如何在Python中实现一个简单的爬虫程序

import requests
from bs4 import BeautifulSoup

url = "目标网站的URL"
response = requests.get(url)
html = response.text

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

# 示例：提取新闻标题和链接
news_list = soup.find_all("a", class_="news-title")  # 假设新闻标题使用CSS类名 "news-title"

for news in news_list:
    title = news.text
    link = news["href"]
    print(title, link)

# 示例：将数据存储到文件
with open("news.txt", "w", encoding="utf-8") as f:
    for news in news_list:
        title = news.text
        link = news["href"]
        f.write(f"{title}    {link}
")

import time

# 示例：设置延时和爬取数量
interval = 2  # 延时2秒
count = 0  # 爬取数量计数器

for news in news_list:
    if count < 10:  # 爬取10条新闻
        title = news.text
        link = news["href"]
        print(title, link)

        count += 1
        time.sleep(interval)  # 延时
    else:
        break