2014-07-13 05:03:22 +08:00
|
|
|
|
# -*- coding: utf-8 -*-
|
|
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class RUHDIE(InfoExtractor):
|
2016-03-21 23:36:32 +08:00
|
|
|
|
_VALID_URL = r'https?://(?:www\.)?ruhd\.ru/play\.php\?vid=(?P<id>\d+)'
|
2014-07-13 05:03:22 +08:00
|
|
|
|
_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):
|
2014-10-27 07:20:54 +08:00
|
|
|
|
video_id = self._match_id(url)
|
2014-07-13 05:03:22 +08:00
|
|
|
|
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(
|
2014-10-27 07:20:54 +08:00
|
|
|
|
r'<title>([^<]+) RUHD.ru - Видео Высокого качества №1 в России!</title>',
|
|
|
|
|
|
webpage, 'title')
|
2014-07-13 05:03:22 +08:00
|
|
|
|
description = self._html_search_regex(
|
2014-10-27 07:20:54 +08:00
|
|
|
|
r'(?s)<div id="longdesc">(.+?)<span id="showlink">',
|
|
|
|
|
|
webpage, 'description', fatal=False)
|
2014-07-13 05:03:22 +08:00
|
|
|
|
thumbnail = self._html_search_regex(
|
2014-10-27 07:20:54 +08:00
|
|
|
|
r'<param name="previewImage" value="([^"]+)"',
|
|
|
|
|
|
webpage, 'thumbnail', fatal=False)
|
2014-07-13 05:03:22 +08:00
|
|
|
|
if thumbnail:
|
|
|
|
|
|
thumbnail = 'http://www.ruhd.ru' + thumbnail
|
|
|
|
|
|
|
|
|
|
|
|
return {
|
|
|
|
|
|
'id': video_id,
|
|
|
|
|
|
'url': video_url,
|
|
|
|
|
|
'title': title,
|
|
|
|
|
|
'description': description,
|
|
|
|
|
|
'thumbnail': thumbnail,
|
|
|
|
|
|
}
|
