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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .jwplatform import JWPlatformBaseIE
   5 from ..utils import (
   6     decode_packed_codes,
   7     js_to_json,
   8 )
   9
  10
  11 class VidziIE(JWPlatformBaseIE):
  12     _VALID_URL = r'https?://(?:www\.)?vidzi\.tv/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
  13     _TESTS = [{
  14         'url': 'http://vidzi.tv/cghql9yq6emu.html',
  15         'md5': '4f16c71ca0c8c8635ab6932b5f3f1660',
  16         'info_dict': {
  17             'id': 'cghql9yq6emu',
  18             'ext': 'mp4',
  19             'title': 'youtube-dl test video  1\\\\2\'3/4<5\\\\6ä7↭',
  20         },
  21         'params': {
  22             # m3u8 download
  23             'skip_download': True,
  24         },
  25     }, {
  26         'url': 'http://vidzi.tv/embed-4z2yb0rzphe9-600x338.html',
  27         'skip_download': True,
  28     }]
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32
  33         webpage = self._download_webpage(
  34             'http://vidzi.tv/%s' % video_id, video_id)
  35         title = self._html_search_regex(
  36             r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title')
  37
  38         code = decode_packed_codes(webpage).replace('\\\'', '\'')
  39         jwplayer_data = self._parse_json(
  40             self._search_regex(r'setup\(([^)]+)\)', code, 'jwplayer data'),
  41             video_id, transform_source=js_to_json)
  42
  43         info_dict = self._parse_jwplayer_data(jwplayer_data, video_id, require_title=False)
  44         info_dict['title'] = title
  45
  46         return info_dict