_ Git - youtube-dl/blob - youtube_dl/extractor/eporner.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 (
   8     parse_duration,
   9     str_to_int,
  10 )
  11
  12
  13 class EpornerIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\w+)/(?P<display_id>[\w-]+)'
  15     _TESTS = [{
  16         'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/',
  17         'md5': '39d486f046212d8e1b911c52ab4691f8',
  18         'info_dict': {
  19             'id': '95008',
  20             'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video',
  21             'ext': 'mp4',
  22             'title': 'Infamous Tiffany Teen Strip Tease Video',
  23             'duration': 1838,
  24             'view_count': int,
  25             'age_limit': 18,
  26         },
  27     },
  28     # New (May 2016) URL layout
  29     {
  30         'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0/Star-Wars-XXX-Parody/',
  31         'md5': '3469eeaa93b6967a34cdbdbb9d064b33',
  32         'info_dict': {
  33             'id': '3YRUtzMcWn0',
  34             'display_id': 'Star-Wars-XXX-Parody',
  35             'ext': 'mp4',
  36             'title': 'Star Wars XXX Parody',
  37             'duration': 361.0,
  38             'view_count': int,
  39             'age_limit': 18,
  40         },
  41     }]
  42
  43     def _real_extract(self, url):
  44         mobj = re.match(self._VALID_URL, url)
  45         video_id = mobj.group('id')
  46         display_id = mobj.group('display_id')
  47
  48         webpage = self._download_webpage(url, display_id)
  49         title = self._html_search_regex(
  50             r'<title>(.*?) - EPORNER', webpage, 'title')
  51
  52         redirect_url = 'http://www.eporner.com/config5/%s' % video_id
  53         player_code = self._download_webpage(
  54             redirect_url, display_id, note='Downloading player config')
  55
  56         sources = self._search_regex(
  57             r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', player_code, 'sources')
  58
  59         formats = []
  60         for video_url, format_id in re.findall(r'file\s*:\s*"([^"]+)",\s*label\s*:\s*"([^"]+)"', sources):
  61             fmt = {
  62                 'url': video_url,
  63                 'format_id': format_id,
  64             }
  65             m = re.search(r'^(\d+)', format_id)
  66             if m:
  67                 fmt['height'] = int(m.group(1))
  68             formats.append(fmt)
  69         self._sort_formats(formats)
  70
  71         duration = parse_duration(self._html_search_meta('duration', webpage))
  72         view_count = str_to_int(self._search_regex(
  73             r'id="cinemaviews">\s*([0-9,]+)\s*<small>views',
  74             webpage, 'view count', fatal=False))
  75
  76         return {
  77             'id': video_id,
  78             'display_id': display_id,
  79             'title': title,
  80             'duration': duration,
  81             'view_count': view_count,
  82             'formats': formats,
  83             'age_limit': 18,
  84         }