homepage

In httplib.py, line 336, the following code appears: 
 def _set_hostport(self, host, port):
 if port is None:
 i = string.find(host, ':')
 if i >= 0:
 port = int(host[i+1:])
 host = host[:i]
 else:
 port = self.default_port
 self.host = host
 self.port = port
Ths code breaks if the host string ends with ":", so that
int("") is called. In the old (1.5.2) version of this 
module, the corresponding int () conversion used to be 
enclosed in a try/except pair: 
 try: port = string.atoi(port)
 except string.atoi_error:
 raise socket.error, "nonnumeric port"
and this fixed the problem. 
Note BTW that now the error reported by int is 
"ValueError: invalid literal for int():"
rather than the above string.atoi_error. 
I found this problem while downloading web pages, 
but unfortunately I cannot pinpoint which page 
caused the problem. 
Luca de Alfaro

The only effect is that it raises ValueError instead of socket.error.
Where is this a problem?
(Note that string.atoi_error is an alias for ValueError.)

There are three (minor?) problems with raising
ValueError. 
1) Compatibility. I had some code for 1.5.2 that
was trying to load web pages checking for various
errors, and it was expecting this error to cause
a socket error, not a value error. 
2) Accuracy. ValueError can be caused by
anything. The 'non-numeric port' error is much 
more informative. I don't want to catch
ValueError, because it can be caused in too 
many situations. I also cannot check 
myself that the port is fine, because the 
port and the URL are often given by a 
redirect (errors 301 and 302, if I remember
correctly). This in fact was the situation 
that caused the problem. 
Hence, my only real solution was to patch my version of httplib. 
3) Style. I am somewhat new to Python, but I was
under the impression that, stilistically, 
a ValueError was used to convey a situation that
was the fault of the programmer, while other 
more specific errors were used for unexpected 
situations (communication, etc). Since the 
socket is the result of a URL redirection 
(errors 301 or 302), the programmer is not in 
a position to prevent this error by "better 
checking". Hence, I would consider a
network-relted exception to be more appropriate 
here. 
But who am I to argue with the creator of Python? 
;-)
Luca

Thanks for explaining this more.
I am surprised that a 301 redirect would give an invalid port -- but surely webmasters aren't perfect. :-)
The argument that urllib.Urlopener.open() checks for socket.error but not for other errors is a good one.
However I don't see the httplib.py code raising socket.error elsewhere. I'll ask Jeremy. The rest of the module seems to be using a totally different set of exceptions. On the other hand, it *can* raise socket.error, implicitly (when various socket calls are being made).

I have been trying to pin down a problem in Redhat's
Update agent which is written in Python (..mostly)
which happens when a proxy is specified. 
In RH7.0, they are still using Python 1.5.2 and the message
'nonnumeric port' is received when a proxy is specified
in the following form:
http://proxy.yourdomain.com:80
but the following:
proxy.yourdomain.com:80
works..
looking at the code, it seems that it expects that the only
colon would be near the end of the url and makes no
allowance for 'http:' nor 'https:'...
Regards / Martin

Logged In: YES 
user_id=44345
Here's a suggested patch that matches the exception
structure used by httplib. It adds a subclass of 
HTTPException called InvalidURL and raises that when
int(port) gets incorrect input.

Logged In: YES 
user_id=31392
Skip's change was checked in a while ago.