[Twisted-Python] getPage using ssl proxy

[Konrads Smelkovs]

I found answer to my own question:

class NoVerifyClientContextFactory:
    """A context factory for SSL clients."""

    isClient = 1
    method = SSL.SSLv3_METHOD

    def getContext(self):
        def x(*args):
            return True
        ctx=SSL.Context(self.method)
        #print dir(ctx)
        ctx.set_verify(SSL.VERIFY_NONE,x)
        return ctx
def getPage(url, contextFactory=None, *args, **kwargs):
    scheme, host, port, path = _parse(url)
    factory = HTTPClientFactory(url, *args, **kwargs)
    if 1: # use a proxy
        host, port = 'localhost', 8080
        factory.path = url
    if scheme == 'https':
        from twisted.internet import ssl
        if contextFactory is None:
            contextFactory = NoVerifyClientContextFactory()
        reactor.connectSSL(host, port, factory, contextFactory)
    else:
        reactor.connectTCP(host, port, factory)
    return factory.deferred

--
Konrads Smelkovs
Applied IT sorcery.


On Thu, Jul 30, 2009 at 10:15 PM, Konrads Smelkovs <konrads at smelkovs.com>wrote:

> Hello,
>
> I am writing some scraper scripts and need to pass them through an
> intercepting proxy. getPage does not support a proxy argument and this code
> I found on internet won't work with SSL proxy (stalls indefinitely):
>
> def getPage(url, contextFactory=None, *args, **kwargs):
>     scheme, host, port, path = _parse(url)
>     factory = HTTPClientFactory(url, *args, **kwargs)
>     if 0: # use a proxy
>         host, port = 'localhost', 8080
>         factory.path = url
>     if scheme == 'https':
>         from twisted.internet import ssl
>         if contextFactory is None:
>             contextFactory = ssl.ClientContextFactory()
>         reactor.connectSSL(host, port, factory, contextFactory)
>     else:
>         reactor.connectTCP(host, port, factory)
>     return factory.deferred
>
> Plain http proxying works. My guess is that there is an issue with
> self-signed or otherwise invalid certificate the http proxy supplies. Any
> clues?
>
> --
> Konrads Smelkovs
> Applied IT sorcery.
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://twistedmatrix.com/pipermail/twisted-python/attachments/20090801/646294d9/attachment.htm