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 (
   8     unified_strdate,
   9     parse_duration,
  10     int_or_none,
  11 )
  12
  13
  14 class WatchIndianPornIE(InfoExtractor):
  15     IE_DESC = 'Watch Indian Porn'
  16     _VALID_URL = r'https?://(?:www\.)?watchindianporn\.net/(?:[^/]+/)*video/(?P<display_id>[^/]+)-(?P<id>[a-zA-Z0-9]+)\.html'
  17     _TEST = {
  18         'url': 'http://www.watchindianporn.net/video/hot-milf-from-kerala-shows-off-her-gorgeous-large-breasts-on-camera-RZa2avywNPa.html',
  19         'md5': '249589a164dde236ec65832bfce17440',
  20         'info_dict': {
  21             'id': 'RZa2avywNPa',
  22             'display_id': 'hot-milf-from-kerala-shows-off-her-gorgeous-large-breasts-on-camera',
  23             'ext': 'mp4',
  24             'title': 'Hot milf from kerala shows off her gorgeous large breasts on camera',
  25             'thumbnail': 're:^https?://.*\.jpg$',
  26             'uploader': 'LoveJay',
  27             'upload_date': '20160428',
  28             'duration': 226,
  29             'view_count': int,
  30             'comment_count': int,
  31             'categories': list,
  32             'age_limit': 18,
  33         }
  34     }
  35
  36     def _real_extract(self, url):
  37         mobj = re.match(self._VALID_URL, url)
  38         video_id = mobj.group('id')
  39         display_id = mobj.group('display_id')
  40
  41         webpage = self._download_webpage(url, display_id)
  42
  43         video_url = self._html_search_regex(
  44             r"url: escape\('([^']+)'\)", webpage, 'url')
  45
  46         title = self._html_search_regex(
  47             r'<h2 class="he2"><span>(.*?)</span>',
  48             webpage, 'title')
  49         thumbnail = self._html_search_regex(
  50             r'<span id="container"><img\s+src="([^"]+)"',
  51             webpage, 'thumbnail', fatal=False)
  52
  53         uploader = self._html_search_regex(
  54             r'class="aupa">\s*(.*?)</a>',
  55             webpage, 'uploader')
  56         upload_date = unified_strdate(self._html_search_regex(
  57             r'Added: <strong>(.+?)</strong>', webpage, 'upload date', fatal=False))
  58
  59         duration = parse_duration(self._search_regex(
  60             r'<td>Time:\s*</td>\s*<td align="right"><span>\s*(.+?)\s*</span>',
  61             webpage, 'duration', fatal=False))
  62
  63         view_count = int_or_none(self._search_regex(
  64             r'<td>Views:\s*</td>\s*<td align="right"><span>\s*(\d+)\s*</span>',
  65             webpage, 'view count', fatal=False))
  66         comment_count = int_or_none(self._search_regex(
  67             r'<td>Comments:\s*</td>\s*<td align="right"><span>\s*(\d+)\s*</span>',
  68             webpage, 'comment count', fatal=False))
  69
  70         categories = re.findall(
  71             r'<a href="[^"]+/search/video/desi"><span>([^<]+)</span></a>',
  72             webpage)
  73
  74         return {
  75             'id': video_id,
  76             'display_id': display_id,
  77             'url': video_url,
  78             'http_headers': {
  79                 'Referer': url,
  80             },
  81             'title': title,
  82             'thumbnail': thumbnail,
  83             'uploader': uploader,
  84             'upload_date': upload_date,
  85             'duration': duration,
  86             'view_count': view_count,
  87             'comment_count': comment_count,
  88             'categories': categories,
  89             'age_limit': 18,
  90         }