免责声明:本文仅做技术交流与学习...

爬取后,结合暗黑搜索引擎等等进行进一步搜索.

edu_src.py

import requests, time
from bs4 import BeautifulSoup
for i in range(1, 20):url = f'https://src.sjtu.edu.cn/rank/firm/0/?page={i}'print(f"正在获取第{i}页数据")s = requests.get(url).text# print(s)soup = BeautifulSoup(s, 'html.parser')edu1 = soup.find_all('tr')# print(edu1)for edu in edu1:try:edu_name = edu.a.text# print(edu_name)with open('edu_name.txt', 'a+',encoding='utf-8') as f:f.write(edu_name + '\n')except:passprint(f"{i}页已经写入!!!")