youtube_dl/extractor/francetv.py

   1 # coding: utf-8
   2
   3 from __future__ import unicode_literals
   4
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..compat import compat_urlparse
   9 from ..utils import (
  10     clean_html,
  11     ExtractorError,
  12     int_or_none,
  13     parse_duration,
  14     determine_ext,
  15 )
  16 from .dailymotion import DailymotionIE
  17
  18
  19 class FranceTVBaseInfoExtractor(InfoExtractor):
  20     def _extract_video(self, video_id, catalogue=None):
  21         info = self._download_json(
  22             'https://sivideo.webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/',
  23             video_id, 'Downloading video JSON', query={
  24                 'idDiffusion': video_id,
  25                 'catalogue': catalogue or '',
  26             })
  27
  28         if info.get('status') == 'NOK':
  29             raise ExtractorError(
  30                 '%s returned error: %s' % (self.IE_NAME, info['message']), expected=True)
  31         allowed_countries = info['videos'][0].get('geoblocage')
  32         if allowed_countries:
  33             georestricted = True
  34             geo_info = self._download_json(
  35                 'http://geo.francetv.fr/ws/edgescape.json', video_id,
  36                 'Downloading geo restriction info')
  37             country = geo_info['reponse']['geo_info']['country_code']
  38             if country not in allowed_countries:
  39                 raise ExtractorError(
  40                     'The video is not available from your location',
  41                     expected=True)
  42         else:
  43             georestricted = False
  44
  45         formats = []
  46         for video in info['videos']:
  47             if video['statut'] != 'ONLINE':
  48                 continue
  49             video_url = video['url']
  50             if not video_url:
  51                 continue
  52             format_id = video['format']
  53             ext = determine_ext(video_url)
  54             if ext == 'f4m':
  55                 if georestricted:
  56                     # See https://github.com/rg3/youtube-dl/issues/3963
  57                     # m3u8 urls work fine
  58                     continue
  59                 f4m_url = self._download_webpage(
  60                     'http://hdfauth.francetv.fr/esi/TA?url=%s' % video_url,
  61                     video_id, 'Downloading f4m manifest token', fatal=False)
  62                 if f4m_url:
  63                     formats.extend(self._extract_f4m_formats(
  64                         f4m_url + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44',
  65                         video_id, f4m_id=format_id, fatal=False))
  66             elif ext == 'm3u8':
  67                 m3u8_url = self._download_webpage(
  68                     'http://hdfauth.francetv.fr/esi/TA?url=%s' % video_url,
  69                     video_id, 'Downloading m3u8 token', fatal=False)
  70                 if m3u8_url:
  71                     formats.extend(self._extract_m3u8_formats(
  72                         m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
  73                         m3u8_id=format_id, fatal=False))
  74             elif video_url.startswith('rtmp'):
  75                 formats.append({
  76                     'url': video_url,
  77                     'format_id': 'rtmp-%s' % format_id,
  78                     'ext': 'flv',
  79                 })
  80             else:
  81                 if self._is_valid_url(video_url, video_id, format_id):
  82                     formats.append({
  83                         'url': video_url,
  84                         'format_id': format_id,
  85                     })
  86         self._sort_formats(formats)
  87
  88         title = info['titre']
  89         subtitle = info.get('sous_titre')
  90         if subtitle:
  91             title += ' - %s' % subtitle
  92         title = title.strip()
  93
  94         subtitles = {}
  95         subtitles_list = [{
  96             'url': subformat['url'],
  97             'ext': subformat.get('format'),
  98         } for subformat in info.get('subtitles', []) if subformat.get('url')]
  99         if subtitles_list:
 100             subtitles['fr'] = subtitles_list
 101
 102         return {
 103             'id': video_id,
 104             'title': title,
 105             'description': clean_html(info['synopsis']),
 106             'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
 107             'duration': int_or_none(info.get('real_duration')) or parse_duration(info['duree']),
 108             'timestamp': int_or_none(info['diffusion']['timestamp']),
 109             'formats': formats,
 110             'subtitles': subtitles,
 111         }
 112
 113
 114 class FranceTVIE(FranceTVBaseInfoExtractor):
 115     _VALID_URL = r'https?://(?:(?:www\.)?france\.tv|mobile\.france\.tv)/(?:[^/]+/)*(?P<id>[^/]+)\.html'
 116
 117     _TESTS = [{
 118         'url': 'https://www.france.tv/france-2/13h15-le-dimanche/140921-les-mysteres-de-jesus.html',
 119         'info_dict': {
 120             'id': '157550144',
 121             'ext': 'mp4',
 122             'title': '13h15, le dimanche... - Les mystères de Jésus',
 123             'description': 'md5:75efe8d4c0a8205e5904498ffe1e1a42',
 124             'timestamp': 1494156300,
 125             'upload_date': '20170507',
 126         },
 127         'params': {
 128             # m3u8 downloads
 129             'skip_download': True,
 130         },
 131     }, {
 132         # france3
 133         'url': 'https://www.france.tv/france-3/des-chiffres-et-des-lettres/139063-emission-du-mardi-9-mai-2017.html',
 134         'only_matching': True,
 135     }, {
 136         # france4
 137         'url': 'https://www.france.tv/france-4/hero-corp/saison-1/134151-apres-le-calme.html',
 138         'only_matching': True,
 139     }, {
 140         # france5
 141         'url': 'https://www.france.tv/france-5/c-a-dire/saison-10/137013-c-a-dire.html',
 142         'only_matching': True,
 143     }, {
 144         # franceo
 145         'url': 'https://www.france.tv/france-o/archipels/132249-mon-ancetre-l-esclave.html',
 146         'only_matching': True,
 147     }, {
 148         # france2 live
 149         'url': 'https://www.france.tv/france-2/direct.html',
 150         'only_matching': True,
 151     }, {
 152         'url': 'https://www.france.tv/documentaires/histoire/136517-argentine-les-500-bebes-voles-de-la-dictature.html',
 153         'only_matching': True,
 154     }, {
 155         'url': 'https://www.france.tv/jeux-et-divertissements/divertissements/133965-le-web-contre-attaque.html',
 156         'only_matching': True,
 157     }, {
 158         'url': 'https://mobile.france.tv/france-5/c-dans-l-air/137347-emission-du-vendredi-12-mai-2017.html',
 159         'only_matching': True,
 160     }, {
 161         'url': 'https://www.france.tv/142749-rouge-sang.html',
 162         'only_matching': True,
 163     }]
 164
 165     def _real_extract(self, url):
 166         display_id = self._match_id(url)
 167
 168         webpage = self._download_webpage(url, display_id)
 169
 170         catalogue = None
 171         video_id = self._search_regex(
 172             r'data-main-video=(["\'])(?P<id>(?:(?!\1).)+)\1',
 173             webpage, 'video id', default=None, group='id')
 174
 175         if not video_id:
 176             video_id, catalogue = self._html_search_regex(
 177                 r'(?:href=|player\.setVideo\(\s*)"http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"',
 178                 webpage, 'video ID').split('@')
 179         return self._extract_video(video_id, catalogue)
 180
 181
 182 class FranceTVEmbedIE(FranceTVBaseInfoExtractor):
 183     _VALID_URL = r'https?://embed\.francetv\.fr/*\?.*?\bue=(?P<id>[^&]+)'
 184
 185     _TEST = {
 186         'url': 'http://embed.francetv.fr/?ue=7fd581a2ccf59d2fc5719c5c13cf6961',
 187         'info_dict': {
 188             'id': 'NI_983319',
 189             'ext': 'mp4',
 190             'title': 'Le Pen Reims',
 191             'upload_date': '20170505',
 192             'timestamp': 1493981780,
 193             'duration': 16,
 194         },
 195     }
 196
 197     def _real_extract(self, url):
 198         video_id = self._match_id(url)
 199
 200         video = self._download_json(
 201             'http://api-embed.webservices.francetelevisions.fr/key/%s' % video_id,
 202             video_id)
 203
 204         return self._extract_video(video['video_id'], video.get('catalog'))
 205
 206
 207 class FranceTVInfoIE(FranceTVBaseInfoExtractor):
 208     IE_NAME = 'francetvinfo.fr'
 209     _VALID_URL = r'https?://(?:www|mobile|france3-regions)\.francetvinfo\.fr/(?:[^/]+/)*(?P<title>[^/?#&.]+)'
 210
 211     _TESTS = [{
 212         'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
 213         'info_dict': {
 214             'id': '84981923',
 215             'ext': 'mp4',
 216             'title': 'Soir 3',
 217             'upload_date': '20130826',
 218             'timestamp': 1377548400,
 219             'subtitles': {
 220                 'fr': 'mincount:2',
 221             },
 222         },
 223         'params': {
 224             # m3u8 downloads
 225             'skip_download': True,
 226         },
 227     }, {
 228         'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',
 229         'info_dict': {
 230             'id': 'EV_20019',
 231             'ext': 'mp4',
 232             'title': 'Débat des candidats à la Commission européenne',
 233             'description': 'Débat des candidats à la Commission européenne',
 234         },
 235         'params': {
 236             'skip_download': 'HLS (reqires ffmpeg)'
 237         },
 238         'skip': 'Ce direct est terminé et sera disponible en rattrapage dans quelques minutes.',
 239     }, {
 240         'url': 'http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html',
 241         'md5': 'f485bda6e185e7d15dbc69b72bae993e',
 242         'info_dict': {
 243             'id': 'NI_173343',
 244             'ext': 'mp4',
 245             'title': 'Les entreprises familiales : le secret de la réussite',
 246             'thumbnail': r're:^https?://.*\.jpe?g$',
 247             'timestamp': 1433273139,
 248             'upload_date': '20150602',
 249         },
 250         'params': {
 251             # m3u8 downloads
 252             'skip_download': True,
 253         },
 254     }, {
 255         'url': 'http://france3-regions.francetvinfo.fr/bretagne/cotes-d-armor/thalassa-echappee-breizh-ce-venredi-dans-les-cotes-d-armor-954961.html',
 256         'md5': 'f485bda6e185e7d15dbc69b72bae993e',
 257         'info_dict': {
 258             'id': 'NI_657393',
 259             'ext': 'mp4',
 260             'title': 'Olivier Monthus, réalisateur de "Bretagne, le choix de l’Armor"',
 261             'description': 'md5:a3264114c9d29aeca11ced113c37b16c',
 262             'thumbnail': r're:^https?://.*\.jpe?g$',
 263             'timestamp': 1458300695,
 264             'upload_date': '20160318',
 265         },
 266         'params': {
 267             'skip_download': True,
 268         },
 269     }, {
 270         # Dailymotion embed
 271         'url': 'http://www.francetvinfo.fr/politique/notre-dame-des-landes/video-sur-france-inter-cecile-duflot-denonce-le-regard-meprisant-de-patrick-cohen_1520091.html',
 272         'md5': 'ee7f1828f25a648addc90cb2687b1f12',
 273         'info_dict': {
 274             'id': 'x4iiko0',
 275             'ext': 'mp4',
 276             'title': 'NDDL, référendum, Brexit : Cécile Duflot répond à Patrick Cohen',
 277             'description': 'Au lendemain de la victoire du "oui" au référendum sur l\'aéroport de Notre-Dame-des-Landes, l\'ancienne ministre écologiste est l\'invitée de Patrick Cohen. Plus d\'info : https://www.franceinter.fr/emissions/le-7-9/le-7-9-27-juin-2016',
 278             'timestamp': 1467011958,
 279             'upload_date': '20160627',
 280             'uploader': 'France Inter',
 281             'uploader_id': 'x2q2ez',
 282         },
 283         'add_ie': ['Dailymotion'],
 284     }, {
 285         'url': 'http://france3-regions.francetvinfo.fr/limousin/emissions/jt-1213-limousin',
 286         'only_matching': True,
 287     }]
 288
 289     def _real_extract(self, url):
 290         mobj = re.match(self._VALID_URL, url)
 291         page_title = mobj.group('title')
 292         webpage = self._download_webpage(url, page_title)
 293
 294         dailymotion_urls = DailymotionIE._extract_urls(webpage)
 295         if dailymotion_urls:
 296             return self.playlist_result([
 297                 self.url_result(dailymotion_url, DailymotionIE.ie_key())
 298                 for dailymotion_url in dailymotion_urls])
 299
 300         video_id, catalogue = self._search_regex(
 301             (r'id-video=([^@]+@[^"]+)',
 302              r'<a[^>]+href="(?:https?:)?//videos\.francetv\.fr/video/([^@]+@[^"]+)"'),
 303             webpage, 'video id').split('@')
 304         return self._extract_video(video_id, catalogue)
 305
 306
 307 class GenerationWhatIE(InfoExtractor):
 308     IE_NAME = 'france2.fr:generation-what'
 309     _VALID_URL = r'https?://generation-what\.francetv\.fr/[^/]+/video/(?P<id>[^/?#]+)'
 310
 311     _TESTS = [{
 312         'url': 'http://generation-what.francetv.fr/portrait/video/present-arms',
 313         'info_dict': {
 314             'id': 'wtvKYUG45iw',
 315             'ext': 'mp4',
 316             'title': 'Generation What - Garde à vous - FRA',
 317             'uploader': 'Generation What',
 318             'uploader_id': 'UCHH9p1eetWCgt4kXBYCb3_w',
 319             'upload_date': '20160411',
 320         },
 321     }, {
 322         'url': 'http://generation-what.francetv.fr/europe/video/present-arms',
 323         'only_matching': True,
 324     }]
 325
 326     def _real_extract(self, url):
 327         display_id = self._match_id(url)
 328         webpage = self._download_webpage(url, display_id)
 329         youtube_id = self._search_regex(
 330             r"window\.videoURL\s*=\s*'([0-9A-Za-z_-]{11})';",
 331             webpage, 'youtube id')
 332         return self.url_result(youtube_id, 'Youtube', youtube_id)
 333
 334
 335 class CultureboxIE(FranceTVBaseInfoExtractor):
 336     IE_NAME = 'culturebox.francetvinfo.fr'
 337     _VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'
 338
 339     _TEST = {
 340         'url': 'http://culturebox.francetvinfo.fr/live/musique/musique-classique/le-livre-vermeil-de-montserrat-a-la-cathedrale-delne-214511',
 341         'md5': '9b88dc156781c4dbebd4c3e066e0b1d6',
 342         'info_dict': {
 343             'id': 'EV_50111',
 344             'ext': 'flv',
 345             'title': "Le Livre Vermeil de Montserrat à la Cathédrale d'Elne",
 346             'description': 'md5:f8a4ad202e8fe533e2c493cc12e739d9',
 347             'upload_date': '20150320',
 348             'timestamp': 1426892400,
 349             'duration': 2760.9,
 350         },
 351     }
 352
 353     def _real_extract(self, url):
 354         mobj = re.match(self._VALID_URL, url)
 355         name = mobj.group('name')
 356
 357         webpage = self._download_webpage(url, name)
 358
 359         if ">Ce live n'est plus disponible en replay<" in webpage:
 360             raise ExtractorError('Video %s is not available' % name, expected=True)
 361
 362         video_id, catalogue = self._search_regex(
 363             r'["\'>]https?://videos\.francetv\.fr/video/([^@]+@.+?)["\'<]',
 364             webpage, 'video id').split('@')
 365
 366         return self._extract_video(video_id, catalogue)