yt-dlp/youtube_dl/extractor/sockshare.py

81 lines
2.5 KiB
Python
Raw Normal View History

2014-07-15 19:07:20 -04:00
# coding: utf-8
from __future__ import unicode_literals
from ..utils import (
ExtractorError,
compat_urllib_parse,
compat_urllib_request,
2014-07-22 19:40:01 -04:00
determine_ext,
2014-07-15 19:07:20 -04:00
)
import re
from .common import InfoExtractor
class SockshareIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?sockshare\.com/file/(?P<id>[0-9A-Za-z]+)'
_FILE_DELETED_REGEX = r'This file doesn\'t exist, or has been removed\.</div>'
_TEST = {
'url': 'http://www.sockshare.com/file/437BE28B89D799D7',
'md5': '9d0bf1cfb6dbeaa8d562f6c97506c5bd',
'info_dict': {
'id': '437BE28B89D799D7',
'title': 'big_buck_bunny_720p_surround.avi',
'ext': 'avi',
'thumbnail': 're:^http://.*\.jpg$',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
url = 'http://sockshare.com/file/%s' % video_id
webpage = self._download_webpage(url, video_id)
if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
2014-07-21 07:25:59 -04:00
raise ExtractorError('Video %s does not exist' % video_id,
2014-07-15 19:07:20 -04:00
expected=True)
confirm_hash = self._html_search_regex(r'''(?x)<input\s+
type="hidden"\s+
value="([^"]*)"\s+
name="hash"
''', webpage, 'hash')
fields = {
"hash": confirm_hash,
"confirm": "Continue as Free User"
}
post = compat_urllib_parse.urlencode(fields)
req = compat_urllib_request.Request(url, post)
# Apparently, this header is required for confirmation to work.
req.add_header('Host', 'www.sockshare.com')
req.add_header('Content-type', 'application/x-www-form-urlencoded')
2014-07-21 07:25:59 -04:00
webpage = self._download_webpage(
req, video_id, 'Downloading video page')
2014-07-15 19:07:20 -04:00
2014-07-21 07:25:59 -04:00
video_url = self._html_search_regex(
r'<a href="([^"]*)".+class="download_file_link"',
webpage, 'file url')
2014-07-15 19:07:20 -04:00
video_url = "http://www.sockshare.com" + video_url
title = self._html_search_regex(r'<h1>(.+)<strong>', webpage, 'title')
2014-07-21 07:25:59 -04:00
thumbnail = self._html_search_regex(
r'<img\s+src="([^"]*)".+?name="bg"',
webpage, 'thumbnail')
2014-07-15 19:07:20 -04:00
formats = [{
'format_id': 'sd',
'url': video_url,
2014-07-22 19:40:01 -04:00
'ext': determine_ext(title),
2014-07-15 19:07:20 -04:00
}]
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'formats': formats,
}