1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-05 02:32:44 +01:00
yt-dlp/youtube_dl/extractor/vbox7.py
2016-08-13 15:47:20 +07:00

66 lines
2.1 KiB
Python

# encoding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
ExtractorError,
sanitized_Request,
urlencode_postdata,
)
class Vbox7IE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?vbox7\.com/play:(?P<id>[^/]+)'
_TESTS = [{
'url': 'http://vbox7.com/play:0946fff23c',
'md5': 'a60f9ab3a3a2f013ef9a967d5f7be5bf',
'info_dict': {
'id': '0946fff23c',
'ext': 'mp4',
'title': 'Борисов: Притеснен съм за бъдещето на България',
},
}, {
'url': 'http://vbox7.com/play:249bb972c2',
'md5': '99f65c0c9ef9b682b97313e052734c3f',
'info_dict': {
'id': '249bb972c2',
'ext': 'mp4',
'title': 'Смях! Чудо - чист за секунди - Скрита камера',
},
'skip': 'georestricted',
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(
r'<title>(.*)</title>', webpage, 'title').split('/')[0].strip()
video_url = self._search_regex(
r'src\s*:\s*(["\'])(?P<url>.+?.mp4.*?)\1',
webpage, 'video url', default=None, group='url')
thumbnail_url = self._og_search_thumbnail(webpage)
if not video_url:
info_response = self._download_webpage(
'http://vbox7.com/play/magare.do', video_id,
'Downloading info webpage',
data=urlencode_postdata({'as3': '1', 'vid': video_id}),
headers={'Content-Type': 'application/x-www-form-urlencoded'})
final_url, thumbnail_url = map(
lambda x: x.split('=')[1], info_response.split('&'))
if '/na.mp4' in video_url:
self.raise_geo_restricted()
return {
'id': video_id,
'url': self._proto_relative_url(video_url, 'http:'),
'title': title,
'thumbnail': thumbnail_url,
}