1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-18 16:26:23 +00:00
youtube-dl/youtube_dl/extractor/vbox7.py

105 lines
3.3 KiB
Python
Raw Normal View History

2016-10-02 11:39:18 +00:00
# coding: utf-8
2014-02-04 22:02:53 +00:00
from __future__ import unicode_literals
import re
2013-06-23 20:25:46 +00:00
from .common import InfoExtractor
2016-12-20 14:51:11 +00:00
from ..utils import ExtractorError
2013-06-23 20:25:46 +00:00
class Vbox7IE(InfoExtractor):
2016-12-20 14:51:11 +00:00
_VALID_URL = r'''(?x)
https?://
(?:[^/]+\.)?vbox7\.com/
(?:
play:|
(?:
emb/external\.php|
player/ext\.swf
)\?.*?\bvid=
)
(?P<id>[\da-fA-F]+)
'''
2016-08-13 08:47:20 +00:00
_TESTS = [{
'url': 'http://vbox7.com/play:0946fff23c',
'md5': 'a60f9ab3a3a2f013ef9a967d5f7be5bf',
'info_dict': {
'id': '0946fff23c',
'ext': 'mp4',
'title': 'Борисов: Притеснен съм за бъдещето на България',
2016-12-20 14:51:11 +00:00
'description': 'По думите му е опасно страната ни да бъде обявена за "сигурна"',
'thumbnail': r're:^https?://.*\.jpg$',
2016-12-20 14:51:11 +00:00
'timestamp': 1470982814,
'upload_date': '20160812',
'uploader': 'zdraveibulgaria',
},
'params': {
'proxy': '127.0.0.1:8118',
2016-08-13 08:47:20 +00:00
},
}, {
2014-02-04 22:02:53 +00:00
'url': 'http://vbox7.com/play:249bb972c2',
'md5': '99f65c0c9ef9b682b97313e052734c3f',
'info_dict': {
'id': '249bb972c2',
'ext': 'mp4',
2014-02-04 22:02:53 +00:00
'title': 'Смях! Чудо - чист за секунди - Скрита камера',
},
2016-08-13 08:47:20 +00:00
'skip': 'georestricted',
2016-08-16 17:42:02 +00:00
}, {
'url': 'http://vbox7.com/emb/external.php?vid=a240d20f9c&autoplay=1',
'only_matching': True,
2016-12-20 14:51:11 +00:00
}, {
'url': 'http://i49.vbox7.com/player/ext.swf?vid=0946fff23c&autoplay=1',
'only_matching': True,
2016-08-13 08:47:20 +00:00
}]
2013-06-23 20:25:46 +00:00
@staticmethod
def _extract_url(webpage):
mobj = re.search(
r'<iframe[^>]+src=(?P<q>["\'])(?P<url>(?:https?:)?//vbox7\.com/emb/external\.php.+?)(?P=q)',
webpage)
if mobj:
return mobj.group('url')
2014-02-04 22:02:53 +00:00
def _real_extract(self, url):
video_id = self._match_id(url)
2013-06-23 20:25:46 +00:00
2016-12-20 14:51:11 +00:00
response = self._download_json(
'https://www.vbox7.com/ajax/video/nextvideo.php?vid=%s' % video_id,
video_id)
2016-08-13 08:47:20 +00:00
2016-12-20 14:51:11 +00:00
if 'error' in response:
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, response['error']), expected=True)
2016-08-13 08:47:20 +00:00
2016-12-20 14:51:11 +00:00
video = response['options']
2016-08-13 08:47:20 +00:00
2016-12-20 14:51:11 +00:00
title = video['title']
video_url = video['src']
2016-08-13 08:47:20 +00:00
if '/na.mp4' in video_url:
self.raise_geo_restricted()
2013-06-23 20:25:46 +00:00
2016-12-20 14:51:11 +00:00
uploader = video.get('uploader')
webpage = self._download_webpage(
'http://vbox7.com/play:%s' % video_id, video_id, fatal=None)
info = {}
if webpage:
info = self._search_json_ld(
webpage.replace('"/*@context"', '"@context"'), video_id,
fatal=False)
2016-12-20 14:51:11 +00:00
info.update({
2014-02-04 22:02:53 +00:00
'id': video_id,
'title': title,
2016-12-20 14:51:11 +00:00
'url': video_url,
'uploader': uploader,
'thumbnail': self._proto_relative_url(
info.get('thumbnail') or self._og_search_thumbnail(webpage),
'http:'),
})
return info