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 (
  10     compat_urllib_parse_urlparse,
  11     compat_urlparse,
  12 )
  13 from ..utils import (
  14     clean_html,
  15     ExtractorError,
  16     int_or_none,
  17     float_or_none,
  18     parse_duration,
  19     determine_ext,
  20 )
  21 from .dailymotion import DailymotionCloudIE
  22
  23
  24 class FranceTVBaseInfoExtractor(InfoExtractor):
  25     def _extract_video(self, video_id, catalogue):
  26         info = self._download_json(
  27             'http://webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/?idDiffusion=%s&catalogue=%s'
  28             % (video_id, catalogue),
  29             video_id, 'Downloading video JSON')
  30
  31         if info.get('status') == 'NOK':
  32             raise ExtractorError(
  33                 '%s returned error: %s' % (self.IE_NAME, info['message']), expected=True)
  34         allowed_countries = info['videos'][0].get('geoblocage')
  35         if allowed_countries:
  36             georestricted = True
  37             geo_info = self._download_json(
  38                 'http://geo.francetv.fr/ws/edgescape.json', video_id,
  39                 'Downloading geo restriction info')
  40             country = geo_info['reponse']['geo_info']['country_code']
  41             if country not in allowed_countries:
  42                 raise ExtractorError(
  43                     'The video is not available from your location',
  44                     expected=True)
  45         else:
  46             georestricted = False
  47
  48         formats = []
  49         for video in info['videos']:
  50             if video['statut'] != 'ONLINE':
  51                 continue
  52             video_url = video['url']
  53             if not video_url:
  54                 continue
  55             format_id = video['format']
  56             ext = determine_ext(video_url)
  57             if ext == 'f4m':
  58                 if georestricted:
  59                     # See https://github.com/rg3/youtube-dl/issues/3963
  60                     # m3u8 urls work fine
  61                     continue
  62                 video_url_parsed = compat_urllib_parse_urlparse(video_url)
  63                 f4m_url = self._download_webpage(
  64                     'http://hdfauth.francetv.fr/esi/TA?url=%s' % video_url_parsed.path,
  65                     video_id, 'Downloading f4m manifest token', fatal=False)
  66                 if f4m_url:
  67                     formats.extend(self._extract_f4m_formats(f4m_url, video_id, 1, format_id))
  68             elif ext == 'm3u8':
  69                 formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4', m3u8_id=format_id))
  70             elif video_url.startswith('rtmp'):
  71                 formats.append({
  72                     'url': video_url,
  73                     'format_id': 'rtmp-%s' % format_id,
  74                     'ext': 'flv',
  75                     'preference': 1,
  76                 })
  77             else:
  78                 formats.append({
  79                     'url': video_url,
  80                     'format_id': format_id,
  81                     'preference': -1,
  82                 })
  83         self._sort_formats(formats)
  84
  85         return {
  86             'id': video_id,
  87             'title': info['titre'],
  88             'description': clean_html(info['synopsis']),
  89             'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
  90             'duration': float_or_none(info.get('real_duration'), 1000) or parse_duration(info['duree']),
  91             'timestamp': int_or_none(info['diffusion']['timestamp']),
  92             'formats': formats,
  93         }
  94
  95
  96 class PluzzIE(FranceTVBaseInfoExtractor):
  97     IE_NAME = 'pluzz.francetv.fr'
  98     _VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'
  99
 100     # Can't use tests, videos expire in 7 days
 101
 102     def _real_extract(self, url):
 103         title = re.match(self._VALID_URL, url).group(1)
 104         webpage = self._download_webpage(url, title)
 105         video_id = self._search_regex(
 106             r'data-diffusion="(\d+)"', webpage, 'ID')
 107         return self._extract_video(video_id, 'Pluzz')
 108
 109
 110 class FranceTvInfoIE(FranceTVBaseInfoExtractor):
 111     IE_NAME = 'francetvinfo.fr'
 112     _VALID_URL = r'https?://(?:www|mobile)\.francetvinfo\.fr/.*/(?P<title>.+)\.html'
 113
 114     _TESTS = [{
 115         'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
 116         'info_dict': {
 117             'id': '84981923',
 118             'ext': 'flv',
 119             'title': 'Soir 3',
 120             'upload_date': '20130826',
 121             'timestamp': 1377548400,
 122         },
 123     }, {
 124         'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',
 125         'info_dict': {
 126             'id': 'EV_20019',
 127             'ext': 'mp4',
 128             'title': 'Débat des candidats à la Commission européenne',
 129             'description': 'Débat des candidats à la Commission européenne',
 130         },
 131         'params': {
 132             'skip_download': 'HLS (reqires ffmpeg)'
 133         },
 134         'skip': 'Ce direct est terminé et sera disponible en rattrapage dans quelques minutes.',
 135     }, {
 136         'url': 'http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html',
 137         'md5': 'f485bda6e185e7d15dbc69b72bae993e',
 138         'info_dict': {
 139             'id': '556e03339473995ee145930c',
 140             'ext': 'mp4',
 141             'title': 'Les entreprises familiales : le secret de la réussite',
 142             'thumbnail': 're:^https?://.*\.jpe?g$',
 143         }
 144     }]
 145
 146     def _real_extract(self, url):
 147         mobj = re.match(self._VALID_URL, url)
 148         page_title = mobj.group('title')
 149         webpage = self._download_webpage(url, page_title)
 150
 151         dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
 152         if dmcloud_url:
 153             return self.url_result(dmcloud_url, 'DailymotionCloud')
 154
 155         video_id, catalogue = self._search_regex(
 156             r'id-video=([^@]+@[^"]+)', webpage, 'video id').split('@')
 157         return self._extract_video(video_id, catalogue)
 158
 159
 160 class FranceTVIE(FranceTVBaseInfoExtractor):
 161     IE_NAME = 'francetv'
 162     IE_DESC = 'France 2, 3, 4, 5 and Ô'
 163     _VALID_URL = r'''(?x)
 164                     https?://
 165                         (?:
 166                             (?:www\.)?france[2345o]\.fr/
 167                                 (?:
 168                                     emissions/[^/]+/(?:videos|diffusions)?|
 169                                     videos
 170                                 )
 171                             /|
 172                             embed\.francetv\.fr/\?ue=
 173                         )
 174                         (?P<id>[^/?]+)
 175                     '''
 176
 177     _TESTS = [
 178         # france2
 179         {
 180             'url': 'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
 181             'md5': 'c03fc87cb85429ffd55df32b9fc05523',
 182             'info_dict': {
 183                 'id': '109169362',
 184                 'ext': 'flv',
 185                 'title': '13h15, le dimanche...',
 186                 'description': 'md5:9a0932bb465f22d377a449be9d1a0ff7',
 187                 'upload_date': '20140914',
 188                 'timestamp': 1410693600,
 189             },
 190         },
 191         # france3
 192         {
 193             'url': 'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
 194             'md5': '679bb8f8921f8623bd658fa2f8364da0',
 195             'info_dict': {
 196                 'id': '000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
 197                 'ext': 'mp4',
 198                 'title': 'Le scandale du prix des médicaments',
 199                 'description': 'md5:1384089fbee2f04fc6c9de025ee2e9ce',
 200                 'upload_date': '20131113',
 201                 'timestamp': 1384380000,
 202             },
 203         },
 204         # france4
 205         {
 206             'url': 'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
 207             'md5': 'a182bf8d2c43d88d46ec48fbdd260c1c',
 208             'info_dict': {
 209                 'id': 'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
 210                 'ext': 'mp4',
 211                 'title': 'Hero Corp Making of - Extrait 1',
 212                 'description': 'md5:c87d54871b1790679aec1197e73d650a',
 213                 'upload_date': '20131106',
 214                 'timestamp': 1383766500,
 215             },
 216         },
 217         # france5
 218         {
 219             'url': 'http://www.france5.fr/emissions/c-a-dire/videos/92837968',
 220             'md5': '78f0f4064f9074438e660785bbf2c5d9',
 221             'info_dict': {
 222                 'id': '108961659',
 223                 'ext': 'flv',
 224                 'title': 'C à dire ?!',
 225                 'description': 'md5:1a4aeab476eb657bf57c4ff122129f81',
 226                 'upload_date': '20140915',
 227                 'timestamp': 1410795000,
 228             },
 229         },
 230         # franceo
 231         {
 232             'url': 'http://www.franceo.fr/jt/info-afrique/04-12-2013',
 233             'md5': '52f0bfe202848b15915a2f39aaa8981b',
 234             'info_dict': {
 235                 'id': '108634970',
 236                 'ext': 'flv',
 237                 'title': 'Infô Afrique',
 238                 'description': 'md5:ebf346da789428841bee0fd2a935ea55',
 239                 'upload_date': '20140915',
 240                 'timestamp': 1410822000,
 241             },
 242         },
 243         {
 244             # francetv embed
 245             'url': 'http://embed.francetv.fr/?ue=8d7d3da1e3047c42ade5a5d7dfd3fc87',
 246             'info_dict': {
 247                 'id': 'EV_30231',
 248                 'ext': 'flv',
 249                 'title': 'Alcaline, le concert avec Calogero',
 250                 'description': 'md5:',
 251                 'upload_date': '20150226',
 252                 'timestamp': 1424989860,
 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)