youtube_dl/extractor/vodlocker.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7     NO_DEFAULT,
   8     sanitized_Request,
   9     urlencode_postdata,
  10 )
  11
  12
  13 class VodlockerIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?vodlocker\.(?:com|city)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
  15
  16     _TESTS = [{
  17         'url': 'http://vodlocker.com/e8wvyzz4sl42',
  18         'md5': 'ce0c2d18fa0735f1bd91b69b0e54aacf',
  19         'info_dict': {
  20             'id': 'e8wvyzz4sl42',
  21             'ext': 'mp4',
  22             'title': 'Germany vs Brazil',
  23             'thumbnail': r're:http://.*\.jpg',
  24         },
  25     }]
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29         webpage = self._download_webpage(url, video_id)
  30
  31         if any(p in webpage for p in (
  32                 '>THIS FILE WAS DELETED<',
  33                 '>File Not Found<',
  34                 'The file you were looking for could not be found, sorry for any inconvenience.<',
  35                 '>The file was removed')):
  36             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  37
  38         fields = self._hidden_inputs(webpage)
  39
  40         if fields['op'] == 'download1':
  41             self._sleep(3, video_id)  # they do detect when requests happen too fast!
  42             post = urlencode_postdata(fields)
  43             req = sanitized_Request(url, post)
  44             req.add_header('Content-type', 'application/x-www-form-urlencoded')
  45             webpage = self._download_webpage(
  46                 req, video_id, 'Downloading video page')
  47
  48         def extract_file_url(html, default=NO_DEFAULT):
  49             return self._search_regex(
  50                 r'file:\s*"(http[^\"]+)",', html, 'file url', default=default)
  51
  52         video_url = extract_file_url(webpage, default=None)
  53
  54         if not video_url:
  55             embed_url = self._search_regex(
  56                 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?vodlocker\.(?:com|city)/embed-.+?)\1',
  57                 webpage, 'embed url', group='url')
  58             embed_webpage = self._download_webpage(
  59                 embed_url, video_id, 'Downloading embed webpage')
  60             video_url = extract_file_url(embed_webpage)
  61             thumbnail_webpage = embed_webpage
  62         else:
  63             thumbnail_webpage = webpage
  64
  65         title = self._search_regex(
  66             r'id="file_title".*?>\s*(.*?)\s*<(?:br|span)', webpage, 'title')
  67         thumbnail = self._search_regex(
  68             r'image:\s*"(http[^\"]+)",', thumbnail_webpage, 'thumbnail', fatal=False)
  69
  70         formats = [{
  71             'format_id': 'sd',
  72             'url': video_url,
  73         }]
  74
  75         return {
  76             'id': video_id,
  77             'title': title,
  78             'thumbnail': thumbnail,
  79             'formats': formats,
  80         }