Get
urllib的request模块可以非常方便地抓取URL内容，也就是发送一个GET请求到指定的页面，然后返回HTTP的响应：
from urllib import request
with request.urlopen('http://www.baidu.com') as f:
data = f.read()
# 打印状态码看是否成功
print('status:',f.status,f.reason)
for k,v in f.getheaders():
print('%s:%s' % (k,v))
print('data:',data.decode('utf-8'))
就能看到下面的打印的东西
Connection:close
Content-Type:text/html
Last-Modified:Mon Dec 12 14:35:49 2016
Vary:Accept-Encoding
Date:Mon Dec 12 14:35:49 2016
Cache-Control:no-cache
Content-Length:2090
data: <!doctype html><html><body><script>function R(u){if(/webkit/i.test(navigator.userAgent)){var l=top.window.document.createElement("a");l.rel="noreferrer";l.href=u;top.window.document.body.appendChild(l);var h=top.window.document.createEvent("MouseEvents");h.initEvent("click",true,true);setTimeout(function(){l.dispatchEvent(h)},300);}else{top.window.document.write('<meta http-equiv="Refresh" Content="0; Url='+u+'"/>');}
setTimeout(function(){top.document.location.replace(u)},1000);}
function B(){if((window.navigator.userAgent.search(/MSIE 6.0/i)!=-1||window.navigator.userAgent.search(/MSIE 7.0/i)!=-1||window.navigator.userAgent.search(/MSIE 8.0/i)!=-1||window.navigator.userAgent.search(/MSIE 9.0/i)!=-1)&&typeof window.navigator.vendor=="undefined"){return"ie9"}else if(window.navigator.userAgent.search(/Chrome/i)!=-1&&window.navigator.vendor.search(/Google/i)!=-1){return"chrome"}else if(window.navigator.userAgent.search(/FIREFOX/i)!=-1){return"ff"}
return"unknown"}
function SW(){var b=B();if(b!="i9"&&b!="chrom"&&b!="f"){R("https://www.baidu.com/?tn=13087099_91_hao_pg");return true;}
return false;}
function CK(){var c=window.document.cookie.split(";");for(var d=0;d<c.length;d++){var g=c[d].split("=")[0];if(g.indexOf("apxlp")>-1)
continue;window.document.cookie=g+"=; path=/; expires=Thu, 01 Jan 1970 00:00:01 GMT;";window.document.cookie=g+"=; domain=.baidu.com; path=/; expires=Thu, 01 Jan 1970 00:00:01 GMT;";window.document.cookie=g+"=; domain=.www.baidu.com; path=/; expires=Thu, 01 Jan 1970 00:00:01 GMT;";};try{localStorage.clear()}catch(e){}}
function IS(){CK();if(SW())
return;R("https://www.baidu.com/?tn=13087099_91_hao_pg");}
var xmlhttp;function reqHome(url){xmlhttp=null;if (window.XMLHttpRequest){ xmlhttp=new XMLHttpRequest();} else if (window.ActiveXObject){ xmlhttp=new ActiveXObject("Microsoft.XMLHTTP");}if (xmlhttp!=null){ xmlhttp.open("GET",url,true); xmlhttp.send(null); }}IS();setTimeout(reqHome("https://www.hao123.com/?tn=13087099_91_hao_pg"),300);</script><script>if(typeof IS=='undefined'){location.reload(true);}</script></body>```
2.如果我们要想模拟浏览器发送GET请求，就需要使用Request对象，通过往Request对象添加HTTP头，我们就可以把请求伪装成浏览器。例如，模拟iPhone 6去请求豆瓣首页：
from urllib import request
# 创建request对象
req = request.Request('http://www.douban.com/')
# 添加请求头
req.add_header('User-Agent', 'Mozilla/6.0 (iPhone; CPU iPhone OS 8_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/8.0 Mobile/10A5376e Safari/8536.25')
with request.urlopen(req) as f:
data = f.read()
# 打印状态码看是否成功
print('status:',f.status,f.reason)
for k,v in f.getheaders():
print('%s:%s' % (k,v))
print('data:',data.decode('utf-8'))
###POST
如果要以POST发送一个请求，只需要把参数data以bytes形式传入。
我们模拟一个微博登录，先读取登录的邮箱和口令，然后按照weibo.cn的登录页的格式以username=xxx&password=xxx的编码传入：
from urllib import request,parse
print('login to weibo.cn....')
email = input('Email' )
password = input('Password')
# post 请求体，相当于oc中的httpBody
login_data = parse.urlencode([('username',email),('password',password),('entry','mweibo')])
# 创建requestduix
req = request.Request('https://passport.weibo.cn/sso/login')
# 设置请求头
req.add_header('Origin', 'https://passport.weibo.cn')
req.add_header('User-Agent', 'Mozilla/6.0 (iPhone; CPU iPhone OS 8_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/8.0 Mobile/10A5376e Safari/8536.25')
req.add_header('Referer', 'https://passport.weibo.cn/signin/login?entry=mweibo&res=wel&wm=3349&r=http%3A%2F%2Fm.weibo.cn%2F')
with request.urlopen(req,data=login_data.encode('utf-8')) as f:
print('status:',f.status,f.reason)
Handler
如果还需要更复杂的控制，比如通过一个Proxy去访问网站，我们需要利用ProxyHandler来处理，示例代码如下：
proxy_handler = urllib.request.ProxyHandler({'http': 'http://www.example.com:3128/'})
proxy_auth_handler = urllib.request.ProxyBasicAuthHandler()
proxy_auth_handler.add_password('realm', 'host', 'username', 'password')
opener = urllib.request.build_opener(proxy_handler, proxy_auth_handler)
with opener.open('http://www.example.com/login.html') as f:
pass
网友评论