yt_dlp/extractor/pornhd.py

   1 from __future__ import unicode_literals
   2
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     determine_ext,
   7     ExtractorError,
   8     int_or_none,
   9     js_to_json,
  10     merge_dicts,
  11     urljoin,
  12 )
  13
  14
  15 class PornHdIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?'
  17     _TESTS = [{
  18         'url': 'http://www.pornhd.com/videos/9864/selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
  19         'md5': '87f1540746c1d32ec7a2305c12b96b25',
  20         'info_dict': {
  21             'id': '9864',
  22             'display_id': 'selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
  23             'ext': 'mp4',
  24             'title': 'Restroom selfie masturbation',
  25             'description': 'md5:3748420395e03e31ac96857a8f125b2b',
  26             'thumbnail': r're:^https?://.*\.jpg',
  27             'view_count': int,
  28             'like_count': int,
  29             'age_limit': 18,
  30         },
  31         'skip': 'HTTP Error 404: Not Found',
  32     }, {
  33         'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
  34         'md5': '1b7b3a40b9d65a8e5b25f7ab9ee6d6de',
  35         'info_dict': {
  36             'id': '1962',
  37             'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
  38             'ext': 'mp4',
  39             'title': 'md5:98c6f8b2d9c229d0f0fde47f61a1a759',
  40             'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
  41             'thumbnail': r're:^https?://.*\.jpg',
  42             'view_count': int,
  43             'like_count': int,
  44             'age_limit': 18,
  45         },
  46     }]
  47
  48     def _real_extract(self, url):
  49         mobj = self._match_valid_url(url)
  50         video_id = mobj.group('id')
  51         display_id = mobj.group('display_id')
  52
  53         webpage = self._download_webpage(url, display_id or video_id)
  54
  55         title = self._html_search_regex(
  56             [r'<span[^>]+class=["\']video-name["\'][^>]*>([^<]+)',
  57              r'<title>(.+?) - .*?[Pp]ornHD.*?</title>'], webpage, 'title')
  58
  59         sources = self._parse_json(js_to_json(self._search_regex(
  60             r"(?s)sources'?\s*[:=]\s*(\{.+?\})",
  61             webpage, 'sources', default='{}')), video_id)
  62
  63         info = {}
  64         if not sources:
  65             entries = self._parse_html5_media_entries(url, webpage, video_id)
  66             if entries:
  67                 info = entries[0]
  68
  69         if not sources and not info:
  70             message = self._html_search_regex(
  71                 r'(?s)<(div|p)[^>]+class="no-video"[^>]*>(?P<value>.+?)</\1',
  72                 webpage, 'error message', group='value')
  73             raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
  74
  75         formats = []
  76         for format_id, video_url in sources.items():
  77             video_url = urljoin(url, video_url)
  78             if not video_url:
  79                 continue
  80             height = int_or_none(self._search_regex(
  81                 r'^(\d+)[pP]', format_id, 'height', default=None))
  82             formats.append({
  83                 'url': video_url,
  84                 'ext': determine_ext(video_url, 'mp4'),
  85                 'format_id': format_id,
  86                 'height': height,
  87             })
  88         if formats:
  89             info['formats'] = formats
  90         self._sort_formats(info['formats'])
  91
  92         description = self._html_search_regex(
  93             (r'(?s)<section[^>]+class=["\']video-description[^>]+>(?P<value>.+?)</section>',
  94              r'<(div|p)[^>]+class="description"[^>]*>(?P<value>[^<]+)</\1'),
  95             webpage, 'description', fatal=False,
  96             group='value') or self._html_search_meta(
  97             'description', webpage, default=None) or self._og_search_description(webpage)
  98         view_count = int_or_none(self._html_search_regex(
  99             r'(\d+) views\s*<', webpage, 'view count', fatal=False))
 100         thumbnail = self._search_regex(
 101             r"poster'?\s*:\s*([\"'])(?P<url>(?:(?!\1).)+)\1", webpage,
 102             'thumbnail', default=None, group='url')
 103
 104         like_count = int_or_none(self._search_regex(
 105             (r'(\d+)</span>\s*likes',
 106              r'(\d+)\s*</11[^>]+>(?:&nbsp;|\s)*\blikes',
 107              r'class=["\']save-count["\'][^>]*>\s*(\d+)'),
 108             webpage, 'like count', fatal=False))
 109
 110         return merge_dicts(info, {
 111             'id': video_id,
 112             'display_id': display_id,
 113             'title': title,
 114             'description': description,
 115             'thumbnail': thumbnail,
 116             'view_count': view_count,
 117             'like_count': like_count,
 118             'formats': formats,
 119             'age_limit': 18,
 120         })