python-urllib2模块

参考：

http://blog.csdn.net/wklken/article/details/7364390

http://hankjin.blog.163.com/blog/static/3373193720105140583594/

1、基本用法：

 res=urllib2.urlopen(url)
 print res.read()

2. 加上要get或post的数据

 data={"name":"hank", "passwd":"hjz"}
 urllib2.urlopen(url, urllib.urlencode(data))

3. 加上http头

 header={"User-Agent": "Mozilla-Firefox5.0"}
 urllib2.urlopen(url, urllib.urlencode(data), header)

4. 加上session

 cj = cookielib.CookieJar()
 cjhandler=urllib2.HTTPCookieProcessor(cj)
 opener = urllib2.build_opener(cjhandler)
 urllib2.install_opener(opener)

5. 加上Basic认证

 password_mgr = urllib2.HTTPPasswordMgrWithDefaultRealm()
 top_level_url = "http://www.163.com/"
 password_mgr.add_password(None, top_level_url, username, password)
 handler = urllib2.HTTPBasicAuthHandler(password_mgr)
 opener = urllib2.build_opener(handler)
 urllib2.install_opener(opener)

6. 使用代理

 proxy_support = urllib2.ProxyHandler({"http":"http://1.2.3.4:3128/"})
 opener = urllib2.build_opener(proxy_support)
 urllib2.install_opener(opener)

7. 设置超时

socket.setdefaulttimeout(5)
或者
urllib2.urlopen(url, timeout=5)

大段代码参考：

     #!/usr/bin/python
     # -*- coding:utf-8 -*-
     # urllib2_test.py
     # author: wklken
     # 2012-03-17 wklken@yeah.net  

     import urllib,urllib2,cookielib,socket  

     url = "http://www.testurl....." #change yourself
     #最简单方式
     def use_urllib2():
       try:
         f = urllib2.urlopen(url, timeout=5).read()
       except urllib2.URLError, e:
         print e.reason
       print len(f)  

     #使用Request
     def get_request():
       #可以设置超时
       socket.setdefaulttimeout(5)
       #可以加入参数  [无参数，使用get，以下这种方式，使用post]
       params = {"wd":"a","b":""}
       #可以加入请求头信息，以便识别
       i_headers = {"User-Agent": "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9.1) Gecko/20090624 Firefox/3.5",
                  "Accept": "text/plain"}
       #use post,have some params post to server,if not support ,will throw exception
       #req = urllib2.Request(url, data=urllib.urlencode(params), headers=i_headers)
       req = urllib2.Request(url, headers=i_headers)  

       #创建request后，还可以进行其他添加,若是key重复，后者生效
       #request.add_header('Accept','application/json')
       #可以指定提交方式
       #request.get_method = lambda: 'PUT'
       try:
         page = urllib2.urlopen(req)
         print len(page.read())
         #like get
         #url_params = urllib.urlencode({"a":"1", "b":"2"})
         #final_url = url + "?" + url_params
         #print final_url
         #data = urllib2.urlopen(final_url).read()
         #print "Method:get ", len(data)
       except urllib2.HTTPError, e:
         print "Error Code:", e.code
       except urllib2.URLError, e:
         print "Error Reason:", e.reason  

     def use_proxy():
       enable_proxy = False
       proxy_handler = urllib2.ProxyHandler({"http":"http://proxyurlXXXX.com:8080"})
       null_proxy_handler = urllib2.ProxyHandler({})
       if enable_proxy:
         opener = urllib2.build_opener(proxy_handler, urllib2.HTTPHandler)
       else:
         opener = urllib2.build_opener(null_proxy_handler, urllib2.HTTPHandler)
       #此句设置urllib2的全局opener
       urllib2.install_opener(opener)
       content = urllib2.urlopen(url).read()
       print "proxy len:",len(content)  

     class NoExceptionCookieProcesser(urllib2.HTTPCookieProcessor):
       def http_error_403(self, req, fp, code, msg, hdrs):
         return fp
       def http_error_400(self, req, fp, code, msg, hdrs):
         return fp
       def http_error_500(self, req, fp, code, msg, hdrs):
         return fp  

     def hand_cookie():
       cookie = cookielib.CookieJar()
       #cookie_handler = urllib2.HTTPCookieProcessor(cookie)
       #after add error exception handler
       cookie_handler = NoExceptionCookieProcesser(cookie)
       opener = urllib2.build_opener(cookie_handler, urllib2.HTTPHandler)
       url_login = "https://www.yourwebsite/?login"
       params = {"username":"user","password":""}
       opener.open(url_login, urllib.urlencode(params))
       for item in cookie:
         print item.name,item.value
       #urllib2.install_opener(opener)
       #content = urllib2.urlopen(url).read()
       #print len(content)
     #得到重定向 N 次以后最后页面URL
     def get_request_direct():
       import httplib
       httplib.HTTPConnection.debuglevel = 1
       request = urllib2.Request("http://www.google.com")
       request.add_header("Accept", "text/html,*/*")
       request.add_header("Connection", "Keep-Alive")
       opener = urllib2.build_opener()
       f = opener.open(request)
       print f.url
       print f.headers.dict
       print len(f.read())  

     if __name__ == "__main__":
       use_urllib2()
       get_request()
       get_request_direct()
       use_proxy()
       hand_cookie()  

测试wsgi接口的小例子：

 url ='http://192.168.33.11:9008/getActivityInfo'
 data = '''{"userid":"123","type":"1","flag":"t32"}'''
 # 使用 urllib.urlencode会报错。。
 # response = urllib2.urlopen(url, urllib.urlencode(data))
 response = urllib2.urlopen(url, data)
 print response.getcode()
 print response.read()