_ Git - youtube-dl/blob - youtube_dl/extractor/sexykarma.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     unified_strdate,
   9     parse_duration,
  10     int_or_none,
  11 )
  12
  13
  14 class SexyKarmaIE(InfoExtractor):
  15     IE_DESC = 'Sexy Karma and Watch Indian Porn'
  16     _VALID_URL = r'https?://(?:www\.)?(?:sexykarma\.com|watchindianporn\.net)/(?:[^/]+/)*video/(?P<display_id>[^/]+)-(?P<id>[a-zA-Z0-9]+)\.html'
  17     _TESTS = [{
  18         'url': 'http://www.sexykarma.com/gonewild/video/taking-a-quick-pee-yHI70cOyIHt.html',
  19         'md5': 'b9798e7d1ef1765116a8f516c8091dbd',
  20         'info_dict': {
  21             'id': 'yHI70cOyIHt',
  22             'display_id': 'taking-a-quick-pee',
  23             'ext': 'mp4',
  24             'title': 'Taking a quick pee.',
  25             'thumbnail': 're:^https?://.*\.jpg$',
  26             'uploader': 'wildginger7',
  27             'upload_date': '20141007',
  28             'duration': 22,
  29             'view_count': int,
  30             'comment_count': int,
  31             'categories': list,
  32         }
  33     }, {
  34         'url': 'http://www.sexykarma.com/gonewild/video/pot-pixie-tribute-8Id6EZPbuHf.html',
  35         'md5': 'dd216c68d29b49b12842b9babe762a5d',
  36         'info_dict': {
  37             'id': '8Id6EZPbuHf',
  38             'display_id': 'pot-pixie-tribute',
  39             'ext': 'mp4',
  40             'title': 'pot_pixie tribute',
  41             'thumbnail': 're:^https?://.*\.jpg$',
  42             'uploader': 'banffite',
  43             'upload_date': '20141013',
  44             'duration': 16,
  45             'view_count': int,
  46             'comment_count': int,
  47             'categories': list,
  48         }
  49     }, {
  50         'url': 'http://www.watchindianporn.net/video/desi-dancer-namrata-stripping-completely-nude-and-dancing-on-a-hot-number-dW2mtctxJfs.html',
  51         'md5': '9afb80675550406ed9a63ac2819ef69d',
  52         'info_dict': {
  53             'id': 'dW2mtctxJfs',
  54             'display_id': 'desi-dancer-namrata-stripping-completely-nude-and-dancing-on-a-hot-number',
  55             'ext': 'mp4',
  56             'title': 'Desi dancer namrata stripping completely nude and dancing on a hot number',
  57             'thumbnail': 're:^https?://.*\.jpg$',
  58             'uploader': 'Don',
  59             'upload_date': '20140213',
  60             'duration': 83,
  61             'view_count': int,
  62             'comment_count': int,
  63             'categories': list,
  64         }
  65     }]
  66
  67     def _real_extract(self, url):
  68         mobj = re.match(self._VALID_URL, url)
  69         video_id = mobj.group('id')
  70         display_id = mobj.group('display_id')
  71
  72         webpage = self._download_webpage(url, display_id)
  73
  74         video_url = self._html_search_regex(
  75             r"url: escape\('([^']+)'\)", webpage, 'url')
  76
  77         title = self._html_search_regex(
  78             r'<h2 class="he2"><span>(.*?)</span>',
  79             webpage, 'title')
  80         thumbnail = self._html_search_regex(
  81             r'<span id="container"><img\s+src="([^"]+)"',
  82             webpage, 'thumbnail', fatal=False)
  83
  84         uploader = self._html_search_regex(
  85             r'class="aupa">\s*(.*?)</a>',
  86             webpage, 'uploader')
  87         upload_date = unified_strdate(self._html_search_regex(
  88             r'Added: <strong>(.+?)</strong>', webpage, 'upload date', fatal=False))
  89
  90         duration = parse_duration(self._search_regex(
  91             r'<td>Time:\s*</td>\s*<td align="right"><span>\s*(.+?)\s*</span>',
  92             webpage, 'duration', fatal=False))
  93
  94         view_count = int_or_none(self._search_regex(
  95             r'<td>Views:\s*</td>\s*<td align="right"><span>\s*(\d+)\s*</span>',
  96             webpage, 'view count', fatal=False))
  97         comment_count = int_or_none(self._search_regex(
  98             r'<td>Comments:\s*</td>\s*<td align="right"><span>\s*(\d+)\s*</span>',
  99             webpage, 'comment count', fatal=False))
 100
 101         categories = re.findall(
 102             r'<a href="[^"]+/search/video/desi"><span>([^<]+)</span></a>',
 103             webpage)
 104
 105         return {
 106             'id': video_id,
 107             'display_id': display_id,
 108             'url': video_url,
 109             'title': title,
 110             'thumbnail': thumbnail,
 111             'uploader': uploader,
 112             'upload_date': upload_date,
 113             'duration': duration,
 114             'view_count': view_count,
 115             'comment_count': comment_count,
 116             'categories': categories,
 117         }