youtube_dl/extractor/pornhd.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     determine_ext,
   8     ExtractorError,
   9     int_or_none,
  10     js_to_json,
  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     }, {
  32         # removed video
  33         'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
  34         'md5': '956b8ca569f7f4d8ec563e2c41598441',
  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': 'Sierra loves doing laundry',
  40             'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
  41             'thumbnail': r're:^https?://.*\.jpg',
  42             'view_count': int,
  43             'like_count': int,
  44             'age_limit': 18,
  45         },
  46         'skip': 'Not available anymore',
  47     }]
  48
  49     def _real_extract(self, url):
  50         mobj = re.match(self._VALID_URL, url)
  51         video_id = mobj.group('id')
  52         display_id = mobj.group('display_id')
  53
  54         webpage = self._download_webpage(url, display_id or video_id)
  55
  56         title = self._html_search_regex(
  57             [r'<span[^>]+class=["\']video-name["\'][^>]*>([^<]+)',
  58              r'<title>(.+?) - .*?[Pp]ornHD.*?</title>'], webpage, 'title')
  59
  60         sources = self._parse_json(js_to_json(self._search_regex(
  61             r"(?s)sources'?\s*[:=]\s*(\{.+?\})",
  62             webpage, 'sources', default='{}')), video_id)
  63
  64         if not sources:
  65             message = self._html_search_regex(
  66                 r'(?s)<(div|p)[^>]+class="no-video"[^>]*>(?P<value>.+?)</\1',
  67                 webpage, 'error message', group='value')
  68             raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
  69
  70         formats = []
  71         for format_id, video_url in sources.items():
  72             video_url = urljoin(url, video_url)
  73             if not video_url:
  74                 continue
  75             height = int_or_none(self._search_regex(
  76                 r'^(\d+)[pP]', format_id, 'height', default=None))
  77             formats.append({
  78                 'url': video_url,
  79                 'ext': determine_ext(video_url, 'mp4'),
  80                 'format_id': format_id,
  81                 'height': height,
  82             })
  83         self._sort_formats(formats)
  84
  85         description = self._html_search_regex(
  86             r'<(div|p)[^>]+class="description"[^>]*>(?P<value>[^<]+)</\1',
  87             webpage, 'description', fatal=False, group='value')
  88         view_count = int_or_none(self._html_search_regex(
  89             r'(\d+) views\s*<', webpage, 'view count', fatal=False))
  90         thumbnail = self._search_regex(
  91             r"poster'?\s*:\s*([\"'])(?P<url>(?:(?!\1).)+)\1", webpage,
  92             'thumbnail', fatal=False, group='url')
  93
  94         like_count = int_or_none(self._search_regex(
  95             (r'(\d+)\s*</11[^>]+>(?:&nbsp;|\s)*\blikes',
  96              r'class=["\']save-count["\'][^>]*>\s*(\d+)'),
  97             webpage, 'like count', fatal=False))
  98
  99         return {
 100             'id': video_id,
 101             'display_id': display_id,
 102             'title': title,
 103             'description': description,
 104             'thumbnail': thumbnail,
 105             'view_count': view_count,
 106             'like_count': like_count,
 107             'formats': formats,
 108             'age_limit': 18,
 109         }