#coding:utf-8

import random
import time
import requests
from lxml import etree


def get_data(url,headers):
    response = requests.get(url = url,headers = headers)
    response.encoding = 'utf-8'
    if response.status_code == 200:
        html = etree.HTML(response.text)
        all_li = html.xpath('//ul[@class=\'tj3_1\']/li')
        for item in all_li:
            new = item.xpath('./a/text()')[0]
            new_url = 'https://news.youth.cn/jsxw/'+item.xpath('./a/@href')[0].strip('.')
            date = item.xpath('./font/text()')[0]
            print('新闻标题为{}\n新闻url地址为{}\n新闻发布时间为{}'.format(new,new_url,date))
def main():
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.55 Safari/537.36 Edg/96.0.1054.34'
    }
    for i in range(10):
        if i == 0:
            url = 'https://news.youth.cn/jsxw/index.htm'
            get_data(url,headers)
        else:
            url = 'https://news.youth.cn/jsxw/index_{}.htm'.format(i)
            get_data(url,headers)
        time.sleep(random.randint(2,4))

if __name__ == '__main__':
    main()

老师我的新闻标题为什么是乱码