youtube_dl/extractor/francetv.py

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