[sockshare] Add new extractor

This commit is contained in:
Naglis Jonaitis 2014-07-16 02:07:20 +03:00
parent ee90ddab94
commit 66aa382eae
2 changed files with 78 additions and 0 deletions

View file

@ -262,6 +262,7 @@ from .smotri import (
SmotriUserIE, SmotriUserIE,
SmotriBroadcastIE, SmotriBroadcastIE,
) )
from .sockshare import SockshareIE
from .sohu import SohuIE from .sohu import SohuIE
from .soundcloud import ( from .soundcloud import (
SoundcloudIE, SoundcloudIE,

View file

@ -0,0 +1,77 @@
# coding: utf-8
from __future__ import unicode_literals
from ..utils import (
ExtractorError,
compat_urllib_parse,
compat_urllib_request,
determine_ext,
)
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:
raise ExtractorError(u'Video %s does not exist' % video_id,
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')
webpage = self._download_webpage(req, video_id, 'Downloading video page')
video_url = self._html_search_regex(r'<a href="([^"]*)".+class="download_file_link"', webpage, 'file url')
video_url = "http://www.sockshare.com" + video_url
title = self._html_search_regex(r'<h1>(.+)<strong>', webpage, 'title')
thumbnail = self._html_search_regex(r'<img\ssrc="([^"]*)".+name="bg"',
webpage, 'thumbnail')
ext = determine_ext(title)
formats = [{
'format_id': 'sd',
'url': video_url,
'ext': ext,
}]
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'formats': formats,
}