yt_dlp/extractor/vodlocker.py

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