_ Git - youtube-dl/blob - youtube_dl/extractor/sexykarma.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 import re
   6 import datetime
   7
   8 class SexyKarmaIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?sexykarma\.com/gonewild/video/.+\-(?P<id>[a-zA-Z0-9\-]+)(.html)'
  10     _TESTS = [{
  11         'url': 'http://www.sexykarma.com/gonewild/video/taking-a-quick-pee-yHI70cOyIHt.html',
  12         'md5': 'b9798e7d1ef1765116a8f516c8091dbd',
  13         'info_dict': {
  14             'id': 'yHI70cOyIHt',
  15             'ext': 'mp4',
  16             'title': 'Taking a quick pee.',
  17             'uploader_id': 'wildginger7',
  18             'thumbnail': 're:^https?://.*\.jpg$',
  19             'duration': int,
  20             'view_count': int,
  21             'upload_date': '20141007',
  22         }
  23     }, {
  24         'url': 'http://www.sexykarma.com/gonewild/video/pot-pixie-tribute-8Id6EZPbuHf.html',
  25         'md5': 'dd216c68d29b49b12842b9babe762a5d',
  26         'info_dict': {
  27             'id': '8Id6EZPbuHf',
  28             'ext': 'mp4',
  29             'title': 'pot_pixie tribute',
  30             'uploader_id': 'banffite',
  31             'thumbnail': 're:^https?://.*\.jpg$',
  32             'duration': int,
  33             'view_count': int,
  34             'upload_date': '20141013',
  35         }
  36     }]
  37
  38     def _real_extract(self, url):
  39         video_id = self._match_id(url)
  40
  41         webpage = self._download_webpage(url, video_id)
  42
  43         title = self._html_search_regex(r'<h2 class="he2"><span>(.*?)</span>', webpage, 'title')
  44         uploader_id = self._html_search_regex(r'class="aupa">\n*(.*?)</a>', webpage, 'uploader')
  45         url = self._html_search_regex(r'<p><a href="(.*?)" ?\n*target="_blank"><font color', webpage, 'url')
  46         thumbnail = self._html_search_regex(r'<div id="player" style="z-index:1;"> <span id="edge"></span> <span id="container"><img[\n ]*src="(.+?)"', webpage, 'thumbnail')
  47
  48         str_duration = self._html_search_regex(r'<tr>[\n\s]*<td>Time: </td>[\n\s]*<td align="right"><span>(.+)\n*', webpage, 'duration')
  49         duration = self._to_seconds(str_duration)
  50
  51         str_views = self._html_search_regex(r'<tr>[\n\s]*<td>Views: </td>[\n\s]*<td align="right"><span>(.+)</span>', webpage, 'view_count')
  52         view_count = int(str_views)
  53         # print view_count
  54
  55         date = self._html_search_regex(r'class="aup">Added: <strong>(.*?)</strong>', webpage, 'date')
  56         d = datetime.datetime.strptime(date, '%B %d, %Y')
  57         upload_date = d.strftime('%Y%m%d')
  58
  59         return {
  60             'id': video_id,
  61             'title': title,
  62             'uploader_id': uploader_id,
  63             'url': url,
  64             'thumbnail': thumbnail,
  65             'duration': duration,
  66             'view_count': view_count,
  67             'upload_date': upload_date,
  68         }
  69
  70     def _to_seconds(self, timestr):
  71         seconds= 0
  72         for part in timestr.split(':'):
  73             seconds= seconds*60 + int(part)
  74         return seconds