爬取网站练习

import re
with open('redbull.txt', 'r', encoding='utf-8') as f:
    data = f.read()

title_list = re.findall('<h2>(.*?)</h2>', data)
address_list = re.findall("<p class='mapIco'>(.*?)</p>", data)
email_list = re.findall("<p class='mailIco'>(.*?)</p>", data)
phone_list = re.findall("<p class='telIco'>(.*?)</p>", data)

all_list = list(zip(title_list, address_list, email_list, phone_list))

for item in all_list:
    print("""
        公司：%s
        地址：%s
        邮箱：%s
        电话：%s
    """ % (item[0], item[1], item[2], item[3]))

标签：item,网站,练习,list,爬取,re,title,data,findall
来源： https://www.cnblogs.com/erfeier/p/15824627.html