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

   1 # encoding: utf-8
   2 import re
   3 import xml.etree.ElementTree
   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         xml_desc = self._download_webpage(
  14             'http://www.francetvinfo.fr/appftv/webservices/video/'
  15             'getInfosOeuvre.php?id-diffusion='
  16             + video_id, video_id, 'Downloading XML config')
  17         info = xml.etree.ElementTree.fromstring(xml_desc.encode('utf-8'))
  18
  19         manifest_url = info.find('videos/video/url').text
  20         video_url = manifest_url.replace('manifest.f4m', 'index_2_av.m3u8')
  21         video_url = video_url.replace('/z/', '/i/')
  22         thumbnail_path = info.find('image').text
  23
  24         return {'id': video_id,
  25                 'ext': 'mp4',
  26                 'url': video_url,
  27                 'title': info.find('titre').text,
  28                 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path),
  29                 'description': info.find('synopsis').text,
  30                 }
  31
  32
  33 class PluzzIE(FranceTVBaseInfoExtractor):
  34     IE_NAME = u'pluzz.francetv.fr'
  35     _VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'
  36
  37     _TEST = {
  38         u'url': u'http://pluzz.francetv.fr/videos/allo_rufo_saison5_,88439064.html',
  39         u'file': u'88439064.mp4',
  40         u'info_dict': {
  41             u'title': u'Allô Rufo',
  42             u'description': u'md5:d909f1ebdf963814b65772aea250400e',
  43         },
  44         u'params': {
  45             u'skip_download': True,
  46         },
  47     }
  48
  49     def _real_extract(self, url):
  50         title = re.match(self._VALID_URL, url).group(1)
  51         webpage = self._download_webpage(url, title)
  52         video_id = self._search_regex(
  53             r'data-diffusion="(\d+)"', webpage, 'ID')
  54         return self._extract_video(video_id)
  55
  56
  57 class FranceTvInfoIE(FranceTVBaseInfoExtractor):
  58     IE_NAME = u'francetvinfo.fr'
  59     _VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P<title>.+).html'
  60
  61     _TEST = {
  62         u'url': u'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
  63         u'file': u'84981923.mp4',
  64         u'info_dict': {
  65             u'title': u'Soir 3',
  66         },
  67         u'params': {
  68             u'skip_download': True,
  69         },
  70     }
  71
  72     def _real_extract(self, url):
  73         mobj = re.match(self._VALID_URL, url)
  74         page_title = mobj.group('title')
  75         webpage = self._download_webpage(url, page_title)
  76         video_id = self._search_regex(r'id-video=(\d+?)"', webpage, u'video id')
  77         return self._extract_video(video_id)