_ Git - youtube-dl/blob - youtube_dl/extractor/vodlocker.py

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_urllib_parse
   6 from ..utils import sanitized_Request
   7
   8
   9 class VodlockerIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
  11
  12     _TESTS = [{
  13         'url': 'http://vodlocker.com/e8wvyzz4sl42',
  14         'md5': 'ce0c2d18fa0735f1bd91b69b0e54aacf',
  15         'info_dict': {
  16             'id': 'e8wvyzz4sl42',
  17             'ext': 'mp4',
  18             'title': 'Germany vs Brazil',
  19             'thumbnail': 're:http://.*\.jpg',
  20         },
  21     }]
  22
  23     def _real_extract(self, url):
  24         video_id = self._match_id(url)
  25         webpage = self._download_webpage(url, video_id)
  26
  27         fields = self._hidden_inputs(webpage)
  28
  29         if fields['op'] == 'download1':
  30             self._sleep(3, video_id)  # they do detect when requests happen too fast!
  31             post = compat_urllib_parse.urlencode(fields)
  32             req = sanitized_Request(url, post)
  33             req.add_header('Content-type', 'application/x-www-form-urlencoded')
  34             webpage = self._download_webpage(
  35                 req, video_id, 'Downloading video page')
  36
  37         title = self._search_regex(
  38             r'id="file_title".*?>\s*(.*?)\s*<(?:br|span)', webpage, 'title')
  39         thumbnail = self._search_regex(
  40             r'image:\s*"(http[^\"]+)",', webpage, 'thumbnail')
  41         url = self._search_regex(
  42             r'file:\s*"(http[^\"]+)",', webpage, 'file url')
  43
  44         formats = [{
  45             'format_id': 'sd',
  46             'url': url,
  47         }]
  48
  49         return {
  50             'id': video_id,
  51             'title': title,
  52             'thumbnail': thumbnail,
  53             'formats': formats,
  54         }