urllib2

import urllib2
response = urllib2.urlopen("http://www.baidu.com")
print response.read()

urlopen(url, data, timeout)

构造Requset

import urllib2

request = urllib2.Request("http://www.baidu.com")
response = urllib2.urlopen(request)
print response.read()

POST方式：
import urllib
import urllib2

values = {"username":"1016903103@qq.com","password":"XXXX"}
data = urllib.urlencode(values)
url = "https://passport.csdn.net/account/login?from=http://my.csdn.net/my/mycsdn"
request = urllib2.Request(url,data)
response = urllib2.urlopen(request)
print response.read()

GET方式：
import urllib
import urllib2
values={}
values['username'] = "1016903103@qq.com"
values['password']="XXXX"
data = urllib.urlencode(values)
url = "http://passport.csdn.net/account/login"
geturl = url + "?"+data
request = urllib2.Request(geturl)
response = urllib2.urlopen(request)
print response.read()

设置Headers

import urllib
import urllib2

url = 'http://www.server.com/login'
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
values = {'username' : 'cqc',  'password' : 'XXXX' }
headers = { 'User-Agent' : user_agent }
data = urllib.urlencode(values)
request = urllib2.Request(url, data, headers)
response = urllib2.urlopen(request)
page = response.read()

对付”反盗链”的方式，对付防盗链，服务器会识别headers中的referer是不是它自己，如果不是，有的服务器不会响应，所以我们还可以在headers中加入referer

headers = { 'User-Agent' : 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'  ,'Referer':'http://www.zhihu.com/articles' }

Proxy（代理）的设置

import urllib2
enable_proxy = True
proxy_handler = urllib2.ProxyHandler({"http" : 'http://some-proxy.com:8080'})
null_proxy_handler = urllib2.ProxyHandler({})
if enable_proxy:
opener = urllib2.build_opener(proxy_handler)
else:
opener = urllib2.build_opener(null_proxy_handler)
urllib2.install_opener(opener)

Timeout 设置

import urllib2
response = urllib2.urlopen('http://www.baidu.com', timeout=10)

import urllib2
response = urllib2.urlopen('http://www.baidu.com',data, 10)

使用 HTTP 的 PUT 和 DELETE 方法
request = urllib2.Request(uri, data=data)
request.get_method = lambda: 'PUT' # or 'DELETE'
response = urllib2.urlopen(request)

Python爬虫入门五之URLError异常处理

http://blog.csdn.net/cqcre