
完整代码
import requests
import pandas as pd
import yagmail
import random
import csv
from lxml import etree
import schedule
import time
shijian = time.strftime('%Y-%m-%d')
def get_text():
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.129 Safari/537.36 Edg/81.0.416.68'
}
url = 'https://news.163.com/'
res = requests.get(url = url,headers = headers)
etrees = etree.HTML(res.text)
news_show = etrees.xpath('//*[@id="js_top_news"]/div[2]')
finall1 = []
list0 = []
for news in news_show:
finall1.append(news.xpath('./h2/a/@href')