python通过伪装头部数据抵抗反爬虫的实例

GET /u012870721 HTTP/1.1
Accept-Encoding: identity
Host: blog.csdn.net
User-Agent: <span style="color:#ff0000;">Python-urllib/3.6</span>
Connection: close

Connection: keep-alive
Upgrade-Insecure-Requests: 1
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36
Referer: http://write.blog.csdn.net/postlist
Accept-Encoding: gzip, deflate
Accept-Language: zh-CN,zh;q=0.8

from urllib import request
html_url = "http://blog.csdn.net/u012870721";
#伪装构造头
header ={
 "Connection": "keep-alive",
 "Upgrade-Insecure-Requests": "1",
 "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36",
 "Accept":" text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
 "Accept-Encoding": "gzip,deflate",
 "Accept-Language": "zh-CN,zh;q=0.8"
};

#int main()
#{
req = request.Request(url=html_url, headers=header);

resp = request.urlopen(req);
# return 0;
# }

GET /u012870721 HTTP/1.1 
Host: blog.csdn.net 
Connection: close 
Upgrade-Insecure-Requests: 1 
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36 
Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8 
Accept-Encoding: gzip,deflate 
Accept-Language: zh-CN,zh;q=0.8