在使用urllib的时候经常会死掉，以前debug过，是没有设置 timing out 所以超时后就会死掉。

PycURL是curl的python库，虽然有些curl的功能没有实现，但是还是很强劲的。

curl是非常强劲的一个工具，

google内部用它来 debug GDATA API. Using cURL to interact with Google data services

可以去 http://pycurl.sourceforge.net/ 下载最新的PycURL。

import pycurl
import StringIO

url = "http://www.google.com/"
crl = pycurl.Curl()
crl.setopt(pycurl.VERBOSE,1)
crl.setopt(pycurl.FOLLOWLOCATION, 1)
crl.setopt(pycurl.MAXREDIRS, 5)
crl.fp = StringIO.StringIO()
crl.setopt(pycurl.URL, url)
crl.setopt(crl.WRITEFUNCTION, crl.fp.write)
crl.perform()
print crl.fp.getvalue()

import pycurl
import StringIO

url = "http://www.google.com/"
crl = pycurl.Curl()
crl.setopt(pycurl.VERBOSE,1)
crl.setopt(pycurl.FOLLOWLOCATION, 1)
crl.setopt(pycurl.MAXREDIRS, 5)
crl.fp = StringIO.StringIO()
crl.setopt(pycurl.URL, url)
crl.setopt(crl.WRITEFUNCTION, crl.fp.write)

# Option -b/--cookie <name=string/file> Cookie string or file to read cookies from
# Note: must be a string, not a file object.
crl.setopt(pycurl.COOKIEFILE, "cookie_file_name")

# Option -c/--cookie-jar <file> Write cookies to this file after operation
# Note: must be a string, not a file object.
crl.setopt(pycurl.COOKIEJAR, "cookie_file_name")

crl.perform()
print crl.fp.getvalue()

import pycurl
import StringIO
import urllib

url = "http://www.google.com/"
post_data_dic = {"name":"value"}
crl = pycurl.Curl()
crl.setopt(pycurl.VERBOSE,1)
crl.setopt(pycurl.FOLLOWLOCATION, 1)
crl.setopt(pycurl.MAXREDIRS, 5)
#crl.setopt(pycurl.AUTOREFERER,1)

crl.setopt(pycurl.CONNECTTIMEOUT, 60)
crl.setopt(pycurl.TIMEOUT, 300)
#crl.setopt(pycurl.PROXY,proxy)
crl.setopt(pycurl.HTTPPROXYTUNNEL,1)
#crl.setopt(pycurl.NOSIGNAL, 1)
crl.fp = StringIO.StringIO()
crl.setopt(pycurl.USERAGENT, "dhgu hoho")

# Option -d/--data <data>   HTTP POST data
crl.setopt(crl.POSTFIELDS,  urllib.urlencode(post_data_dic))

crl.setopt(pycurl.URL, url)
crl.setopt(crl.WRITEFUNCTION, crl.fp.write)
crl.perform()

print crl.fp.getvalue()

import socket
socket.setdefaulttimeout(5.0)