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         return {
  82             'id': video_id,
  83             'title': info['titre'],
  84             'description': clean_html(info['synopsis']),
  85             'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
  86             'duration': int_or_none(info.get('real_duration')) or parse_duration(info['duree']),
  87             'timestamp': int_or_none(info['diffusion']['timestamp']),
  88             'formats': formats,
  89         }
  90
  91
  92 class PluzzIE(FranceTVBaseInfoExtractor):
  93     IE_NAME = 'pluzz.francetv.fr'
  94     _VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'
  95
  96     # Can't use tests, videos expire in 7 days
  97
  98     def _real_extract(self, url):
  99         title = re.match(self._VALID_URL, url).group(1)
 100         webpage = self._download_webpage(url, title)
 101         video_id = self._search_regex(
 102             r'data-diffusion="(\d+)"', webpage, 'ID')
 103         return self._extract_video(video_id, 'Pluzz')
 104
 105
 106 class FranceTvInfoIE(FranceTVBaseInfoExtractor):
 107     IE_NAME = 'francetvinfo.fr'
 108     _VALID_URL = r'https?://(?:www|mobile)\.francetvinfo\.fr/.*/(?P<title>.+)\.html'
 109
 110     _TESTS = [{
 111         'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
 112         'info_dict': {
 113             'id': '84981923',
 114             'ext': 'flv',
 115             'title': 'Soir 3',
 116             'upload_date': '20130826',
 117             'timestamp': 1377548400,
 118         },
 119     }, {
 120         'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',
 121         'info_dict': {
 122             'id': 'EV_20019',
 123             'ext': 'mp4',
 124             'title': 'Débat des candidats à la Commission européenne',
 125             'description': 'Débat des candidats à la Commission européenne',
 126         },
 127         'params': {
 128             'skip_download': 'HLS (reqires ffmpeg)'
 129         },
 130         'skip': 'Ce direct est terminé et sera disponible en rattrapage dans quelques minutes.',
 131     }, {
 132         'url': 'http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html',
 133         'md5': 'f485bda6e185e7d15dbc69b72bae993e',
 134         'info_dict': {
 135             'id': '556e03339473995ee145930c',
 136             'ext': 'mp4',
 137             'title': 'Les entreprises familiales : le secret de la réussite',
 138             'thumbnail': 're:^https?://.*\.jpe?g$',
 139         }
 140     }]
 141
 142     def _real_extract(self, url):
 143         mobj = re.match(self._VALID_URL, url)
 144         page_title = mobj.group('title')
 145         webpage = self._download_webpage(url, page_title)
 146
 147         dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
 148         if dmcloud_url:
 149             return self.url_result(dmcloud_url, 'DailymotionCloud')
 150
 151         video_id, catalogue = self._search_regex(
 152             r'id-video=([^@]+@[^"]+)', webpage, 'video id').split('@')
 153         return self._extract_video(video_id, catalogue)
 154
 155
 156 class FranceTVIE(FranceTVBaseInfoExtractor):
 157     IE_NAME = 'francetv'
 158     IE_DESC = 'France 2, 3, 4, 5 and Ô'
 159     _VALID_URL = r'''(?x)
 160                     https?://
 161                         (?:
 162                             (?:www\.)?france[2345o]\.fr/
 163                                 (?:
 164                                     emissions/[^/]+/(?:videos|diffusions)|
 165                                     emission/[^/]+|
 166                                     videos|
 167                                     jt
 168                                 )
 169                             /|
 170                             embed\.francetv\.fr/\?ue=
 171                         )
 172                         (?P<id>[^/?]+)
 173                     '''
 174
 175     _TESTS = [
 176         # france2
 177         {
 178             'url': 'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
 179             'md5': 'c03fc87cb85429ffd55df32b9fc05523',
 180             'info_dict': {
 181                 'id': '109169362',
 182                 'ext': 'flv',
 183                 'title': '13h15, le dimanche...',
 184                 'description': 'md5:9a0932bb465f22d377a449be9d1a0ff7',
 185                 'upload_date': '20140914',
 186                 'timestamp': 1410693600,
 187             },
 188         },
 189         # france3
 190         {
 191             'url': 'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
 192             'md5': '679bb8f8921f8623bd658fa2f8364da0',
 193             'info_dict': {
 194                 'id': '000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
 195                 'ext': 'mp4',
 196                 'title': 'Le scandale du prix des médicaments',
 197                 'description': 'md5:1384089fbee2f04fc6c9de025ee2e9ce',
 198                 'upload_date': '20131113',
 199                 'timestamp': 1384380000,
 200             },
 201         },
 202         # france4
 203         {
 204             'url': 'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
 205             'md5': 'a182bf8d2c43d88d46ec48fbdd260c1c',
 206             'info_dict': {
 207                 'id': 'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
 208                 'ext': 'mp4',
 209                 'title': 'Hero Corp Making of - Extrait 1',
 210                 'description': 'md5:c87d54871b1790679aec1197e73d650a',
 211                 'upload_date': '20131106',
 212                 'timestamp': 1383766500,
 213             },
 214         },
 215         # france5
 216         {
 217             'url': 'http://www.france5.fr/emissions/c-a-dire/videos/92837968',
 218             'md5': '78f0f4064f9074438e660785bbf2c5d9',
 219             'info_dict': {
 220                 'id': '108961659',
 221                 'ext': 'flv',
 222                 'title': 'C à dire ?!',
 223                 'description': 'md5:1a4aeab476eb657bf57c4ff122129f81',
 224                 'upload_date': '20140915',
 225                 'timestamp': 1410795000,
 226             },
 227         },
 228         # franceo
 229         {
 230             'url': 'http://www.franceo.fr/jt/info-soir/18-07-2015',
 231             'md5': '47d5816d3b24351cdce512ad7ab31da8',
 232             'info_dict': {
 233                 'id': '125377621',
 234                 'ext': 'flv',
 235                 'title': 'Infô soir',
 236                 'description': 'md5:01b8c6915a3d93d8bbbd692651714309',
 237                 'upload_date': '20150718',
 238                 'timestamp': 1437241200,
 239                 'duration': 414,
 240             },
 241         },
 242         {
 243             # francetv embed
 244             'url': 'http://embed.francetv.fr/?ue=8d7d3da1e3047c42ade5a5d7dfd3fc87',
 245             'info_dict': {
 246                 'id': 'EV_30231',
 247                 'ext': 'flv',
 248                 'title': 'Alcaline, le concert avec Calogero',
 249                 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
 250                 'upload_date': '20150226',
 251                 'timestamp': 1424989860,
 252                 'duration': 5400,
 253             },
 254         },
 255         {
 256             'url': 'http://www.france4.fr/emission/highlander/diffusion-du-17-07-2015-04h05',
 257             'only_matching': True,
 258         },
 259         {
 260             'url': 'http://www.franceo.fr/videos/125377617',
 261             'only_matching': True,
 262         }
 263     ]
 264
 265     def _real_extract(self, url):
 266         video_id = self._match_id(url)
 267         webpage = self._download_webpage(url, video_id)
 268         video_id, catalogue = self._html_search_regex(
 269             r'href="http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"',
 270             webpage, 'video ID').split('@')
 271         return self._extract_video(video_id, catalogue)
 272
 273
 274 class GenerationQuoiIE(InfoExtractor):
 275     IE_NAME = 'france2.fr:generation-quoi'
 276     _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<id>[^/?#]+)'
 277
 278     _TEST = {
 279         'url': 'http://generation-quoi.france2.fr/portrait/garde-a-vous',
 280         'info_dict': {
 281             'id': 'k7FJX8VBcvvLmX4wA5Q',
 282             'ext': 'mp4',
 283             'title': 'Génération Quoi - Garde à Vous',
 284             'uploader': 'Génération Quoi',
 285         },
 286         'params': {
 287             # It uses Dailymotion
 288             'skip_download': True,
 289         },
 290     }
 291
 292     def _real_extract(self, url):
 293         display_id = self._match_id(url)
 294         info_url = compat_urlparse.urljoin(url, '/medias/video/%s.json' % display_id)
 295         info_json = self._download_webpage(info_url, display_id)
 296         info = json.loads(info_json)
 297         return self.url_result('http://www.dailymotion.com/video/%s' % info['id'],
 298                                ie='Dailymotion')
 299
 300
 301 class CultureboxIE(FranceTVBaseInfoExtractor):
 302     IE_NAME = 'culturebox.francetvinfo.fr'
 303     _VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'
 304
 305     _TEST = {
 306         'url': 'http://culturebox.francetvinfo.fr/live/musique/musique-classique/le-livre-vermeil-de-montserrat-a-la-cathedrale-delne-214511',
 307         'md5': '9b88dc156781c4dbebd4c3e066e0b1d6',
 308         'info_dict': {
 309             'id': 'EV_50111',
 310             'ext': 'flv',
 311             'title': "Le Livre Vermeil de Montserrat à la Cathédrale d'Elne",
 312             'description': 'md5:f8a4ad202e8fe533e2c493cc12e739d9',
 313             'upload_date': '20150320',
 314             'timestamp': 1426892400,
 315             'duration': 2760.9,
 316         },
 317     }
 318
 319     def _real_extract(self, url):
 320         mobj = re.match(self._VALID_URL, url)
 321         name = mobj.group('name')
 322
 323         webpage = self._download_webpage(url, name)
 324
 325         if ">Ce live n'est plus disponible en replay<" in webpage:
 326             raise ExtractorError('Video %s is not available' % name, expected=True)
 327
 328         video_id, catalogue = self._search_regex(
 329             r'"http://videos\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video id').split('@')
 330
 331         return self._extract_video(video_id, catalogue)