yt-dlc/youtube_dl/extractor/shared.py

72 lines
2.1 KiB
Python
Raw Normal View History

2014-07-24 14:12:45 +00:00
from __future__ import unicode_literals
import base64
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
2014-07-24 14:12:45 +00:00
from ..utils import (
ExtractorError,
int_or_none,
)
class SharedIE(InfoExtractor):
2015-08-26 16:04:39 +00:00
IE_DESC = 'shared.sx and vivo.sx'
_VALID_URL = r'http://(?:shared|vivo)\.sx/(?P<id>[\da-z]{10})'
2014-07-24 14:12:45 +00:00
2015-08-26 16:05:45 +00:00
_TESTS = [{
2014-07-24 14:12:45 +00:00
'url': 'http://shared.sx/0060718775',
2014-08-13 11:24:46 +00:00
'md5': '106fefed92a8a2adb8c98e6a0652f49b',
2014-07-24 14:12:45 +00:00
'info_dict': {
'id': '0060718775',
'ext': 'mp4',
2014-08-13 11:24:46 +00:00
'title': 'Bmp4',
2014-07-24 14:12:45 +00:00
},
2015-08-26 16:05:45 +00:00
}, {
'url': 'http://vivo.sx/d7ddda0e78',
'md5': '15b3af41be0b4fe01f4df075c2678b2c',
'info_dict': {
'id': 'd7ddda0e78',
'ext': 'mp4',
'title': 'Chicken',
'filesize': 528031,
},
}]
2014-07-24 14:12:45 +00:00
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
2014-07-24 14:12:45 +00:00
if '>File does not exist<' in webpage:
raise ExtractorError(
'Video %s does not exist' % video_id, expected=True)
2014-07-24 14:12:45 +00:00
download_form = self._hidden_inputs(webpage)
request = compat_urllib_request.Request(
url, compat_urllib_parse.urlencode(download_form))
2014-07-24 14:12:45 +00:00
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
video_page = self._download_webpage(
request, video_id, 'Downloading video page')
2014-07-24 14:12:45 +00:00
video_url = self._html_search_regex(
r'data-url="([^"]+)"', video_page, 'video URL')
title = base64.b64decode(self._html_search_meta(
2015-05-21 18:10:05 +00:00
'full:title', webpage, 'title').encode('utf-8')).decode('utf-8')
filesize = int_or_none(self._html_search_meta(
'full:size', webpage, 'file size', fatal=False))
2014-07-24 14:12:45 +00:00
thumbnail = self._html_search_regex(
r'data-poster="([^"]+)"', video_page, 'thumbnail', default=None)
2014-07-24 14:12:45 +00:00
return {
'id': video_id,
'url': video_url,
'ext': 'mp4',
'filesize': filesize,
'title': title,
'thumbnail': thumbnail,
2014-11-23 19:41:03 +00:00
}