yt_dlp/extractor/watchindianporn.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import parse_duration
   5
   6
   7 class WatchIndianPornIE(InfoExtractor):
   8     IE_DESC = 'Watch Indian Porn'
   9     _VALID_URL = r'https?://(?:www\.)?watchindianporn\.net/(?:[^/]+/)*video/(?P<display_id>[^/]+)-(?P<id>[a-zA-Z0-9]+)\.html'
  10     _TEST = {
  11         'url': 'http://www.watchindianporn.net/video/hot-milf-from-kerala-shows-off-her-gorgeous-large-breasts-on-camera-RZa2avywNPa.html',
  12         'md5': '249589a164dde236ec65832bfce17440',
  13         'info_dict': {
  14             'id': 'RZa2avywNPa',
  15             'display_id': 'hot-milf-from-kerala-shows-off-her-gorgeous-large-breasts-on-camera',
  16             'ext': 'mp4',
  17             'title': 'Hot milf from kerala shows off her gorgeous large breasts on camera',
  18             'thumbnail': r're:^https?://.*\.jpg$',
  19             'duration': 226,
  20             'view_count': int,
  21             'categories': list,
  22             'age_limit': 18,
  23         }
  24     }
  25
  26     def _real_extract(self, url):
  27         mobj = self._match_valid_url(url)
  28         video_id = mobj.group('id')
  29         display_id = mobj.group('display_id')
  30
  31         webpage = self._download_webpage(url, display_id)
  32
  33         info_dict = self._parse_html5_media_entries(url, webpage, video_id)[0]
  34
  35         title = self._html_search_regex((
  36             r'<title>(.+?)\s*-\s*Indian\s+Porn</title>',
  37             r'<h4>(.+?)</h4>'
  38         ), webpage, 'title')
  39
  40         duration = parse_duration(self._search_regex(
  41             r'Time:\s*<strong>\s*(.+?)\s*</strong>',
  42             webpage, 'duration', fatal=False))
  43
  44         view_count = int(self._search_regex(
  45             r'(?s)Time:\s*<strong>.*?</strong>.*?<strong>\s*(\d+)\s*</strong>',
  46             webpage, 'view count', fatal=False))
  47
  48         categories = re.findall(
  49             r'<a[^>]+class=[\'"]categories[\'"][^>]*>\s*([^<]+)\s*</a>',
  50             webpage)
  51
  52         info_dict.update({
  53             'id': video_id,
  54             'display_id': display_id,
  55             'http_headers': {
  56                 'Referer': url,
  57             },
  58             'title': title,
  59             'duration': duration,
  60             'view_count': view_count,
  61             'categories': categories,
  62             'age_limit': 18,
  63         })
  64
  65         return info_dict