_ 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 (
   7     ExtractorError,
   8     sanitized_Request,
   9 )
  10
  11
  12 class VodlockerIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
  14
  15     _TESTS = [{
  16         'url': 'http://vodlocker.com/e8wvyzz4sl42',
  17         'md5': 'ce0c2d18fa0735f1bd91b69b0e54aacf',
  18         'info_dict': {
  19             'id': 'e8wvyzz4sl42',
  20             'ext': 'mp4',
  21             'title': 'Germany vs Brazil',
  22             'thumbnail': 're:http://.*\.jpg',
  23         },
  24     }]
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28         webpage = self._download_webpage(url, video_id)
  29
  30         if any(p in webpage for p in (
  31                 '>THIS FILE WAS DELETED<',
  32                 '>File Not Found<',
  33                 'The file you were looking for could not be found, sorry for any inconvenience.<')):
  34             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  35
  36         fields = self._hidden_inputs(webpage)
  37
  38         if fields['op'] == 'download1':
  39             self._sleep(3, video_id)  # they do detect when requests happen too fast!
  40             post = compat_urllib_parse.urlencode(fields)
  41             req = sanitized_Request(url, post)
  42             req.add_header('Content-type', 'application/x-www-form-urlencoded')
  43             webpage = self._download_webpage(
  44                 req, video_id, 'Downloading video page')
  45
  46         title = self._search_regex(
  47             r'id="file_title".*?>\s*(.*?)\s*<(?:br|span)', webpage, 'title')
  48         thumbnail = self._search_regex(
  49             r'image:\s*"(http[^\"]+)",', webpage, 'thumbnail')
  50         url = self._search_regex(
  51             r'file:\s*"(http[^\"]+)",', webpage, 'file url')
  52
  53         formats = [{
  54             'format_id': 'sd',
  55             'url': url,
  56         }]
  57
  58         return {
  59             'id': video_id,
  60             'title': title,
  61             'thumbnail': thumbnail,
  62             'formats': formats,
  63         }