Raphaël G. Git Repositories - youtubedl/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$',
  26             'uploader': 'wildginger7',
  27             'upload_date': '20141008',
  28             'duration': 22,
  29             'view_count': int,
  30             'comment_count': int,
  31             'categories': list,
  32             'age_limit': 18,
  33         }
  34     }, {
  35         'url': 'http://www.sexykarma.com/gonewild/video/pot-pixie-tribute-8Id6EZPbuHf.html',
  36         'md5': 'dd216c68d29b49b12842b9babe762a5d',
  37         'info_dict': {
  38             'id': '8Id6EZPbuHf',
  39             'display_id': 'pot-pixie-tribute',
  40             'ext': 'mp4',
  41             'title': 'pot_pixie tribute',
  42             'thumbnail': 're:^https?://.*\.jpg$',
  43             'uploader': 'banffite',
  44             'upload_date': '20141013',
  45             'duration': 16,
  46             'view_count': int,
  47             'comment_count': int,
  48             'categories': list,
  49             'age_limit': 18,
  50         }
  51     }, {
  52         'url': 'http://www.watchindianporn.net/video/desi-dancer-namrata-stripping-completely-nude-and-dancing-on-a-hot-number-dW2mtctxJfs.html',
  53         'md5': '9afb80675550406ed9a63ac2819ef69d',
  54         'info_dict': {
  55             'id': 'dW2mtctxJfs',
  56             'display_id': 'desi-dancer-namrata-stripping-completely-nude-and-dancing-on-a-hot-number',
  57             'ext': 'mp4',
  58             'title': 'Desi dancer namrata stripping completely nude and dancing on a hot number',
  59             'thumbnail': 're:^https?://.*\.jpg$',
  60             'uploader': 'Don',
  61             'upload_date': '20140213',
  62             'duration': 83,
  63             'view_count': int,
  64             'comment_count': int,
  65             'categories': list,
  66             'age_limit': 18,
  67         }
  68     }]
  69
  70     def _real_extract(self, url):
  71         mobj = re.match(self._VALID_URL, url)
  72         video_id = mobj.group('id')
  73         display_id = mobj.group('display_id')
  74
  75         webpage = self._download_webpage(url, display_id)
  76
  77         video_url = self._html_search_regex(
  78             r"url: escape\('([^']+)'\)", webpage, 'url')
  79
  80         title = self._html_search_regex(
  81             r'<h2 class="he2"><span>(.*?)</span>',
  82             webpage, 'title')
  83         thumbnail = self._html_search_regex(
  84             r'<span id="container"><img\s+src="([^"]+)"',
  85             webpage, 'thumbnail', fatal=False)
  86
  87         uploader = self._html_search_regex(
  88             r'class="aupa">\s*(.*?)</a>',
  89             webpage, 'uploader')
  90         upload_date = unified_strdate(self._html_search_regex(
  91             r'Added: <strong>(.+?)</strong>', webpage, 'upload date', fatal=False))
  92
  93         duration = parse_duration(self._search_regex(
  94             r'<td>Time:\s*</td>\s*<td align="right"><span>\s*(.+?)\s*</span>',
  95             webpage, 'duration', fatal=False))
  96
  97         view_count = int_or_none(self._search_regex(
  98             r'<td>Views:\s*</td>\s*<td align="right"><span>\s*(\d+)\s*</span>',
  99             webpage, 'view count', fatal=False))
 100         comment_count = int_or_none(self._search_regex(
 101             r'<td>Comments:\s*</td>\s*<td align="right"><span>\s*(\d+)\s*</span>',
 102             webpage, 'comment count', fatal=False))
 103
 104         categories = re.findall(
 105             r'<a href="[^"]+/search/video/desi"><span>([^<]+)</span></a>',
 106             webpage)
 107
 108         return {
 109             'id': video_id,
 110             'display_id': display_id,
 111             'url': video_url,
 112             'title': title,
 113             'thumbnail': thumbnail,
 114             'uploader': uploader,
 115             'upload_date': upload_date,
 116             'duration': duration,
 117             'view_count': view_count,
 118             'comment_count': comment_count,
 119             'categories': categories,
 120             'age_limit': 18,
 121         }