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

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     find_xpath_attr,
   6     determine_ext,
   7 )
   8
   9 class VideofyMeIE(InfoExtractor):
  10     _VALID_URL = r'https?://(www.videofy.me/.+?|p.videofy.me/v)/(?P<id>\d+)(&|#|$)'
  11     IE_NAME = u'videofy.me'
  12
  13     _TEST = {
  14         u'url': u'http://www.videofy.me/thisisvideofyme/1100701',
  15         u'file':  u'1100701.mp4',
  16         u'md5': u'c77d700bdc16ae2e9f3c26019bd96143',
  17         u'info_dict': {
  18             u'title': u'This is VideofyMe',
  19             u'description': None,
  20             u'uploader': u'VideofyMe',
  21             u'uploader_id': u'thisisvideofyme',
  22         },
  23
  24     }
  25
  26     def _real_extract(self, url):
  27         mobj = re.match(self._VALID_URL, url)
  28         video_id = mobj.group('id')
  29         config = self._download_xml('http://sunshine.videofy.me/?videoId=%s' % video_id,
  30                                             video_id)
  31         video = config.find('video')
  32         sources = video.find('sources')
  33         url_node = next(node for node in [find_xpath_attr(sources, 'source', 'id', 'HQ %s' % key)
  34             for key in ['on', 'av', 'off']] if node is not None)
  35         video_url = url_node.find('url').text
  36
  37         return {'id': video_id,
  38                 'title': video.find('title').text,
  39                 'url': video_url,
  40                 'ext': determine_ext(video_url),
  41                 'thumbnail': video.find('thumb').text,
  42                 'description': video.find('description').text,
  43                 'uploader': config.find('blog/name').text,
  44                 'uploader_id': video.find('identifier').text,
  45                 'view_count': re.search(r'\d+', video.find('views').text).group(),
  46                 }