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
  30         formats = []
  31         for video in info['videos']:
  32             if video['statut'] != 'ONLINE':
  33                 continue
  34             video_url = video['url']
  35             if not video_url:
  36                 continue
  37             format_id = video['format']
  38             if video_url.endswith('.f4m'):
  39                 video_url_parsed = compat_urllib_parse_urlparse(video_url)
  40                 f4m_url = self._download_webpage(
  41                     'http://hdfauth.francetv.fr/esi/urltokengen2.html?url=%s' % video_url_parsed.path,
  42                     video_id, 'Downloading f4m manifest token', fatal=False)
  43                 if f4m_url:
  44                     f4m_formats = self._extract_f4m_formats(f4m_url, video_id)
  45                     for f4m_format in f4m_formats:
  46                         f4m_format['preference'] = 1
  47                     formats.extend(f4m_formats)
  48             elif video_url.endswith('.m3u8'):
  49                 formats.extend(self._extract_m3u8_formats(video_url, video_id))
  50             elif video_url.startswith('rtmp'):
  51                 formats.append({
  52                     'url': video_url,
  53                     'format_id': 'rtmp-%s' % format_id,
  54                     'ext': 'flv',
  55                     'preference': 1,
  56                 })
  57             else:
  58                 formats.append({
  59                     'url': video_url,
  60                     'format_id': format_id,
  61                     'preference': 2,
  62                 })
  63         self._sort_formats(formats)
  64
  65         return {
  66             'id': video_id,
  67             'title': info['titre'],
  68             'description': clean_html(info['synopsis']),
  69             'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
  70             'duration': parse_duration(info['duree']),
  71             'timestamp': int_or_none(info['diffusion']['timestamp']),
  72             'formats': formats,
  73         }
  74
  75
  76 class PluzzIE(FranceTVBaseInfoExtractor):
  77     IE_NAME = 'pluzz.francetv.fr'
  78     _VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'
  79
  80     # Can't use tests, videos expire in 7 days
  81
  82     def _real_extract(self, url):
  83         title = re.match(self._VALID_URL, url).group(1)
  84         webpage = self._download_webpage(url, title)
  85         video_id = self._search_regex(
  86             r'data-diffusion="(\d+)"', webpage, 'ID')
  87         return self._extract_video(video_id, 'Pluzz')
  88
  89
  90 class FranceTvInfoIE(FranceTVBaseInfoExtractor):
  91     IE_NAME = 'francetvinfo.fr'
  92     _VALID_URL = r'https?://(?:www|mobile)\.francetvinfo\.fr/.*/(?P<title>.+)\.html'
  93
  94     _TESTS = [{
  95         'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
  96         'md5': '9cecf35f99c4079c199e9817882a9a1c',
  97         'info_dict': {
  98             'id': '84981923',
  99             'ext': 'flv',
 100             'title': 'Soir 3',
 101             'upload_date': '20130826',
 102             'timestamp': 1377548400,
 103         },
 104     }, {
 105         'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',
 106         'info_dict': {
 107             'id': 'EV_20019',
 108             'ext': 'mp4',
 109             'title': 'Débat des candidats à la Commission européenne',
 110             'description': 'Débat des candidats à la Commission européenne',
 111         },
 112         'params': {
 113             'skip_download': 'HLS (reqires ffmpeg)'
 114         },
 115         'skip': 'Ce direct est terminé et sera disponible en rattrapage dans quelques minutes.',
 116     }]
 117
 118     def _real_extract(self, url):
 119         mobj = re.match(self._VALID_URL, url)
 120         page_title = mobj.group('title')
 121         webpage = self._download_webpage(url, page_title)
 122         video_id, catalogue = self._search_regex(
 123             r'id-video=([^@]+@[^"]+)', webpage, 'video id').split('@')
 124         return self._extract_video(video_id, catalogue)
 125
 126
 127 class FranceTVIE(FranceTVBaseInfoExtractor):
 128     IE_NAME = 'francetv'
 129     IE_DESC = 'France 2, 3, 4, 5 and Ô'
 130     _VALID_URL = r'''(?x)https?://www\.france[2345o]\.fr/
 131         (?:
 132             emissions/.*?/(videos|emissions)/(?P<id>[^/?]+)
 133         |   (emissions?|jt)/(?P<key>[^/?]+)
 134         )'''
 135
 136     _TESTS = [
 137         # france2
 138         {
 139             'url': 'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
 140             'md5': 'c03fc87cb85429ffd55df32b9fc05523',
 141             'info_dict': {
 142                 'id': '109169362',
 143                 'ext': 'flv',
 144                 'title': '13h15, le dimanche...',
 145                 'description': 'md5:9a0932bb465f22d377a449be9d1a0ff7',
 146                 'upload_date': '20140914',
 147                 'timestamp': 1410693600,
 148             },
 149         },
 150         # france3
 151         {
 152             'url': 'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
 153             'md5': '679bb8f8921f8623bd658fa2f8364da0',
 154             'info_dict': {
 155                 'id': '000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
 156                 'ext': 'mp4',
 157                 'title': 'Le scandale du prix des médicaments',
 158                 'description': 'md5:1384089fbee2f04fc6c9de025ee2e9ce',
 159                 'upload_date': '20131113',
 160                 'timestamp': 1384380000,
 161             },
 162         },
 163         # france4
 164         {
 165             'url': 'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
 166             'md5': 'a182bf8d2c43d88d46ec48fbdd260c1c',
 167             'info_dict': {
 168                 'id': 'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
 169                 'ext': 'mp4',
 170                 'title': 'Hero Corp Making of - Extrait 1',
 171                 'description': 'md5:c87d54871b1790679aec1197e73d650a',
 172                 'upload_date': '20131106',
 173                 'timestamp': 1383766500,
 174             },
 175         },
 176         # france5
 177         {
 178             'url': 'http://www.france5.fr/emissions/c-a-dire/videos/92837968',
 179             'md5': '78f0f4064f9074438e660785bbf2c5d9',
 180             'info_dict': {
 181                 'id': '108961659',
 182                 'ext': 'flv',
 183                 'title': 'C à dire ?!',
 184                 'description': 'md5:1a4aeab476eb657bf57c4ff122129f81',
 185                 'upload_date': '20140915',
 186                 'timestamp': 1410795000,
 187             },
 188         },
 189         # franceo
 190         {
 191             'url': 'http://www.franceo.fr/jt/info-afrique/04-12-2013',
 192             'md5': '52f0bfe202848b15915a2f39aaa8981b',
 193             'info_dict': {
 194                 'id': '108634970',
 195                 'ext': 'flv',
 196                 'title': 'Infô Afrique',
 197                 'description': 'md5:ebf346da789428841bee0fd2a935ea55',
 198                 'upload_date': '20140915',
 199                 'timestamp': 1410822000,
 200             },
 201         },
 202     ]
 203
 204     def _real_extract(self, url):
 205         mobj = re.match(self._VALID_URL, url)
 206         webpage = self._download_webpage(url, mobj.group('key') or mobj.group('id'))
 207         video_id, catalogue = self._html_search_regex(
 208             r'href="http://videos\.francetv\.fr/video/([^@]+@[^"]+)"',
 209             webpage, 'video ID').split('@')
 210         return self._extract_video(video_id, catalogue)
 211
 212
 213 class GenerationQuoiIE(InfoExtractor):
 214     IE_NAME = 'france2.fr:generation-quoi'
 215     _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<name>.*)(\?|$)'
 216
 217     _TEST = {
 218         'url': 'http://generation-quoi.france2.fr/portrait/garde-a-vous',
 219         'file': 'k7FJX8VBcvvLmX4wA5Q.mp4',
 220         'info_dict': {
 221             'title': 'Génération Quoi - Garde à Vous',
 222             'uploader': 'Génération Quoi',
 223         },
 224         'params': {
 225             # It uses Dailymotion
 226             'skip_download': True,
 227         },
 228         'skip': 'Only available from France',
 229     }
 230
 231     def _real_extract(self, url):
 232         mobj = re.match(self._VALID_URL, url)
 233         name = mobj.group('name')
 234         info_url = compat_urlparse.urljoin(url, '/medias/video/%s.json' % name)
 235         info_json = self._download_webpage(info_url, name)
 236         info = json.loads(info_json)
 237         return self.url_result('http://www.dailymotion.com/video/%s' % info['id'],
 238             ie='Dailymotion')
 239
 240
 241 class CultureboxIE(FranceTVBaseInfoExtractor):
 242     IE_NAME = 'culturebox.francetvinfo.fr'
 243     _VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'
 244
 245     _TEST = {
 246         'url': 'http://culturebox.francetvinfo.fr/festivals/dans-les-jardins-de-william-christie/dans-les-jardins-de-william-christie-le-camus-162553',
 247         'md5': '5ad6dec1ffb2a3fbcb20cc4b744be8d6',
 248         'info_dict': {
 249             'id': 'EV_22853',
 250             'ext': 'flv',
 251             'title': 'Dans les jardins de William Christie - Le Camus',
 252             'description': 'md5:4710c82315c40f0c865ca8b9a68b5299',
 253             'upload_date': '20140829',
 254             'timestamp': 1409317200,
 255         },
 256     }
 257
 258     def _real_extract(self, url):
 259         mobj = re.match(self._VALID_URL, url)
 260         name = mobj.group('name')
 261         webpage = self._download_webpage(url, name)
 262         video_id, catalogue = self._search_regex(
 263             r'"http://videos\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video id').split('@')
 264
 265         return self._extract_video(video_id, catalogue)