爬虫怎么使用代理ip

Question

想问一下怎么使用代理ip啊？网上看到有卖代理ip的，怎么用它来登录网页呢？刚开始学爬虫不大会用额，，

Answer 1

直接上代码，有报错的话可以自行调试一下，逻辑很简单不难的：

import requests
from selenium import webdriver

def conc_ip(url):
    try:
        page=requests.get('http://pandavip.xiongmaodaili.com/xiongmao-web/apiPlus/vgl?secret=306f6ea948242db0f9498b6e4551ca30&orderNo=VGL20220424120425lK79Ei4m&count=1&isTxt=1&proxyType=1&validTime=0&removal=0&cityIds=')  %假设用的熊猫代理
        data1 = page.text
        ip = data1[0:-8]
        port = data1[-7:-2]
        pxstr = "http://"+ip+":"+port
        print(pxstr)
        requests.get(url, proxies={"http":pxstr})
    except:
        print('connect failed')
        print("切换回自己的IP: " + requests.get(url,proxies={"http": ""}).text)
    else:
        print('success')  #测试代理ip是否正常使用
        
    new_data={"http":"http://"+ip+":"+port}
    #print(new_data)
    resp = requests.get(url = 'http://ip-api.com/json/%s' % (ip))
    data = resp.json()
    print(data)

    options = webdriver.ChromeOptions()
    #添加IP代理
    options.add_argument("--proxy-server="+pxstr)
    driver = webdriver.Chrome(chrome_options=options)
    driver.get(url)

if __name__ == '__main__':
    url = "https://"  #url用你自己的
    conc_ip(url)