1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-23 08:26:50 +00:00

[ruhd] Add extractor

This commit is contained in:
Sergey M․ 2014-07-13 04:03:22 +07:00
parent 34dbcb8505
commit 81650f95e2
2 changed files with 47 additions and 0 deletions

View File

@ -240,6 +240,7 @@ from .rtbf import RTBFIE
from .rtlnow import RTLnowIE from .rtlnow import RTLnowIE
from .rts import RTSIE from .rts import RTSIE
from .rtve import RTVEALaCartaIE from .rtve import RTVEALaCartaIE
from .ruhd import RUHDIE
from .rutube import ( from .rutube import (
RutubeIE, RutubeIE,
RutubeChannelIE, RutubeChannelIE,

View File

@ -0,0 +1,46 @@
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class RUHDIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?ruhd\.ru/play\.php\?vid=(?P<id>\d+)'
_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):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
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(
r'<title>([^<]+)&nbsp;&nbsp; RUHD.ru - Видео Высокого качества №1 в России!</title>', webpage, 'title')
description = self._html_search_regex(
r'(?s)<div id="longdesc">(.+?)<span id="showlink">', webpage, 'description', fatal=False)
thumbnail = self._html_search_regex(
r'<param name="previewImage" value="([^"]+)"', webpage, 'thumbnail', fatal=False)
if thumbnail:
thumbnail = 'http://www.ruhd.ru' + thumbnail
return {
'id': video_id,
'url': video_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
}