爬取 meiriyiwen.com 的每日一文和随机文章保存到程序的相同目录下的 article.txt
文件中
import requests
from lxml import etree
import time
import os
def getArticle(url):
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'
}
# get 请求
r = requests.get(url, headers=headers)
# 提取数据
html = etree.HTML