Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/hornbunny.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     parse_duration,
   8 )
   9
  10
  11 class HornBunnyIE(InfoExtractor):
  12     _VALID_URL = r'http?://(?:www\.)?hornbunny\.com/videos/(?P<title_dash>[a-z-]+)-(?P<id>\d+)\.html'
  13     _TEST = {
  14         'url': 'http://hornbunny.com/videos/panty-slut-jerk-off-instruction-5227.html',
  15         'md5': 'e20fd862d1894b67564c96f180f43924',
  16         'info_dict': {
  17             'id': '5227',
  18             'ext': 'mp4',
  19             'title': 'panty slut jerk off instruction',
  20             'duration': 550,
  21             'age_limit': 18,
  22             'view_count': int,
  23             'thumbnail': r're:^https?://.*\.jpg$',
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29
  30         webpage = self._download_webpage(url, video_id)
  31         title = self._og_search_title(webpage)
  32         info_dict = self._parse_html5_media_entries(url, webpage, video_id)[0]
  33
  34         duration = parse_duration(self._search_regex(
  35             r'<strong>Runtime:</strong>\s*([0-9:]+)</div>',
  36             webpage, 'duration', fatal=False))
  37         view_count = int_or_none(self._search_regex(
  38             r'<strong>Views:</strong>\s*(\d+)</div>',
  39             webpage, 'view count', fatal=False))
  40
  41         info_dict.update({
  42             'id': video_id,
  43             'title': title,
  44             'duration': duration,
  45             'view_count': view_count,
  46             'age_limit': 18,
  47         })
  48
  49         return info_dict