qq_41620823的博客

这里使用两种方式做数据爬取 这是网页源码形式 1.beautifulsoup的html.parse解码 import requests from bs4 import BeautifulSoup import csv def get_city_dict(): """获取城市和对应链接字典 第一步""" url = 'http://www.air-level.com/...

import os import requests from bs4 import BeautifulSoup def get_htmls(url, html_numbers): # 得到网页地址列表 response = requests.get(url) soup = BeautifulSoup(response.text, 'html.parser') out...