requests的代理使用

import requests
from lxml import etree
headers = {
    'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.80 Safari/537.36',
}
url = 'https://www.sogou.com/web?query=ip'
#使用代理服务器发起请求
#proxies={'代理类型':'ip:port'}
page_text = requests.get(url=url,headers=headers,proxies={'https':'42.57.150.150:4278'}).text
tree = etree.HTML(page_text)
data = tree.xpath('//*[@id="ipsearchresult"]/strong/text()')[0]
print(data)

如何获取代理

打开芝麻代理，注意这里有实名认证，不可恶意使用代理去攻击别人的网站，即通过代理也是可溯源的：API获取-芝麻HTTP代理

构建代理池,一个代理一般可以支持20-30次并发请求

from bs4 import BeautifulSoup
from lxml import etree
import requests
import time
import random
headers = {
    'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36'
}
#构建一个代理池，通过芝麻代理获取代理
proxy_url = 'http://webapi.http.zhimacangku.com/getip?num=10&type=2&pro=&city=0&yys=0&port=1&pack=222763&ts=0&ys=0&cs=0&lb=1&sb=0&pb=4&mr=1&regions='
json_data = requests.get(url=proxy_url,headers=headers).json()
json_list = json_data['data']
proxy_list = [] #代理池,每次请求，可以随机从代理池中选择一个代理来用
for dic in json_list:
    ip = dic['ip']
    port = dic['port']
    n_dic = {
        'https':ip+':'+str(port)
    }
    proxy_list.append(n_dic)

url = 'https://www.sogou.com/web?query=ip'
page_text = requests.get(url=url,headers=headers,proxies=random.choice(proxy_list)).text
tree = etree.HTML(page_text)
data = tree.xpath('//*[@id="ipsearchresult"]/strong/text()')[0]
print(data)