yt_dlp/extractor/vodlocker.py

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