import requests from bs4 import BeautifulSoup

获取百度首页

url = 'https://www.baidu.com/' response = requests.get(url)

解析HTML

soup = BeautifulSoup(response.text, 'html.parser')

获取所有链接

links = [] for link in soup.find_all('a'): href = link.get('href') if href and href.startswith('http'): links.append(href)

输出链接

for link in links: print(link)