使用线程从网站查找链接

import threading
import requests
from bs4 import BeautifulSoup

# 定义一个函数来处理单个网页
def find_links(url):
    try:
        response = requests.get(url)
        soup = BeautifulSoup(response.text, 'html.parser')
        links = [a['href'] for a in soup.find_all('a', href=True)]
        print(f"Found {len(links)} links in {url}")
        return links
    except Exception as e:
        print(f"Error processing {url}: {e}")
        return []

# 定义一个线程类
class LinkFinderThread(threading.Thread):
    def __init__(self, url):
        threading.Thread.__init__(self)
        self.url = url

    def run(self):
        find_links(self.url)

# 主程序
if __name__ == "__main__":
    urls = [
        "https://example.com",
        "https://example.org",
        "https://example.net"
    ]

    threads = []
    for url in urls:
        thread = LinkFinderThread(url)
        thread.start()
        threads.append(thread)

    for thread in threads:
        thread.join()