使用Python访问网页主要有三种方式: urllib, urllib2, httplib
urllib比较简单,功能相对也比较弱,httplib简单强大,但不支持session
1. 最简单的页面访问(获取服务器端的Response包)
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)
#转载其他的:
使用opener和handler
opener = urllib2.build_opener(handler)
urllib2.install_opener(opener)
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)