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

   1 # encoding: 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 DailymotionCloudIE
  18
  19
  20 class FranceTVBaseInfoExtractor(InfoExtractor):
  21     def _extract_video(self, video_id, catalogue):
  22         info = self._download_json(
  23             'http://webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/?idDiffusion=%s&catalogue=%s'
  24             % (video_id, catalogue),
  25             video_id, 'Downloading video JSON')
  26
  27         if info.get('status') == 'NOK':
  28             raise ExtractorError(
  29                 '%s returned error: %s' % (self.IE_NAME, info['message']), expected=True)
  30         allowed_countries = info['videos'][0].get('geoblocage')
  31         if allowed_countries:
  32             georestricted = True
  33             geo_info = self._download_json(
  34                 'http://geo.francetv.fr/ws/edgescape.json', video_id,
  35                 'Downloading geo restriction info')
  36             country = geo_info['reponse']['geo_info']['country_code']
  37             if country not in allowed_countries:
  38                 raise ExtractorError(
  39                     'The video is not available from your location',
  40                     expected=True)
  41         else:
  42             georestricted = False
  43
  44         formats = []
  45         for video in info['videos']:
  46             if video['statut'] != 'ONLINE':
  47                 continue
  48             video_url = video['url']
  49             if not video_url:
  50                 continue
  51             format_id = video['format']
  52             ext = determine_ext(video_url)
  53             if ext == 'f4m':
  54                 if georestricted:
  55                     # See https://github.com/rg3/youtube-dl/issues/3963
  56                     # m3u8 urls work fine
  57                     continue
  58                 f4m_url = self._download_webpage(
  59                     'http://hdfauth.francetv.fr/esi/TA?url=%s' % video_url,
  60                     video_id, 'Downloading f4m manifest token', fatal=False)
  61                 if f4m_url:
  62                     formats.extend(self._extract_f4m_formats(
  63                         f4m_url + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id, 1, format_id))
  64             elif ext == 'm3u8':
  65                 formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4', m3u8_id=format_id))
  66             elif video_url.startswith('rtmp'):
  67                 formats.append({
  68                     'url': video_url,
  69                     'format_id': 'rtmp-%s' % format_id,
  70                     'ext': 'flv',
  71                     'preference': 1,
  72                 })
  73             else:
  74                 formats.append({
  75                     'url': video_url,
  76                     'format_id': format_id,
  77                     'preference': -1,
  78                 })
  79         self._sort_formats(formats)
  80
  81         title = info['titre']
  82         subtitle = info.get('sous_titre')
  83         if subtitle:
  84             title += ' - %s' % subtitle
  85
  86         subtitles = {}
  87         subtitles_list = [{
  88             'url': subformat['url'],
  89             'ext': subformat.get('format'),
  90         } for subformat in info.get('subtitles', []) if subformat.get('url')]
  91         if subtitles_list:
  92             subtitles['fr'] = subtitles_list
  93
  94         return {
  95             'id': video_id,
  96             'title': title,
  97             'description': clean_html(info['synopsis']),
  98             'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
  99             'duration': int_or_none(info.get('real_duration')) or parse_duration(info['duree']),
 100             'timestamp': int_or_none(info['diffusion']['timestamp']),
 101             'formats': formats,
 102             'subtitles': subtitles,
 103         }
 104
 105
 106 class PluzzIE(FranceTVBaseInfoExtractor):
 107     IE_NAME = 'pluzz.francetv.fr'
 108     _VALID_URL = r'https?://(?:m\.)?pluzz\.francetv\.fr/videos/(?P<id>.+?)\.html'
 109
 110     # Can't use tests, videos expire in 7 days
 111
 112     def _real_extract(self, url):
 113         display_id = self._match_id(url)
 114
 115         webpage = self._download_webpage(url, display_id)
 116
 117         video_id = self._html_search_meta(
 118             'id_video', webpage, 'video id', default=None)
 119         if not video_id:
 120             video_id = self._search_regex(
 121                 r'data-diffusion=["\'](\d+)', webpage, 'video id')
 122
 123         return self._extract_video(video_id, 'Pluzz')
 124
 125
 126 class FranceTvInfoIE(FranceTVBaseInfoExtractor):
 127     IE_NAME = 'francetvinfo.fr'
 128     _VALID_URL = r'https?://(?:www|mobile)\.francetvinfo\.fr/.*/(?P<title>.+)\.html'
 129
 130     _TESTS = [{
 131         'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
 132         'info_dict': {
 133             'id': '84981923',
 134             'ext': 'flv',
 135             'title': 'Soir 3',
 136             'upload_date': '20130826',
 137             'timestamp': 1377548400,
 138             'subtitles': {
 139                 'fr': 'mincount:2',
 140             },
 141         },
 142     }, {
 143         'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',
 144         'info_dict': {
 145             'id': 'EV_20019',
 146             'ext': 'mp4',
 147             'title': 'Débat des candidats à la Commission européenne',
 148             'description': 'Débat des candidats à la Commission européenne',
 149         },
 150         'params': {
 151             'skip_download': 'HLS (reqires ffmpeg)'
 152         },
 153         'skip': 'Ce direct est terminé et sera disponible en rattrapage dans quelques minutes.',
 154     }, {
 155         'url': 'http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html',
 156         'md5': 'f485bda6e185e7d15dbc69b72bae993e',
 157         'info_dict': {
 158             'id': '556e03339473995ee145930c',
 159             'ext': 'mp4',
 160             'title': 'Les entreprises familiales : le secret de la réussite',
 161             'thumbnail': 're:^https?://.*\.jpe?g$',
 162         }
 163     }]
 164
 165     def _real_extract(self, url):
 166         mobj = re.match(self._VALID_URL, url)
 167         page_title = mobj.group('title')
 168         webpage = self._download_webpage(url, page_title)
 169
 170         dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
 171         if dmcloud_url:
 172             return self.url_result(dmcloud_url, 'DailymotionCloud')
 173
 174         video_id, catalogue = self._search_regex(
 175             r'id-video=([^@]+@[^"]+)', webpage, 'video id').split('@')
 176         return self._extract_video(video_id, catalogue)
 177
 178
 179 class FranceTVIE(FranceTVBaseInfoExtractor):
 180     IE_NAME = 'francetv'
 181     IE_DESC = 'France 2, 3, 4, 5 and Ô'
 182     _VALID_URL = r'''(?x)
 183                     https?://
 184                         (?:
 185                             (?:www\.)?france[2345o]\.fr/
 186                                 (?:
 187                                     emissions/[^/]+/(?:videos|diffusions)|
 188                                     emission/[^/]+|
 189                                     videos|
 190                                     jt
 191                                 )
 192                             /|
 193                             embed\.francetv\.fr/\?ue=
 194                         )
 195                         (?P<id>[^/?]+)
 196                     '''
 197
 198     _TESTS = [
 199         # france2
 200         {
 201             'url': 'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
 202             'md5': 'c03fc87cb85429ffd55df32b9fc05523',
 203             'info_dict': {
 204                 'id': '109169362',
 205                 'ext': 'flv',
 206                 'title': '13h15, le dimanche...',
 207                 'description': 'md5:9a0932bb465f22d377a449be9d1a0ff7',
 208                 'upload_date': '20140914',
 209                 'timestamp': 1410693600,
 210             },
 211         },
 212         # france3
 213         {
 214             'url': 'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
 215             'md5': '679bb8f8921f8623bd658fa2f8364da0',
 216             'info_dict': {
 217                 'id': '000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
 218                 'ext': 'mp4',
 219                 'title': 'Le scandale du prix des médicaments',
 220                 'description': 'md5:1384089fbee2f04fc6c9de025ee2e9ce',
 221                 'upload_date': '20131113',
 222                 'timestamp': 1384380000,
 223             },
 224         },
 225         # france4
 226         {
 227             'url': 'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
 228             'md5': 'a182bf8d2c43d88d46ec48fbdd260c1c',
 229             'info_dict': {
 230                 'id': 'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
 231                 'ext': 'mp4',
 232                 'title': 'Hero Corp Making of - Extrait 1',
 233                 'description': 'md5:c87d54871b1790679aec1197e73d650a',
 234                 'upload_date': '20131106',
 235                 'timestamp': 1383766500,
 236             },
 237         },
 238         # france5
 239         {
 240             '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',
 241             'md5': 'f6c577df3806e26471b3d21631241fd0',
 242             'info_dict': {
 243                 'id': '123327454',
 244                 'ext': 'flv',
 245                 'title': 'C à dire ?! - Quels sont les enjeux de cette rentrée politique ?',
 246                 'description': 'md5:4a0d5cb5dce89d353522a84462bae5a4',
 247                 'upload_date': '20150831',
 248                 'timestamp': 1441035120,
 249             },
 250         },
 251         # franceo
 252         {
 253             'url': 'http://www.franceo.fr/jt/info-soir/18-07-2015',
 254             'md5': '47d5816d3b24351cdce512ad7ab31da8',
 255             'info_dict': {
 256                 'id': '125377621',
 257                 'ext': 'flv',
 258                 'title': 'Infô soir',
 259                 'description': 'md5:01b8c6915a3d93d8bbbd692651714309',
 260                 'upload_date': '20150718',
 261                 'timestamp': 1437241200,
 262                 'duration': 414,
 263             },
 264         },
 265         {
 266             # francetv embed
 267             'url': 'http://embed.francetv.fr/?ue=8d7d3da1e3047c42ade5a5d7dfd3fc87',
 268             'info_dict': {
 269                 'id': 'EV_30231',
 270                 'ext': 'flv',
 271                 'title': 'Alcaline, le concert avec Calogero',
 272                 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
 273                 'upload_date': '20150226',
 274                 'timestamp': 1424989860,
 275                 'duration': 5400,
 276             },
 277         },
 278         {
 279             'url': 'http://www.france4.fr/emission/highlander/diffusion-du-17-07-2015-04h05',
 280             'only_matching': True,
 281         },
 282         {
 283             'url': 'http://www.franceo.fr/videos/125377617',
 284             'only_matching': True,
 285         }
 286     ]
 287
 288     def _real_extract(self, url):
 289         video_id = self._match_id(url)
 290         webpage = self._download_webpage(url, video_id)
 291         video_id, catalogue = self._html_search_regex(
 292             r'(?:href=|player\.setVideo\(\s*)"http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"',
 293             webpage, 'video ID').split('@')
 294         return self._extract_video(video_id, catalogue)
 295
 296
 297 class GenerationQuoiIE(InfoExtractor):
 298     IE_NAME = 'france2.fr:generation-quoi'
 299     _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<id>[^/?#]+)'
 300
 301     _TEST = {
 302         'url': 'http://generation-quoi.france2.fr/portrait/garde-a-vous',
 303         'info_dict': {
 304             'id': 'k7FJX8VBcvvLmX4wA5Q',
 305             'ext': 'mp4',
 306             'title': 'Génération Quoi - Garde à Vous',
 307             'uploader': 'Génération Quoi',
 308         },
 309         'params': {
 310             # It uses Dailymotion
 311             'skip_download': True,
 312         },
 313     }
 314
 315     def _real_extract(self, url):
 316         display_id = self._match_id(url)
 317         info_url = compat_urlparse.urljoin(url, '/medias/video/%s.json' % display_id)
 318         info_json = self._download_webpage(info_url, display_id)
 319         info = json.loads(info_json)
 320         return self.url_result('http://www.dailymotion.com/video/%s' % info['id'],
 321                                ie='Dailymotion')
 322
 323
 324 class CultureboxIE(FranceTVBaseInfoExtractor):
 325     IE_NAME = 'culturebox.francetvinfo.fr'
 326     _VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'
 327
 328     _TEST = {
 329         'url': 'http://culturebox.francetvinfo.fr/live/musique/musique-classique/le-livre-vermeil-de-montserrat-a-la-cathedrale-delne-214511',
 330         'md5': '9b88dc156781c4dbebd4c3e066e0b1d6',
 331         'info_dict': {
 332             'id': 'EV_50111',
 333             'ext': 'flv',
 334             'title': "Le Livre Vermeil de Montserrat à la Cathédrale d'Elne",
 335             'description': 'md5:f8a4ad202e8fe533e2c493cc12e739d9',
 336             'upload_date': '20150320',
 337             'timestamp': 1426892400,
 338             'duration': 2760.9,
 339         },
 340     }
 341
 342     def _real_extract(self, url):
 343         mobj = re.match(self._VALID_URL, url)
 344         name = mobj.group('name')
 345
 346         webpage = self._download_webpage(url, name)
 347
 348         if ">Ce live n'est plus disponible en replay<" in webpage:
 349             raise ExtractorError('Video %s is not available' % name, expected=True)
 350
 351         video_id, catalogue = self._search_regex(
 352             r'"http://videos\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video id').split('@')
 353
 354         return self._extract_video(video_id, catalogue)