yt_dlp/extractor/youjizz.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     determine_ext,
   4     int_or_none,
   5     parse_duration,
   6     url_or_none,
   7 )
   8
   9
  10 class YouJizzIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:\w+\.)?youjizz\.com/videos/(?:[^/#?]*-(?P<id>\d+)\.html|embed/(?P<embed_id>\d+))'
  12     _TESTS = [{
  13         'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
  14         'md5': 'b1e1dfaa8bb9537d8b84eeda9cf4acf4',
  15         'info_dict': {
  16             'id': '2189178',
  17             'ext': 'mp4',
  18             'title': 'Zeichentrick 1',
  19             'age_limit': 18,
  20             'duration': 2874,
  21         },
  22     }, {
  23         'url': 'http://www.youjizz.com/videos/-2189178.html',
  24         'only_matching': True,
  25     }, {
  26         'url': 'https://www.youjizz.com/videos/embed/31991001',
  27         'only_matching': True,
  28     }]
  29
  30     def _real_extract(self, url):
  31         mobj = self._match_valid_url(url)
  32         video_id = mobj.group('id') or mobj.group('embed_id')
  33
  34         webpage = self._download_webpage(url, video_id)
  35
  36         title = self._html_extract_title(webpage)
  37
  38         formats = []
  39
  40         encodings = self._parse_json(
  41             self._search_regex(
  42                 r'[Ee]ncodings\s*=\s*(\[.+?\]);\n', webpage, 'encodings',
  43                 default='[]'),
  44             video_id, fatal=False)
  45         for encoding in encodings:
  46             if not isinstance(encoding, dict):
  47                 continue
  48             format_url = url_or_none(encoding.get('filename'))
  49             if not format_url:
  50                 continue
  51             if determine_ext(format_url) == 'm3u8':
  52                 formats.extend(self._extract_m3u8_formats(
  53                     format_url, video_id, 'mp4', entry_protocol='m3u8_native',
  54                     m3u8_id='hls', fatal=False))
  55             else:
  56                 format_id = encoding.get('name') or encoding.get('quality')
  57                 height = int_or_none(self._search_regex(
  58                     r'^(\d+)[pP]', format_id, 'height', default=None))
  59                 formats.append({
  60                     'url': format_url,
  61                     'format_id': format_id,
  62                     'height': height,
  63                 })
  64
  65         if formats:
  66             info_dict = {
  67                 'formats': formats,
  68             }
  69         else:
  70             # YouJizz's HTML5 player has invalid HTML
  71             webpage = webpage.replace('"controls', '" controls')
  72             info_dict = self._parse_html5_media_entries(
  73                 url, webpage, video_id)[0]
  74
  75         duration = parse_duration(self._search_regex(
  76             r'<strong>Runtime:</strong>([^<]+)', webpage, 'duration',
  77             default=None))
  78         uploader = self._search_regex(
  79             r'<strong>Uploaded By:.*?<a[^>]*>([^<]+)', webpage, 'uploader',
  80             default=None)
  81
  82         info_dict.update({
  83             'id': video_id,
  84             'title': title,
  85             'age_limit': self._rta_search(webpage),
  86             'duration': duration,
  87             'uploader': uploader,
  88         })
  89
  90         return info_dict