爬虫基础 之使用代理

from urllib import request
import random
headers = {
    'User-Agent':"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.83 Safari/537.36 Edg/85.0.564.41"
}
url = "http://httpbin.org/ip"
ua_list = [
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36",
    "Mozilla/5.0 (X11; Ubuntu; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2919.83 Safari/537.36",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2866.71 Safari/537.36",
]
req = request.Request(url,headers=headers)
#print(req)
req.add_header('User-Agent',random.choice(ua_list))
#print(req)
resp = request.urlopen(req)
print(resp.read()) #b'{\n  "origin": "59.63.224.118"\n}\n' 没有使用代理

ip_list = [
 {"http":"171.35.175.151:9999"},
 {"http":"171.35.175.151:9999"},
 {"http":"171.35.175.151:9999"},
 {"http":"171.35.175.151:9999"},
 {"http":"171.35.175.151:9999"},
]
proxy = random.choice(ip_list)





#使用ProxyHandler 传入 代理ip和端口号 构建一个handler
 handler = request.ProxyHandler(proxies=proxy)
 #使用handler 创建一个打开器

opener = request.build_opener(handler)
 #125.110.68.138:9000

resp = opener.open(url)
print(resp.read())

万水千山总是情，点个关注行不行。