo of a CommunityViz export to Google Earth, one of the 3D viewing options.', + 'thumbnail': 're:^https?://.*\.(?:gif|jpg)$', + } + }, { + 'url': 'http://www.screencast.com/t/X3ddTrYh', + 'md5': '669ee55ff9c51988b4ebc0877cc8b159', + 'info_dict': { + 'id': 'X3ddTrYh', + 'ext': 'wmv', + 'title': 'Toolkit 6 User Group Webinar (2014-03-04) - Default Judgment and First Impression', + 'description': 'md5:7b9f393bc92af02326a5c5889639eab0', + 'thumbnail': 're:^https?://.*\.(?:gif|jpg)$', + } + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex( + r'<embed name="Video".*?src="([^"]+)"', webpage, + 'QuickTime embed', default=None) + + if video_url is None: + flash_vars_s = self._html_search_regex( + r'<param name="flashVars" value="([^"]+)"', webpage, 'flash vars', + default=None) + if not flash_vars_s: + flash_vars_s = self._html_search_regex( + r'<param name="initParams" value="([^"]+)"', webpage, 'flash vars', + default=None) + if flash_vars_s: + flash_vars_s = flash_vars_s.replace(',', '&') + if flash_vars_s: + flash_vars = compat_parse_qs(flash_vars_s) + video_url_raw = compat_urllib_request.quote( + flash_vars['content'][0]) + video_url = video_url_raw.replace('http%3A', 'http:') + + if video_url is None: + video_meta = self._html_search_meta( + 'og:video', webpage, default=None) + if video_meta: + video_url = self._search_regex( + r'src=(.*?)(?:$|&)', video_meta, + 'meta tag video URL', default=None) + + if video_url is None: + raise ExtractorError('Cannot find video') + + title = self._og_search_title(webpage, default=None) + if title is None: + title = self._html_search_regex( + [r'<b>Title:</b> ([^<]*)</div>', + r'class="tabSeperator">></span><span class="tabText">(.*?)<'], + webpage, 'title') + thumbnail = self._og_search_thumbnail(webpage) + description = self._og_search_description(webpage, default=None) + if description is None: + description = self._html_search_meta('description', webpage) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py new file mode 100644 index 000000000..badba2ac6 --- /dev/null +++ b/youtube_dl/extractor/shared.py @@ -0,0 +1,57 @@ +from __future__ import unicode_literals + +import re +import base64 + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_urllib_request, + compat_urllib_parse, + int_or_none, +) + + +class SharedIE(InfoExtractor): + _VALID_URL = r'http://shared\.sx/(?P<id>[\da-z]{10})' + + _TEST = { + 'url': 'http://shared.sx/0060718775', + 'md5': '106fefed92a8a2adb8c98e6a0652f49b', + 'info_dict': { + 'id': '0060718775', + 'ext': 'mp4', + 'title': 'Bmp4', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + page = self._download_webpage(url, video_id) + + if re.search(r'>File does not exist<', page) is not None: + raise ExtractorError('Video %s does not exist' % video_id, expected=True) + + download_form = dict(re.findall(r'<input type="hidden" name="([^"]+)" value="([^"]*)"', page)) + + request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(download_form)) + request.add_header('Content-Type', 'application/x-www-form-urlencoded') + + video_page = self._download_webpage(request, video_id, 'Downloading video page') + + video_url = self._html_search_regex(r'data-url="([^"]+)"', video_page, 'video URL') + title = base64.b64decode(self._html_search_meta('full:title', page, 'title')).decode('utf-8') + filesize = int_or_none(self._html_search_meta('full:size', page, 'file size', fatal=False)) + thumbnail = self._html_search_regex( + r'data-poster="([^"]+)"', video_page, 'thumbnail', fatal=False, default=None) + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp4', + 'filesize': filesize, + 'title': title, + 'thumbnail': thumbnail, + }
\ No newline at end of file diff --git a/youtube_dl/extractor/slutload.py b/youtube_dl/extractor/slutload.py index ecc0abfda..e6e7d0865 100644 --- a/youtube_dl/extractor/slutload.py +++ b/youtube_dl/extractor/slutload.py @@ -3,9 +3,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - ExtractorError, -) class SlutloadIE(InfoExtractor): diff --git a/youtube_dl/extractor/snotr.py b/youtube_dl/extractor/snotr.py new file mode 100644 index 000000000..da3b05a8d --- /dev/null +++ b/youtube_dl/extractor/snotr.py @@ -0,0 +1,68 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + float_or_none, + str_to_int, + parse_duration, +) + + +class SnotrIE(InfoExtractor): + _VALID_URL = r'http?://(?:www\.)?snotr\.com/video/(?P<id>\d+)/([\w]+)' + _TESTS = [{ + 'url': 'http://www.snotr.com/video/13708/Drone_flying_through_fireworks', + 'info_dict': { + 'id': '13708', + 'ext': 'flv', + 'title': 'Drone flying through fireworks!', + 'duration': 247, + 'filesize_approx': 98566144, + 'description': 'A drone flying through Fourth of July Fireworks', + } + }, { + 'url': 'http://www.snotr.com/video/530/David_Letteman_-_George_W_Bush_Top_10', + 'info_dict': { + 'id': '530', + 'ext': 'flv', + 'title': 'David Letteman - George W. Bush Top 10', + 'duration': 126, + 'filesize_approx': 8912896, + 'description': 'The top 10 George W. Bush moments, brought to you by David Letterman!', + } + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + title = self._og_search_title(webpage) + + description = self._og_search_description(webpage) + video_url = "http://cdn.videos.snotr.com/%s.flv" % video_id + + view_count = str_to_int(self._html_search_regex( + r'<p>\n<strong>Views:</strong>\n([\d,\.]+)</p>', + webpage, 'view count', fatal=False)) + + duration = parse_duration(self._html_search_regex( + r'<p>\n<strong>Length:</strong>\n\s*([0-9:]+).*?</p>', + webpage, 'duration', fatal=False)) + + filesize_approx = float_or_none(self._html_search_regex( + r'<p>\n<strong>Filesize:</strong>\n\s*([0-9.]+)\s*megabyte</p>', + webpage, 'filesize', fatal=False), invscale=1024 * 1024) + + return { + 'id': video_id, + 'description': description, + 'title': title, + 'url': video_url, + 'view_count': view_count, + 'duration': duration, + 'filesize_approx': filesize_approx, + } diff --git a/youtube_dl/extractor/sockshare.py b/youtube_dl/extractor/sockshare.py new file mode 100644 index 000000000..dc9f80550 --- /dev/null +++ b/youtube_dl/extractor/sockshare.py @@ -0,0 +1,80 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from ..utils import ( + ExtractorError, + compat_urllib_parse, + compat_urllib_request, + determine_ext, +) +import re + +from .common import InfoExtractor + + +class SockshareIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?sockshare\.com/file/(?P<id>[0-9A-Za-z]+)' + _FILE_DELETED_REGEX = r'This file doesn\'t exist, or has been removed\.</div>' + _TEST = { + 'url': 'http://www.sockshare.com/file/437BE28B89D799D7', + 'md5': '9d0bf1cfb6dbeaa8d562f6c97506c5bd', + 'info_dict': { + 'id': '437BE28B89D799D7', + 'title': 'big_buck_bunny_720p_surround.avi', + 'ext': 'avi', + 'thumbnail': 're:^http://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + url = 'http://sockshare.com/file/%s' % video_id + webpage = self._download_webpage(url, video_id) + + if re.search(self._FILE_DELETED_REGEX, webpage) is not None: + raise ExtractorError('Video %s does not exist' % video_id, + expected=True) + + confirm_hash = self._html_search_regex(r'''(?x)<input\s+ + type="hidden"\s+ + value="([^"]*)"\s+ + name="hash" + ''', webpage, 'hash') + + fields = { + "hash": confirm_hash, + "confirm": "Continue as Free User" + } + + post = compat_urllib_parse.urlencode(fields) + req = compat_urllib_request.Request(url, post) + # Apparently, this header is required for confirmation to work. + req.add_header('Host', 'www.sockshare.com') + req.add_header('Content-type', 'application/x-www-form-urlencoded') + + webpage = self._download_webpage( + req, video_id, 'Downloading video page') + + video_url = self._html_search_regex( + r'<a href="([^"]*)".+class="download_file_link"', + webpage, 'file url') + video_url = "http://www.sockshare.com" + video_url + title = self._html_search_regex(r'<h1>(.+)<strong>', webpage, 'title') + thumbnail = self._html_search_regex( + r'<img\s+src="([^"]*)".+?name="bg"', + webpage, 'thumbnail') + + formats = [{ + 'format_id': 'sd', + 'url': video_url, + 'ext': determine_ext(title), + }] + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index d6f453fb9..097d0e418 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -1,7 +1,6 @@ # encoding: utf-8 from __future__ import unicode_literals -import json import re import itertools @@ -12,6 +11,7 @@ from ..utils import ( compat_urllib_parse, ExtractorError, + int_or_none, unified_strdate, ) @@ -44,7 +44,8 @@ class SoundcloudIE(InfoExtractor): "upload_date": "20121011", "description": "No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o'd", "uploader": "E.T. ExTerrestrial Music", - "title": "Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1" + "title": "Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1", + "duration": 143, } }, # not streamable song @@ -57,6 +58,7 @@ class SoundcloudIE(InfoExtractor): 'description': 'From Stockholm Sweden\r\nPovel / Magnus / Filip / David\r\nwww.theroyalconcept.com', 'uploader': 'The Royal Concept', 'upload_date': '20120521', + 'duration': 227, }, 'params': { # rtmp @@ -74,19 +76,21 @@ class SoundcloudIE(InfoExtractor): 'uploader': 'jaimeMF', 'description': 'test chars: \"\'/\\ä↭', 'upload_date': '20131209', + 'duration': 9, }, }, # downloadable song { - 'url': 'https://soundcloud.com/simgretina/just-your-problem-baby-1', - 'md5': '56a8b69568acaa967b4c49f9d1d52d19', + 'url': 'https://soundcloud.com/oddsamples/bus-brakes', + 'md5': '7624f2351f8a3b2e7cd51522496e7631', 'info_dict': { - 'id': '105614606', - 'ext': 'wav', - 'title': 'Just Your Problem Baby (Acapella)', - 'description': 'Vocals', - 'uploader': 'Sim Gretina', - 'upload_date': '20130815', + 'id': '128590877', + 'ext': 'mp3', + 'title': 'Bus Brakes', + 'description': 'md5:0170be75dd395c96025d210d261c784e', + 'uploader': 'oddsamples', + 'upload_date': '20140109', + 'duration': 17, }, }, ] @@ -119,6 +123,7 @@ class SoundcloudIE(InfoExtractor): 'title': info['title'], 'description': info['description'], 'thumbnail': thumbnail, + 'duration': int_or_none(info.get('duration'), 1000), } formats = [] if info.get('downloadable', False): @@ -250,7 +255,7 @@ class SoundcloudSetIE(SoundcloudIE): class SoundcloudUserIE(SoundcloudIE): - _VALID_URL = r'https?://(www\.)?soundcloud\.com/(?P<user>[^/]+)(/?(tracks/)?)?(\?.*)?$' + _VALID_URL = r'https?://(www\.)?soundcloud\.com/(?P<user>[^/]+)/?((?P<rsrc>tracks|likes)/?)?(\?.*)?$' IE_NAME = 'soundcloud:user' # it's in tests/test_playlists.py @@ -259,24 +264,31 @@ class SoundcloudUserIE(SoundcloudIE): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) uploader = mobj.group('user') + resource = mobj.group('rsrc') + if resource is None: + resource = 'tracks' + elif resource == 'likes': + resource = 'favorites' url = 'http://soundcloud.com/%s/' % uploader resolv_url = self._resolv_url(url) user = self._download_json( resolv_url, uploader, 'Downloading user info') - base_url = 'http://api.soundcloud.com/users/%s/tracks.json?' % uploader + base_url = 'http://api.soundcloud.com/users/%s/%s.json?' % (uploader, resource) entries = [] for i in itertools.count(): data = compat_urllib_parse.urlencode({ 'offset': i * 50, + 'limit': 50, 'client_id': self._CLIENT_ID, }) new_entries = self._download_json( base_url + data, uploader, 'Downloading track page %s' % (i + 1)) - entries.extend(self._extract_info_dict(e, quiet=True) for e in new_entries) - if len(new_entries) < 50: + if len(new_entries) == 0: + self.to_screen('%s: End page received' % uploader) break + entries.extend(self._extract_info_dict(e, quiet=True) for e in new_entries) return { '_type': 'playlist', diff --git a/youtube_dl/extractor/soundgasm.py b/youtube_dl/extractor/soundgasm.py new file mode 100644 index 000000000..a4f8ce6c3 --- /dev/null +++ b/youtube_dl/extractor/soundgasm.py @@ -0,0 +1,40 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class SoundgasmIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<user>[0-9a-zA-Z_\-]+)/(?P<title>[0-9a-zA-Z_\-]+)' + _TEST = { + 'url': 'http://soundgasm.net/u/ytdl/Piano-sample', + 'md5': '010082a2c802c5275bb00030743e75ad', + 'info_dict': { + 'id': '88abd86ea000cafe98f96321b23cc1206cbcbcc9', + 'ext': 'm4a', + 'title': 'ytdl_Piano-sample', + 'description': 'Royalty Free Sample Music' + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('title') + audio_title = mobj.group('user') + '_' + mobj.group('title') + webpage = self._download_webpage(url, display_id) + audio_url = self._html_search_regex( + r'(?s)m4a\:\s"([^"]+)"', webpage, 'audio URL') + audio_id = re.split('\/|\.', audio_url)[-2] + description = self._html_search_regex( + r'(?s)<li>Description:\s(.*?)<\/li>', webpage, 'description', + fatal=False) + + return { + 'id': audio_id, + 'display_id': display_id, + 'url': audio_url, + 'title': audio_title, + 'description': description + } diff --git a/youtube_dl/extractor/southparkstudios.py b/youtube_dl/extractor/southpark.py index aea8e6439..c20397b3d 100644 --- a/youtube_dl/extractor/southparkstudios.py +++ b/youtube_dl/extractor/southpark.py @@ -3,24 +3,24 @@ from __future__ import unicode_literals from .mtv import MTVServicesInfoExtractor -class SouthParkStudiosIE(MTVServicesInfoExtractor): - IE_NAME = 'southparkstudios.com' - _VALID_URL = r'https?://(www\.)?(?P<url>southparkstudios\.com/(clips|full-episodes)/(?P<id>.+?)(\?|#|$))' +class SouthParkIE(MTVServicesInfoExtractor): + IE_NAME = 'southpark.cc.com' + _VALID_URL = r'https?://(www\.)?(?P<url>southpark\.cc\.com/(clips|full-episodes)/(?P<id>.+?)(\?|#|$))' _FEED_URL = 'http://www.southparkstudios.com/feeds/video-player/mrss' _TESTS = [{ - 'url': 'http://www.southparkstudios.com/clips/104437/bat-daded#tab=featured', + 'url': 'http://southpark.cc.com/clips/104437/bat-daded#tab=featured', 'info_dict': { 'id': 'a7bff6c2-ed00-11e0-aca6-0026b9414f30', 'ext': 'mp4', - 'title': 'Bat Daded', + 'title': 'South Park|Bat Daded', 'description': 'Randy disqualifies South Park by getting into a fight with Bat Dad.', }, }] -class SouthparkDeIE(SouthParkStudiosIE): +class SouthparkDeIE(SouthParkIE): IE_NAME = 'southpark.de' _VALID_URL = r'https?://(www\.)?(?P<url>southpark\.de/(clips|alle-episoden)/(?P<id>.+?)(\?|#|$))' _FEED_URL = 'http://www.southpark.de/feeds/video-player/mrss/' diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py index 9156d7faf..340a38440 100644 --- a/youtube_dl/extractor/spiegel.py +++ b/youtube_dl/extractor/spiegel.py @@ -1,3 +1,4 @@ +# encoding: utf-8 from __future__ import unicode_literals import re @@ -9,18 +10,33 @@ class SpiegelIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$' _TESTS = [{ 'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html', - 'file': '1259285.mp4', 'md5': '2c2754212136f35fb4b19767d242f66e', 'info_dict': { + 'id': '1259285', + 'ext': 'mp4', 'title': 'Vulkanausbruch in Ecuador: Der "Feuerschlund" ist wieder aktiv', + 'description': 'md5:8029d8310232196eb235d27575a8b9f4', + 'duration': 49, }, - }, - { + }, { 'url': 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html', - 'file': '1309159.mp4', 'md5': 'f2cdf638d7aa47654e251e1aee360af1', 'info_dict': { + 'id': '1309159', + 'ext': 'mp4', 'title': 'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers', + 'description': 'md5:c2322b65e58f385a820c10fa03b2d088', + 'duration': 983, + }, + }, { + 'url': 'http://www.spiegel.de/video/johann-westhauser-videobotschaft-des-hoehlenforschers-video-1502367.html', + 'md5': '54f58ba0e752e3c07bc2a26222dd0acf', + 'info_dict': { + 'id': '1502367', + 'ext': 'mp4', + 'title': 'Videobotschaft: Höhlenforscher Westhauser dankt seinen Rettern', + 'description': 'md5:c6f1ec11413ebd1088b6813943e5fc91', + 'duration': 42, }, }] @@ -30,18 +46,20 @@ class SpiegelIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - video_title = self._html_search_regex( + title = self._html_search_regex( r'<div class="module-title">(.*?)</div>', webpage, 'title') + description = self._html_search_meta('description', webpage, 'description') + + base_url = self._search_regex( + r'var\s+server\s*=\s*"([^"]+)\"', webpage, 'server URL') - xml_url = 'http://video2.spiegel.de/flash/' + video_id + '.xml' - idoc = self._download_xml( - xml_url, video_id, - note='Downloading XML', errnote='Failed to download XML') + xml_url = base_url + video_id + '.xml' + idoc = self._download_xml(xml_url, video_id) formats = [ { 'format_id': n.tag.rpartition('type')[2], - 'url': 'http://video2.spiegel.de/flash/' + n.find('./filename').text, + 'url': base_url + n.find('./filename').text, 'width': int(n.find('./width').text), 'height': int(n.find('./height').text), 'abr': int(n.find('./audiobitrate').text), @@ -59,7 +77,8 @@ class SpiegelIE(InfoExtractor): return { 'id': video_id, - 'title': video_title, + 'title': title, + 'description': description, 'duration': duration, 'formats': formats, } diff --git a/youtube_dl/extractor/spiegeltv.py b/youtube_dl/extractor/spiegeltv.py new file mode 100644 index 000000000..7f388aced --- /dev/null +++ b/youtube_dl/extractor/spiegeltv.py @@ -0,0 +1,81 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +from .common import InfoExtractor + + +class SpiegeltvIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?spiegel\.tv/filme/(?P<id>[\-a-z0-9]+)' + _TEST = { + 'url': 'http://www.spiegel.tv/filme/flug-mh370/', + 'info_dict': { + 'id': 'flug-mh370', + 'ext': 'm4v', + 'title': 'Flug MH370', + 'description': 'Das Rätsel um die Boeing 777 der Malaysia-Airlines', + 'thumbnail': 're:http://.*\.jpg$', + }, + 'params': { + # rtmp download + 'skip_download': True, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + title = self._html_search_regex(r'<h1.*?>(.*?)</h1>', webpage, 'title') + + apihost = 'http://spiegeltv-ivms2-restapi.s3.amazonaws.com' + version_json = self._download_json( + '%s/version.json' % apihost, video_id, + note='Downloading version information') + version_name = version_json['version_name'] + + slug_json = self._download_json( + '%s/%s/restapi/slugs/%s.json' % (apihost, version_name, video_id), + video_id, + note='Downloading object information') + oid = slug_json['object_id'] + + media_json = self._download_json( + '%s/%s/restapi/media/%s.json' % (apihost, version_name, oid), + video_id, note='Downloading media information') + uuid = media_json['uuid'] + is_wide = media_json['is_wide'] + + server_json = self._download_json( + 'http://www.spiegel.tv/streaming_servers/', video_id, + note='Downloading server information') + server = server_json[0]['endpoint'] + + thumbnails = [] + for image in media_json['images']: + thumbnails.append({ + 'url': image['url'], + 'width': image['width'], + 'height': image['height'], + }) + + description = media_json['subtitle'] + duration = media_json['duration_in_ms'] / 1000. + + if is_wide: + format = '16x9' + else: + format = '4x3' + + url = server + 'mp4:' + uuid + '_spiegeltv_0500_' + format + '.m4v' + + return { + 'id': video_id, + 'title': title, + 'url': url, + 'ext': 'm4v', + 'description': description, + 'duration': duration, + 'thumbnails': thumbnails + }
\ No newline at end of file diff --git a/youtube_dl/extractor/steam.py b/youtube_dl/extractor/steam.py index 1d8d57224..183dcb03c 100644 --- a/youtube_dl/extractor/steam.py +++ b/youtube_dl/extractor/steam.py @@ -53,7 +53,7 @@ class SteamIE(InfoExtractor): 'ext': 'mp4', 'upload_date': '20140329', 'title': 'FRONTIERS - Final Greenlight Trailer', - 'description': "The final trailer for the Steam Greenlight launch. Hooray, progress! Here's the official Greenlight page: http://steamcommunity.com/sharedfiles/filedetails/?id=242472205", + 'description': 'md5:dc96a773669d0ca1b36c13c1f30250d9', 'uploader': 'AAD Productions', 'uploader_id': 'AtomicAgeDogGames', } diff --git a/youtube_dl/extractor/streamcloud.py b/youtube_dl/extractor/streamcloud.py index 9faf3a5e3..172def221 100644 --- a/youtube_dl/extractor/streamcloud.py +++ b/youtube_dl/extractor/streamcloud.py @@ -1,4 +1,6 @@ # coding: utf-8 +from __future__ import unicode_literals + import re import time @@ -10,18 +12,18 @@ from ..utils import ( class StreamcloudIE(InfoExtractor): - IE_NAME = u'streamcloud.eu' + IE_NAME = 'streamcloud.eu' _VALID_URL = r'https?://streamcloud\.eu/(?P<id>[a-zA-Z0-9_-]+)/(?P<fname>[^#?]*)\.html' _TEST = { - u'url': u'http://streamcloud.eu/skp9j99s4bpz/youtube-dl_test_video_____________-BaW_jenozKc.mp4.html', - u'file': u'skp9j99s4bpz.mp4', - u'md5': u'6bea4c7fa5daaacc2a946b7146286686', - u'info_dict': { - u'title': u'youtube-dl test video \'/\\ ä ↭', - u'duration': 9, + 'url': 'http://streamcloud.eu/skp9j99s4bpz/youtube-dl_test_video_____________-BaW_jenozKc.mp4.html', + 'md5': '6bea4c7fa5daaacc2a946b7146286686', + 'info_dict': { + 'id': 'skp9j99s4bpz', + 'ext': 'mp4', + 'title': 'youtube-dl test video \'/\\ ä ↭', }, - u'skip': u'Only available from the EU' + 'skip': 'Only available from the EU' } def _real_extract(self, url): @@ -46,21 +48,17 @@ class StreamcloudIE(InfoExtractor): req = compat_urllib_request.Request(url, post, headers) webpage = self._download_webpage( - req, video_id, note=u'Downloading video page ...') + req, video_id, note='Downloading video page ...') title = self._html_search_regex( - r'<h1[^>]*>([^<]+)<', webpage, u'title') + r'<h1[^>]*>([^<]+)<', webpage, 'title') video_url = self._search_regex( - r'file:\s*"([^"]+)"', webpage, u'video URL') - duration_str = self._search_regex( - r'duration:\s*"?([0-9]+)"?', webpage, u'duration', fatal=False) - duration = None if duration_str is None else int(duration_str) + r'file:\s*"([^"]+)"', webpage, 'video URL') thumbnail = self._search_regex( - r'image:\s*"([^"]+)"', webpage, u'thumbnail URL', fatal=False) + r'image:\s*"([^"]+)"', webpage, 'thumbnail URL', fatal=False) return { 'id': video_id, 'title': title, 'url': video_url, - 'duration': duration, 'thumbnail': thumbnail, } diff --git a/youtube_dl/extractor/streamcz.py b/youtube_dl/extractor/streamcz.py index 7362904db..73efe9542 100644 --- a/youtube_dl/extractor/streamcz.py +++ b/youtube_dl/extractor/streamcz.py @@ -5,13 +5,16 @@ import re import json from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + int_or_none, + compat_str, +) class StreamCZIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?stream\.cz/.+/(?P<videoid>.+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.stream.cz/peklonataliri/765767-ecka-pro-deti', 'md5': '6d3ca61a8d0633c9c542b92fcb936b0c', 'info_dict': { @@ -22,7 +25,18 @@ class StreamCZIE(InfoExtractor): 'thumbnail': 'http://im.stream.cz/episode/52961d7e19d423f8f06f0100', 'duration': 256, }, - } + }, { + 'url': 'http://www.stream.cz/blanik/10002447-tri-roky-pro-mazanka', + 'md5': '246272e753e26bbace7fcd9deca0650c', + 'info_dict': { + 'id': '10002447', + 'ext': 'mp4', + 'title': 'Kancelář Blaník: Tři roky pro Mazánka', + 'description': 'md5:9177695a8b756a0a8ab160de4043b392', + 'thumbnail': 'http://im.stream.cz/episode/537f838c50c11f8d21320000', + 'duration': 368, + }, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -57,7 +71,7 @@ class StreamCZIE(InfoExtractor): self._sort_formats(formats) return { - 'id': str(jsonData['id']), + 'id': compat_str(jsonData['episode_id']), 'title': self._og_search_title(webpage), 'thumbnail': jsonData['episode_image_original_url'].replace('//', 'http://'), 'formats': formats, diff --git a/youtube_dl/extractor/swrmediathek.py b/youtube_dl/extractor/swrmediathek.py new file mode 100644 index 000000000..5d9d70367 --- /dev/null +++ b/youtube_dl/extractor/swrmediathek.py @@ -0,0 +1,118 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import parse_duration + + +class SWRMediathekIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?swrmediathek\.de/(?:content/)?player\.htm\?show=(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})' + + _TESTS = [{ + 'url': 'http://swrmediathek.de/player.htm?show=849790d0-dab8-11e3-a953-0026b975f2e6', + 'md5': '8c5f6f0172753368547ca8413a7768ac', + 'info_dict': { + 'id': '849790d0-dab8-11e3-a953-0026b975f2e6', + 'ext': 'mp4', + 'title': 'SWR odysso', + 'description': 'md5:2012e31baad36162e97ce9eb3f157b8a', + 'thumbnail': 're:^http:.*\.jpg$', + 'duration': 2602, + 'upload_date': '20140515', + 'uploader': 'SWR Fernsehen', + 'uploader_id': '990030', + }, + }, { + 'url': 'http://swrmediathek.de/player.htm?show=0e1a8510-ddf2-11e3-9be3-0026b975f2e6', + 'md5': 'b10ab854f912eecc5a6b55cd6fc1f545', + 'info_dict': { + 'id': '0e1a8510-ddf2-11e3-9be3-0026b975f2e6', + 'ext': 'mp4', + 'title': 'Nachtcafé - Alltagsdroge Alkohol - zwischen Sektempfang und Komasaufen', + 'description': 'md5:e0a3adc17e47db2c23aab9ebc36dbee2', + 'thumbnail': 're:http://.*\.jpg', + 'duration': 5305, + 'upload_date': '20140516', + 'uploader': 'SWR Fernsehen', + 'uploader_id': '990030', + }, + }, { + 'url': 'http://swrmediathek.de/player.htm?show=bba23e10-cb93-11e3-bf7f-0026b975f2e6', + 'md5': '4382e4ef2c9d7ce6852535fa867a0dd3', + 'info_dict': { + 'id': 'bba23e10-cb93-11e3-bf7f-0026b975f2e6', + 'ext': 'mp3', + 'title': 'Saša Stanišic: Vor dem Fest', + 'description': 'md5:5b792387dc3fbb171eb709060654e8c9', + 'thumbnail': 're:http://.*\.jpg', + 'duration': 3366, + 'upload_date': '20140520', + 'uploader': 'SWR 2', + 'uploader_id': '284670', + } + }, { + 'url': 'http://swrmediathek.de/content/player.htm?show=52dc7e00-15c5-11e4-84bc-0026b975f2e6', + 'md5': '881531487d0633080a8cc88d31ef896f', + 'info_dict': { + 'id': '52dc7e00-15c5-11e4-84bc-0026b975f2e6', + 'ext': 'mp4', + 'title': 'Familienspaß am Bodensee', + 'description': 'md5:0b591225a32cfde7be1629ed49fe4315', + 'thumbnail': 're:http://.*\.jpg', + 'duration': 1784, + 'upload_date': '20140727', + 'uploader': 'SWR Fernsehen BW', + 'uploader_id': '281130', + } + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + video = self._download_json( + 'http://swrmediathek.de/AjaxEntry?ekey=%s' % video_id, video_id, 'Downloading video JSON') + + attr = video['attr'] + media_type = attr['entry_etype'] + + formats = [] + for entry in video['sub']: + if entry['name'] != 'entry_media': + continue + + entry_attr = entry['attr'] + codec = entry_attr['val0'] + quality = int(entry_attr['val1']) + + fmt = { + 'url': entry_attr['val2'], + 'quality': quality, + } + + if media_type == 'Video': + fmt.update({ + 'format_note': ['144p', '288p', '544p'][quality-1], + 'vcodec': codec, + }) + elif media_type == 'Audio': + fmt.update({ + 'acodec': codec, + }) + formats.append(fmt) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': attr['entry_title'], + 'description': attr['entry_descl'], + 'thumbnail': attr['entry_image_16_9'], + 'duration': parse_duration(attr['entry_durat']), + 'upload_date': attr['entry_pdatet'][:-4], + 'uploader': attr['channel_title'], + 'uploader_id': attr['channel_idkey'], + 'formats': formats, + }
\ No newline at end of file diff --git a/youtube_dl/extractor/tagesschau.py b/youtube_dl/extractor/tagesschau.py new file mode 100644 index 000000000..b87047451 --- /dev/null +++ b/youtube_dl/extractor/tagesschau.py @@ -0,0 +1,69 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class TagesschauIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/video/video(?P<id>-?[0-9]+)\.html' + + _TESTS = [{ + 'url': 'http://www.tagesschau.de/multimedia/video/video1399128.html', + 'md5': 'bcdeac2194fb296d599ce7929dfa4009', + 'info_dict': { + 'id': '1399128', + 'ext': 'mp4', + 'title': 'Harald Range, Generalbundesanwalt, zu den Ermittlungen', + 'description': 'md5:69da3c61275b426426d711bde96463ab', + 'thumbnail': 're:^http:.*\.jpg$', + }, + }] + + _FORMATS = { + 's': {'width': 256, 'height': 144, 'quality': 1}, + 'm': {'width': 512, 'height': 288, 'quality': 2}, + 'l': {'width': 960, 'height': 544, 'quality': 3}, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + if video_id.startswith('-'): + display_id = video_id.strip('-') + else: + display_id = video_id + + webpage = self._download_webpage(url, display_id) + + playerpage = self._download_webpage( + 'http://www.tagesschau.de/multimedia/video/video%s~player_autoplay-true.html' % video_id, + display_id, 'Downloading player page') + + medias = re.findall( + r'"(http://media.+?)", type:"video/(.+?)", quality:"(.+?)"', + playerpage) + + formats = [] + for url, ext, res in medias: + f = { + 'format_id': res + '_' + ext, + 'url': url, + 'ext': ext, + } + f.update(self._FORMATS.get(res, {})) + formats.append(f) + + self._sort_formats(formats) + + thumbnail = re.findall(r'"(/multimedia/.+?\.jpg)"', playerpage)[-1] + + return { + 'id': display_id, + 'title': self._og_search_title(webpage).strip(), + 'thumbnail': 'http://www.tagesschau.de' + thumbnail, + 'formats': formats, + 'description': self._og_search_description(webpage).strip(), + } diff --git a/youtube_dl/extractor/teachertube.py b/youtube_dl/extractor/teachertube.py new file mode 100644 index 000000000..46d727d1d --- /dev/null +++ b/youtube_dl/extractor/teachertube.py @@ -0,0 +1,126 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + qualities, + determine_ext, +) + + +class TeacherTubeIE(InfoExtractor): + IE_NAME = 'teachertube' + IE_DESC = 'teachertube.com videos' + + _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(viewVideo\.php\?video_id=|music\.php\?music_id=|video/(?:[\da-z-]+-)?|audio/)(?P<id>\d+)' + + _TESTS = [{ + 'url': 'http://www.teachertube.com/viewVideo.php?video_id=339997', + 'md5': 'f9434ef992fd65936d72999951ee254c', + 'info_dict': { + 'id': '339997', + 'ext': 'mp4', + 'title': 'Measures of dispersion from a frequency table', + 'description': 'Measures of dispersion from a frequency table', + 'thumbnail': 're:http://.*\.jpg', + }, + }, { + 'url': 'http://www.teachertube.com/viewVideo.php?video_id=340064', + 'md5': '0d625ec6bc9bf50f70170942ad580676', + 'info_dict': { + 'id': '340064', + 'ext': 'mp4', + 'title': 'How to Make Paper Dolls _ Paper Art Projects', + 'description': 'Learn how to make paper dolls in this simple', + 'thumbnail': 're:http://.*\.jpg', + }, + }, { + 'url': 'http://www.teachertube.com/music.php?music_id=8805', + 'md5': '01e8352006c65757caf7b961f6050e21', + 'info_dict': { + 'id': '8805', + 'ext': 'mp3', + 'title': 'PER ASPERA AD ASTRA', + 'description': 'RADIJSKA EMISIJA ZRAKOPLOVNE TEHNI?KE ?KOLE P', + }, + }, { + 'url': 'http://www.teachertube.com/video/intro-video-schleicher-297790', + 'md5': '9c79fbb2dd7154823996fc28d4a26998', + 'info_dict': { + 'id': '297790', + 'ext': 'mp4', + 'title': 'Intro Video - Schleicher', + 'description': 'Intro Video - Why to flip, how flipping will', + }, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + title = self._html_search_meta('title', webpage, 'title', fatal=True) + TITLE_SUFFIX = ' - TeacherTube' + if title.endswith(TITLE_SUFFIX): + title = title[:-len(TITLE_SUFFIX)].strip() + + description = self._html_search_meta('description', webpage, 'description') + if description: + description = description.strip() + + quality = qualities(['mp3', 'flv', 'mp4']) + + media_urls = re.findall(r'data-contenturl="([^"]+)"', webpage) + media_urls.extend(re.findall(r'var\s+filePath\s*=\s*"([^"]+)"', webpage)) + media_urls.extend(re.findall(r'\'file\'\s*:\s*["\']([^"\']+)["\'],', webpage)) + + formats = [ + { + 'url': media_url, + 'quality': quality(determine_ext(media_url)) + } for media_url in set(media_urls) + ] + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'thumbnail': self._html_search_regex(r'\'image\'\s*:\s*["\']([^"\']+)["\']', webpage, 'thumbnail'), + 'formats': formats, + 'description': description, + } + + +class TeacherTubeUserIE(InfoExtractor): + IE_NAME = 'teachertube:user:collection' + IE_DESC = 'teachertube.com user and collection videos' + + _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(user/profile|collection)/(?P<user>[0-9a-zA-Z]+)/?' + + _MEDIA_RE = r'''(?sx) + class="?sidebar_thumb_time"?>[0-9:]+</div> + \s* + <a\s+href="(https?://(?:www\.)?teachertube\.com/(?:video|audio)/[^"]+)" + ''' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + user_id = mobj.group('user') + + urls = [] + webpage = self._download_webpage(url, user_id) + urls.extend(re.findall(self._MEDIA_RE, webpage)) + + pages = re.findall(r'/ajax-user/user-videos/%s\?page=([0-9]+)' % user_id, webpage)[:-1] + for p in pages: + more = 'http://www.teachertube.com/ajax-user/user-videos/%s?page=%s' % (user_id, p) + webpage = self._download_webpage(more, user_id, 'Downloading page %s/%s' % (p, len(pages))) + video_urls = re.findall(self._MEDIA_RE, webpage) + urls.extend(video_urls) + + entries = [self.url_result(vurl, 'TeacherTube') for vurl in urls] + return self.playlist_result(entries, user_id) diff --git a/youtube_dl/extractor/teachingchannel.py b/youtube_dl/extractor/teachingchannel.py new file mode 100644 index 000000000..117afa9bf --- /dev/null +++ b/youtube_dl/extractor/teachingchannel.py @@ -0,0 +1,33 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from .ooyala import OoyalaIE + + +class TeachingChannelIE(InfoExtractor): + _VALID_URL = r'https?://www\.teachingchannel\.org/videos/(?P<title>.+)' + + _TEST = { + 'url': 'https://www.teachingchannel.org/videos/teacher-teaming-evolution', + 'info_dict': { + 'id': 'F3bnlzbToeI6pLEfRyrlfooIILUjz4nM', + 'ext': 'mp4', + 'title': 'A History of Teaming', + 'description': 'md5:2a9033db8da81f2edffa4c99888140b3', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + title = mobj.group('title') + webpage = self._download_webpage(url, title) + ooyala_code = self._search_regex( + r'data-embed-code=\'(.+?)\'', webpage, 'ooyala code') + + return OoyalaIE._build_url_result(ooyala_code) diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py index f8dd7e955..fa796ce72 100644 --- a/youtube_dl/extractor/teamcoco.py +++ b/youtube_dl/extractor/teamcoco.py @@ -37,7 +37,7 @@ class TeamcocoIE(InfoExtractor): video_id = mobj.group("video_id") if not video_id: video_id = self._html_search_regex( - r'<article class="video" data-id="(\d+?)"', + r'data-node-id="(\d+?)"', webpage, 'video id') data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index d260c91c2..bce32a873 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -27,7 +27,7 @@ class TEDIE(SubtitlesInfoExtractor): ''' _TESTS = [{ 'url': 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html', - 'md5': '4ea1dada91e4174b53dac2bb8ace429d', + 'md5': 'fc94ac279feebbce69f21c0c6ee82810', 'info_dict': { 'id': '102', 'ext': 'mp4', diff --git a/youtube_dl/extractor/tenplay.py b/youtube_dl/extractor/tenplay.py new file mode 100644 index 000000000..81ba169fb --- /dev/null +++ b/youtube_dl/extractor/tenplay.py @@ -0,0 +1,82 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class TenPlayIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?ten(play)?\.com\.au/.+' + _TEST = { + 'url': 'http://tenplay.com.au/ten-insider/extra/season-2013/tenplay-tv-your-way', + #'md5': 'd68703d9f73dc8fccf3320ab34202590', + 'info_dict': { + 'id': '2695695426001', + 'ext': 'flv', + 'title': 'TENplay: TV your way', + 'description': 'Welcome to a new TV experience. Enjoy a taste of the TENplay benefits.', + 'timestamp': 1380150606.889, + 'upload_date': '20130925', + 'uploader': 'TENplay', + }, + 'params': { + 'skip_download': True, # Requires rtmpdump + } + } + + _video_fields = [ + "id", "name", "shortDescription", "longDescription", "creationDate", + "publishedDate", "lastModifiedDate", "customFields", "videoStillURL", + "thumbnailURL", "referenceId", "length", "playsTotal", + "playsTrailingWeek", "renditions", "captioning", "startDate", "endDate"] + + def _real_extract(self, url): + webpage = self._download_webpage(url, url) + video_id = self._html_search_regex( + r'videoID: "(\d+?)"', webpage, 'video_id') + api_token = self._html_search_regex( + r'apiToken: "([a-zA-Z0-9-_\.]+?)"', webpage, 'api_token') + title = self._html_search_regex( + r'<meta property="og:title" content="\s*(.*?)\s*"\s*/?\s*>', + webpage, 'title') + + json = self._download_json('https://api.brightcove.com/services/library?command=find_video_by_id&video_id=%s&token=%s&video_fields=%s' % (video_id, api_token, ','.join(self._video_fields)), title) + + formats = [] + for rendition in json['renditions']: + url = rendition['remoteUrl'] or rendition['url'] + protocol = 'rtmp' if url.startswith('rtmp') else 'http' + ext = 'flv' if protocol == 'rtmp' else rendition['videoContainer'].lower() + + if protocol == 'rtmp': + url = url.replace('&mp4:', '') + + formats.append({ + 'format_id': '_'.join(['rtmp', rendition['videoContainer'].lower(), rendition['videoCodec'].lower()]), + 'width': rendition['frameWidth'], + 'height': rendition['frameHeight'], + 'tbr': rendition['encodingRate'] / 1024, + 'filesize': rendition['size'], + 'protocol': protocol, + 'ext': ext, + 'vcodec': rendition['videoCodec'].lower(), + 'container': rendition['videoContainer'].lower(), + 'url': url, + }) + + return { + 'id': video_id, + 'display_id': json['referenceId'], + 'title': json['name'], + 'description': json['shortDescription'] or json['longDescription'], + 'formats': formats, + 'thumbnails': [{ + 'url': json['videoStillURL'] + }, { + 'url': json['thumbnailURL'] + }], + 'thumbnail': json['videoStillURL'], + 'duration': json['length'] / 1000, + 'timestamp': float(json['creationDate']) / 1000, + 'uploader': json['customFields']['production_company_distributor'] if 'production_company_distributor' in json['customFields'] else 'TENplay', + 'view_count': json['playsTotal'] + } diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index f15780ef5..b6b2dba9c 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re import json @@ -18,17 +20,17 @@ class ThePlatformIE(InfoExtractor): _TEST = { # from http://www.metacafe.com/watch/cb-e9I_cZgTgIPd/blackberrys_big_bold_z30/ - u'url': u'http://link.theplatform.com/s/dJ5BDC/e9I_cZgTgIPd/meta.smil?format=smil&Tracking=true&mbr=true', - u'info_dict': { - u'id': u'e9I_cZgTgIPd', - u'ext': u'flv', - u'title': u'Blackberry\'s big, bold Z30', - u'description': u'The Z30 is Blackberry\'s biggest, baddest mobile messaging device yet.', - u'duration': 247, + 'url': 'http://link.theplatform.com/s/dJ5BDC/e9I_cZgTgIPd/meta.smil?format=smil&Tracking=true&mbr=true', + 'info_dict': { + 'id': 'e9I_cZgTgIPd', + 'ext': 'flv', + 'title': 'Blackberry\'s big, bold Z30', + 'description': 'The Z30 is Blackberry\'s biggest, baddest mobile messaging device yet.', + 'duration': 247, }, - u'params': { + 'params': { # rtmp download - u'skip_download': True, + 'skip_download': True, }, } @@ -39,7 +41,7 @@ class ThePlatformIE(InfoExtractor): error_msg = next( n.attrib['abstract'] for n in meta.findall(_x('.//smil:ref')) - if n.attrib.get('title') == u'Geographic Restriction') + if n.attrib.get('title') == 'Geographic Restriction') except StopIteration: pass else: @@ -101,8 +103,7 @@ class ThePlatformIE(InfoExtractor): config_url = url+ '&form=json' config_url = config_url.replace('swf/', 'config/') config_url = config_url.replace('onsite/', 'onsite/config/') - config_json = self._download_webpage(config_url, video_id, u'Downloading config') - config = json.loads(config_json) + config = self._download_json(config_url, video_id, 'Downloading config') smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4&manifest=f4m' else: smil_url = ('http://link.theplatform.com/s/dJ5BDC/{0}/meta.smil?' diff --git a/youtube_dl/extractor/tlc.py b/youtube_dl/extractor/tlc.py index ad175b83e..d848ee186 100644 --- a/youtube_dl/extractor/tlc.py +++ b/youtube_dl/extractor/tlc.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor from .brightcove import BrightcoveIE from .discovery import DiscoveryIE +from ..utils import compat_urlparse class TlcIE(DiscoveryIE): @@ -51,6 +52,10 @@ class TlcDeIE(InfoExtractor): # Otherwise we don't get the correct 'BrightcoveExperience' element, # example: http://www.tlc.de/sendungen/cake-boss/videos/cake-boss-cannoli-drama/ iframe_url = iframe_url.replace('.htm?', '.php?') + url_fragment = compat_urlparse.urlparse(url).fragment + if url_fragment: + # Since the fragment is not send to the server, we always get the same iframe + iframe_url = re.sub(r'playlist=(\d+)', 'playlist=%s' % url_fragment, iframe_url) iframe = self._download_webpage(iframe_url, title) return { diff --git a/youtube_dl/extractor/toypics.py b/youtube_dl/extractor/toypics.py index 34008afc6..0f389bd93 100644 --- a/youtube_dl/extractor/toypics.py +++ b/youtube_dl/extractor/toypics.py @@ -1,10 +1,13 @@ +# -*- coding:utf-8 -*- +from __future__ import unicode_literals + from .common import InfoExtractor import re class ToypicsIE(InfoExtractor): IE_DESC = 'Toypics user profile' - _VALID_URL = r'http://videos\.toypics\.net/view/(?P<id>[0-9]+)/.*' + _VALID_URL = r'https?://videos\.toypics\.net/view/(?P<id>[0-9]+)/.*' _TEST = { 'url': 'http://videos.toypics.net/view/514/chancebulged,-2-1/', 'md5': '16e806ad6d6f58079d210fe30985e08b', @@ -61,7 +64,7 @@ class ToypicsUserIE(InfoExtractor): note='Downloading page %d/%d' % (n, page_count)) urls.extend( re.findall( - r'<p class="video-entry-title">\n\s*<a href="(http://videos.toypics.net/view/[^"]+)">', + r'<p class="video-entry-title">\s+<a href="(https?://videos.toypics.net/view/[^"]+)">', lpage)) return { diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py index 36bc36ad8..08a48c05a 100644 --- a/youtube_dl/extractor/tube8.py +++ b/youtube_dl/extractor/tube8.py @@ -17,9 +17,10 @@ class Tube8IE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/){2}(?P<id>\d+)' _TEST = { 'url': 'http://www.tube8.com/teen/kasia-music-video/229795/', - 'file': '229795.mp4', - 'md5': 'e9e0b0c86734e5e3766e653509475db0', + 'md5': '44bf12b98313827dd52d35b8706a4ea0', 'info_dict': { + 'id': '229795', + 'ext': 'mp4', 'description': 'hot teen Kasia grinding', 'uploader': 'unknown', 'title': 'Kasia music video', diff --git a/youtube_dl/extractor/tumblr.py b/youtube_dl/extractor/tumblr.py index 544369068..2882c1809 100644 --- a/youtube_dl/extractor/tumblr.py +++ b/youtube_dl/extractor/tumblr.py @@ -1,3 +1,4 @@ +# -*- coding: utf-8 -*- from __future__ import unicode_literals import re @@ -10,14 +11,27 @@ from ..utils import ( class TumblrIE(InfoExtractor): _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)($|/)' - _TEST = { + _TESTS = [{ 'url': 'http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes', - 'file': '54196191430.mp4', 'md5': '479bb068e5b16462f5176a6828829767', 'info_dict': { - "title": "tatiana maslany news" + 'id': '54196191430', + 'ext': 'mp4', + 'title': 'tatiana maslany news, Orphan Black || DVD extra - behind the scenes ↳...', + 'description': 'md5:dfac39636969fe6bf1caa2d50405f069', + 'thumbnail': 're:http://.*\.jpg', } - } + }, { + 'url': 'http://5sostrum.tumblr.com/post/90208453769/yall-forgetting-the-greatest-keek-of-them-all', + 'md5': 'bf348ef8c0ef84fbf1cbd6fa6e000359', + 'info_dict': { + 'id': '90208453769', + 'ext': 'mp4', + 'title': '5SOS STRUM ;)', + 'description': 'md5:dba62ac8639482759c8eb10ce474586a', + 'thumbnail': 're:http://.*\.jpg', + } + }] def _real_extract(self, url): m_url = re.match(self._VALID_URL, url) @@ -48,6 +62,7 @@ class TumblrIE(InfoExtractor): return [{'id': video_id, 'url': video_url, 'title': video_title, + 'description': self._html_search_meta('description', webpage), 'thumbnail': video_thumbnail, 'ext': ext }] diff --git a/youtube_dl/extractor/tutv.py b/youtube_dl/extractor/tutv.py index c980153ec..d516b6427 100644 --- a/youtube_dl/extractor/tutv.py +++ b/youtube_dl/extractor/tutv.py @@ -1,21 +1,21 @@ from __future__ import unicode_literals + import base64 import re from .common import InfoExtractor -from ..utils import ( - compat_parse_qs, -) +from ..utils import compat_parse_qs class TutvIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?tu\.tv/videos/(?P<id>[^/?]+)' _TEST = { - 'url': 'http://tu.tv/videos/noah-en-pabellon-cuahutemoc', - 'file': '2742556.flv', - 'md5': '5eb766671f69b82e528dc1e7769c5cb2', + 'url': 'http://tu.tv/videos/robots-futbolistas', + 'md5': '627c7c124ac2a9b5ab6addb94e0e65f7', 'info_dict': { - 'title': 'Noah en pabellon cuahutemoc', + 'id': '2973058', + 'ext': 'flv', + 'title': 'Robots futbolistas', }, } @@ -26,10 +26,9 @@ class TutvIE(InfoExtractor): webpage = self._download_webpage(url, video_id) internal_id = self._search_regex(r'codVideo=([0-9]+)', webpage, 'internal video ID') - data_url = 'http://tu.tv/flvurl.php?codVideo=' + str(internal_id) - data_content = self._download_webpage(data_url, video_id, note='Downloading video info') - data = compat_parse_qs(data_content) - video_url = base64.b64decode(data['kpt'][0]).decode('utf-8') + data_content = self._download_webpage( + 'http://tu.tv/flvurl.php?codVideo=%s' % internal_id, video_id, 'Downloading video info') + video_url = base64.b64decode(compat_parse_qs(data_content)['kpt'][0]).decode('utf-8') return { 'id': internal_id, diff --git a/youtube_dl/extractor/tvplay.py b/youtube_dl/extractor/tvplay.py new file mode 100644 index 000000000..a56a7ab5f --- /dev/null +++ b/youtube_dl/extractor/tvplay.py @@ -0,0 +1,85 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + parse_iso8601, + qualities, +) + + +class TVPlayIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?tvplay\.lv/parraides/[^/]+/(?P<id>\d+)' + _TESTS = [ + { + 'url': 'http://www.tvplay.lv/parraides/vinas-melo-labak/418113?autostart=true', + 'info_dict': { + 'id': '418113', + 'ext': 'flv', + 'title': 'Kādi ir īri? - Viņas melo labāk', + 'description': 'Baiba apsmej īrus, kādi tie ir un ko viņi dara.', + 'duration': 25, + 'timestamp': 1406097056, + 'upload_date': '20140723', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + video = self._download_json( + 'http://playapi.mtgx.tv/v1/videos/%s' % video_id, video_id, 'Downloading video JSON') + + if video['is_geo_blocked']: + raise ExtractorError( + 'This content is not available in your country due to copyright reasons', expected=True) + + streams = self._download_json( + 'http://playapi.mtgx.tv/v1/videos/stream/%s' % video_id, video_id, 'Downloading streams JSON') + + quality = qualities(['hls', 'medium', 'high']) + formats = [] + for format_id, video_url in streams['streams'].items(): + if not video_url: + continue + fmt = { + 'format_id': format_id, + 'preference': quality(format_id), + } + if video_url.startswith('rtmp'): + m = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', video_url) + if not m: + continue + fmt.update({ + 'ext': 'flv', + 'url': m.group('url'), + 'app': m.group('app'), + 'play_path': m.group('playpath'), + }) + else: + fmt.update({ + 'url': video_url, + }) + formats.append(fmt) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': video['title'], + 'description': video['description'], + 'duration': video['duration'], + 'timestamp': parse_iso8601(video['created_at']), + 'view_count': video['views']['total'], + 'age_limit': video.get('age_limit', 0), + 'formats': formats, + } diff --git a/youtube_dl/extractor/ubu.py b/youtube_dl/extractor/ubu.py new file mode 100644 index 000000000..0182d67ec --- /dev/null +++ b/youtube_dl/extractor/ubu.py @@ -0,0 +1,56 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import int_or_none + + +class UbuIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?ubu\.com/film/(?P<id>[\da-z_-]+)\.html' + _TEST = { + 'url': 'http://ubu.com/film/her_noise.html', + 'md5': '8edd46ee8aa6b265fb5ed6cf05c36bc9', + 'info_dict': { + 'id': 'her_noise', + 'ext': 'mp4', + 'title': 'Her Noise - The Making Of (2007)', + 'duration': 3600, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex( + r'<title>.+?Film & Video: ([^<]+)</title>', webpage, 'title') + + duration = int_or_none(self._html_search_regex( + r'Duration: (\d+) minutes', webpage, 'duration', fatal=False, default=None)) + if duration: + duration *= 60 + + formats = [] + + FORMAT_REGEXES = [ + ['sq', r"'flashvars'\s*,\s*'file=([^']+)'"], + ['hq', r'href="(http://ubumexico\.centro\.org\.mx/video/[^"]+)"'] + ] + + for format_id, format_regex in FORMAT_REGEXES: + m = re.search(format_regex, webpage) + if m: + formats.append({ + 'url': m.group(1), + 'format_id': format_id, + }) + + return { + 'id': video_id, + 'title': title, + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/ustream.py b/youtube_dl/extractor/ustream.py index e4bb3b949..488b10df9 100644 --- a/youtube_dl/extractor/ustream.py +++ b/youtube_dl/extractor/ustream.py @@ -11,29 +11,36 @@ from ..utils import ( class UstreamIE(InfoExtractor): - _VALID_URL = r'https?://www\.ustream\.tv/(?P<type>recorded|embed)/(?P<videoID>\d+)' + _VALID_URL = r'https?://www\.ustream\.tv/(?P<type>recorded|embed|embed/recorded)/(?P<videoID>\d+)' IE_NAME = 'ustream' _TEST = { 'url': 'http://www.ustream.tv/recorded/20274954', - 'file': '20274954.flv', 'md5': '088f151799e8f572f84eb62f17d73e5c', 'info_dict': { - "uploader": "Young Americans for Liberty", - "title": "Young Americans for Liberty February 7, 2012 2:28 AM", + 'id': '20274954', + 'ext': 'flv', + 'uploader': 'Young Americans for Liberty', + 'title': 'Young Americans for Liberty February 7, 2012 2:28 AM', }, } def _real_extract(self, url): m = re.match(self._VALID_URL, url) + video_id = m.group('videoID') + + # some sites use this embed format (see: http://github.com/rg3/youtube-dl/issues/2990) + if m.group('type') == 'embed/recorded': + video_id = m.group('videoID') + desktop_url = 'http://www.ustream.tv/recorded/' + video_id + return self.url_result(desktop_url, 'Ustream') if m.group('type') == 'embed': video_id = m.group('videoID') webpage = self._download_webpage(url, video_id) - desktop_video_id = self._html_search_regex(r'ContentVideoIds=\["([^"]*?)"\]', webpage, 'desktop_video_id') + desktop_video_id = self._html_search_regex( + r'ContentVideoIds=\["([^"]*?)"\]', webpage, 'desktop_video_id') desktop_url = 'http://www.ustream.tv/recorded/' + desktop_video_id return self.url_result(desktop_url, 'Ustream') - video_id = m.group('videoID') - video_url = 'http://tcdn.ustream.tv/video/%s' % video_id webpage = self._download_webpage(url, video_id) diff --git a/youtube_dl/extractor/veoh.py b/youtube_dl/extractor/veoh.py index d16993daf..a7953a7e7 100644 --- a/youtube_dl/extractor/veoh.py +++ b/youtube_dl/extractor/veoh.py @@ -7,6 +7,7 @@ from .common import InfoExtractor from ..utils import ( compat_urllib_request, int_or_none, + ExtractorError, ) @@ -48,6 +49,7 @@ class VeohIE(InfoExtractor): 'description': 'md5:f5a11c51f8fb51d2315bca0937526891', 'uploader': 'newsy-videos', }, + 'skip': 'This video has been deleted.', }, ] @@ -94,8 +96,12 @@ class VeohIE(InfoExtractor): if video_id.startswith('v'): rsp = self._download_xml( r'http://www.veoh.com/api/findByPermalink?permalink=%s' % video_id, video_id, 'Downloading video XML') - if rsp.get('stat') == 'ok': + stat = rsp.get('stat') + if stat == 'ok': return self._extract_video(rsp.find('./videoList/video')) + elif stat == 'fail': + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, rsp.find('./errorList/error').get('errorMessage')), expected=True) webpage = self._download_webpage(url, video_id) age_limit = 0 diff --git a/youtube_dl/extractor/vevo.py b/youtube_dl/extractor/vevo.py index ea34a8f16..d2ffd1b6b 100644 --- a/youtube_dl/extractor/vevo.py +++ b/youtube_dl/extractor/vevo.py @@ -16,7 +16,7 @@ class VevoIE(InfoExtractor): (currently used by MTVIE) """ _VALID_URL = r'''(?x) - (?:https?://www\.vevo\.com/watch/(?:[^/]+/[^/]+/)?| + (?:https?://www\.vevo\.com/watch/(?:[^/]+/(?:[^/]+/)?)?| https?://cache\.vevo\.com/m/html/embed\.html\?video=| https?://videoplayer\.vevo\.com/embed/embedded\?videoId=| vevo:) @@ -177,6 +177,7 @@ class VevoIE(InfoExtractor): self._downloader.report_warning( 'Cannot download SMIL information, falling back to JSON ..') + self._sort_formats(formats) timestamp_ms = int(self._search_regex( r'/Date\((\d+)\)/', video_info['launchDate'], 'launch date')) diff --git a/youtube_dl/extractor/vh1.py b/youtube_dl/extractor/vh1.py new file mode 100644 index 000000000..2f77e3898 --- /dev/null +++ b/youtube_dl/extractor/vh1.py @@ -0,0 +1,124 @@ +from __future__ import unicode_literals + +from .mtv import MTVIE + +import re +from ..utils import fix_xml_ampersands + + +class VH1IE(MTVIE): + IE_NAME = 'vh1.com' + _FEED_URL = 'http://www.vh1.com/player/embed/AS3/fullepisode/rss/' + _TESTS = [{ + 'url': 'http://www.vh1.com/video/metal-evolution/full-episodes/progressive-metal/1678612/playlist.jhtml', + 'playlist': [ + { + 'md5': '7827a7505f59633983165bbd2c119b52', + 'info_dict': { + 'id': '731565', + 'ext': 'mp4', + 'title': 'Metal Evolution: Ep. 11 Act 1', + 'description': 'Many rock academics have proclaimed that the truly progressive musicianship of the last 20 years has been found right here in the world of heavy metal, rather than obvious locales such as jazz, fusion or progressive rock. It stands to reason then, that much of this jaw-dropping virtuosity occurs within what\'s known as progressive metal, a genre that takes root with the likes of Rush in the \'70s, Queensryche and Fates Warning in the \'80s, and Dream Theater in the \'90s. Since then, the genre has exploded with creativity, spawning mind-bending, genre-defying acts such as Tool, Mastodon, Coheed And Cambria, Porcupine Tree, Meshuggah, A Perfect Circle and Opeth. Episode 12 looks at the extreme musicianship of these bands, as well as their often extreme literary prowess and conceptual strength, the end result being a rich level of respect and attention such challenging acts have brought upon the world of heavy metal, from a critical community usually dismissive of the form.' + } + }, + { + 'md5': '34fb4b7321c546b54deda2102a61821f', + 'info_dict': { + 'id': '731567', + 'ext': 'mp4', + 'title': 'Metal Evolution: Ep. 11 Act 2', + 'description': 'Many rock academics have proclaimed that the truly progressive musicianship of the last 20 years has been found right here in the world of heavy metal, rather than obvious locales such as jazz, fusion or progressive rock. It stands to reason then, that much of this jaw-dropping virtuosity occurs within what\'s known as progressive metal, a genre that takes root with the likes of Rush in the \'70s, Queensryche and Fates Warning in the \'80s, and Dream Theater in the \'90s. Since then, the genre has exploded with creativity, spawning mind-bending, genre-defying acts such as Tool, Mastodon, Coheed And Cambria, Porcupine Tree, Meshuggah, A Perfect Circle and Opeth. Episode 11 looks at the extreme musicianship of these bands, as well as their often extreme literary prowess and conceptual strength, the end result being a rich level of respect and attention such challenging acts have brought upon the world of heavy metal, from a critical community usually dismissive of the form.' + } + }, + { + 'md5': '813f38dba4c1b8647196135ebbf7e048', + 'info_dict': { + 'id': '731568', + 'ext': 'mp4', + 'title': 'Metal Evolution: Ep. 11 Act 3', + 'description': 'Many rock academics have proclaimed that the truly progressive musicianship of the last 20 years has been found right here in the world of heavy metal, rather than obvious locales such as jazz, fusion or progressive rock. It stands to reason then, that much of this jaw-dropping virtuosity occurs within what\'s known as progressive metal, a genre that takes root with the likes of Rush in the \'70s, Queensryche and Fates Warning in the \'80s, and Dream Theater in the \'90s. Since then, the genre has exploded with creativity, spawning mind-bending, genre-defying acts such as Tool, Mastodon, Coheed And Cambria, Porcupine Tree, Meshuggah, A Perfect Circle and Opeth. Episode 11 looks at the extreme musicianship of these bands, as well as their often extreme literary prowess and conceptual strength, the end result being a rich level of respect and attention such challenging acts have brought upon the world of heavy metal, from a critical community usually dismissive of the form.' + } + }, + { + 'md5': '51adb72439dfaed11c799115d76e497f', + 'info_dict': { + 'id': '731569', + 'ext': 'mp4', + 'title': 'Metal Evolution: Ep. 11 Act 4', + 'description': 'Many rock academics have proclaimed that the truly progressive musicianship of the last 20 years has been found right here in the world of heavy metal, rather than obvious locales such as jazz, fusion or progressive rock. It stands to reason then, that much of this jaw-dropping virtuosity occurs within what\'s known as progressive metal, a genre that takes root with the likes of Rush in the \'70s, Queensryche and Fates Warning in the \'80s, and Dream Theater in the \'90s. Since then, the genre has exploded with creativity, spawning mind-bending, genre-defying acts such as Tool, Mastodon, Coheed And Cambria, Porcupine Tree, Meshuggah, A Perfect Circle and Opeth. Episode 11 looks at the extreme musicianship of these bands, as well as their often extreme literary prowess and conceptual strength, the end result being a rich level of respect and attention such challenging acts have brought upon the world of heavy metal, from a critical community usually dismissive of the form.' + } + }, + { + 'md5': '93d554aaf79320703b73a95288c76a6e', + 'info_dict': { + 'id': '731570', + 'ext': 'mp4', + 'title': 'Metal Evolution: Ep. 11 Act 5', + 'description': 'Many rock academics have proclaimed that the truly progressive musicianship of the last 20 years has been found right here in the world of heavy metal, rather than obvious locales such as jazz, fusion or progressive rock. It stands to reason then, that much of this jaw-dropping virtuosity occurs within what\'s known as progressive metal, a genre that takes root with the likes of Rush in the \'70s, Queensryche and Fates Warning in the \'80s, and Dream Theater in the \'90s. Since then, the genre has exploded with creativity, spawning mind-bending, genre-defying acts such as Tool, Mastodon, Coheed And Cambria, Porcupine Tree, Meshuggah, A Perfect Circle and Opeth. Episode 11 looks at the extreme musicianship of these bands, as well as their often extreme literary prowess and conceptual strength, the end result being a rich level of respect and attention such challenging acts have brought upon the world of heavy metal, from a critical community usually dismissive of the form.' + } + } + ], + 'skip': 'Blocked outside the US', + }, { + # Clip + 'url': 'http://www.vh1.com/video/misc/706675/metal-evolution-episode-1-pre-metal-show-clip.jhtml#id=1674118', + 'md5': '7d67cf6d9cdc6b4f3d3ac97a55403844', + 'info_dict': { + 'id': '706675', + 'ext': 'mp4', + 'title': 'Metal Evolution: Episode 1 Pre-Metal Show Clip', + 'description': 'The greatest documentary ever made about Heavy Metal begins as our host Sam Dunn travels the globe to seek out the origins and influences that helped create Heavy Metal. Sam speaks to legends like Kirk Hammett, Alice Cooper, Slash, Bill Ward, Geezer Butler, Tom Morello, Ace Frehley, Lemmy Kilmister, Dave Davies, and many many more. This episode is the prologue for the 11 hour series, and Sam goes back to the very beginning to reveal how Heavy Metal was created.' + }, + 'skip': 'Blocked outside the US', + }, { + # Short link + 'url': 'http://www.vh1.com/video/play.jhtml?id=1678353', + 'md5': '853192b87ad978732b67dd8e549b266a', + 'info_dict': { + 'id': '730355', + 'ext': 'mp4', + 'title': 'Metal Evolution: Episode 11 Progressive Metal Sneak', + 'description': 'In Metal Evolution\'s finale sneak, Sam sits with Michael Giles of King Crimson and gets feedback from Metallica guitarist Kirk Hammett on why the group was influential.' + }, + 'skip': 'Blocked outside the US', + }, { + 'url': 'http://www.vh1.com/video/macklemore-ryan-lewis/900535/cant-hold-us-ft-ray-dalton.jhtml', + 'md5': 'b1bcb5b4380c9d7f544065589432dee7', + 'info_dict': { + 'id': '900535', + 'ext': 'mp4', + 'title': 'Macklemore & Ryan Lewis - "Can\'t Hold Us ft. Ray Dalton"', + 'description': 'The Heist' + }, + 'skip': 'Blocked outside the US', + }] + + _VALID_URL = r'''(?x) + https?://www\.vh1\.com/video/ + (?: + .+?/full-episodes/.+?/(?P<playlist_id>[^/]+)/playlist\.jhtml + | + (?: + play.jhtml\?id=| + misc/.+?/.+?\.jhtml\#id= + ) + (?P<video_id>[0-9]+)$ + | + [^/]+/(?P<music_id>[0-9]+)/[^/]+? + ) + ''' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj.group('music_id'): + id_field = 'vid' + video_id = mobj.group('music_id') + else: + video_id = mobj.group('playlist_id') or mobj.group('video_id') + id_field = 'id' + doc_url = '%s?%s=%s' % (self._FEED_URL, id_field, video_id) + + idoc = self._download_xml( + doc_url, video_id, + 'Downloading info', transform_source=fix_xml_ampersands) + return [self._get_video_info(item) for item in idoc.findall('.//item')] diff --git a/youtube_dl/extractor/videott.py b/youtube_dl/extractor/videott.py index b5034b02f..a647807d0 100644 --- a/youtube_dl/extractor/videott.py +++ b/youtube_dl/extractor/videott.py @@ -4,7 +4,10 @@ import re import base64 from .common import InfoExtractor -from ..utils import unified_strdate +from ..utils import ( + unified_strdate, + int_or_none, +) class VideoTtIE(InfoExtractor): @@ -50,9 +53,9 @@ class VideoTtIE(InfoExtractor): 'thumbnail': settings['config']['thumbnail'], 'upload_date': unified_strdate(video['added']), 'uploader': video['owner'], - 'view_count': int(video['view_count']), - 'comment_count': int(video['comment_count']), - 'like_count': int(video['liked']), - 'dislike_count': int(video['disliked']), + 'view_count': int_or_none(video['view_count']), + 'comment_count': None if video.get('comment_count') == '--' else int_or_none(video['comment_count']), + 'like_count': int_or_none(video['liked']), + 'dislike_count': int_or_none(video['disliked']), 'formats': formats, }
\ No newline at end of file diff --git a/youtube_dl/extractor/vidme.py b/youtube_dl/extractor/vidme.py new file mode 100644 index 000000000..5c89824c1 --- /dev/null +++ b/youtube_dl/extractor/vidme.py @@ -0,0 +1,68 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + float_or_none, + str_to_int, +) + + +class VidmeIE(InfoExtractor): + _VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]+)' + _TEST = { + 'url': 'https://vid.me/QNB', + 'md5': 'f42d05e7149aeaec5c037b17e5d3dc82', + 'info_dict': { + 'id': 'QNB', + 'ext': 'mp4', + 'title': 'Fishing for piranha - the easy way', + 'description': 'source: https://www.facebook.com/photo.php?v=312276045600871', + 'duration': 119.92, + 'timestamp': 1406313244, + 'upload_date': '20140725', + 'thumbnail': 're:^https?://.*\.jpg', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + 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='') + thumbnail = self._og_search_thumbnail(webpage) + timestamp = int_or_none(self._og_search_property('updated_time', webpage, fatal=False)) + width = int_or_none(self._og_search_property('video:width', webpage, fatal=False)) + height = int_or_none(self._og_search_property('video:height', webpage, fatal=False)) + 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)) + 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, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'width': width, + 'height': height, + '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 255855558..11c7d7e81 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -98,7 +98,7 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): 'info_dict': { 'id': '54469442', 'ext': 'mp4', - 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software', + 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012', 'uploader': 'The BLN & Business of Software', 'uploader_id': 'theblnbusinessofsoftware', 'duration': 3610, @@ -122,6 +122,21 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): }, }, { + 'url': 'http://vimeo.com/channels/keypeele/75629013', + 'md5': '2f86a05afe9d7abc0b9126d229bbe15d', + 'note': 'Video is freely available via original URL ' + 'and protected with password when accessed via http://vimeo.com/75629013', + 'info_dict': { + 'id': '75629013', + 'ext': 'mp4', + 'title': 'Key & Peele: Terrorist Interrogation', + 'description': 'md5:8678b246399b070816b12313e8b4eb5c', + 'uploader_id': 'atencio', + 'uploader': 'Peter Atencio', + 'duration': 187, + }, + }, + { 'url': 'http://vimeo.com/76979871', 'md5': '3363dd6ffebe3784d56f4132317fd446', 'note': 'Video with subtitles', @@ -196,8 +211,6 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): video_id = mobj.group('id') if mobj.group('pro') or mobj.group('player'): url = 'http://player.vimeo.com/video/' + video_id - else: - url = 'https://vimeo.com/' + video_id # Retrieve video webpage to extract further information request = compat_urllib_request.Request(url, None, headers) @@ -263,7 +276,7 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): if video_thumbnail is None: video_thumbs = config["video"].get("thumbs") if video_thumbs and isinstance(video_thumbs, dict): - _, video_thumbnail = sorted((int(width), t_url) for (width, t_url) in video_thumbs.items())[-1] + _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1] # Extract video description video_description = None diff --git a/youtube_dl/extractor/vimple.py b/youtube_dl/extractor/vimple.py new file mode 100644 index 000000000..33d370e1c --- /dev/null +++ b/youtube_dl/extractor/vimple.py @@ -0,0 +1,86 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import base64 +import re +import xml.etree.ElementTree +import zlib + +from .common import InfoExtractor +from ..utils import int_or_none + + +class VimpleIE(InfoExtractor): + IE_DESC = 'Vimple.ru' + _VALID_URL = r'https?://(player.vimple.ru/iframe|vimple.ru)/(?P<id>[a-f0-9]{10,})' + _TESTS = [ + # Quality: Large, from iframe + { + 'url': 'http://player.vimple.ru/iframe/b132bdfd71b546d3972f9ab9a25f201c', + 'info_dict': { + 'id': 'b132bdfd71b546d3972f9ab9a25f201c', + 'title': 'great-escape-minecraft.flv', + 'ext': 'mp4', + 'duration': 352, + 'webpage_url': 'http://vimple.ru/b132bdfd71b546d3972f9ab9a25f201c', + }, + }, + # Quality: Medium, from mainpage + { + 'url': 'http://vimple.ru/a15950562888453b8e6f9572dc8600cd', + 'info_dict': { + 'id': 'a15950562888453b8e6f9572dc8600cd', + 'title': 'DB 01', + 'ext': 'flv', + 'duration': 1484, + 'webpage_url': 'http://vimple.ru/a15950562888453b8e6f9572dc8600cd', + } + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + iframe_url = 'http://player.vimple.ru/iframe/%s' % video_id + + iframe = self._download_webpage( + iframe_url, video_id, + note='Downloading iframe', errnote='unable to fetch iframe') + player_url = self._html_search_regex( + r'"(http://player.vimple.ru/flash/.+?)"', iframe, 'player url') + + player = self._request_webpage( + player_url, video_id, note='Downloading swf player').read() + + player = zlib.decompress(player[8:]) + + xml_pieces = re.findall(b'([a-zA-Z0-9 =+/]{500})', player) + xml_pieces = [piece[1:-1] for piece in xml_pieces] + + xml_data = b''.join(xml_pieces) + xml_data = base64.b64decode(xml_data) + + xml_data = xml.etree.ElementTree.fromstring(xml_data) + + video = xml_data.find('Video') + quality = video.get('quality') + q_tag = video.find(quality.capitalize()) + + formats = [ + { + 'url': q_tag.get('url'), + 'tbr': int(q_tag.get('bitrate')), + 'filesize': int(q_tag.get('filesize')), + 'format_id': quality, + }, + ] + + return { + 'id': video_id, + 'title': video.find('Title').text, + 'formats': formats, + 'thumbnail': video.find('Poster').get('url'), + 'duration': int_or_none(video.get('duration')), + 'webpage_url': video.find('Share').get('videoPageUrl'), + } diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index fb082f364..918bd1098 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -16,7 +16,7 @@ from ..utils import ( class VKIE(InfoExtractor): IE_NAME = 'vk.com' - _VALID_URL = r'https?://vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:videos.*?\?.*?z=)?video(?P<videoid>.*?)(?:\?|%2F|$))' + _VALID_URL = r'https?://(?:m\.)?vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:.+?\?.*?z=)?video(?P<videoid>.*?)(?:\?|%2F|$))' _NETRC_MACHINE = 'vk' _TESTS = [ @@ -27,7 +27,7 @@ class VKIE(InfoExtractor): 'id': '162222515', 'ext': 'flv', 'title': 'ProtivoGunz - Хуёвая песня', - 'uploader': 'Noize MC', + 'uploader': 're:Noize MC.*', 'duration': 195, }, }, @@ -62,11 +62,47 @@ class VKIE(InfoExtractor): 'id': '164049491', 'ext': 'mp4', 'uploader': 'Триллеры', - 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]\u00a0', + 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]', 'duration': 8352, }, 'skip': 'Requires vk account credentials', }, + { + 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a', + 'md5': 'd82c22e449f036282d1d3f7f4d276869', + 'info_dict': { + 'id': '166094326', + 'ext': 'mp4', + 'uploader': 'Киномания - лучшее из мира кино', + 'title': 'Запах женщины (1992)', + 'duration': 9392, + }, + 'skip': 'Requires vk account credentials', + }, + { + 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d', + 'md5': '4d7a5ef8cf114dfa09577e57b2993202', + 'info_dict': { + 'id': '168067957', + 'ext': 'mp4', + 'uploader': 'Киномания - лучшее из мира кино', + 'title': ' ', + 'duration': 7291, + }, + 'skip': 'Requires vk account credentials', + }, + { + 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540', + 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6', + 'note': 'ivi.ru embed', + 'info_dict': { + 'id': '60690', + 'ext': 'mp4', + 'title': 'Книга Илая', + 'duration': 6771, + }, + 'skip': 'Only works from Russia', + }, ] def _login(self): @@ -110,6 +146,16 @@ class VKIE(InfoExtractor): if m_yt is not None: self.to_screen('Youtube video detected') return self.url_result(m_yt.group(1), 'Youtube') + + m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.*?});', info_page) + if m_opts: + m_opts_url = re.search(r"url\s*:\s*'([^']+)", m_opts.group(1)) + if m_opts_url: + opts_url = m_opts_url.group(1) + if opts_url.startswith('//'): + opts_url = 'http:' + opts_url + return self.url_result(opts_url) + data_json = self._search_regex(r'var vars = ({.*?});', info_page, 'vars') data = json.loads(data_json) diff --git a/youtube_dl/extractor/vodlocker.py b/youtube_dl/extractor/vodlocker.py new file mode 100644 index 000000000..6d3b78749 --- /dev/null +++ b/youtube_dl/extractor/vodlocker.py @@ -0,0 +1,63 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import re +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + compat_urllib_request, +) + + +class VodlockerIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?P<id>[0-9a-zA-Z]+)(?:\..*?)?' + + _TESTS = [{ + 'url': 'http://vodlocker.com/e8wvyzz4sl42', + 'md5': 'ce0c2d18fa0735f1bd91b69b0e54aacf', + 'info_dict': { + 'id': 'e8wvyzz4sl42', + 'ext': 'mp4', + 'title': 'Germany vs Brazil', + 'thumbnail': 're:http://.*\.jpg', + }, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + + fields = dict(re.findall(r'''(?x)<input\s+ + type="hidden"\s+ + name="([^"]+)"\s+ + (?:id="[^"]+"\s+)? + value="([^"]*)" + ''', webpage)) + + if fields['op'] == 'download1': + self._sleep(3, video_id) # they do detect when requests happen too fast! + post = compat_urllib_parse.urlencode(fields) + req = compat_urllib_request.Request(url, post) + req.add_header('Content-type', 'application/x-www-form-urlencoded') + webpage = self._download_webpage( + req, video_id, 'Downloading video page') + + title = self._search_regex( + r'id="file_title".*?>\s*(.*?)\s*<span', webpage, 'title') + thumbnail = self._search_regex( + r'image:\s*"(http[^\"]+)",', webpage, 'thumbnail') + url = self._search_regex( + r'file:\s*"(http[^\"]+)",', webpage, 'file url') + + formats = [{ + 'format_id': 'sd', + 'url': url, + }] + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/vube.py b/youtube_dl/extractor/vube.py index 7b77865cb..2544c24bd 100644 --- a/youtube_dl/extractor/vube.py +++ b/youtube_dl/extractor/vube.py @@ -3,7 +3,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + int_or_none, + compat_str, +) class VubeIE(InfoExtractor): @@ -20,12 +23,15 @@ class VubeIE(InfoExtractor): 'ext': 'mp4', 'title': 'Chiara Grispo - Price Tag by Jessie J', 'description': 'md5:8ea652a1f36818352428cb5134933313', - 'thumbnail': 'http://frame.thestaticvube.com/snap/228x128/102e7e63057-5ebc-4f5c-4065-6ce4ebde131f.jpg', + 'thumbnail': 're:^http://frame\.thestaticvube\.com/snap/[0-9x]+/102e7e63057-5ebc-4f5c-4065-6ce4ebde131f\.jpg$', 'uploader': 'Chiara.Grispo', - 'uploader_id': '1u3hX0znhP', 'timestamp': 1388743358, 'upload_date': '20140103', - 'duration': 170.56 + 'duration': 170.56, + 'like_count': int, + 'dislike_count': int, + 'comment_count': int, + 'categories': ['pop', 'music', 'cover', 'singing', 'jessie j', 'price tag', 'chiara grispo'], } }, { @@ -36,12 +42,33 @@ class VubeIE(InfoExtractor): 'ext': 'mp4', 'title': 'My 7 year old Sister and I singing "Alive" by Krewella', 'description': 'md5:40bcacb97796339f1690642c21d56f4a', - 'thumbnail': 'http://frame.thestaticvube.com/snap/228x128/102265d5a9f-0f17-4f6b-5753-adf08484ee1e.jpg', + 'thumbnail': 're:^http://frame\.thestaticvube\.com/snap/[0-9x]+/102265d5a9f-0f17-4f6b-5753-adf08484ee1e\.jpg$', 'uploader': 'Seraina', - 'uploader_id': 'XU9VE2BQ2q', 'timestamp': 1396492438, 'upload_date': '20140403', - 'duration': 240.107 + 'duration': 240.107, + 'like_count': int, + 'dislike_count': int, + 'comment_count': int, + 'categories': ['seraina', 'jessica', 'krewella', 'alive'], + } + }, { + 'url': 'http://vube.com/vote/Siren+Gene/0nmsMY5vEq?n=2&t=s', + 'md5': '0584fc13b50f887127d9d1007589d27f', + 'info_dict': { + 'id': '0nmsMY5vEq', + 'ext': 'mp4', + 'title': 'Frozen - Let It Go Cover by Siren Gene', + 'description': 'My rendition of "Let It Go" originally sung by Idina Menzel.', + 'thumbnail': 're:^http://frame\.thestaticvube\.com/snap/[0-9x]+/10283ab622a-86c9-4681-51f2-30d1f65774af\.jpg$', + 'uploader': 'Siren', + 'timestamp': 1395448018, + 'upload_date': '20140322', + 'duration': 221.788, + 'like_count': int, + 'dislike_count': int, + 'comment_count': int, + 'categories': ['let it go', 'cover', 'idina menzel', 'frozen', 'singing', 'disney', 'siren gene'], } } ] @@ -51,39 +78,52 @@ class VubeIE(InfoExtractor): video_id = mobj.group('id') video = self._download_json( - 'http://vube.com/api/v2/video/%s' % video_id, video_id, 'Downloading video JSON') + 'http://vube.com/t-api/v1/video/%s' % video_id, video_id, 'Downloading video JSON') public_id = video['public_id'] - formats = [ - { - 'url': 'http://video.thestaticvube.com/video/%s/%s.mp4' % (fmt['media_resolution_id'], public_id), - 'height': int(fmt['height']), - 'abr': int(fmt['audio_bitrate']), - 'vbr': int(fmt['video_bitrate']), - 'format_id': fmt['media_resolution_id'] - } for fmt in video['mtm'] if fmt['transcoding_status'] == 'processed' - ] + formats = [] + + for media in video['media'].get('video', []) + video['media'].get('audio', []): + if media['transcoding_status'] != 'processed': + continue + fmt = { + 'url': 'http://video.thestaticvube.com/video/%s/%s.mp4' % (media['media_resolution_id'], public_id), + 'abr': int(media['audio_bitrate']), + 'format_id': compat_str(media['media_resolution_id']), + } + vbr = int(media['video_bitrate']) + if vbr: + fmt.update({ + 'vbr': vbr, + 'height': int(media['height']), + }) + formats.append(fmt) self._sort_formats(formats) title = video['title'] description = video.get('description') - thumbnail = video['thumbnail_src'] - if thumbnail.startswith('//'): - thumbnail = 'http:' + thumbnail - uploader = video['user_alias'] - uploader_id = video['user_url_id'] - timestamp = int(video['upload_time']) + thumbnail = self._proto_relative_url(video.get('thumbnail_src'), scheme='http:') + uploader = video.get('user_alias') or video.get('channel') + timestamp = int_or_none(video.get('upload_time')) duration = video['duration'] view_count = video.get('raw_view_count') like_count = video.get('total_likes') - dislike_count= video.get('total_hates') + dislike_count = video.get('total_hates') - comment = self._download_json( - 'http://vube.com/api/video/%s/comment' % video_id, video_id, 'Downloading video comment JSON') + comments = video.get('comments') + comment_count = None + if comments is None: + comment_data = self._download_json( + 'http://vube.com/api/video/%s/comment' % video_id, + video_id, 'Downloading video comment JSON', fatal=False) + if comment_data is not None: + comment_count = int_or_none(comment_data.get('total')) + else: + comment_count = len(comments) - comment_count = int_or_none(comment.get('total')) + categories = [tag['text'] for tag in video['tags']] return { 'id': video_id, @@ -92,11 +132,11 @@ class VubeIE(InfoExtractor): 'description': description, 'thumbnail': thumbnail, 'uploader': uploader, - 'uploader_id': uploader_id, 'timestamp': timestamp, 'duration': duration, 'view_count': view_count, 'like_count': like_count, 'dislike_count': dislike_count, 'comment_count': comment_count, + 'categories': categories, } diff --git a/youtube_dl/extractor/vulture.py b/youtube_dl/extractor/vulture.py new file mode 100644 index 000000000..1eb24a3d6 --- /dev/null +++ b/youtube_dl/extractor/vulture.py @@ -0,0 +1,69 @@ +from __future__ import unicode_literals + +import json +import os.path +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_iso8601, +) + + +class VultureIE(InfoExtractor): + IE_NAME = 'vulture.com' + _VALID_URL = r'https?://video\.vulture\.com/video/(?P<display_id>[^/]+)/' + _TEST = { + 'url': 'http://video.vulture.com/video/Mindy-Kaling-s-Harvard-Speech/player?layout=compact&read_more=1', + 'md5': '8d997845642a2b5152820f7257871bc8', + 'info_dict': { + 'id': '6GHRQL3RV7MSD1H4', + 'ext': 'mp4', + 'title': 'kaling-speech-2-MAGNIFY STANDARD CONTAINER REVISED', + 'uploader_id': 'Sarah', + 'thumbnail': 're:^http://.*\.jpg$', + 'timestamp': 1401288564, + 'upload_date': '20140528', + 'description': 'Uplifting and witty, as predicted.', + 'duration': 1015, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + query_string = self._search_regex( + r"queryString\s*=\s*'([^']+)'", webpage, 'query string') + video_id = self._search_regex( + r'content=([^&]+)', query_string, 'video ID') + query_url = 'http://video.vulture.com/embed/player/container/1000/1000/?%s' % query_string + + query_webpage = self._download_webpage( + query_url, display_id, note='Downloading query page') + params_json = self._search_regex( + r'(?sm)new MagnifyEmbeddablePlayer\({.*?contentItem:\s*(\{.*?\})\n,\n', + query_webpage, + 'player params') + params = json.loads(params_json) + + upload_timestamp = parse_iso8601(params['posted'].replace(' ', 'T')) + uploader_id = params.get('user', {}).get('handle') + + media_item = params['media_item'] + title = os.path.splitext(media_item['title'])[0] + duration = int_or_none(media_item.get('duration_seconds')) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': media_item['pipeline_xid'], + 'title': title, + 'timestamp': upload_timestamp, + 'thumbnail': params.get('thumbnail_url'), + 'uploader_id': uploader_id, + 'description': params.get('description'), + 'duration': duration, + } diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py index feeb44b45..54d37da61 100644 --- a/youtube_dl/extractor/wdr.py +++ b/youtube_dl/extractor/wdr.py @@ -1,3 +1,4 @@ +# -*- coding: utf-8 -*- from __future__ import unicode_literals import re @@ -54,14 +55,14 @@ class WDRIE(InfoExtractor): }, }, { - 'url': 'http://www.funkhauseuropa.de/av/audiogrenzenlosleckerbaklava101-audioplayer.html', - 'md5': 'cfff440d4ee64114083ac44676df5d15', + 'url': 'http://www.funkhauseuropa.de/av/audioflaviacoelhoamaramar100-audioplayer.html', + 'md5': '99a1443ff29af19f6c52cf6f4dc1f4aa', 'info_dict': { - 'id': 'mdb-363068', + 'id': 'mdb-478135', 'ext': 'mp3', - 'title': 'Grenzenlos lecker - Baklava', + 'title': 'Flavia Coelho: Amar é Amar', 'description': 'md5:7b29e97e10dfb6e265238b32fa35b23a', - 'upload_date': '20140311', + 'upload_date': '20140717', }, }, ] @@ -80,7 +81,7 @@ class WDRIE(InfoExtractor): ] return self.playlist_result(entries, page_id) - flashvars = compat_urlparse.parse_qs( + flashvars = compat_parse_qs( self._html_search_regex(r'<param name="flashvars" value="([^"]+)"', webpage, 'flashvars')) page_id = flashvars['trackerClipId'][0] @@ -127,9 +128,10 @@ class WDRMobileIE(InfoExtractor): 'info_dict': { 'title': '4283021', 'id': '421735', + 'ext': 'mp4', 'age_limit': 0, }, - '_skip': 'Will be depublicized shortly' + 'skip': 'Problems with loading data.' } def _real_extract(self, url): @@ -139,6 +141,7 @@ class WDRMobileIE(InfoExtractor): 'title': mobj.group('title'), 'age_limit': int(mobj.group('age_limit')), 'url': url, + 'ext': determine_ext(url), 'user_agent': 'mobile', } diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py index bc31c2e64..e6bfa9e14 100644 --- a/youtube_dl/extractor/wistia.py +++ b/youtube_dl/extractor/wistia.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import json import re @@ -5,14 +7,16 @@ from .common import InfoExtractor class WistiaIE(InfoExtractor): - _VALID_URL = r'^https?://(?:fast\.)?wistia\.net/embed/iframe/(?P<id>[a-z0-9]+)' + _VALID_URL = r'https?://(?:fast\.)?wistia\.net/embed/iframe/(?P<id>[a-z0-9]+)' _TEST = { - u"url": u"http://fast.wistia.net/embed/iframe/sh7fpupwlt", - u"file": u"sh7fpupwlt.mov", - u"md5": u"cafeb56ec0c53c18c97405eecb3133df", - u"info_dict": { - u"title": u"cfh_resourceful_zdkh_final_1" + 'url': 'http://fast.wistia.net/embed/iframe/sh7fpupwlt', + 'md5': 'cafeb56ec0c53c18c97405eecb3133df', + 'info_dict': { + 'id': 'sh7fpupwlt', + 'ext': 'mov', + 'title': 'Being Resourceful', + 'duration': 117, }, } @@ -22,7 +26,7 @@ class WistiaIE(InfoExtractor): webpage = self._download_webpage(url, video_id) data_json = self._html_search_regex( - r'Wistia.iframeInit\((.*?), {}\);', webpage, u'video data') + r'Wistia\.iframeInit\((.*?), {}\);', webpage, 'video data') data = json.loads(data_json) @@ -54,4 +58,5 @@ class WistiaIE(InfoExtractor): 'title': data['name'], 'formats': formats, 'thumbnails': thumbnails, + 'duration': data.get('duration'), } diff --git a/youtube_dl/extractor/wrzuta.py b/youtube_dl/extractor/wrzuta.py new file mode 100644 index 000000000..34dd6d952 --- /dev/null +++ b/youtube_dl/extractor/wrzuta.py @@ -0,0 +1,81 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + qualities, +) + + +class WrzutaIE(InfoExtractor): + IE_NAME = 'wrzuta.pl' + + _VALID_URL = r'https?://(?P<uploader>[0-9a-zA-Z]+)\.wrzuta\.pl/(?P<typ>film|audio)/(?P<id>[0-9a-zA-Z]+)' + + _TESTS = [{ + 'url': 'http://laboratoriumdextera.wrzuta.pl/film/aq4hIZWrkBu/nike_football_the_last_game', + 'md5': '9e67e05bed7c03b82488d87233a9efe7', + 'info_dict': { + 'id': 'aq4hIZWrkBu', + 'ext': 'mp4', + 'title': 'Nike Football: The Last Game', + 'duration': 307, + 'uploader_id': 'laboratoriumdextera', + 'description': 'md5:7fb5ef3c21c5893375fda51d9b15d9cd', + }, + }, { + 'url': 'http://w729.wrzuta.pl/audio/9oXJqdcndqv/david_guetta_amp_showtek_ft._vassy_-_bad', + 'md5': '1e546a18e1c22ac6e9adce17b8961ff5', + 'info_dict': { + 'id': '9oXJqdcndqv', + 'ext': 'ogg', + 'title': 'David Guetta & Showtek ft. Vassy - Bad', + 'duration': 270, + 'uploader_id': 'w729', + 'description': 'md5:4628f01c666bbaaecefa83476cfa794a', + }, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + typ = mobj.group('typ') + uploader = mobj.group('uploader') + + webpage = self._download_webpage(url, video_id) + + quality = qualities(['SD', 'MQ', 'HQ', 'HD']) + + audio_table = {'flv': 'mp3', 'webm': 'ogg'} + + embedpage = self._download_json('http://www.wrzuta.pl/npp/embed/%s/%s' % (uploader, video_id), video_id) + + formats = [] + for media in embedpage['url']: + if typ == 'audio': + ext = audio_table[media['type'].split('@')[0]] + else: + ext = media['type'].split('@')[0] + + formats.append({ + 'format_id': '%s_%s' % (ext, media['quality'].lower()), + 'url': media['url'], + 'ext': ext, + 'quality': quality(media['quality']), + }) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': self._og_search_title(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + 'formats': formats, + 'duration': int_or_none(embedpage['duration']), + 'uploader_id': uploader, + 'description': self._og_search_description(webpage), + 'age_limit': embedpage.get('minimalAge', 0), + } diff --git a/youtube_dl/extractor/xboxclips.py b/youtube_dl/extractor/xboxclips.py new file mode 100644 index 000000000..a9aa72e73 --- /dev/null +++ b/youtube_dl/extractor/xboxclips.py @@ -0,0 +1,57 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_iso8601, + float_or_none, + int_or_none, +) + + +class XboxClipsIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?xboxclips\.com/video\.php\?.*vid=(?P<id>[\w-]{36})' + _TEST = { + 'url': 'https://xboxclips.com/video.php?uid=2533274823424419&gamertag=Iabdulelah&vid=074a69a9-5faf-46aa-b93b-9909c1720325', + 'md5': 'fbe1ec805e920aeb8eced3c3e657df5d', + 'info_dict': { + 'id': '074a69a9-5faf-46aa-b93b-9909c1720325', + 'ext': 'mp4', + 'title': 'Iabdulelah playing Upload Studio', + 'filesize_approx': 28101836.8, + 'timestamp': 1407388500, + 'upload_date': '20140807', + 'duration': 56, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex( + r'>Link: <a href="([^"]+)">', webpage, 'video URL') + title = self._html_search_regex( + r'<title>XboxClips \| ([^<]+)</title>', webpage, 'title') + timestamp = parse_iso8601(self._html_search_regex( + r'>Recorded: ([^<]+)<', webpage, 'upload date', fatal=False)) + filesize = float_or_none(self._html_search_regex( + r'>Size: ([\d\.]+)MB<', webpage, 'file size', fatal=False), invscale=1024 * 1024) + duration = int_or_none(self._html_search_regex( + r'>Duration: (\d+) Seconds<', webpage, 'duration', fatal=False)) + view_count = int_or_none(self._html_search_regex( + r'>Views: (\d+)<', webpage, 'view count', fatal=False)) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'timestamp': timestamp, + 'filesize_approx': filesize, + 'duration': duration, + 'view_count': view_count, + } diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py index 85e99e1b0..7e0044824 100644 --- a/youtube_dl/extractor/xvideos.py +++ b/youtube_dl/extractor/xvideos.py @@ -5,18 +5,21 @@ import re from .common import InfoExtractor from ..utils import ( compat_urllib_parse, + ExtractorError, + clean_html, ) class XVideosIE(InfoExtractor): _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' _TEST = { - 'url': 'http://www.xvideos.com/video939581/funny_porns_by_s_-1', - 'file': '939581.flv', - 'md5': '1d0c835822f0a71a7bf011855db929d0', + 'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl', + 'md5': '4b46ae6ea5e6e9086e714d883313c0c9', 'info_dict': { - "title": "Funny Porns By >>>>S<<<<<< -1", - "age_limit": 18, + 'id': '4588838', + 'ext': 'flv', + 'title': 'Biker Takes his Girl', + 'age_limit': 18, } } @@ -28,6 +31,10 @@ class XVideosIE(InfoExtractor): self.report_extraction(video_id) + mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage) + if mobj: + raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True) + # Extract video URL video_url = compat_urllib_parse.unquote( self._search_regex(r'flv_url=(.+?)&', webpage, 'video URL')) diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index 393f6ffbe..0e3b33b16 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -15,13 +15,13 @@ from ..utils import ( class YahooIE(InfoExtractor): IE_DESC = 'Yahoo screen and movies' - _VALID_URL = r'https?://(?:screen|movies)\.yahoo\.com/.*?-(?P<id>[0-9]+)(?:-[a-z]+)?\.html' + _VALID_URL = r'(?P<url>https?://(?:screen|movies)\.yahoo\.com/.*?-(?P<id>[0-9]+)(?:-[a-z]+)?\.html)' _TESTS = [ { 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', 'md5': '4962b075c08be8690a922ee026d05e69', 'info_dict': { - 'id': '214727115', + 'id': '2d25e626-2378-391f-ada0-ddaf1417e588', 'ext': 'mp4', 'title': 'Julian Smith & Travis Legg Watch Julian Smith', 'description': 'Julian and Travis watch Julian Smith', @@ -31,7 +31,7 @@ class YahooIE(InfoExtractor): 'url': 'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html', 'md5': 'd6e6fc6e1313c608f316ddad7b82b306', 'info_dict': { - 'id': '103000935', + 'id': 'd1dedf8c-d58c-38c3-8963-e899929ae0a9', 'ext': 'mp4', 'title': 'Codefellas - The Cougar Lies with Spanish Moss', 'description': 'Agent Topple\'s mustache does its dirty work, and Nicole brokers a deal for peace. But why is the NSA collecting millions of Instagram brunch photos? And if your waffles have nothing to hide, what are they so worried about?', @@ -46,21 +46,34 @@ class YahooIE(InfoExtractor): 'title': 'The World Loves Spider-Man', 'description': '''People all over the world are celebrating the release of \"The Amazing Spider-Man 2.\" We're taking a look at the enthusiastic response Spider-Man has received from viewers all over the world.''', } - } + }, + { + 'url': 'https://screen.yahoo.com/community/community-sizzle-reel-203225340.html?format=embed', + 'md5': '60e8ac193d8fb71997caa8fce54c6460', + 'info_dict': { + 'id': '4fe78544-8d48-39d8-97cd-13f205d9fcdb', + 'ext': 'mp4', + 'title': "Yahoo Saves 'Community'", + 'description': 'md5:4d4145af2fd3de00cbb6c1d664105053', + } + }, ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + url = mobj.group('url') webpage = self._download_webpage(url, video_id) items_json = self._search_regex( r'mediaItems: ({.*?})$', webpage, 'items', flags=re.MULTILINE, default=None) if items_json is None: - long_id = self._search_regex( + CONTENT_ID_REGEXES = [ r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"', - webpage, 'content ID') + r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"' + ] + long_id = self._search_regex(CONTENT_ID_REGEXES, webpage, 'content ID') video_id = long_id else: items = json.loads(items_json) @@ -68,9 +81,9 @@ class YahooIE(InfoExtractor): # The 'meta' field is not always in the video webpage, we request it # from another page long_id = info['id'] - return self._get_info(long_id, video_id) + return self._get_info(long_id, video_id, webpage) - def _get_info(self, long_id, video_id): + def _get_info(self, long_id, video_id, webpage): query = ('SELECT * FROM yahoo.media.video.streams WHERE id="%s"' ' AND plrs="86Gj0vCaSzV_Iuf6hNylf2" AND region="US"' ' AND protocol="http"' % long_id) @@ -113,7 +126,7 @@ class YahooIE(InfoExtractor): 'title': meta['title'], 'formats': formats, 'description': clean_html(meta['description']), - 'thumbnail': meta['thumbnail'], + 'thumbnail': meta['thumbnail'] if meta.get('thumbnail') else self._og_search_thumbnail(webpage), } @@ -137,7 +150,7 @@ class YahooNewsIE(YahooIE): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) long_id = self._search_regex(r'contentId: \'(.+?)\',', webpage, 'long id') - return self._get_info(long_id, video_id) + return self._get_info(long_id, video_id, webpage) class YahooSearchIE(SearchInfoExtractor): diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 981ca62c0..225e2b7f4 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1,19 +1,17 @@ # coding: utf-8 -import collections import errno import io import itertools import json import os.path import re -import struct import traceback -import zlib from .common import InfoExtractor, SearchInfoExtractor from .subtitles import SubtitlesInfoExtractor from ..jsinterp import JSInterpreter +from ..swfinterp import SWFInterpreter from ..utils import ( compat_chr, compat_parse_qs, @@ -223,9 +221,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, + '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, + '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, # Dash webm audio - '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 48, 'preference': -50}, + '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50}, '172': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50}, # RTMP (unnamed) @@ -344,14 +344,22 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): """Indicate the download will use the RTMP protocol.""" self.to_screen(u'RTMP download detected') - def _extract_signature_function(self, video_id, player_url, slen): - id_m = re.match(r'.*-(?P<id>[a-zA-Z0-9_-]+)\.(?P<ext>[a-z]+)$', - player_url) + def _signature_cache_id(self, example_sig): + """ Return a string representation of a signature """ + return u'.'.join(compat_str(len(part)) for part in example_sig.split('.')) + + def _extract_signature_function(self, video_id, player_url, example_sig): + id_m = re.match( + r'.*-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.(?P<ext>[a-z]+)$', + player_url) + if not id_m: + raise ExtractorError('Cannot identify player %r' % player_url) player_type = id_m.group('ext') player_id = id_m.group('id') # Read from filesystem cache - func_id = '%s_%s_%d' % (player_type, player_id, slen) + func_id = '%s_%s_%s' % ( + player_type, player_id, self._signature_cache_id(example_sig)) assert os.path.basename(func_id) == func_id cache_dir = get_cachedir(self._downloader.params) @@ -366,6 +374,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): return lambda s: u''.join(s[i] for i in cache_spec) except IOError: pass # No cache available + except ValueError: + try: + file_size = os.path.getsize(cache_fn) + except (OSError, IOError) as oe: + file_size = str(oe) + self._downloader.report_warning( + u'Cache %s failed (%s)' % (cache_fn, file_size)) if player_type == 'js': code = self._download_webpage( @@ -385,7 +400,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): if cache_enabled: try: - test_string = u''.join(map(compat_chr, range(slen))) + test_string = u''.join(map(compat_chr, range(len(example_sig)))) cache_res = res(test_string) cache_spec = [ord(c) for c in cache_res] try: @@ -401,7 +416,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): return res - def _print_sig_code(self, func, slen): + def _print_sig_code(self, func, example_sig): def gen_sig_code(idxs): def _genslice(start, end, step): starts = u'' if start == 0 else str(start) @@ -430,16 +445,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): else: yield _genslice(start, i, step) - test_string = u''.join(map(compat_chr, range(slen))) + test_string = u''.join(map(compat_chr, range(len(example_sig)))) cache_res = func(test_string) cache_spec = [ord(c) for c in cache_res] expr_code = u' + '.join(gen_sig_code(cache_spec)) - code = u'if len(s) == %d:\n return %s\n' % (slen, expr_code) + signature_id_tuple = '(%s)' % ( + ', '.join(compat_str(len(p)) for p in example_sig.split('.'))) + code = (u'if tuple(len(p) for p in s.split(\'.\')) == %s:\n' + u' return %s\n') % (signature_id_tuple, expr_code) self.to_screen(u'Extracted signature function:\n' + code) def _parse_sig_js(self, jscode): funcname = self._search_regex( - r'signature=([a-zA-Z]+)', jscode, + r'signature=([$a-zA-Z]+)', jscode, u'Initial JS player signature function name') jsi = JSInterpreter(jscode) @@ -447,487 +465,35 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): return lambda s: initial_function([s]) def _parse_sig_swf(self, file_contents): - if file_contents[1:3] != b'WS': - raise ExtractorError( - u'Not an SWF file; header is %r' % file_contents[:3]) - if file_contents[:1] == b'C': - content = zlib.decompress(file_contents[8:]) - else: - raise NotImplementedError(u'Unsupported compression format %r' % - file_contents[:1]) - - def extract_tags(content): - pos = 0 - while pos < len(content): - header16 = struct.unpack('<H', content[pos:pos+2])[0] - pos += 2 - tag_code = header16 >> 6 - tag_len = header16 & 0x3f - if tag_len == 0x3f: - tag_len = struct.unpack('<I', content[pos:pos+4])[0] - pos += 4 - assert pos+tag_len <= len(content) - yield (tag_code, content[pos:pos+tag_len]) - pos += tag_len - - code_tag = next(tag - for tag_code, tag in extract_tags(content) - if tag_code == 82) - p = code_tag.index(b'\0', 4) + 1 - code_reader = io.BytesIO(code_tag[p:]) - - # Parse ABC (AVM2 ByteCode) - def read_int(reader=None): - if reader is None: - reader = code_reader - res = 0 - shift = 0 - for _ in range(5): - buf = reader.read(1) - assert len(buf) == 1 - b = struct.unpack('<B', buf)[0] - res = res | ((b & 0x7f) << shift) - if b & 0x80 == 0: - break - shift += 7 - return res - - def u30(reader=None): - res = read_int(reader) - assert res & 0xf0000000 == 0 - return res - u32 = read_int - - def s32(reader=None): - v = read_int(reader) - if v & 0x80000000 != 0: - v = - ((v ^ 0xffffffff) + 1) - return v - - def read_string(reader=None): - if reader is None: - reader = code_reader - slen = u30(reader) - resb = reader.read(slen) - assert len(resb) == slen - return resb.decode('utf-8') - - def read_bytes(count, reader=None): - if reader is None: - reader = code_reader - resb = reader.read(count) - assert len(resb) == count - return resb - - def read_byte(reader=None): - resb = read_bytes(1, reader=reader) - res = struct.unpack('<B', resb)[0] - return res - - # minor_version + major_version - read_bytes(2 + 2) - - # Constant pool - int_count = u30() - for _c in range(1, int_count): - s32() - uint_count = u30() - for _c in range(1, uint_count): - u32() - double_count = u30() - read_bytes((double_count-1) * 8) - string_count = u30() - constant_strings = [u''] - for _c in range(1, string_count): - s = read_string() - constant_strings.append(s) - namespace_count = u30() - for _c in range(1, namespace_count): - read_bytes(1) # kind - u30() # name - ns_set_count = u30() - for _c in range(1, ns_set_count): - count = u30() - for _c2 in range(count): - u30() - multiname_count = u30() - MULTINAME_SIZES = { - 0x07: 2, # QName - 0x0d: 2, # QNameA - 0x0f: 1, # RTQName - 0x10: 1, # RTQNameA - 0x11: 0, # RTQNameL - 0x12: 0, # RTQNameLA - 0x09: 2, # Multiname - 0x0e: 2, # MultinameA - 0x1b: 1, # MultinameL - 0x1c: 1, # MultinameLA - } - multinames = [u''] - for _c in range(1, multiname_count): - kind = u30() - assert kind in MULTINAME_SIZES, u'Invalid multiname kind %r' % kind - if kind == 0x07: - u30() # namespace_idx - name_idx = u30() - multinames.append(constant_strings[name_idx]) - else: - multinames.append('[MULTINAME kind: %d]' % kind) - for _c2 in range(MULTINAME_SIZES[kind]): - u30() - - # Methods - method_count = u30() - MethodInfo = collections.namedtuple( - 'MethodInfo', - ['NEED_ARGUMENTS', 'NEED_REST']) - method_infos = [] - for method_id in range(method_count): - param_count = u30() - u30() # return type - for _ in range(param_count): - u30() # param type - u30() # name index (always 0 for youtube) - flags = read_byte() - if flags & 0x08 != 0: - # Options present - option_count = u30() - for c in range(option_count): - u30() # val - read_bytes(1) # kind - if flags & 0x80 != 0: - # Param names present - for _ in range(param_count): - u30() # param name - mi = MethodInfo(flags & 0x01 != 0, flags & 0x04 != 0) - method_infos.append(mi) - - # Metadata - metadata_count = u30() - for _c in range(metadata_count): - u30() # name - item_count = u30() - for _c2 in range(item_count): - u30() # key - u30() # value - - def parse_traits_info(): - trait_name_idx = u30() - kind_full = read_byte() - kind = kind_full & 0x0f - attrs = kind_full >> 4 - methods = {} - if kind in [0x00, 0x06]: # Slot or Const - u30() # Slot id - u30() # type_name_idx - vindex = u30() - if vindex != 0: - read_byte() # vkind - elif kind in [0x01, 0x02, 0x03]: # Method / Getter / Setter - u30() # disp_id - method_idx = u30() - methods[multinames[trait_name_idx]] = method_idx - elif kind == 0x04: # Class - u30() # slot_id - u30() # classi - elif kind == 0x05: # Function - u30() # slot_id - function_idx = u30() - methods[function_idx] = multinames[trait_name_idx] - else: - raise ExtractorError(u'Unsupported trait kind %d' % kind) - - if attrs & 0x4 != 0: # Metadata present - metadata_count = u30() - for _c3 in range(metadata_count): - u30() # metadata index - - return methods - - # Classes + swfi = SWFInterpreter(file_contents) TARGET_CLASSNAME = u'SignatureDecipher' - searched_idx = multinames.index(TARGET_CLASSNAME) - searched_class_id = None - class_count = u30() - for class_id in range(class_count): - name_idx = u30() - if name_idx == searched_idx: - # We found the class we're looking for! - searched_class_id = class_id - u30() # super_name idx - flags = read_byte() - if flags & 0x08 != 0: # Protected namespace is present - u30() # protected_ns_idx - intrf_count = u30() - for _c2 in range(intrf_count): - u30() - u30() # iinit - trait_count = u30() - for _c2 in range(trait_count): - parse_traits_info() - - if searched_class_id is None: - raise ExtractorError(u'Target class %r not found' % - TARGET_CLASSNAME) - - method_names = {} - method_idxs = {} - for class_id in range(class_count): - u30() # cinit - trait_count = u30() - for _c2 in range(trait_count): - trait_methods = parse_traits_info() - if class_id == searched_class_id: - method_names.update(trait_methods.items()) - method_idxs.update(dict( - (idx, name) - for name, idx in trait_methods.items())) - - # Scripts - script_count = u30() - for _c in range(script_count): - u30() # init - trait_count = u30() - for _c2 in range(trait_count): - parse_traits_info() - - # Method bodies - method_body_count = u30() - Method = collections.namedtuple('Method', ['code', 'local_count']) - methods = {} - for _c in range(method_body_count): - method_idx = u30() - u30() # max_stack - local_count = u30() - u30() # init_scope_depth - u30() # max_scope_depth - code_length = u30() - code = read_bytes(code_length) - if method_idx in method_idxs: - m = Method(code, local_count) - methods[method_idxs[method_idx]] = m - exception_count = u30() - for _c2 in range(exception_count): - u30() # from - u30() # to - u30() # target - u30() # exc_type - u30() # var_name - trait_count = u30() - for _c2 in range(trait_count): - parse_traits_info() - - assert p + code_reader.tell() == len(code_tag) - assert len(methods) == len(method_idxs) - - method_pyfunctions = {} - - def extract_function(func_name): - if func_name in method_pyfunctions: - return method_pyfunctions[func_name] - if func_name not in methods: - raise ExtractorError(u'Cannot find function %r' % func_name) - m = methods[func_name] - - def resfunc(args): - registers = ['(this)'] + list(args) + [None] * m.local_count - stack = [] - coder = io.BytesIO(m.code) - while True: - opcode = struct.unpack('!B', coder.read(1))[0] - if opcode == 36: # pushbyte - v = struct.unpack('!B', coder.read(1))[0] - stack.append(v) - elif opcode == 44: # pushstring - idx = u30(coder) - stack.append(constant_strings[idx]) - elif opcode == 48: # pushscope - # We don't implement the scope register, so we'll just - # ignore the popped value - stack.pop() - elif opcode == 70: # callproperty - index = u30(coder) - mname = multinames[index] - arg_count = u30(coder) - args = list(reversed( - [stack.pop() for _ in range(arg_count)])) - obj = stack.pop() - if mname == u'split': - assert len(args) == 1 - assert isinstance(args[0], compat_str) - assert isinstance(obj, compat_str) - if args[0] == u'': - res = list(obj) - else: - res = obj.split(args[0]) - stack.append(res) - elif mname == u'slice': - assert len(args) == 1 - assert isinstance(args[0], int) - assert isinstance(obj, list) - res = obj[args[0]:] - stack.append(res) - elif mname == u'join': - assert len(args) == 1 - assert isinstance(args[0], compat_str) - assert isinstance(obj, list) - res = args[0].join(obj) - stack.append(res) - elif mname in method_pyfunctions: - stack.append(method_pyfunctions[mname](args)) - else: - raise NotImplementedError( - u'Unsupported property %r on %r' - % (mname, obj)) - elif opcode == 72: # returnvalue - res = stack.pop() - return res - elif opcode == 79: # callpropvoid - index = u30(coder) - mname = multinames[index] - arg_count = u30(coder) - args = list(reversed( - [stack.pop() for _ in range(arg_count)])) - obj = stack.pop() - if mname == u'reverse': - assert isinstance(obj, list) - obj.reverse() - else: - raise NotImplementedError( - u'Unsupported (void) property %r on %r' - % (mname, obj)) - elif opcode == 93: # findpropstrict - index = u30(coder) - mname = multinames[index] - res = extract_function(mname) - stack.append(res) - elif opcode == 97: # setproperty - index = u30(coder) - value = stack.pop() - idx = stack.pop() - obj = stack.pop() - assert isinstance(obj, list) - assert isinstance(idx, int) - obj[idx] = value - elif opcode == 98: # getlocal - index = u30(coder) - stack.append(registers[index]) - elif opcode == 99: # setlocal - index = u30(coder) - value = stack.pop() - registers[index] = value - elif opcode == 102: # getproperty - index = u30(coder) - pname = multinames[index] - if pname == u'length': - obj = stack.pop() - assert isinstance(obj, list) - stack.append(len(obj)) - else: # Assume attribute access - idx = stack.pop() - assert isinstance(idx, int) - obj = stack.pop() - assert isinstance(obj, list) - stack.append(obj[idx]) - elif opcode == 128: # coerce - u30(coder) - elif opcode == 133: # coerce_s - assert isinstance(stack[-1], (type(None), compat_str)) - elif opcode == 164: # modulo - value2 = stack.pop() - value1 = stack.pop() - res = value1 % value2 - stack.append(res) - elif opcode == 208: # getlocal_0 - stack.append(registers[0]) - elif opcode == 209: # getlocal_1 - stack.append(registers[1]) - elif opcode == 210: # getlocal_2 - stack.append(registers[2]) - elif opcode == 211: # getlocal_3 - stack.append(registers[3]) - elif opcode == 214: # setlocal_2 - registers[2] = stack.pop() - elif opcode == 215: # setlocal_3 - registers[3] = stack.pop() - else: - raise NotImplementedError( - u'Unsupported opcode %d' % opcode) - - method_pyfunctions[func_name] = resfunc - return resfunc - - initial_function = extract_function(u'decipher') + searched_class = swfi.extract_class(TARGET_CLASSNAME) + initial_function = swfi.extract_function(searched_class, u'decipher') return lambda s: initial_function([s]) def _decrypt_signature(self, s, video_id, player_url, age_gate=False): """Turn the encrypted s field into a working signature""" - if player_url is not None: - if player_url.startswith(u'//'): - player_url = u'https:' + player_url - try: - player_id = (player_url, len(s)) - if player_id not in self._player_cache: - func = self._extract_signature_function( - video_id, player_url, len(s) - ) - self._player_cache[player_id] = func - func = self._player_cache[player_id] - if self._downloader.params.get('youtube_print_sig_code'): - self._print_sig_code(func, len(s)) - return func(s) - except Exception: - tb = traceback.format_exc() - self._downloader.report_warning( - u'Automatic signature extraction failed: ' + tb) - - self._downloader.report_warning( - u'Warning: Falling back to static signature algorithm') - - return self._static_decrypt_signature( - s, video_id, player_url, age_gate) - - def _static_decrypt_signature(self, s, video_id, player_url, age_gate): - if age_gate: - # The videos with age protection use another player, so the - # algorithms can be different. - if len(s) == 86: - return s[2:63] + s[82] + s[64:82] + s[63] - - if len(s) == 93: - return s[86:29:-1] + s[88] + s[28:5:-1] - elif len(s) == 92: - return s[25] + s[3:25] + s[0] + s[26:42] + s[79] + s[43:79] + s[91] + s[80:83] - elif len(s) == 91: - return s[84:27:-1] + s[86] + s[26:5:-1] - elif len(s) == 90: - return s[25] + s[3:25] + s[2] + s[26:40] + s[77] + s[41:77] + s[89] + s[78:81] - elif len(s) == 89: - return s[84:78:-1] + s[87] + s[77:60:-1] + s[0] + s[59:3:-1] - elif len(s) == 88: - return s[7:28] + s[87] + s[29:45] + s[55] + s[46:55] + s[2] + s[56:87] + s[28] - elif len(s) == 87: - return s[6:27] + s[4] + s[28:39] + s[27] + s[40:59] + s[2] + s[60:] - elif len(s) == 86: - return s[80:72:-1] + s[16] + s[71:39:-1] + s[72] + s[38:16:-1] + s[82] + s[15::-1] - elif len(s) == 85: - return s[3:11] + s[0] + s[12:55] + s[84] + s[56:84] - elif len(s) == 84: - return s[78:70:-1] + s[14] + s[69:37:-1] + s[70] + s[36:14:-1] + s[80] + s[:14][::-1] - elif len(s) == 83: - return s[80:63:-1] + s[0] + s[62:0:-1] + s[63] - elif len(s) == 82: - return s[80:37:-1] + s[7] + s[36:7:-1] + s[0] + s[6:0:-1] + s[37] - elif len(s) == 81: - return s[56] + s[79:56:-1] + s[41] + s[55:41:-1] + s[80] + s[40:34:-1] + s[0] + s[33:29:-1] + s[34] + s[28:9:-1] + s[29] + s[8:0:-1] + s[9] - elif len(s) == 80: - return s[1:19] + s[0] + s[20:68] + s[19] + s[69:80] - elif len(s) == 79: - return s[54] + s[77:54:-1] + s[39] + s[53:39:-1] + s[78] + s[38:34:-1] + s[0] + s[33:29:-1] + s[34] + s[28:9:-1] + s[29] + s[8:0:-1] + s[9] + if player_url is None: + raise ExtractorError(u'Cannot decrypt signature without player_url') - else: - raise ExtractorError(u'Unable to decrypt signature, key length %d not supported; retrying might work' % (len(s))) + if player_url.startswith(u'//'): + player_url = u'https:' + player_url + try: + player_id = (player_url, self._signature_cache_id(s)) + if player_id not in self._player_cache: + func = self._extract_signature_function( + video_id, player_url, s + ) + self._player_cache[player_id] = func + func = self._player_cache[player_id] + if self._downloader.params.get('youtube_print_sig_code'): + self._print_sig_code(func, s) + return func(s) + except Exception as e: + tb = traceback.format_exc() + raise ExtractorError( + u'Signature extraction failed: ' + tb, cause=e) def _get_available_subtitles(self, video_id, webpage): try: @@ -942,6 +508,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): sub_lang_list = {} for l in lang_list: lang = l[1] + if lang in sub_lang_list: + continue params = compat_urllib_parse.urlencode({ 'lang': lang, 'v': video_id, @@ -1057,14 +625,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): age_gate = True # We simulate the access to the video from www.youtube.com/v/{video_id} # this can be viewed without login into Youtube - data = compat_urllib_parse.urlencode({'video_id': video_id, - 'el': 'player_embedded', - 'gl': 'US', - 'hl': 'en', - 'eurl': 'https://youtube.googleapis.com/v/' + video_id, - 'asv': 3, - 'sts':'1588', - }) + data = compat_urllib_parse.urlencode({ + 'video_id': video_id, + 'eurl': 'https://youtube.googleapis.com/v/' + video_id, + 'sts': self._search_regex( + r'"sts"\s*:\s*(\d+)', video_webpage, 'sts'), + }) video_info_url = proto + '://www.youtube.com/get_video_info?' + data video_info_webpage = self._download_webpage(video_info_url, video_id, note=False, @@ -1140,7 +706,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): mobj = re.search(r'(?s)id="eow-date.*?>(.*?)</span>', video_webpage) if mobj is None: mobj = re.search( - r'(?s)id="watch-uploader-info".*?>.*?(?:Published|Uploaded) on (.*?)</strong>', + r'(?s)id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live) on (.*?)</strong>', video_webpage) if mobj is not None: upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) @@ -1257,43 +823,54 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): url_map = {} for url_data_str in encoded_url_map.split(','): url_data = compat_parse_qs(url_data_str) - if 'itag' in url_data and 'url' in url_data: - url = url_data['url'][0] - if 'sig' in url_data: - url += '&signature=' + url_data['sig'][0] - elif 's' in url_data: - encrypted_sig = url_data['s'][0] - if self._downloader.params.get('verbose'): - if age_gate: - if player_url is None: - player_version = 'unknown' - else: - player_version = self._search_regex( - r'-(.+)\.swf$', player_url, - u'flash player', fatal=False) + if 'itag' not in url_data or 'url' not in url_data: + continue + format_id = url_data['itag'][0] + url = url_data['url'][0] + + if 'sig' in url_data: + url += '&signature=' + url_data['sig'][0] + elif 's' in url_data: + encrypted_sig = url_data['s'][0] + + if not age_gate: + jsplayer_url_json = self._search_regex( + r'"assets":.+?"js":\s*("[^"]+")', + video_webpage, u'JS player URL') + player_url = json.loads(jsplayer_url_json) + if player_url is None: + player_url_json = self._search_regex( + r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")', + video_webpage, u'age gate player URL') + player_url = json.loads(player_url_json) + + if self._downloader.params.get('verbose'): + if player_url is None: + player_version = 'unknown' + player_desc = 'unknown' + else: + if player_url.endswith('swf'): + player_version = self._search_regex( + r'-(.+?)(?:/watch_as3)?\.swf$', player_url, + u'flash player', fatal=False) player_desc = 'flash player %s' % player_version else: player_version = self._search_regex( - r'html5player-(.+?)\.js', video_webpage, + r'html5player-([^/]+?)(?:/html5player)?\.js', + player_url, 'html5 player', fatal=False) player_desc = u'html5 player %s' % player_version - parts_sizes = u'.'.join(compat_str(len(part)) for part in encrypted_sig.split('.')) - self.to_screen(u'encrypted signature length %d (%s), itag %s, %s' % - (len(encrypted_sig), parts_sizes, url_data['itag'][0], player_desc)) - - if not age_gate: - jsplayer_url_json = self._search_regex( - r'"assets":.+?"js":\s*("[^"]+")', - video_webpage, u'JS player URL') - player_url = json.loads(jsplayer_url_json) - - signature = self._decrypt_signature( - encrypted_sig, video_id, player_url, age_gate) - url += '&signature=' + signature - if 'ratebypass' not in url: - url += '&ratebypass=yes' - url_map[url_data['itag'][0]] = url + parts_sizes = self._signature_cache_id(encrypted_sig) + self.to_screen(u'{%s} signature length %s, %s' % + (format_id, parts_sizes, player_desc)) + + signature = self._decrypt_signature( + encrypted_sig, video_id, player_url, age_gate) + url += '&signature=' + signature + if 'ratebypass' not in url: + url += '&ratebypass=yes' + url_map[format_id] = url formats = _map_to_format_list(url_map) elif video_info.get('hlsvp'): manifest_url = video_info['hlsvp'][0] @@ -1385,13 +962,13 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): | p/ ) ( - (?:PL|EC|UU|FL|RD)?[0-9A-Za-z-_]{10,} + (?:PL|LL|EC|UU|FL|RD)?[0-9A-Za-z-_]{10,} # Top tracks, they can also include dots |(?:MC)[\w\.]* ) .* | - ((?:PL|EC|UU|FL|RD)[0-9A-Za-z-_]{10,}) + ((?:PL|LL|EC|UU|FL|RD)[0-9A-Za-z-_]{10,}) )""" _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s' _MORE_PAGES_INDICATOR = r'data-link-type="next"' @@ -1414,11 +991,9 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): title_span = (search_title('playlist-title') or search_title('title long-title') or search_title('title')) title = clean_html(title_span) - video_re = r'''(?x)data-video-username="(.*?)".*? + video_re = r'''(?x)data-video-username=".*?".*? href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id) - matches = orderedSet(re.findall(video_re, webpage, flags=re.DOTALL)) - # Some of the videos may have been deleted, their username field is empty - ids = [video_id for (username, video_id) in matches if username] + ids = orderedSet(re.findall(video_re, webpage, flags=re.DOTALL)) url_results = self._ids_to_results(ids) return self.playlist_result(url_results, playlist_id, title) @@ -1698,14 +1273,14 @@ class YoutubeSearchURLIE(InfoExtractor): webpage = self._download_webpage(url, query) result_code = self._search_regex( - r'(?s)<ol id="search-results"(.*?)</ol>', webpage, u'result HTML') + r'(?s)<ol class="item-section"(.*?)</ol>', webpage, u'result HTML') part_codes = re.findall( r'(?s)<h3 class="yt-lockup-title">(.*?)</h3>', result_code) entries = [] for part_code in part_codes: part_title = self._html_search_regex( - r'(?s)title="([^"]+)"', part_code, 'item title', fatal=False) + [r'(?s)title="([^"]+)"', r'>([^<]+)</a>'], part_code, 'item title', fatal=False) part_url_snippet = self._html_search_regex( r'(?s)href="([^"]+)"', part_code, 'item URL') part_url = compat_urlparse.urljoin( @@ -1825,10 +1400,21 @@ class YoutubeTruncatedURLIE(InfoExtractor): IE_NAME = 'youtube:truncated_url' IE_DESC = False # Do not list _VALID_URL = r'''(?x) - (?:https?://)?[^/]+/watch\?(?:feature=[a-z_]+)?$| + (?:https?://)?[^/]+/watch\?(?: + feature=[a-z_]+| + annotation_id=annotation_[^&]+ + )?$| (?:https?://)?(?:www\.)?youtube\.com/attribution_link\?a=[^&]+$ ''' + _TESTS = [{ + 'url': 'http://www.youtube.com/watch?annotation_id=annotation_3951667041', + 'only_matching': True, + }, { + 'url': 'http://www.youtube.com/watch?', + 'only_matching': True, + }] + def _real_extract(self, url): raise ExtractorError( u'Did you forget to quote the URL? Remember that & is a meta ' |