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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     decode_packed_codes,
   9     js_to_json,
  10     NO_DEFAULT,
  11     PACKED_CODES_RE,
  12 )
  13
  14
  15 class VidziIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?vidzi\.(?:tv|cc)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
  17     _TESTS = [{
  18         'url': 'http://vidzi.tv/cghql9yq6emu.html',
  19         'md5': '4f16c71ca0c8c8635ab6932b5f3f1660',
  20         'info_dict': {
  21             'id': 'cghql9yq6emu',
  22             'ext': 'mp4',
  23             'title': 'youtube-dl test video  1\\\\2\'3/4<5\\\\6ä7↭',
  24         },
  25         'params': {
  26             # m3u8 download
  27             'skip_download': True,
  28         },
  29     }, {
  30         'url': 'http://vidzi.tv/embed-4z2yb0rzphe9-600x338.html',
  31         'skip_download': True,
  32     }, {
  33         'url': 'http://vidzi.cc/cghql9yq6emu.html',
  34         'skip_download': True,
  35     }]
  36
  37     def _real_extract(self, url):
  38         video_id = self._match_id(url)
  39
  40         webpage = self._download_webpage(
  41             'http://vidzi.tv/%s' % video_id, video_id)
  42         title = self._html_search_regex(
  43             r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title')
  44
  45         packed_codes = [mobj.group(0) for mobj in re.finditer(
  46             PACKED_CODES_RE, webpage)]
  47         for num, pc in enumerate(packed_codes, 1):
  48             code = decode_packed_codes(pc).replace('\\\'', '\'')
  49             jwplayer_data = self._parse_json(
  50                 self._search_regex(
  51                     r'setup\(([^)]+)\)', code, 'jwplayer data',
  52                     default=NO_DEFAULT if num == len(packed_codes) else '{}'),
  53                 video_id, transform_source=js_to_json)
  54             if jwplayer_data:
  55                 break
  56
  57         info_dict = self._parse_jwplayer_data(jwplayer_data, video_id, require_title=False)
  58         info_dict['title'] = title
  59
  60         return info_dict