_ 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     _VALID_URL = r'https?://(?:www\.)?sexykarma\.com/gonewild/video/(?P<display_id>[^/]+)-(?P<id>[a-zA-Z0-9]+)\.html'
  16     _TESTS = [{
  17         'url': 'http://www.sexykarma.com/gonewild/video/taking-a-quick-pee-yHI70cOyIHt.html',
  18         'md5': 'b9798e7d1ef1765116a8f516c8091dbd',
  19         'info_dict': {
  20             'id': 'yHI70cOyIHt',
  21             'display_id': 'taking-a-quick-pee',
  22             'ext': 'mp4',
  23             'title': 'Taking a quick pee.',
  24             'description': '',
  25             'thumbnail': 're:^https?://.*\.jpg$',
  26             'uploader': 'wildginger7',
  27             'upload_date': '20141007',
  28             'duration': 81,
  29             'view_count': int,
  30             'comment_count': int,
  31             'categories': list,
  32         }
  33     }, {
  34         'url': 'http://www.sexykarma.com/gonewild/video/pot-pixie-tribute-8Id6EZPbuHf.html',
  35         'md5': 'dd216c68d29b49b12842b9babe762a5d',
  36         'info_dict': {
  37             'id': '8Id6EZPbuHf',
  38             'display_id': 'pot-pixie-tribute',
  39             'ext': 'mp4',
  40             'title': 'pot_pixie tribute',
  41             'description': 'tribute',
  42             'thumbnail': 're:^https?://.*\.jpg$',
  43             'uploader': 'banffite',
  44             'upload_date': '20141013',
  45             'duration': 16,
  46             'view_count': int,
  47             'comment_count': int,
  48             'categories': list,
  49         }
  50     }]
  51
  52     def _real_extract(self, url):
  53         mobj = re.match(self._VALID_URL, url)
  54         video_id = mobj.group('id')
  55         display_id = mobj.group('display_id')
  56
  57         webpage = self._download_webpage(url, display_id)
  58
  59         video_url = self._html_search_regex(
  60             r'<p>Save this video to your computer: </p><p><a href="([^"]+)"',
  61             webpage, 'url')
  62
  63         title = self._html_search_regex(
  64             r'<h2 class="he2"><span>(.*?)</span>',
  65             webpage, 'title')
  66         description = self._html_search_meta(
  67             'description', webpage, 'description', fatal=False, default='')
  68         thumbnail = self._html_search_regex(
  69             r'<span id="container"><img\s+src="([^"]+)"',
  70             webpage, 'thumbnail', fatal=False)
  71
  72         uploader = self._html_search_regex(
  73             r'class="aupa">\s*(.*?)</a>',
  74             webpage, 'uploader')
  75         upload_date = unified_strdate(self._html_search_regex(
  76             r'Added: <strong>(.+?)</strong>', webpage, 'upload date', fatal=False))
  77
  78         duration = parse_duration(self._search_regex(
  79             r'<td>Time:\s*</td>\s*<td align="right"><span>\s*(.+?)\s*</span>',
  80             webpage, 'duration', fatal=False))
  81
  82         view_count = int_or_none(self._search_regex(
  83             r'<td>Views:\s*</td>\s*<td align="right"><span>\s*(\d+)\s*</span>',
  84             webpage, 'view count', fatal=False))
  85         comment_count = int_or_none(self._search_regex(
  86             r'<td>Comments:\s*</td>\s*<td align="right"><span>\s*(\d+)\s*</span>',
  87             webpage, 'comment count', fatal=False))
  88
  89         categories = self._html_search_meta(
  90             'keywords', webpage, 'categories',
  91             fatal=False, default='').split(',')
  92
  93         return {
  94             'id': video_id,
  95             'display_id': display_id,
  96             'url': video_url,
  97             'title': title,
  98             'description': description,
  99             'thumbnail': thumbnail,
 100             'uploader': uploader,
 101             'upload_date': upload_date,
 102             'duration': duration,
 103             'view_count': view_count,
 104             'comment_count': comment_count,
 105             'categories': categories,
 106         }