youtube_dl/extractor/hornbunny.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import int_or_none
   8
   9 class HornBunnyIE(InfoExtractor):
  10     _VALID_URL = r'http?://(?:www\.)?hornbunny\.com/videos/(?P<title_dash>[a-z-]+)-(?P<id>\d+)\.html'
  11     _TEST = {
  12         'url': 'http://hornbunny.com/videos/panty-slut-jerk-off-instruction-5227.html',
  13         'md5': '95e40865aedd08eff60272b704852ad7',
  14         'info_dict': {
  15             'id': '5227',
  16             'ext': 'flv',
  17             'title': 'panty slut jerk off instruction',
  18             'duration': 550
  19         }
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = re.match(self._VALID_URL, url)
  24         video_id = mobj.group('id')
  25
  26         webpage = self._download_webpage(url, video_id)
  27         title = self._html_search_regex(r'class="title">(.*?)</h2>', webpage, 'title')
  28         redirect_url = self._html_search_regex(r'pg&settings=(.*?)\|0"\);', webpage, 'title')
  29         webpage2 = self._download_webpage(redirect_url, video_id)
  30         video_url = self._html_search_regex(r'flvMask:(.*?);', webpage2, 'video_url')
  31
  32         mobj = re.search(r'<strong>Runtime:</strong> (?P<minutes>\d+):(?P<seconds>\d+)</div>', webpage)
  33         duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
  34
  35         view_count = self._html_search_regex(r'<strong>Views:</strong>  (\d+)</div>', webpage, 'view count', fatal=False)
  36
  37         return {
  38             'id': video_id,
  39             'url': video_url,
  40             'title': title,
  41             'ext': 'flv',
  42             'duration': duration,
  43             'view_count': int_or_none(view_count),
  44         }