1
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-14 20:59:16 +01:00
yt-dlp/youtube_dl/extractor/ruhd.py
2017-01-06 00:58:56 +08:00

46 lines
1.5 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# coding: utf-8
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+)'
_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': r're:^http://.*\.jpg$',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
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,
}