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     ExtractorError,
   8     int_or_none,
   9     js_to_json,
  10 )
  11
  12
  13 class PornHdIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?'
  15     _TESTS = [{
  16         'url': 'http://www.pornhd.com/videos/9864/selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
  17         'md5': 'c8b964b1f0a4b5f7f28ae3a5c9f86ad5',
  18         'info_dict': {
  19             'id': '9864',
  20             'display_id': 'selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
  21             'ext': 'mp4',
  22             'title': 'Restroom selfie masturbation',
  23             'description': 'md5:3748420395e03e31ac96857a8f125b2b',
  24             'thumbnail': r're:^https?://.*\.jpg',
  25             'view_count': int,
  26             'like_count': int,
  27             'age_limit': 18,
  28         }
  29     }, {
  30         # removed video
  31         'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
  32         'md5': '956b8ca569f7f4d8ec563e2c41598441',
  33         'info_dict': {
  34             'id': '1962',
  35             'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
  36             'ext': 'mp4',
  37             'title': 'Sierra loves doing laundry',
  38             'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
  39             'thumbnail': r're:^https?://.*\.jpg',
  40             'view_count': int,
  41             'like_count': int,
  42             'age_limit': 18,
  43         },
  44         'skip': 'Not available anymore',
  45     }]
  46
  47     def _real_extract(self, url):
  48         mobj = re.match(self._VALID_URL, url)
  49         video_id = mobj.group('id')
  50         display_id = mobj.group('display_id')
  51
  52         webpage = self._download_webpage(url, display_id or video_id)
  53
  54         title = self._html_search_regex(
  55             [r'<span[^>]+class=["\']video-name["\'][^>]*>([^<]+)',
  56              r'<title>(.+?) - .*?[Pp]ornHD.*?</title>'], webpage, 'title')
  57
  58         sources = self._parse_json(js_to_json(self._search_regex(
  59             r"(?s)sources'?\s*[:=]\s*(\{.+?\})",
  60             webpage, 'sources', default='{}')), video_id)
  61
  62         if not sources:
  63             message = self._html_search_regex(
  64                 r'(?s)<(div|p)[^>]+class="no-video"[^>]*>(?P<value>.+?)</\1',
  65                 webpage, 'error message', group='value')
  66             raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
  67
  68         formats = []
  69         for format_id, video_url in sources.items():
  70             if not video_url:
  71                 continue
  72             height = int_or_none(self._search_regex(
  73                 r'^(\d+)[pP]', format_id, 'height', default=None))
  74             formats.append({
  75                 'url': video_url,
  76                 'format_id': format_id,
  77                 'height': height,
  78             })
  79         self._sort_formats(formats)
  80
  81         description = self._html_search_regex(
  82             r'<(div|p)[^>]+class="description"[^>]*>(?P<value>[^<]+)</\1',
  83             webpage, 'description', fatal=False, group='value')
  84         view_count = int_or_none(self._html_search_regex(
  85             r'(\d+) views\s*<', webpage, 'view count', fatal=False))
  86         thumbnail = self._search_regex(
  87             r"poster'?\s*:\s*([\"'])(?P<url>(?:(?!\1).)+)\1", webpage,
  88             'thumbnail', fatal=False, group='url')
  89
  90         like_count = int_or_none(self._search_regex(
  91             (r'(\d+)\s*</11[^>]+>(?:&nbsp;|\s)*\blikes',
  92              r'class=["\']save-count["\'][^>]*>\s*(\d+)'),
  93             webpage, 'like count', fatal=False))
  94
  95         return {
  96             'id': video_id,
  97             'display_id': display_id,
  98             'title': title,
  99             'description': description,
 100             'thumbnail': thumbnail,
 101             'view_count': view_count,
 102             'like_count': like_count,
 103             'formats': formats,
 104             'age_limit': 18,
 105         }