_ 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         'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0/Star-Wars-XXX-Parody/',
  30         'only_matching': True,
  31     }]
  32
  33     def _real_extract(self, url):
  34         mobj = re.match(self._VALID_URL, url)
  35         video_id = mobj.group('id')
  36         display_id = mobj.group('display_id')
  37
  38         webpage = self._download_webpage(url, display_id)
  39         title = self._html_search_regex(
  40             r'<title>(.*?) - EPORNER', webpage, 'title')
  41
  42         redirect_url = 'http://www.eporner.com/config5/%s' % video_id
  43         player_code = self._download_webpage(
  44             redirect_url, display_id, note='Downloading player config')
  45
  46         sources = self._search_regex(
  47             r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', player_code, 'sources')
  48
  49         formats = []
  50         for video_url, format_id in re.findall(r'file\s*:\s*"([^"]+)",\s*label\s*:\s*"([^"]+)"', sources):
  51             fmt = {
  52                 'url': video_url,
  53                 'format_id': format_id,
  54             }
  55             m = re.search(r'^(\d+)', format_id)
  56             if m:
  57                 fmt['height'] = int(m.group(1))
  58             formats.append(fmt)
  59         self._sort_formats(formats)
  60
  61         duration = parse_duration(self._html_search_meta('duration', webpage))
  62         view_count = str_to_int(self._search_regex(
  63             r'id="cinemaviews">\s*([0-9,]+)\s*<small>views',
  64             webpage, 'view count', fatal=False))
  65
  66         return {
  67             'id': video_id,
  68             'display_id': display_id,
  69             'title': title,
  70             'duration': duration,
  71             'view_count': view_count,
  72             'formats': formats,
  73             'age_limit': 18,
  74         }