_ Git - youtube-dl/blob - youtube_dl/extractor/francetv.py

   1 # encoding: utf-8
   2 import re
   3 import json
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     compat_urlparse,
   8 )
   9
  10
  11 class FranceTVBaseInfoExtractor(InfoExtractor):
  12     def _extract_video(self, video_id):
  13         info = self._download_xml(
  14             'http://www.francetvinfo.fr/appftv/webservices/video/'
  15             'getInfosOeuvre.php?id-diffusion='
  16             + video_id, video_id, 'Downloading XML config')
  17
  18         manifest_url = info.find('videos/video/url').text
  19         video_url = manifest_url.replace('manifest.f4m', 'index_2_av.m3u8')
  20         video_url = video_url.replace('/z/', '/i/')
  21         thumbnail_path = info.find('image').text
  22
  23         return {'id': video_id,
  24                 'ext': 'mp4',
  25                 'url': video_url,
  26                 'title': info.find('titre').text,
  27                 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path),
  28                 'description': info.find('synopsis').text,
  29                 }
  30
  31
  32 class PluzzIE(FranceTVBaseInfoExtractor):
  33     IE_NAME = u'pluzz.francetv.fr'
  34     _VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'
  35
  36     # Can't use tests, videos expire in 7 days
  37
  38     def _real_extract(self, url):
  39         title = re.match(self._VALID_URL, url).group(1)
  40         webpage = self._download_webpage(url, title)
  41         video_id = self._search_regex(
  42             r'data-diffusion="(\d+)"', webpage, 'ID')
  43         return self._extract_video(video_id)
  44
  45
  46 class FranceTvInfoIE(FranceTVBaseInfoExtractor):
  47     IE_NAME = u'francetvinfo.fr'
  48     _VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P<title>.+).html'
  49
  50     _TEST = {
  51         u'url': u'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
  52         u'file': u'84981923.mp4',
  53         u'info_dict': {
  54             u'title': u'Soir 3',
  55         },
  56         u'params': {
  57             u'skip_download': True,
  58         },
  59     }
  60
  61     def _real_extract(self, url):
  62         mobj = re.match(self._VALID_URL, url)
  63         page_title = mobj.group('title')
  64         webpage = self._download_webpage(url, page_title)
  65         video_id = self._search_regex(r'id-video=(\d+?)"', webpage, u'video id')
  66         return self._extract_video(video_id)
  67
  68
  69 class France2IE(FranceTVBaseInfoExtractor):
  70     IE_NAME = u'france2.fr'
  71     _VALID_URL = r'''(?x)https?://www\.france2\.fr/
  72         (?:
  73             emissions/.*?/videos/(?P<id>\d+)
  74         |   emission/(?P<key>[^/?]+)
  75         )'''
  76
  77     _TEST = {
  78         u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
  79         u'file': u'75540104.mp4',
  80         u'info_dict': {
  81             u'title': u'13h15, le samedi...',
  82             u'description': u'md5:2e5b58ba7a2d3692b35c792be081a03d',
  83         },
  84         u'params': {
  85             u'skip_download': True,
  86         },
  87     }
  88
  89     def _real_extract(self, url):
  90         mobj = re.match(self._VALID_URL, url)
  91         if mobj.group('key'):
  92             webpage = self._download_webpage(url, mobj.group('key'))
  93             video_id = self._html_search_regex(
  94                 r'''(?x)<div\s+class="video-player">\s*
  95                     <a\s+href="http://videos.francetv.fr/video/([0-9]+)"\s+
  96                     class="francetv-video-player">''',
  97                 webpage, u'video ID')
  98         else:
  99             video_id = mobj.group('id')
 100         return self._extract_video(video_id)
 101
 102
 103 class GenerationQuoiIE(InfoExtractor):
 104     IE_NAME = u'france2.fr:generation-quoi'
 105     _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<name>.*)(\?|$)'
 106
 107     _TEST = {
 108         u'url': u'http://generation-quoi.france2.fr/portrait/garde-a-vous',
 109         u'file': u'k7FJX8VBcvvLmX4wA5Q.mp4',
 110         u'info_dict': {
 111             u'title': u'Génération Quoi - Garde à Vous',
 112             u'uploader': u'Génération Quoi',
 113         },
 114         u'params': {
 115             # It uses Dailymotion
 116             u'skip_download': True,
 117         },
 118     }
 119
 120     def _real_extract(self, url):
 121         mobj = re.match(self._VALID_URL, url)
 122         name = mobj.group('name')
 123         info_url = compat_urlparse.urljoin(url, '/medias/video/%s.json' % name)
 124         info_json = self._download_webpage(info_url, name)
 125         info = json.loads(info_json)
 126         return self.url_result('http://www.dailymotion.com/video/%s' % info['id'],
 127             ie='Dailymotion')