yt_dlp/extractor/youjizz.py

   1 from __future__ import unicode_literals
   2
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     determine_ext,
   7     int_or_none,
   8     parse_duration,
   9     url_or_none,
  10 )
  11
  12
  13 class YouJizzIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:\w+\.)?youjizz\.com/videos/(?:[^/#?]*-(?P<id>\d+)\.html|embed/(?P<embed_id>\d+))'
  15     _TESTS = [{
  16         'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
  17         'md5': 'b1e1dfaa8bb9537d8b84eeda9cf4acf4',
  18         'info_dict': {
  19             'id': '2189178',
  20             'ext': 'mp4',
  21             'title': 'Zeichentrick 1',
  22             'age_limit': 18,
  23             'duration': 2874,
  24         }
  25     }, {
  26         'url': 'http://www.youjizz.com/videos/-2189178.html',
  27         'only_matching': True,
  28     }, {
  29         'url': 'https://www.youjizz.com/videos/embed/31991001',
  30         'only_matching': True,
  31     }]
  32
  33     def _real_extract(self, url):
  34         mobj = self._match_valid_url(url)
  35         video_id = mobj.group('id') or mobj.group('embed_id')
  36
  37         webpage = self._download_webpage(url, video_id)
  38
  39         title = self._html_search_regex(
  40             r'<title>(.+?)</title>', webpage, 'title')
  41
  42         formats = []
  43
  44         encodings = self._parse_json(
  45             self._search_regex(
  46                 r'[Ee]ncodings\s*=\s*(\[.+?\]);\n', webpage, 'encodings',
  47                 default='[]'),
  48             video_id, fatal=False)
  49         for encoding in encodings:
  50             if not isinstance(encoding, dict):
  51                 continue
  52             format_url = url_or_none(encoding.get('filename'))
  53             if not format_url:
  54                 continue
  55             if determine_ext(format_url) == 'm3u8':
  56                 formats.extend(self._extract_m3u8_formats(
  57                     format_url, video_id, 'mp4', entry_protocol='m3u8_native',
  58                     m3u8_id='hls', fatal=False))
  59             else:
  60                 format_id = encoding.get('name') or encoding.get('quality')
  61                 height = int_or_none(self._search_regex(
  62                     r'^(\d+)[pP]', format_id, 'height', default=None))
  63                 formats.append({
  64                     'url': format_url,
  65                     'format_id': format_id,
  66                     'height': height,
  67                 })
  68
  69         if formats:
  70             info_dict = {
  71                 'formats': formats,
  72             }
  73         else:
  74             # YouJizz's HTML5 player has invalid HTML
  75             webpage = webpage.replace('"controls', '" controls')
  76             info_dict = self._parse_html5_media_entries(
  77                 url, webpage, video_id)[0]
  78
  79         duration = parse_duration(self._search_regex(
  80             r'<strong>Runtime:</strong>([^<]+)', webpage, 'duration',
  81             default=None))
  82         uploader = self._search_regex(
  83             r'<strong>Uploaded By:.*?<a[^>]*>([^<]+)', webpage, 'uploader',
  84             default=None)
  85
  86         info_dict.update({
  87             'id': video_id,
  88             'title': title,
  89             'age_limit': self._rta_search(webpage),
  90             'duration': duration,
  91             'uploader': uploader,
  92         })
  93
  94         return info_dict