_ Git - youtube-dl/blob - youtube_dl/extractor/d8.py

   1 # encoding: utf-8
   2 import re
   3 import xml.etree.ElementTree
   4
   5 from .common import InfoExtractor
   6 from ..utils import unified_strdate
   7
   8 class D8IE(InfoExtractor):
   9     _VALID_URL = r'https?://www\.d8\.tv/.*?/(?P<path>.*)'
  10     _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/d8/%s'
  11     IE_NAME = u'd8.tv'
  12
  13     _TEST = {
  14         u'url': u'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html',
  15         u'file': u'966289.flv',
  16         u'info_dict': {
  17             u'title': u'Campagne intime - Documentaire exceptionnel',
  18             u'description': u'md5:d2643b799fb190846ae09c61e59a859f',
  19             u'upload_date': u'20131108',
  20         },
  21         u'params': {
  22             u'skip_download': True,
  23         },
  24     }
  25
  26     def _real_extract(self, url):
  27         mobj = re.match(self._VALID_URL, url)
  28         webpage = self._download_webpage(url, mobj.group('path'))
  29         video_id = self._search_regex(r'videoId = "(\d+)";', webpage, u'video id')
  30         info_url = self._VIDEO_INFO_TEMPLATE % video_id
  31         info_page = self._download_webpage(info_url,video_id,
  32                                            u'Downloading video info')
  33
  34         self.report_extraction(video_id)
  35         doc = xml.etree.ElementTree.fromstring(info_page.encode('utf-8'))
  36         video_info = [video for video in doc if video.find('ID').text == video_id][0]
  37         infos = video_info.find('INFOS')
  38         media = video_info.find('MEDIA')
  39         formats = [media.find('VIDEOS/%s' % format)
  40             for format in ['BAS_DEBIT', 'HAUT_DEBIT', 'HD']]
  41         video_url = [format.text for format in formats if format is not None][-1]
  42
  43         return {'id': video_id,
  44                 'title': u'%s - %s' % (infos.find('TITRAGE/TITRE').text,
  45                                        infos.find('TITRAGE/SOUS_TITRE').text),
  46                 'url': video_url,
  47                 'ext': 'flv',
  48                 'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
  49                 'thumbnail': media.find('IMAGES/GRAND').text,
  50                 'description': infos.find('DESCRIPTION').text,
  51                 'view_count': int(infos.find('NB_VUES').text),
  52                 }