mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2025-10-25 03:31:03 +00:00
84 lines
2.5 KiB
Python
84 lines
2.5 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import re
|
|
|
|
from ..compat import (
|
|
compat_urllib_parse,
|
|
compat_urllib_request,
|
|
)
|
|
from ..utils import (
|
|
determine_ext,
|
|
ExtractorError,
|
|
)
|
|
|
|
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',
|
|
}
|
|
}
|
|
|
|
def _real_extract(self, url):
|
|
video_id = self._match_id(url)
|
|
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('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.encode('utf-8'),
|
|
"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>',
|
|
r'var name = "([^"]+)";'),
|
|
webpage, 'title', default=None)
|
|
thumbnail = self._html_search_regex(
|
|
r'<img\s+src="([^"]*)".+?name="bg"',
|
|
webpage, 'thumbnail', default=None)
|
|
|
|
formats = [{
|
|
'format_id': 'sd',
|
|
'url': video_url,
|
|
'ext': determine_ext(title),
|
|
}]
|
|
|
|
return {
|
|
'id': video_id,
|
|
'title': title,
|
|
'thumbnail': thumbnail,
|
|
'formats': formats,
|
|
}
|