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 ..utils import (
  10     compat_urlparse,
  11     ExtractorError,
  12     clean_html,
  13     parse_duration,
  14     compat_urllib_parse_urlparse,
  15     int_or_none,
  16 )
  17
  18
  19 class FranceTVBaseInfoExtractor(InfoExtractor):
  20     def _extract_video(self, video_id, catalogue):
  21         info = self._download_json(
  22             'http://webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/?idDiffusion=%s&catalogue=%s'
  23             % (video_id, catalogue),
  24             video_id, 'Downloading video JSON')
  25
  26         if info.get('status') == 'NOK':
  27             raise ExtractorError(
  28                 '%s returned error: %s' % (self.IE_NAME, info['message']), expected=True)
  29         allowed_countries = info['videos'][0].get('geoblocage')
  30         if allowed_countries:
  31             georestricted = True
  32             geo_info = self._download_json(
  33                 'http://geo.francetv.fr/ws/edgescape.json', video_id,
  34                 'Downloading geo restriction info')
  35             country = geo_info['reponse']['geo_info']['country_code']
  36             if country not in allowed_countries:
  37                 raise ExtractorError(
  38                     'The video is not available from your location',
  39                     expected=True)
  40         else:
  41             georestricted = False
  42
  43         formats = []
  44         for video in info['videos']:
  45             if video['statut'] != 'ONLINE':
  46                 continue
  47             video_url = video['url']
  48             if not video_url:
  49                 continue
  50             format_id = video['format']
  51             if video_url.endswith('.f4m'):
  52                 if georestricted:
  53                     # See https://github.com/rg3/youtube-dl/issues/3963
  54                     # m3u8 urls work fine
  55                     continue
  56                 video_url_parsed = compat_urllib_parse_urlparse(video_url)
  57                 f4m_url = self._download_webpage(
  58                     'http://hdfauth.francetv.fr/esi/urltokengen2.html?url=%s' % video_url_parsed.path,
  59                     video_id, 'Downloading f4m manifest token', fatal=False)
  60                 if f4m_url:
  61                     f4m_formats = self._extract_f4m_formats(f4m_url, video_id)
  62                     for f4m_format in f4m_formats:
  63                         f4m_format['preference'] = 1
  64                     formats.extend(f4m_formats)
  65             elif video_url.endswith('.m3u8'):
  66                 formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4'))
  67             elif video_url.startswith('rtmp'):
  68                 formats.append({
  69                     'url': video_url,
  70                     'format_id': 'rtmp-%s' % format_id,
  71                     'ext': 'flv',
  72                     'preference': 1,
  73                 })
  74             else:
  75                 formats.append({
  76                     'url': video_url,
  77                     'format_id': format_id,
  78                     'preference': -1,
  79                 })
  80         self._sort_formats(formats)
  81
  82         return {
  83             'id': video_id,
  84             'title': info['titre'],
  85             'description': clean_html(info['synopsis']),
  86             'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
  87             'duration': parse_duration(info['duree']),
  88             'timestamp': int_or_none(info['diffusion']['timestamp']),
  89             'formats': formats,
  90         }
  91
  92
  93 class PluzzIE(FranceTVBaseInfoExtractor):
  94     IE_NAME = 'pluzz.francetv.fr'
  95     _VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'
  96
  97     # Can't use tests, videos expire in 7 days
  98
  99     def _real_extract(self, url):
 100         title = re.match(self._VALID_URL, url).group(1)
 101         webpage = self._download_webpage(url, title)
 102         video_id = self._search_regex(
 103             r'data-diffusion="(\d+)"', webpage, 'ID')
 104         return self._extract_video(video_id, 'Pluzz')
 105
 106
 107 class FranceTvInfoIE(FranceTVBaseInfoExtractor):
 108     IE_NAME = 'francetvinfo.fr'
 109     _VALID_URL = r'https?://(?:www|mobile)\.francetvinfo\.fr/.*/(?P<title>.+)\.html'
 110
 111     _TESTS = [{
 112         'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
 113         'info_dict': {
 114             'id': '84981923',
 115             'ext': 'flv',
 116             'title': 'Soir 3',
 117             'upload_date': '20130826',
 118             'timestamp': 1377548400,
 119         },
 120     }, {
 121         'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',
 122         'info_dict': {
 123             'id': 'EV_20019',
 124             'ext': 'mp4',
 125             'title': 'Débat des candidats à la Commission européenne',
 126             'description': 'Débat des candidats à la Commission européenne',
 127         },
 128         'params': {
 129             'skip_download': 'HLS (reqires ffmpeg)'
 130         },
 131         'skip': 'Ce direct est terminé et sera disponible en rattrapage dans quelques minutes.',
 132     }]
 133
 134     def _real_extract(self, url):
 135         mobj = re.match(self._VALID_URL, url)
 136         page_title = mobj.group('title')
 137         webpage = self._download_webpage(url, page_title)
 138         video_id, catalogue = self._search_regex(
 139             r'id-video=([^@]+@[^"]+)', webpage, 'video id').split('@')
 140         return self._extract_video(video_id, catalogue)
 141
 142
 143 class FranceTVIE(FranceTVBaseInfoExtractor):
 144     IE_NAME = 'francetv'
 145     IE_DESC = 'France 2, 3, 4, 5 and Ô'
 146     _VALID_URL = r'''(?x)https?://www\.france[2345o]\.fr/
 147         (?:
 148             emissions/.*?/(videos|emissions)/(?P<id>[^/?]+)
 149         |   (emissions?|jt)/(?P<key>[^/?]+)
 150         )'''
 151
 152     _TESTS = [
 153         # france2
 154         {
 155             'url': 'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
 156             'md5': 'c03fc87cb85429ffd55df32b9fc05523',
 157             'info_dict': {
 158                 'id': '109169362',
 159                 'ext': 'flv',
 160                 'title': '13h15, le dimanche...',
 161                 'description': 'md5:9a0932bb465f22d377a449be9d1a0ff7',
 162                 'upload_date': '20140914',
 163                 'timestamp': 1410693600,
 164             },
 165         },
 166         # france3
 167         {
 168             'url': 'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
 169             'md5': '679bb8f8921f8623bd658fa2f8364da0',
 170             'info_dict': {
 171                 'id': '000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
 172                 'ext': 'mp4',
 173                 'title': 'Le scandale du prix des médicaments',
 174                 'description': 'md5:1384089fbee2f04fc6c9de025ee2e9ce',
 175                 'upload_date': '20131113',
 176                 'timestamp': 1384380000,
 177             },
 178         },
 179         # france4
 180         {
 181             'url': 'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
 182             'md5': 'a182bf8d2c43d88d46ec48fbdd260c1c',
 183             'info_dict': {
 184                 'id': 'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
 185                 'ext': 'mp4',
 186                 'title': 'Hero Corp Making of - Extrait 1',
 187                 'description': 'md5:c87d54871b1790679aec1197e73d650a',
 188                 'upload_date': '20131106',
 189                 'timestamp': 1383766500,
 190             },
 191         },
 192         # france5
 193         {
 194             'url': 'http://www.france5.fr/emissions/c-a-dire/videos/92837968',
 195             'md5': '78f0f4064f9074438e660785bbf2c5d9',
 196             'info_dict': {
 197                 'id': '108961659',
 198                 'ext': 'flv',
 199                 'title': 'C à dire ?!',
 200                 'description': 'md5:1a4aeab476eb657bf57c4ff122129f81',
 201                 'upload_date': '20140915',
 202                 'timestamp': 1410795000,
 203             },
 204         },
 205         # franceo
 206         {
 207             'url': 'http://www.franceo.fr/jt/info-afrique/04-12-2013',
 208             'md5': '52f0bfe202848b15915a2f39aaa8981b',
 209             'info_dict': {
 210                 'id': '108634970',
 211                 'ext': 'flv',
 212                 'title': 'Infô Afrique',
 213                 'description': 'md5:ebf346da789428841bee0fd2a935ea55',
 214                 'upload_date': '20140915',
 215                 'timestamp': 1410822000,
 216             },
 217         },
 218     ]
 219
 220     def _real_extract(self, url):
 221         mobj = re.match(self._VALID_URL, url)
 222         webpage = self._download_webpage(url, mobj.group('key') or mobj.group('id'))
 223         video_id, catalogue = self._html_search_regex(
 224             r'href="http://videos\.francetv\.fr/video/([^@]+@[^"]+)"',
 225             webpage, 'video ID').split('@')
 226         return self._extract_video(video_id, catalogue)
 227
 228
 229 class GenerationQuoiIE(InfoExtractor):
 230     IE_NAME = 'france2.fr:generation-quoi'
 231     _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<name>.*)(\?|$)'
 232
 233     _TEST = {
 234         'url': 'http://generation-quoi.france2.fr/portrait/garde-a-vous',
 235         'file': 'k7FJX8VBcvvLmX4wA5Q.mp4',
 236         'info_dict': {
 237             'title': 'Génération Quoi - Garde à Vous',
 238             'uploader': 'Génération Quoi',
 239         },
 240         'params': {
 241             # It uses Dailymotion
 242             'skip_download': True,
 243         },
 244         'skip': 'Only available from France',
 245     }
 246
 247     def _real_extract(self, url):
 248         mobj = re.match(self._VALID_URL, url)
 249         name = mobj.group('name')
 250         info_url = compat_urlparse.urljoin(url, '/medias/video/%s.json' % name)
 251         info_json = self._download_webpage(info_url, name)
 252         info = json.loads(info_json)
 253         return self.url_result('http://www.dailymotion.com/video/%s' % info['id'],
 254                                ie='Dailymotion')
 255
 256
 257 class CultureboxIE(FranceTVBaseInfoExtractor):
 258     IE_NAME = 'culturebox.francetvinfo.fr'
 259     _VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'
 260
 261     _TEST = {
 262         'url': 'http://culturebox.francetvinfo.fr/festivals/dans-les-jardins-de-william-christie/dans-les-jardins-de-william-christie-le-camus-162553',
 263         'md5': '5ad6dec1ffb2a3fbcb20cc4b744be8d6',
 264         'info_dict': {
 265             'id': 'EV_22853',
 266             'ext': 'flv',
 267             'title': 'Dans les jardins de William Christie - Le Camus',
 268             'description': 'md5:4710c82315c40f0c865ca8b9a68b5299',
 269             'upload_date': '20140829',
 270             'timestamp': 1409317200,
 271         },
 272     }
 273
 274     def _real_extract(self, url):
 275         mobj = re.match(self._VALID_URL, url)
 276         name = mobj.group('name')
 277         webpage = self._download_webpage(url, name)
 278         video_id, catalogue = self._search_regex(
 279             r'"http://videos\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video id').split('@')
 280
 281         return self._extract_video(video_id, catalogue)