import re import requests from bs4 import BeautifulSoup from concurrent.futures import ThreadPoolExecutor

url = input('请输入网页链接：') keywords = input('请输入要查找的关键词，以逗号分隔：').split(",") pattern = '|' .join(keywords) regex = re.compile(pattern)

session = requests.Session() session.headers.update({'User-Agent': 'Mozilla/5.0'}) response = session.get(url, timeout=10) html = response.text

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

result = regex.search(html) if result: print(result.group())

links = soup.find_all('a') with ThreadPoolExecutor(max_workers=10) as pool: responses = pool.map(session.get, (link.get('href') for link in links if link.get('href').startswith('http')), timeout=10) for response in responses: sub_html = response.text sub_results = regex.findall(sub_html) for sub_result in sub_results: print(sub_result)

对代码进行了修改，添加了用户输入链接和关键词的功能。