构建基于山西招生网的数据采集与分析系统

pip install requests beautifulsoup4

import requests

url = 'https://www.sxzs.com/'

response = requests.get(url)

html_content = response.text

print(html_content[:500]) # 打印前500个字符

from bs4 import BeautifulSoup

soup = BeautifulSoup(html_content, 'html.parser')

school_names = [a.text for a in soup.find_all('a') if 'school' in a.get('href', '')]

print(school_names)

headers = {

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'

}

response = requests.get(url, headers=headers)

import time

time.sleep(2) # 每次请求后等待2秒

import csv

with open('schools.csv', mode='w', newline='', encoding='utf-8') as file:

writer = csv.writer(file)

writer.writerow(['School Name'])

writer.writerows([[name] for name in school_names])