1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-24 09:16:50 +01:00
youtube-dl/youtube_dl/extractor/vbox7.py

75 lines
2.5 KiB
Python
Raw Normal View History

2016-10-02 13:39:18 +02:00
# coding: utf-8
2014-02-04 23:02:53 +01:00
from __future__ import unicode_literals
import re
2013-06-23 22:25:46 +02:00
from .common import InfoExtractor
2016-08-13 11:45:34 +02:00
from ..utils import urlencode_postdata
2013-06-23 22:25:46 +02:00
class Vbox7IE(InfoExtractor):
2016-08-16 19:42:02 +02:00
_VALID_URL = r'https?://(?:www\.)?vbox7\.com/(?:play:|emb/external\.php\?.*?\bvid=)(?P<id>[\da-fA-F]+)'
2016-08-13 10:47:20 +02:00
_TESTS = [{
'url': 'http://vbox7.com/play:0946fff23c',
'md5': 'a60f9ab3a3a2f013ef9a967d5f7be5bf',
'info_dict': {
'id': '0946fff23c',
'ext': 'mp4',
'title': 'Борисов: Притеснен съм за бъдещето на България',
},
}, {
2014-02-04 23:02:53 +01:00
'url': 'http://vbox7.com/play:249bb972c2',
'md5': '99f65c0c9ef9b682b97313e052734c3f',
'info_dict': {
'id': '249bb972c2',
'ext': 'mp4',
2014-02-04 23:02:53 +01:00
'title': 'Смях! Чудо - чист за секунди - Скрита камера',
},
2016-08-13 10:47:20 +02:00
'skip': 'georestricted',
2016-08-16 19:42:02 +02:00
}, {
'url': 'http://vbox7.com/emb/external.php?vid=a240d20f9c&autoplay=1',
'only_matching': True,
2016-08-13 10:47:20 +02:00
}]
2013-06-23 22:25:46 +02:00
@staticmethod
def _extract_url(webpage):
mobj = re.search(
'<iframe[^>]+src=(?P<q>["\'])(?P<url>(?:https?:)?//vbox7\.com/emb/external\.php.+?)(?P=q)',
webpage)
if mobj:
return mobj.group('url')
2014-02-04 23:02:53 +01:00
def _real_extract(self, url):
video_id = self._match_id(url)
2013-06-23 22:25:46 +02:00
2016-08-16 19:42:02 +02:00
webpage = self._download_webpage(
'http://vbox7.com/play:%s' % video_id, video_id)
2016-08-13 10:47:20 +02:00
title = self._html_search_regex(
2016-08-16 19:42:02 +02:00
r'<title>(.+?)</title>', webpage, 'title').split('/')[0].strip()
2016-08-13 10:47:20 +02:00
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()
2013-06-23 22:25:46 +02:00
2014-02-04 23:02:53 +01:00
return {
'id': video_id,
2016-08-13 10:47:20 +02:00
'url': self._proto_relative_url(video_url, 'http:'),
2014-02-04 23:02:53 +01:00
'title': title,
2013-06-23 22:25:46 +02:00
'thumbnail': thumbnail_url,
2014-02-04 23:02:53 +01:00
}