mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-05 02:32:44 +01:00
1cc79574fc
· Import from compat what comes from compat. Yes, some names are available in utils too, but that's an implementation detail. · Use _match_id consistently whenever possible · Fix some outdated tests · Use consistent valid URL (always match the whole protocol, no ^ at start required) · Use modern test definitions
54 lines
2.0 KiB
Python
54 lines
2.0 KiB
Python
# encoding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
from .common import InfoExtractor
|
|
from ..compat import (
|
|
compat_urllib_parse,
|
|
compat_urllib_request,
|
|
)
|
|
from ..utils import (
|
|
ExtractorError,
|
|
)
|
|
|
|
|
|
class Vbox7IE(InfoExtractor):
|
|
_VALID_URL = r'http://(?:www\.)?vbox7\.com/play:(?P<id>[^/]+)'
|
|
_TEST = {
|
|
'url': 'http://vbox7.com/play:249bb972c2',
|
|
'md5': '99f65c0c9ef9b682b97313e052734c3f',
|
|
'info_dict': {
|
|
'id': '249bb972c2',
|
|
'ext': 'mp4',
|
|
'title': 'Смях! Чудо - чист за секунди - Скрита камера',
|
|
},
|
|
}
|
|
|
|
def _real_extract(self, url):
|
|
video_id = self._match_id(url)
|
|
|
|
redirect_page, urlh = self._download_webpage_handle(url, video_id)
|
|
new_location = self._search_regex(r'window\.location = \'(.*)\';',
|
|
redirect_page, 'redirect location')
|
|
redirect_url = urlh.geturl() + new_location
|
|
webpage = self._download_webpage(redirect_url, video_id,
|
|
'Downloading redirect page')
|
|
|
|
title = self._html_search_regex(r'<title>(.*)</title>',
|
|
webpage, 'title').split('/')[0].strip()
|
|
|
|
info_url = "http://vbox7.com/play/magare.do"
|
|
data = compat_urllib_parse.urlencode({'as3': '1', 'vid': video_id})
|
|
info_request = compat_urllib_request.Request(info_url, data)
|
|
info_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
|
|
info_response = self._download_webpage(info_request, video_id, 'Downloading info webpage')
|
|
if info_response is None:
|
|
raise ExtractorError('Unable to extract the media url')
|
|
(final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&'))
|
|
|
|
return {
|
|
'id': video_id,
|
|
'url': final_url,
|
|
'title': title,
|
|
'thumbnail': thumbnail_url,
|
|
}
|