Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/watchindianporn.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 parse_duration
   8
   9
  10 class WatchIndianPornIE(InfoExtractor):
  11     IE_DESC = 'Watch Indian Porn'
  12     _VALID_URL = r'https?://(?:www\.)?watchindianporn\.net/(?:[^/]+/)*video/(?P<display_id>[^/]+)-(?P<id>[a-zA-Z0-9]+)\.html'
  13     _TEST = {
  14         'url': 'http://www.watchindianporn.net/video/hot-milf-from-kerala-shows-off-her-gorgeous-large-breasts-on-camera-RZa2avywNPa.html',
  15         'md5': '249589a164dde236ec65832bfce17440',
  16         'info_dict': {
  17             'id': 'RZa2avywNPa',
  18             'display_id': 'hot-milf-from-kerala-shows-off-her-gorgeous-large-breasts-on-camera',
  19             'ext': 'mp4',
  20             'title': 'Hot milf from kerala shows off her gorgeous large breasts on camera',
  21             'thumbnail': r're:^https?://.*\.jpg$',
  22             'duration': 226,
  23             'view_count': int,
  24             'categories': list,
  25             'age_limit': 18,
  26         }
  27     }
  28
  29     def _real_extract(self, url):
  30         mobj = re.match(self._VALID_URL, url)
  31         video_id = mobj.group('id')
  32         display_id = mobj.group('display_id')
  33
  34         webpage = self._download_webpage(url, display_id)
  35
  36         info_dict = self._parse_html5_media_entries(url, webpage, video_id)[0]
  37
  38         title = self._html_search_regex((
  39             r'<title>(.+?)\s*-\s*Indian\s+Porn</title>',
  40             r'<h4>(.+?)</h4>'
  41         ), webpage, 'title')
  42
  43         duration = parse_duration(self._search_regex(
  44             r'Time:\s*<strong>\s*(.+?)\s*</strong>',
  45             webpage, 'duration', fatal=False))
  46
  47         view_count = int(self._search_regex(
  48             r'(?s)Time:\s*<strong>.*?</strong>.*?<strong>\s*(\d+)\s*</strong>',
  49             webpage, 'view count', fatal=False))
  50
  51         categories = re.findall(
  52             r'<a[^>]+class=[\'"]categories[\'"][^>]*>\s*([^<]+)\s*</a>',
  53             webpage)
  54
  55         info_dict.update({
  56             'id': video_id,
  57             'display_id': display_id,
  58             'http_headers': {
  59                 'Referer': url,
  60             },
  61             'title': title,
  62             'duration': duration,
  63             'view_count': view_count,
  64             'categories': categories,
  65             'age_limit': 18,
  66         })
  67
  68         return info_dict