2014-07-24 22:12:45 +08:00
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
import base64
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
2015-11-22 00:18:17 +08:00
|
|
|
from ..compat import compat_urllib_parse
|
2014-07-24 22:12:45 +08:00
|
|
|
from ..utils import (
|
|
|
|
ExtractorError,
|
|
|
|
int_or_none,
|
2015-11-22 00:18:17 +08:00
|
|
|
sanitized_Request,
|
2014-07-24 22:12:45 +08:00
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
class SharedIE(InfoExtractor):
|
2015-08-27 00:04:39 +08:00
|
|
|
IE_DESC = 'shared.sx and vivo.sx'
|
2015-08-27 00:03:58 +08:00
|
|
|
_VALID_URL = r'http://(?:shared|vivo)\.sx/(?P<id>[\da-z]{10})'
|
2014-07-24 22:12:45 +08:00
|
|
|
|
2015-08-27 00:05:45 +08:00
|
|
|
_TESTS = [{
|
2014-07-24 22:12:45 +08:00
|
|
|
'url': 'http://shared.sx/0060718775',
|
2014-08-13 19:24:46 +08:00
|
|
|
'md5': '106fefed92a8a2adb8c98e6a0652f49b',
|
2014-07-24 22:12:45 +08:00
|
|
|
'info_dict': {
|
|
|
|
'id': '0060718775',
|
|
|
|
'ext': 'mp4',
|
2014-08-13 19:24:46 +08:00
|
|
|
'title': 'Bmp4',
|
2015-08-27 00:06:10 +08:00
|
|
|
'filesize': 1720110,
|
2014-07-24 22:12:45 +08:00
|
|
|
},
|
2015-08-27 00:05:45 +08:00
|
|
|
}, {
|
|
|
|
'url': 'http://vivo.sx/d7ddda0e78',
|
|
|
|
'md5': '15b3af41be0b4fe01f4df075c2678b2c',
|
|
|
|
'info_dict': {
|
|
|
|
'id': 'd7ddda0e78',
|
|
|
|
'ext': 'mp4',
|
|
|
|
'title': 'Chicken',
|
|
|
|
'filesize': 528031,
|
|
|
|
},
|
|
|
|
}]
|
2014-07-24 22:12:45 +08:00
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2014-12-13 19:24:42 +08:00
|
|
|
video_id = self._match_id(url)
|
|
|
|
webpage = self._download_webpage(url, video_id)
|
2014-07-24 22:12:45 +08:00
|
|
|
|
2014-12-13 19:24:42 +08:00
|
|
|
if '>File does not exist<' in webpage:
|
|
|
|
raise ExtractorError(
|
|
|
|
'Video %s does not exist' % video_id, expected=True)
|
2014-07-24 22:12:45 +08:00
|
|
|
|
2015-07-15 00:36:30 +08:00
|
|
|
download_form = self._hidden_inputs(webpage)
|
2015-11-22 00:18:17 +08:00
|
|
|
request = sanitized_Request(
|
2014-12-13 19:24:42 +08:00
|
|
|
url, compat_urllib_parse.urlencode(download_form))
|
2014-07-24 22:12:45 +08:00
|
|
|
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
|
|
|
|
|
2014-12-13 19:24:42 +08:00
|
|
|
video_page = self._download_webpage(
|
|
|
|
request, video_id, 'Downloading video page')
|
2014-07-24 22:12:45 +08:00
|
|
|
|
2014-12-13 19:24:42 +08:00
|
|
|
video_url = self._html_search_regex(
|
|
|
|
r'data-url="([^"]+)"', video_page, 'video URL')
|
|
|
|
title = base64.b64decode(self._html_search_meta(
|
2015-05-22 02:10:05 +08:00
|
|
|
'full:title', webpage, 'title').encode('utf-8')).decode('utf-8')
|
2014-12-13 19:24:42 +08:00
|
|
|
filesize = int_or_none(self._html_search_meta(
|
|
|
|
'full:size', webpage, 'file size', fatal=False))
|
2014-07-24 22:12:45 +08:00
|
|
|
thumbnail = self._html_search_regex(
|
2014-12-13 19:24:42 +08:00
|
|
|
r'data-poster="([^"]+)"', video_page, 'thumbnail', default=None)
|
2014-07-24 22:12:45 +08:00
|
|
|
|
|
|
|
return {
|
|
|
|
'id': video_id,
|
|
|
|
'url': video_url,
|
|
|
|
'ext': 'mp4',
|
|
|
|
'filesize': filesize,
|
|
|
|
'title': title,
|
|
|
|
'thumbnail': thumbnail,
|
2014-11-24 03:41:03 +08:00
|
|
|
}
|