[extractor/common] Recognize Indian censorship (#5021)
This commit is contained in:
parent
62b013df0d
commit
77b2986b5b
1 changed files with 10 additions and 0 deletions
|
@ -391,6 +391,16 @@ class InfoExtractor(object):
|
||||||
if blocked_iframe:
|
if blocked_iframe:
|
||||||
msg += ' Visit %s for more details' % blocked_iframe
|
msg += ' Visit %s for more details' % blocked_iframe
|
||||||
raise ExtractorError(msg, expected=True)
|
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
|
||||||
|
|
||||||
|
|
Loading…
Reference in a new issue