Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/teamcoco.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6 )
   7
   8
   9 class TeamcocoIE(InfoExtractor):
  10     _VALID_URL = r'http://teamcoco\.com/video/(?P<url_title>.*)'
  11
  12     def _real_extract(self, url):
  13         mobj = re.match(self._VALID_URL, url)
  14         if mobj is None:
  15             raise ExtractorError(u'Invalid URL: %s' % url)
  16         url_title = mobj.group('url_title')
  17         webpage = self._download_webpage(url, url_title)
  18
  19         video_id = self._html_search_regex(r'<article class="video" data-id="(\d+?)"',
  20             webpage, u'video id')
  21
  22         self.report_extraction(video_id)
  23
  24         video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
  25             webpage, u'title')
  26
  27         thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)"',
  28             webpage, u'thumbnail', fatal=False)
  29
  30         video_description = self._html_search_regex(r'<meta property="og:description" content="(.*?)"',
  31             webpage, u'description', fatal=False)
  32
  33         data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
  34         data = self._download_webpage(data_url, video_id, 'Downloading data webpage')
  35
  36         video_url = self._html_search_regex(r'<file type="high".*?>(.*?)</file>',
  37             data, u'video URL')
  38
  39         return [{
  40             'id':          video_id,
  41             'url':         video_url,
  42             'ext':         'mp4',
  43             'title':       video_title,
  44             'thumbnail':   thumbnail,
  45             'description': video_description,
  46         }]