youtube-dl/youtube_dl/extractor/ruhd.py

46 lines
1.5 KiB
Python
Raw Normal View History

2016-10-02 11:39:18 +00:00
# coding: utf-8
2014-07-12 21:03:22 +00:00
from __future__ import unicode_literals
from .common import InfoExtractor
class RUHDIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ruhd\.ru/play\.php\?vid=(?P<id>\d+)'
2014-07-12 21:03:22 +00:00
_TEST = {
'url': 'http://www.ruhd.ru/play.php?vid=207',
'md5': 'd1a9ec4edf8598e3fbd92bb16072ba83',
'info_dict': {
'id': '207',
'ext': 'divx',
'title': 'КОТ бааааам',
'description': 'классный кот)',
'thumbnail': 're:^http://.*\.jpg$',
}
}
def _real_extract(self, url):
2014-10-26 23:20:54 +00:00
video_id = self._match_id(url)
2014-07-12 21:03:22 +00:00
webpage = self._download_webpage(url, video_id)
video_url = self._html_search_regex(
r'<param name="src" value="([^"]+)"', webpage, 'video url')
title = self._html_search_regex(
2014-10-26 23:20:54 +00:00
r'<title>([^<]+)&nbsp;&nbsp; RUHD.ru - Видео Высокого качества №1 в России!</title>',
webpage, 'title')
2014-07-12 21:03:22 +00:00
description = self._html_search_regex(
2014-10-26 23:20:54 +00:00
r'(?s)<div id="longdesc">(.+?)<span id="showlink">',
webpage, 'description', fatal=False)
2014-07-12 21:03:22 +00:00
thumbnail = self._html_search_regex(
2014-10-26 23:20:54 +00:00
r'<param name="previewImage" value="([^"]+)"',
webpage, 'thumbnail', fatal=False)
2014-07-12 21:03:22 +00:00
if thumbnail:
thumbnail = 'http://www.ruhd.ru' + thumbnail
return {
'id': video_id,
'url': video_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
}