_ Git - youtube-dl/blob - youtube_dl/extractor/pornhd.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   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     _TEST = {
  16         'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
  17         'md5': '956b8ca569f7f4d8ec563e2c41598441',
  18         'info_dict': {
  19             'id': '1962',
  20             'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
  21             'ext': 'mp4',
  22             'title': 'Sierra loves doing laundry',
  23             'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
  24             'thumbnail': 're:^https?://.*\.jpg',
  25             'view_count': int,
  26             'age_limit': 18,
  27         }
  28     }
  29
  30     def _real_extract(self, url):
  31         mobj = re.match(self._VALID_URL, url)
  32         video_id = mobj.group('id')
  33         display_id = mobj.group('display_id')
  34
  35         webpage = self._download_webpage(url, display_id or video_id)
  36
  37         title = self._html_search_regex(
  38             [r'<span[^>]+class=["\']video-name["\'][^>]*>([^<]+)',
  39              r'<title>(.+?) - .*?[Pp]ornHD.*?</title>'], webpage, 'title')
  40         description = self._html_search_regex(
  41             r'<(div|p)[^>]+class="description"[^>]*>(?P<value>[^<]+)</\1',
  42             webpage, 'description', fatal=False, group='value')
  43         view_count = int_or_none(self._html_search_regex(
  44             r'(\d+) views\s*<', webpage, 'view count', fatal=False))
  45         thumbnail = self._search_regex(
  46             r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)
  47
  48         sources = json.loads(js_to_json(self._search_regex(
  49             r"(?s)'sources'\s*:\s*(\{.+?\})\s*\}[;,)]",
  50             webpage, 'sources')))
  51         formats = []
  52         for format_id, video_url in sources.items():
  53             if not video_url:
  54                 continue
  55             height = int_or_none(self._search_regex(
  56                 r'^(\d+)[pP]', format_id, 'height', default=None))
  57             formats.append({
  58                 'url': video_url,
  59                 'format_id': format_id,
  60                 'height': height,
  61             })
  62         self._sort_formats(formats)
  63
  64         return {
  65             'id': video_id,
  66             'display_id': display_id,
  67             'title': title,
  68             'description': description,
  69             'thumbnail': thumbnail,
  70             'view_count': view_count,
  71             'formats': formats,
  72             'age_limit': 18,
  73         }