yt_dlp/extractor/pornhd.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     determine_ext,
   4     ExtractorError,
   5     int_or_none,
   6     js_to_json,
   7     merge_dicts,
   8     urljoin,
   9 )
  10
  11
  12 class PornHdIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?'
  14     _TESTS = [{
  15         'url': 'http://www.pornhd.com/videos/9864/selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
  16         'md5': '87f1540746c1d32ec7a2305c12b96b25',
  17         'info_dict': {
  18             'id': '9864',
  19             'display_id': 'selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
  20             'ext': 'mp4',
  21             'title': 'Restroom selfie masturbation',
  22             'description': 'md5:3748420395e03e31ac96857a8f125b2b',
  23             'thumbnail': r're:^https?://.*\.jpg',
  24             'view_count': int,
  25             'like_count': int,
  26             'age_limit': 18,
  27         },
  28         'skip': 'HTTP Error 404: Not Found',
  29     }, {
  30         'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
  31         'md5': '1b7b3a40b9d65a8e5b25f7ab9ee6d6de',
  32         'info_dict': {
  33             'id': '1962',
  34             'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
  35             'ext': 'mp4',
  36             'title': 'md5:98c6f8b2d9c229d0f0fde47f61a1a759',
  37             'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
  38             'thumbnail': r're:^https?://.*\.jpg',
  39             'view_count': int,
  40             'like_count': int,
  41             'age_limit': 18,
  42         },
  43     }]
  44
  45     def _real_extract(self, url):
  46         mobj = self._match_valid_url(url)
  47         video_id = mobj.group('id')
  48         display_id = mobj.group('display_id')
  49
  50         webpage = self._download_webpage(url, display_id or video_id)
  51
  52         title = self._html_search_regex(
  53             [r'<span[^>]+class=["\']video-name["\'][^>]*>([^<]+)',
  54              r'<title>(.+?) - .*?[Pp]ornHD.*?</title>'], webpage, 'title')
  55
  56         sources = self._parse_json(js_to_json(self._search_regex(
  57             r"(?s)sources'?\s*[:=]\s*(\{.+?\})",
  58             webpage, 'sources', default='{}')), video_id)
  59
  60         info = {}
  61         if not sources:
  62             entries = self._parse_html5_media_entries(url, webpage, video_id)
  63             if entries:
  64                 info = entries[0]
  65
  66         if not sources and not info:
  67             message = self._html_search_regex(
  68                 r'(?s)<(div|p)[^>]+class="no-video"[^>]*>(?P<value>.+?)</\1',
  69                 webpage, 'error message', group='value')
  70             raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
  71
  72         formats = []
  73         for format_id, video_url in sources.items():
  74             video_url = urljoin(url, video_url)
  75             if not video_url:
  76                 continue
  77             height = int_or_none(self._search_regex(
  78                 r'^(\d+)[pP]', format_id, 'height', default=None))
  79             formats.append({
  80                 'url': video_url,
  81                 'ext': determine_ext(video_url, 'mp4'),
  82                 'format_id': format_id,
  83                 'height': height,
  84             })
  85         if formats:
  86             info['formats'] = formats
  87
  88         description = self._html_search_regex(
  89             (r'(?s)<section[^>]+class=["\']video-description[^>]+>(?P<value>.+?)</section>',
  90              r'<(div|p)[^>]+class="description"[^>]*>(?P<value>[^<]+)</\1'),
  91             webpage, 'description', fatal=False,
  92             group='value') or self._html_search_meta(
  93             'description', webpage, default=None) or self._og_search_description(webpage)
  94         view_count = int_or_none(self._html_search_regex(
  95             r'(\d+) views\s*<', webpage, 'view count', fatal=False))
  96         thumbnail = self._search_regex(
  97             r"poster'?\s*:\s*([\"'])(?P<url>(?:(?!\1).)+)\1", webpage,
  98             'thumbnail', default=None, group='url')
  99
 100         like_count = int_or_none(self._search_regex(
 101             (r'(\d+)</span>\s*likes',
 102              r'(\d+)\s*</11[^>]+>(?:&nbsp;|\s)*\blikes',
 103              r'class=["\']save-count["\'][^>]*>\s*(\d+)'),
 104             webpage, 'like count', fatal=False))
 105
 106         return merge_dicts(info, {
 107             'id': video_id,
 108             'display_id': display_id,
 109             'title': title,
 110             'description': description,
 111             'thumbnail': thumbnail,
 112             'view_count': view_count,
 113             'like_count': like_count,
 114             'formats': formats,
 115             'age_limit': 18,
 116         })