ytdl/youtube_dl/extractor/vidzi.py

39 lines
1.2 KiB
Python
Raw Normal View History

2014-11-23 20:41:03 +01:00
# coding: utf-8
2014-10-24 15:17:17 +02:00
from __future__ import unicode_literals
2014-10-17 18:38:16 +02:00
from .common import InfoExtractor
2014-10-24 15:17:17 +02:00
2014-10-17 18:38:16 +02:00
class VidziIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?vidzi\.tv/(?P<id>\w+)'
_TEST = {
'url': 'http://vidzi.tv/cghql9yq6emu.html',
'md5': '4f16c71ca0c8c8635ab6932b5f3f1660',
2014-10-17 18:38:16 +02:00
'info_dict': {
'id': 'cghql9yq6emu',
2014-10-17 18:38:16 +02:00
'ext': 'mp4',
'title': 'youtube-dl test video 1\\\\2\'3/4<5\\\\6ä7↭',
2014-10-17 18:38:16 +02:00
},
}
def _real_extract(self, url):
2014-10-24 15:17:17 +02:00
video_id = self._match_id(url)
2014-11-23 20:41:03 +01:00
2014-10-24 15:17:17 +02:00
webpage = self._download_webpage(url, video_id)
video_host = self._html_search_regex(
r'id=\'vplayer\'><img src="http://(.*?)/i', webpage,
'video host')
video_hash = self._html_search_regex(
r'\|([a-z0-9]+)\|hls\|type', webpage, 'video_hash')
ext = self._html_search_regex(
r'\|tracks\|([a-z0-9]+)\|', webpage, 'video ext')
video_url = 'http://' + video_host + '/' + video_hash + '/v.' + ext
2014-10-24 15:17:17 +02:00
title = self._html_search_regex(
r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title')
2014-11-23 20:41:03 +01:00
2014-10-17 18:38:16 +02:00
return {
'id': video_id,
'title': title,
'url': video_url,
}