PyCharm爬取新闻代码

PyCharm是一款功能强大的Python集成开发环境（IDE），它可以用于编写爬虫脚本，包括爬取新闻数据。下面是一个简单的Python爬虫代码示例，使用了requests库来发送HTTP请求获取新闻内容，并BeautifulSoup库解析HTML：

import requests
from bs4 import BeautifulSoup

# 目标新闻网站URL
url = "https://example.com/news"  # 替换为你想爬取的新闻网站地址

def get_news(url):
    try:
        response = requests.get(url)
        response.raise_for_status()  # 检查请求是否成功
        soup = BeautifulSoup(response.text, 'html.parser')
        
        # 获取新闻标题和链接区域
        news_blocks = soup.find_all('div', class_='news-item')  # 类名可能会因网站而异

        for block in news_blocks:
            title = block.h2.a.text  # 标题
            link = block.h2.a['href']  # 链接
            
            print(f'Title: {title}\nLink: {link}\n---')

    except requests.exceptions.RequestException as e:
        print(f"An error occurred: {e}")

get_news(url)