yt_dlp/extractor/hellporno.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     int_or_none,
   6     merge_dicts,
   7     remove_end,
   8     unified_timestamp,
   9 )
  10
  11
  12 class HellPornoIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?hellporno\.(?:com/videos|net/v)/(?P<id>[^/]+)'
  14     _TESTS = [{
  15         'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
  16         'md5': 'f0a46ebc0bed0c72ae8fe4629f7de5f3',
  17         'info_dict': {
  18             'id': '149116',
  19             'display_id': 'dixie-is-posing-with-naked-ass-very-erotic',
  20             'ext': 'mp4',
  21             'title': 'Dixie is posing with naked ass very erotic',
  22             'description': 'md5:9a72922749354edb1c4b6e540ad3d215',
  23             'categories': list,
  24             'thumbnail': r're:https?://.*\.jpg$',
  25             'duration': 240,
  26             'timestamp': 1398762720,
  27             'upload_date': '20140429',
  28             'view_count': int,
  29             'age_limit': 18,
  30         },
  31     }, {
  32         'url': 'http://hellporno.net/v/186271/',
  33         'only_matching': True,
  34     }]
  35
  36     def _real_extract(self, url):
  37         display_id = self._match_id(url)
  38
  39         webpage = self._download_webpage(url, display_id)
  40
  41         title = remove_end(self._html_extract_title(webpage), ' - Hell Porno')
  42
  43         info = self._parse_html5_media_entries(url, webpage, display_id)[0]
  44         self._sort_formats(info['formats'])
  45
  46         video_id = self._search_regex(
  47             (r'chs_object\s*=\s*["\'](\d+)',
  48              r'params\[["\']video_id["\']\]\s*=\s*(\d+)'), webpage, 'video id',
  49             default=display_id)
  50         description = self._search_regex(
  51             r'class=["\']desc_video_view_v2[^>]+>([^<]+)', webpage,
  52             'description', fatal=False)
  53         categories = [
  54             c.strip()
  55             for c in self._html_search_meta(
  56                 'keywords', webpage, 'categories', default='').split(',')
  57             if c.strip()]
  58         duration = int_or_none(self._og_search_property(
  59             'video:duration', webpage, fatal=False))
  60         timestamp = unified_timestamp(self._og_search_property(
  61             'video:release_date', webpage, fatal=False))
  62         view_count = int_or_none(self._search_regex(
  63             r'>Views\s+(\d+)', webpage, 'view count', fatal=False))
  64
  65         return merge_dicts(info, {
  66             'id': video_id,
  67             'display_id': display_id,
  68             'title': title,
  69             'description': description,
  70             'categories': categories,
  71             'duration': duration,
  72             'timestamp': timestamp,
  73             'view_count': view_count,
  74             'age_limit': 18,
  75         })