yt_dlp/extractor/pornovoisines.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     float_or_none,
   5     unified_strdate,
   6 )
   7
   8
   9 class PornoVoisinesIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?pornovoisines\.com/videos/show/(?P<id>\d+)/(?P<display_id>[^/.]+)'
  11
  12     _TEST = {
  13         'url': 'http://www.pornovoisines.com/videos/show/919/recherche-appartement.html',
  14         'md5': '6f8aca6a058592ab49fe701c8ba8317b',
  15         'info_dict': {
  16             'id': '919',
  17             'display_id': 'recherche-appartement',
  18             'ext': 'mp4',
  19             'title': 'Recherche appartement',
  20             'description': 'md5:fe10cb92ae2dd3ed94bb4080d11ff493',
  21             'thumbnail': r're:^https?://.*\.jpg$',
  22             'upload_date': '20140925',
  23             'duration': 120,
  24             'view_count': int,
  25             'average_rating': float,
  26             'categories': ['Débutante', 'Débutantes', 'Scénario', 'Sodomie'],
  27             'age_limit': 18,
  28             'subtitles': {
  29                 'fr': [{
  30                     'ext': 'vtt',
  31                 }]
  32             },
  33         }
  34     }
  35
  36     def _real_extract(self, url):
  37         mobj = self._match_valid_url(url)
  38         video_id = mobj.group('id')
  39         display_id = mobj.group('display_id')
  40
  41         settings_url = self._download_json(
  42             'http://www.pornovoisines.com/api/video/%s/getsettingsurl/' % video_id,
  43             video_id, note='Getting settings URL')['video_settings_url']
  44         settings = self._download_json(settings_url, video_id)['data']
  45
  46         formats = []
  47         for kind, data in settings['variants'].items():
  48             if kind == 'HLS':
  49                 formats.extend(self._extract_m3u8_formats(
  50                     data, video_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id='hls'))
  51             elif kind == 'MP4':
  52                 for item in data:
  53                     formats.append({
  54                         'url': item['url'],
  55                         'height': item.get('height'),
  56                         'bitrate': item.get('bitrate'),
  57                     })
  58
  59         webpage = self._download_webpage(url, video_id)
  60
  61         title = self._og_search_title(webpage)
  62         description = self._og_search_description(webpage)
  63
  64         # The webpage has a bug - there's no space between "thumb" and src=
  65         thumbnail = self._html_search_regex(
  66             r'<img[^>]+class=([\'"])thumb\1[^>]*src=([\'"])(?P<url>[^"]+)\2',
  67             webpage, 'thumbnail', fatal=False, group='url')
  68
  69         upload_date = unified_strdate(self._search_regex(
  70             r'Le\s*<b>([\d/]+)', webpage, 'upload date', fatal=False))
  71         duration = settings.get('main', {}).get('duration')
  72         view_count = int_or_none(self._search_regex(
  73             r'(\d+) vues', webpage, 'view count', fatal=False))
  74         average_rating = self._search_regex(
  75             r'Note\s*:\s*(\d+(?:,\d+)?)', webpage, 'average rating', fatal=False)
  76         if average_rating:
  77             average_rating = float_or_none(average_rating.replace(',', '.'))
  78
  79         categories = self._html_search_regex(
  80             r'(?s)Catégories\s*:\s*<b>(.+?)</b>', webpage, 'categories', fatal=False)
  81         if categories:
  82             categories = [category.strip() for category in categories.split(',')]
  83
  84         subtitles = {'fr': [{
  85             'url': subtitle,
  86         } for subtitle in settings.get('main', {}).get('vtt_tracks', {}).values()]}
  87
  88         return {
  89             'id': video_id,
  90             'display_id': display_id,
  91             'formats': formats,
  92             'title': title,
  93             'description': description,
  94             'thumbnail': thumbnail,
  95             'upload_date': upload_date,
  96             'duration': duration,
  97             'view_count': view_count,
  98             'average_rating': average_rating,
  99             'categories': categories,
 100             'age_limit': 18,
 101             'subtitles': subtitles,
 102         }