pycurl.py

import pycurl
import StringIO
import re
def initCurl():
    c=pycurl.Curl()
    #c.setopt(pycurl.COOKIEFILE,"cookie_file_name")
    #c.setopt(pycurl.COOKIEJAR,"cookie_file_name")
    c.setopt(pycurl.FOLLOWLOCATION,0)
    c.setopt(pycurl.CONNECTTIMEOUT, 1) #
    c.setopt(pycurl.MAXREDIRS,1)
    c.setopt(pycurl.NOSIGNAL, 1)
    #c.setopt(pycurl.HEADERFUNCTION, header_callback)
    # c.setopt(pycurl.PROXY,'http://www.x.x.x.com:8080')
    # c.setopt(pycurl.PROXYUSERPWD,'aaa:bbb')
    return c

def headerCallback(buf):
    match=re.search(r"Server\:\s+(.*)",buf)
    if match:
        return  match.group(1)

def GetData(curl,url,code=True):
    try:

        head=['Accept:*/*',
              'User-Agent:Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.97 Safari/537.11'
            ]
        buf=StringIO.StringIO()
        curl.setopt(pycurl.WRITEFUNCTION,buf.write)
        curl.setopt(pycurl.URL,url)
        curl.setopt(pycurl.HTTPHEADER,head)
        curl.perform()
        the_page=buf.getvalue()

        if code==True:
            return curl.getinfo(pycurl.HTTP_CODE)
        elif code=='head':
            curl.setopt(pycurl.HEADERFUNCTION, headerCallback)#here!! i want to get the server information :iis or apache ,but #not work,

        else:
            return the_page
        buf.close()
    except pycurl.error,e:
        return 'site cannot visit'

#another file Named test.py :
from curl import initCurl,GetData
c=initCurl()
website="http://www.google.com"
head=GetData(c,website,code='head')
print head