0
0
Fork 0

[extractor/common] Move censorship checks to a separate method and add check for just another ISP

main
Sergey M․ 2017-04-02 03:56:49 +07:00
parent b3633fa0ce
commit 4457823dda
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 29 additions and 19 deletions

View File

@ -547,6 +547,34 @@ class InfoExtractor(object):
return encoding return encoding
def __check_blocked(self, content):
first_block = content[:512]
if ('<title>Access to this site is blocked</title>' in content and
'Websense' in first_block):
msg = 'Access to this webpage has been blocked by Websense filtering software in your network.'
blocked_iframe = self._html_search_regex(
r'<iframe src="([^"]+)"', content,
'Websense information URL', default=None)
if blocked_iframe:
msg += ' Visit %s for more details' % blocked_iframe
raise ExtractorError(msg, expected=True)
if '<title>The URL you requested has been blocked</title>' in first_block:
msg = (
'Access to this webpage has been blocked by Indian censorship. '
'Use a VPN or proxy server (with --proxy) to route around it.')
block_msg = self._html_search_regex(
r'</h1><p>(.*?)</p>',
content, 'block message', default=None)
if block_msg:
msg += ' (Message: "%s")' % block_msg.replace('\n', ' ')
raise ExtractorError(msg, expected=True)
if ('<title>TTK :: Доступ к ресурсу ограничен</title>' in content and
'blocklist.rkn.gov.ru' in content):
raise ExtractorError(
'Access to this webpage has been blocked by decision of the Russian government. '
'Visit http://blocklist.rkn.gov.ru/ for a block reason.',
expected=True)
def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None, encoding=None): def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None, encoding=None):
content_type = urlh.headers.get('Content-Type', '') content_type = urlh.headers.get('Content-Type', '')
webpage_bytes = urlh.read() webpage_bytes = urlh.read()
@ -588,25 +616,7 @@ class InfoExtractor(object):
except LookupError: except LookupError:
content = webpage_bytes.decode('utf-8', 'replace') content = webpage_bytes.decode('utf-8', 'replace')
if ('<title>Access to this site is blocked</title>' in content and self.__check_blocked(content)
'Websense' in content[:512]):
msg = 'Access to this webpage has been blocked by Websense filtering software in your network.'
blocked_iframe = self._html_search_regex(
r'<iframe src="([^"]+)"', content,
'Websense information URL', default=None)
if blocked_iframe:
msg += ' Visit %s for more details' % blocked_iframe
raise ExtractorError(msg, expected=True)
if '<title>The URL you requested has been blocked</title>' in content[:512]:
msg = (
'Access to this webpage has been blocked by Indian censorship. '
'Use a VPN or proxy server (with --proxy) to route around it.')
block_msg = self._html_search_regex(
r'</h1><p>(.*?)</p>',
content, 'block message', default=None)
if block_msg:
msg += ' (Message: "%s")' % block_msg.replace('\n', ' ')
raise ExtractorError(msg, expected=True)
return content return content