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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class VidziIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?vidzi\.tv/(?P<id>\w+)'
   9     _TEST = {
  10         'url': 'http://vidzi.tv/cghql9yq6emu.html',
  11         'md5': '4f16c71ca0c8c8635ab6932b5f3f1660',
  12         'info_dict': {
  13             'id': 'cghql9yq6emu',
  14             'ext': 'mp4',
  15             'title': 'youtube-dl test video  1\\\\2\'3/4<5\\\\6ä7↭',
  16         },
  17     }
  18
  19     def _real_extract(self, url):
  20         video_id = self._match_id(url)
  21
  22         webpage = self._download_webpage(url, video_id)
  23         video_host = self._html_search_regex(
  24             r'id=\'vplayer\'><img src="http://(.*?)/i', webpage,
  25             'video host')
  26         video_hash = self._html_search_regex(
  27             r'\|([a-z0-9]+)\|hls\|type', webpage, 'video_hash')
  28         ext = self._html_search_regex(
  29             r'\|tracks\|([a-z0-9]+)\|', webpage, 'video ext')
  30         video_url = 'http://' + video_host + '/' + video_hash + '/v.' + ext
  31         title = self._html_search_regex(
  32             r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title')
  33
  34         return {
  35             'id': video_id,
  36             'title': title,
  37             'url': video_url,
  38         }