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         return {
  87             'id': video_id,
  88             'title': title,
  89             'description': clean_html(info['synopsis']),
  90             'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
  91             'duration': int_or_none(info.get('real_duration')) or parse_duration(info['duree']),
  92             'timestamp': int_or_none(info['diffusion']['timestamp']),
  93             'formats': formats,
  94         }
  95
  96
  97 class PluzzIE(FranceTVBaseInfoExtractor):
  98     IE_NAME = 'pluzz.francetv.fr'
  99     _VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'
 100
 101     # Can't use tests, videos expire in 7 days
 102
 103     def _real_extract(self, url):
 104         title = re.match(self._VALID_URL, url).group(1)
 105         webpage = self._download_webpage(url, title)
 106         video_id = self._search_regex(
 107             r'data-diffusion="(\d+)"', webpage, 'ID')
 108         return self._extract_video(video_id, 'Pluzz')
 109
 110
 111 class FranceTvInfoIE(FranceTVBaseInfoExtractor):
 112     IE_NAME = 'francetvinfo.fr'
 113     _VALID_URL = r'https?://(?:www|mobile)\.francetvinfo\.fr/.*/(?P<title>.+)\.html'
 114
 115     _TESTS = [{
 116         'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
 117         'info_dict': {
 118             'id': '84981923',
 119             'ext': 'flv',
 120             'title': 'Soir 3',
 121             'upload_date': '20130826',
 122             'timestamp': 1377548400,
 123         },
 124     }, {
 125         'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',
 126         'info_dict': {
 127             'id': 'EV_20019',
 128             'ext': 'mp4',
 129             'title': 'Débat des candidats à la Commission européenne',
 130             'description': 'Débat des candidats à la Commission européenne',
 131         },
 132         'params': {
 133             'skip_download': 'HLS (reqires ffmpeg)'
 134         },
 135         'skip': 'Ce direct est terminé et sera disponible en rattrapage dans quelques minutes.',
 136     }, {
 137         'url': 'http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html',
 138         'md5': 'f485bda6e185e7d15dbc69b72bae993e',
 139         'info_dict': {
 140             'id': '556e03339473995ee145930c',
 141             'ext': 'mp4',
 142             'title': 'Les entreprises familiales : le secret de la réussite',
 143             'thumbnail': 're:^https?://.*\.jpe?g$',
 144         }
 145     }]
 146
 147     def _real_extract(self, url):
 148         mobj = re.match(self._VALID_URL, url)
 149         page_title = mobj.group('title')
 150         webpage = self._download_webpage(url, page_title)
 151
 152         dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
 153         if dmcloud_url:
 154             return self.url_result(dmcloud_url, 'DailymotionCloud')
 155
 156         video_id, catalogue = self._search_regex(
 157             r'id-video=([^@]+@[^"]+)', webpage, 'video id').split('@')
 158         return self._extract_video(video_id, catalogue)
 159
 160
 161 class FranceTVIE(FranceTVBaseInfoExtractor):
 162     IE_NAME = 'francetv'
 163     IE_DESC = 'France 2, 3, 4, 5 and Ô'
 164     _VALID_URL = r'''(?x)
 165                     https?://
 166                         (?:
 167                             (?:www\.)?france[2345o]\.fr/
 168                                 (?:
 169                                     emissions/[^/]+/(?:videos|diffusions)|
 170                                     emission/[^/]+|
 171                                     videos|
 172                                     jt
 173                                 )
 174                             /|
 175                             embed\.francetv\.fr/\?ue=
 176                         )
 177                         (?P<id>[^/?]+)
 178                     '''
 179
 180     _TESTS = [
 181         # france2
 182         {
 183             'url': 'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
 184             'md5': 'c03fc87cb85429ffd55df32b9fc05523',
 185             'info_dict': {
 186                 'id': '109169362',
 187                 'ext': 'flv',
 188                 'title': '13h15, le dimanche...',
 189                 'description': 'md5:9a0932bb465f22d377a449be9d1a0ff7',
 190                 'upload_date': '20140914',
 191                 'timestamp': 1410693600,
 192             },
 193         },
 194         # france3
 195         {
 196             'url': 'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
 197             'md5': '679bb8f8921f8623bd658fa2f8364da0',
 198             'info_dict': {
 199                 'id': '000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
 200                 'ext': 'mp4',
 201                 'title': 'Le scandale du prix des médicaments',
 202                 'description': 'md5:1384089fbee2f04fc6c9de025ee2e9ce',
 203                 'upload_date': '20131113',
 204                 'timestamp': 1384380000,
 205             },
 206         },
 207         # france4
 208         {
 209             'url': 'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
 210             'md5': 'a182bf8d2c43d88d46ec48fbdd260c1c',
 211             'info_dict': {
 212                 'id': 'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
 213                 'ext': 'mp4',
 214                 'title': 'Hero Corp Making of - Extrait 1',
 215                 'description': 'md5:c87d54871b1790679aec1197e73d650a',
 216                 'upload_date': '20131106',
 217                 'timestamp': 1383766500,
 218             },
 219         },
 220         # france5
 221         {
 222             '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',
 223             'md5': 'f6c577df3806e26471b3d21631241fd0',
 224             'info_dict': {
 225                 'id': '123327454',
 226                 'ext': 'flv',
 227                 'title': 'C à dire ?! - Quels sont les enjeux de cette rentrée politique ?',
 228                 'description': 'md5:4a0d5cb5dce89d353522a84462bae5a4',
 229                 'upload_date': '20150831',
 230                 'timestamp': 1441035120,
 231             },
 232         },
 233         # franceo
 234         {
 235             'url': 'http://www.franceo.fr/jt/info-soir/18-07-2015',
 236             'md5': '47d5816d3b24351cdce512ad7ab31da8',
 237             'info_dict': {
 238                 'id': '125377621',
 239                 'ext': 'flv',
 240                 'title': 'Infô soir',
 241                 'description': 'md5:01b8c6915a3d93d8bbbd692651714309',
 242                 'upload_date': '20150718',
 243                 'timestamp': 1437241200,
 244                 'duration': 414,
 245             },
 246         },
 247         {
 248             # francetv embed
 249             'url': 'http://embed.francetv.fr/?ue=8d7d3da1e3047c42ade5a5d7dfd3fc87',
 250             'info_dict': {
 251                 'id': 'EV_30231',
 252                 'ext': 'flv',
 253                 'title': 'Alcaline, le concert avec Calogero',
 254                 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
 255                 'upload_date': '20150226',
 256                 'timestamp': 1424989860,
 257                 'duration': 5400,
 258             },
 259         },
 260         {
 261             'url': 'http://www.france4.fr/emission/highlander/diffusion-du-17-07-2015-04h05',
 262             'only_matching': True,
 263         },
 264         {
 265             'url': 'http://www.franceo.fr/videos/125377617',
 266             'only_matching': True,
 267         }
 268     ]
 269
 270     def _real_extract(self, url):
 271         video_id = self._match_id(url)
 272         webpage = self._download_webpage(url, video_id)
 273         video_id, catalogue = self._html_search_regex(
 274             r'href="http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"',
 275             webpage, 'video ID').split('@')
 276         return self._extract_video(video_id, catalogue)
 277
 278
 279 class GenerationQuoiIE(InfoExtractor):
 280     IE_NAME = 'france2.fr:generation-quoi'
 281     _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<id>[^/?#]+)'
 282
 283     _TEST = {
 284         'url': 'http://generation-quoi.france2.fr/portrait/garde-a-vous',
 285         'info_dict': {
 286             'id': 'k7FJX8VBcvvLmX4wA5Q',
 287             'ext': 'mp4',
 288             'title': 'Génération Quoi - Garde à Vous',
 289             'uploader': 'Génération Quoi',
 290         },
 291         'params': {
 292             # It uses Dailymotion
 293             'skip_download': True,
 294         },
 295     }
 296
 297     def _real_extract(self, url):
 298         display_id = self._match_id(url)
 299         info_url = compat_urlparse.urljoin(url, '/medias/video/%s.json' % display_id)
 300         info_json = self._download_webpage(info_url, display_id)
 301         info = json.loads(info_json)
 302         return self.url_result('http://www.dailymotion.com/video/%s' % info['id'],
 303                                ie='Dailymotion')
 304
 305
 306 class CultureboxIE(FranceTVBaseInfoExtractor):
 307     IE_NAME = 'culturebox.francetvinfo.fr'
 308     _VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'
 309
 310     _TEST = {
 311         'url': 'http://culturebox.francetvinfo.fr/live/musique/musique-classique/le-livre-vermeil-de-montserrat-a-la-cathedrale-delne-214511',
 312         'md5': '9b88dc156781c4dbebd4c3e066e0b1d6',
 313         'info_dict': {
 314             'id': 'EV_50111',
 315             'ext': 'flv',
 316             'title': "Le Livre Vermeil de Montserrat à la Cathédrale d'Elne",
 317             'description': 'md5:f8a4ad202e8fe533e2c493cc12e739d9',
 318             'upload_date': '20150320',
 319             'timestamp': 1426892400,
 320             'duration': 2760.9,
 321         },
 322     }
 323
 324     def _real_extract(self, url):
 325         mobj = re.match(self._VALID_URL, url)
 326         name = mobj.group('name')
 327
 328         webpage = self._download_webpage(url, name)
 329
 330         if ">Ce live n'est plus disponible en replay<" in webpage:
 331             raise ExtractorError('Video %s is not available' % name, expected=True)
 332
 333         video_id, catalogue = self._search_regex(
 334             r'"http://videos\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video id').split('@')
 335
 336         return self._extract_video(video_id, catalogue)