2c不高兴的博客

import reimport osimport requestsglobal ii = 0def get_one_page(url): response = requests.get(url) response.encoding = 'utf-8' html = response.text return htmldef get_urls(html): pattern = re.compile('href="(/touxiang/qinglv/.

引入模块import requests //用于请求网页import re //正则表达式，用于解析筛选网页中的信息要爬的网址headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:98.0) Gecko/20100101 Firefox/98.0' }response = requests.get('https://qq.yh31.com/zjbq/',headers=headers) .