Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/francetv.py

   1 # coding: utf-8
   2
   3 from __future__ import unicode_literals
   4
   5 import re
   6 import json
   7
   8 from .common import InfoExtractor
   9 from ..compat import compat_urlparse
  10 from ..utils import (
  11     clean_html,
  12     ExtractorError,
  13     int_or_none,
  14     parse_duration,
  15     determine_ext,
  16 )
  17 from .dailymotion import (
  18     DailymotionIE,
  19     DailymotionCloudIE,
  20 )
  21
  22
  23 class FranceTVBaseInfoExtractor(InfoExtractor):
  24     def _extract_video(self, video_id, catalogue):
  25         info = self._download_json(
  26             'http://webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/?idDiffusion=%s&catalogue=%s'
  27             % (video_id, catalogue),
  28             video_id, 'Downloading video JSON')
  29
  30         if info.get('status') == 'NOK':
  31             raise ExtractorError(
  32                 '%s returned error: %s' % (self.IE_NAME, info['message']), expected=True)
  33         allowed_countries = info['videos'][0].get('geoblocage')
  34         if allowed_countries:
  35             georestricted = True
  36             geo_info = self._download_json(
  37                 'http://geo.francetv.fr/ws/edgescape.json', video_id,
  38                 'Downloading geo restriction info')
  39             country = geo_info['reponse']['geo_info']['country_code']
  40             if country not in allowed_countries:
  41                 raise ExtractorError(
  42                     'The video is not available from your location',
  43                     expected=True)
  44         else:
  45             georestricted = False
  46
  47         formats = []
  48         for video in info['videos']:
  49             if video['statut'] != 'ONLINE':
  50                 continue
  51             video_url = video['url']
  52             if not video_url:
  53                 continue
  54             format_id = video['format']
  55             ext = determine_ext(video_url)
  56             if ext == 'f4m':
  57                 if georestricted:
  58                     # See https://github.com/rg3/youtube-dl/issues/3963
  59                     # m3u8 urls work fine
  60                     continue
  61                 f4m_url = self._download_webpage(
  62                     'http://hdfauth.francetv.fr/esi/TA?url=%s' % video_url,
  63                     video_id, 'Downloading f4m manifest token', fatal=False)
  64                 if f4m_url:
  65                     formats.extend(self._extract_f4m_formats(
  66                         f4m_url + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44',
  67                         video_id, f4m_id=format_id, fatal=False))
  68             elif ext == 'm3u8':
  69                 formats.extend(self._extract_m3u8_formats(
  70                     video_url, video_id, 'mp4', entry_protocol='m3u8_native',
  71                     m3u8_id=format_id, fatal=False))
  72             elif video_url.startswith('rtmp'):
  73                 formats.append({
  74                     'url': video_url,
  75                     'format_id': 'rtmp-%s' % format_id,
  76                     'ext': 'flv',
  77                 })
  78             else:
  79                 if self._is_valid_url(video_url, video_id, format_id):
  80                     formats.append({
  81                         'url': video_url,
  82                         'format_id': format_id,
  83                     })
  84         self._sort_formats(formats)
  85
  86         title = info['titre']
  87         subtitle = info.get('sous_titre')
  88         if subtitle:
  89             title += ' - %s' % subtitle
  90         title = title.strip()
  91
  92         subtitles = {}
  93         subtitles_list = [{
  94             'url': subformat['url'],
  95             'ext': subformat.get('format'),
  96         } for subformat in info.get('subtitles', []) if subformat.get('url')]
  97         if subtitles_list:
  98             subtitles['fr'] = subtitles_list
  99
 100         return {
 101             'id': video_id,
 102             'title': title,
 103             'description': clean_html(info['synopsis']),
 104             'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
 105             'duration': int_or_none(info.get('real_duration')) or parse_duration(info['duree']),
 106             'timestamp': int_or_none(info['diffusion']['timestamp']),
 107             'formats': formats,
 108             'subtitles': subtitles,
 109         }
 110
 111
 112 class PluzzIE(FranceTVBaseInfoExtractor):
 113     IE_NAME = 'pluzz.francetv.fr'
 114     _VALID_URL = r'https?://(?:m\.)?pluzz\.francetv\.fr/videos/(?P<id>.+?)\.html'
 115
 116     # Can't use tests, videos expire in 7 days
 117
 118     def _real_extract(self, url):
 119         display_id = self._match_id(url)
 120
 121         webpage = self._download_webpage(url, display_id)
 122
 123         video_id = self._html_search_meta(
 124             'id_video', webpage, 'video id', default=None)
 125         if not video_id:
 126             video_id = self._search_regex(
 127                 r'data-diffusion=["\'](\d+)', webpage, 'video id')
 128
 129         return self._extract_video(video_id, 'Pluzz')
 130
 131
 132 class FranceTvInfoIE(FranceTVBaseInfoExtractor):
 133     IE_NAME = 'francetvinfo.fr'
 134     _VALID_URL = r'https?://(?:www|mobile|france3-regions)\.francetvinfo\.fr/(?:[^/]+/)*(?P<title>[^/?#&.]+)'
 135
 136     _TESTS = [{
 137         'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
 138         'info_dict': {
 139             'id': '84981923',
 140             'ext': 'mp4',
 141             'title': 'Soir 3',
 142             'upload_date': '20130826',
 143             'timestamp': 1377548400,
 144             'subtitles': {
 145                 'fr': 'mincount:2',
 146             },
 147         },
 148         'params': {
 149             # m3u8 downloads
 150             'skip_download': True,
 151         },
 152     }, {
 153         'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',
 154         'info_dict': {
 155             'id': 'EV_20019',
 156             'ext': 'mp4',
 157             'title': 'Débat des candidats à la Commission européenne',
 158             'description': 'Débat des candidats à la Commission européenne',
 159         },
 160         'params': {
 161             'skip_download': 'HLS (reqires ffmpeg)'
 162         },
 163         'skip': 'Ce direct est terminé et sera disponible en rattrapage dans quelques minutes.',
 164     }, {
 165         'url': 'http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html',
 166         'md5': 'f485bda6e185e7d15dbc69b72bae993e',
 167         'info_dict': {
 168             'id': 'NI_173343',
 169             'ext': 'mp4',
 170             'title': 'Les entreprises familiales : le secret de la réussite',
 171             'thumbnail': r're:^https?://.*\.jpe?g$',
 172             'timestamp': 1433273139,
 173             'upload_date': '20150602',
 174         },
 175         'params': {
 176             # m3u8 downloads
 177             'skip_download': True,
 178         },
 179     }, {
 180         'url': 'http://france3-regions.francetvinfo.fr/bretagne/cotes-d-armor/thalassa-echappee-breizh-ce-venredi-dans-les-cotes-d-armor-954961.html',
 181         'md5': 'f485bda6e185e7d15dbc69b72bae993e',
 182         'info_dict': {
 183             'id': 'NI_657393',
 184             'ext': 'mp4',
 185             'title': 'Olivier Monthus, réalisateur de "Bretagne, le choix de l’Armor"',
 186             'description': 'md5:a3264114c9d29aeca11ced113c37b16c',
 187             'thumbnail': r're:^https?://.*\.jpe?g$',
 188             'timestamp': 1458300695,
 189             'upload_date': '20160318',
 190         },
 191         'params': {
 192             'skip_download': True,
 193         },
 194     }, {
 195         # Dailymotion embed
 196         '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',
 197         'md5': 'ee7f1828f25a648addc90cb2687b1f12',
 198         'info_dict': {
 199             'id': 'x4iiko0',
 200             'ext': 'mp4',
 201             'title': 'NDDL, référendum, Brexit : Cécile Duflot répond à Patrick Cohen',
 202             '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',
 203             'timestamp': 1467011958,
 204             'upload_date': '20160627',
 205             'uploader': 'France Inter',
 206             'uploader_id': 'x2q2ez',
 207         },
 208         'add_ie': ['Dailymotion'],
 209     }, {
 210         'url': 'http://france3-regions.francetvinfo.fr/limousin/emissions/jt-1213-limousin',
 211         'only_matching': True,
 212     }]
 213
 214     def _real_extract(self, url):
 215         mobj = re.match(self._VALID_URL, url)
 216         page_title = mobj.group('title')
 217         webpage = self._download_webpage(url, page_title)
 218
 219         dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
 220         if dmcloud_url:
 221             return self.url_result(dmcloud_url, DailymotionCloudIE.ie_key())
 222
 223         dailymotion_urls = DailymotionIE._extract_urls(webpage)
 224         if dailymotion_urls:
 225             return self.playlist_result([
 226                 self.url_result(dailymotion_url, DailymotionIE.ie_key())
 227                 for dailymotion_url in dailymotion_urls])
 228
 229         video_id, catalogue = self._search_regex(
 230             (r'id-video=([^@]+@[^"]+)',
 231              r'<a[^>]+href="(?:https?:)?//videos\.francetv\.fr/video/([^@]+@[^"]+)"'),
 232             webpage, 'video id').split('@')
 233         return self._extract_video(video_id, catalogue)
 234
 235
 236 class FranceTVIE(FranceTVBaseInfoExtractor):
 237     IE_NAME = 'francetv'
 238     IE_DESC = 'France 2, 3, 4, 5 and Ô'
 239     _VALID_URL = r'''(?x)
 240                     https?://
 241                         (?:
 242                             (?:www\.)?france[2345o]\.fr/
 243                                 (?:
 244                                     emissions/[^/]+/(?:videos|diffusions)|
 245                                     emission/[^/]+|
 246                                     videos|
 247                                     jt
 248                                 )
 249                             /|
 250                             embed\.francetv\.fr/\?ue=
 251                         )
 252                         (?P<id>[^/?]+)
 253                     '''
 254
 255     _TESTS = [
 256         # france2
 257         {
 258             'url': 'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
 259             'md5': 'c03fc87cb85429ffd55df32b9fc05523',
 260             'info_dict': {
 261                 'id': '109169362',
 262                 'ext': 'flv',
 263                 'title': '13h15, le dimanche...',
 264                 'description': 'md5:9a0932bb465f22d377a449be9d1a0ff7',
 265                 'upload_date': '20140914',
 266                 'timestamp': 1410693600,
 267             },
 268         },
 269         # france3
 270         {
 271             'url': 'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
 272             'md5': '679bb8f8921f8623bd658fa2f8364da0',
 273             'info_dict': {
 274                 'id': '000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
 275                 'ext': 'mp4',
 276                 'title': 'Le scandale du prix des médicaments',
 277                 'description': 'md5:1384089fbee2f04fc6c9de025ee2e9ce',
 278                 'upload_date': '20131113',
 279                 'timestamp': 1384380000,
 280             },
 281         },
 282         # france4
 283         {
 284             'url': 'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
 285             'md5': 'a182bf8d2c43d88d46ec48fbdd260c1c',
 286             'info_dict': {
 287                 'id': 'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
 288                 'ext': 'mp4',
 289                 'title': 'Hero Corp Making of - Extrait 1',
 290                 'description': 'md5:c87d54871b1790679aec1197e73d650a',
 291                 'upload_date': '20131106',
 292                 'timestamp': 1383766500,
 293             },
 294         },
 295         # france5
 296         {
 297             'url': 'http://www.france5.fr/emissions/c-a-dire/videos/quels_sont_les_enjeux_de_cette_rentree_politique__31-08-2015_908948?onglet=tous&page=1',
 298             'md5': 'f6c577df3806e26471b3d21631241fd0',
 299             'info_dict': {
 300                 'id': '123327454',
 301                 'ext': 'flv',
 302                 'title': 'C à dire ?! - Quels sont les enjeux de cette rentrée politique ?',
 303                 'description': 'md5:4a0d5cb5dce89d353522a84462bae5a4',
 304                 'upload_date': '20150831',
 305                 'timestamp': 1441035120,
 306             },
 307         },
 308         # franceo
 309         {
 310             'url': 'http://www.franceo.fr/jt/info-soir/18-07-2015',
 311             'md5': '47d5816d3b24351cdce512ad7ab31da8',
 312             'info_dict': {
 313                 'id': '125377621',
 314                 'ext': 'flv',
 315                 'title': 'Infô soir',
 316                 'description': 'md5:01b8c6915a3d93d8bbbd692651714309',
 317                 'upload_date': '20150718',
 318                 'timestamp': 1437241200,
 319                 'duration': 414,
 320             },
 321         },
 322         {
 323             # francetv embed
 324             'url': 'http://embed.francetv.fr/?ue=8d7d3da1e3047c42ade5a5d7dfd3fc87',
 325             'info_dict': {
 326                 'id': 'EV_30231',
 327                 'ext': 'flv',
 328                 'title': 'Alcaline, le concert avec Calogero',
 329                 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
 330                 'upload_date': '20150226',
 331                 'timestamp': 1424989860,
 332                 'duration': 5400,
 333             },
 334         },
 335         {
 336             'url': 'http://www.france4.fr/emission/highlander/diffusion-du-17-07-2015-04h05',
 337             'only_matching': True,
 338         },
 339         {
 340             'url': 'http://www.franceo.fr/videos/125377617',
 341             'only_matching': True,
 342         }
 343     ]
 344
 345     def _real_extract(self, url):
 346         video_id = self._match_id(url)
 347         webpage = self._download_webpage(url, video_id)
 348         video_id, catalogue = self._html_search_regex(
 349             r'(?:href=|player\.setVideo\(\s*)"http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"',
 350             webpage, 'video ID').split('@')
 351         return self._extract_video(video_id, catalogue)
 352
 353
 354 class GenerationQuoiIE(InfoExtractor):
 355     IE_NAME = 'france2.fr:generation-quoi'
 356     _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<id>[^/?#]+)'
 357
 358     _TEST = {
 359         'url': 'http://generation-quoi.france2.fr/portrait/garde-a-vous',
 360         'info_dict': {
 361             'id': 'k7FJX8VBcvvLmX4wA5Q',
 362             'ext': 'mp4',
 363             'title': 'Génération Quoi - Garde à Vous',
 364             'uploader': 'Génération Quoi',
 365         },
 366         'params': {
 367             # It uses Dailymotion
 368             'skip_download': True,
 369         },
 370     }
 371
 372     def _real_extract(self, url):
 373         display_id = self._match_id(url)
 374         info_url = compat_urlparse.urljoin(url, '/medias/video/%s.json' % display_id)
 375         info_json = self._download_webpage(info_url, display_id)
 376         info = json.loads(info_json)
 377         return self.url_result('http://www.dailymotion.com/video/%s' % info['id'],
 378                                ie='Dailymotion')
 379
 380
 381 class CultureboxIE(FranceTVBaseInfoExtractor):
 382     IE_NAME = 'culturebox.francetvinfo.fr'
 383     _VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'
 384
 385     _TEST = {
 386         'url': 'http://culturebox.francetvinfo.fr/live/musique/musique-classique/le-livre-vermeil-de-montserrat-a-la-cathedrale-delne-214511',
 387         'md5': '9b88dc156781c4dbebd4c3e066e0b1d6',
 388         'info_dict': {
 389             'id': 'EV_50111',
 390             'ext': 'flv',
 391             'title': "Le Livre Vermeil de Montserrat à la Cathédrale d'Elne",
 392             'description': 'md5:f8a4ad202e8fe533e2c493cc12e739d9',
 393             'upload_date': '20150320',
 394             'timestamp': 1426892400,
 395             'duration': 2760.9,
 396         },
 397     }
 398
 399     def _real_extract(self, url):
 400         mobj = re.match(self._VALID_URL, url)
 401         name = mobj.group('name')
 402
 403         webpage = self._download_webpage(url, name)
 404
 405         if ">Ce live n'est plus disponible en replay<" in webpage:
 406             raise ExtractorError('Video %s is not available' % name, expected=True)
 407
 408         video_id, catalogue = self._search_regex(
 409             r'"http://videos\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video id').split('@')
 410
 411         return self._extract_video(video_id, catalogue)