实战：利用requests和bs4，爬取快代理IP并保存

直接上代码

import requests
from bs4 import BeautifulSoup
import time

headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.122 Safari/537.36'
}

def get_infos(url):
    resp = requests.get(url,headers=headers)
    html = resp.text
    soup = BeautifulSoup(html,'lxml')
    trs = soup.find('tbody').find_all('tr')
    infos = []
    for tr in trs:
        info = list(tr.stripped_strings)
        infos.append(info)
    return infos

def save_data(infos,f):
    for info in infos:
        f.write('{},{},{},{},{},{},{}\n'.format(info[0], info[1], info[2], info[3], info[4], info[5], info[6], ))

def main():
    base_url = "https://www.kuaidaili.com/free/inha/{}/"
    for i_page in range(1,11):
        url = base_url.format(i_page)
        infos = get_infos(url)
        time.sleep(5)
        with open('kuaidaili.csv','a',encoding='utf-8-sig') as f:
            f.write('{},{},{},{},{},{},{}\n'.format('IP','PORT','匿名度','类型','位置','响应速度','最后验证时间'))
            save_data(infos,f)



if __name__ == "__main__":
    main()