简单爬虫例子2

import requests
from bs4 import BeautifulSoup

def fetch_and_parse(url):
    # 发送HTTP请求到指定URL
    response = requests.get(url)

    # 检查请求是否成功
    if response.status_code == 200:
        # 使用BeautifulSoup解析HTML内容
        soup = BeautifulSoup(response.text, 'html.parser')
        # 查找所有的class为"layout_li ajaxpost"的li元素
        url_cards = soup.find_all('li', {'class': 'layout_li ajaxpost'})
        print(len(url_cards))
        for url_card in url_cards:
            # 提取文章链接
            link = url_card.find('a', {'class': 'imgeffect'})['href']
            # 提取文章封面图片的src属性值
            img_src = url_card.find('img', {'class': 'thumb'})['src']
            # 提取文章标题
            title = url_card.find('h2').get_text().strip()
            # 提取文章分类
            category = url_card.find('span', {'class': 'is_category'}).get_text().strip()

            print("文章链接:", link)
            print("文章封面:", img_src)
            print("文章标题:", title)
            print("文章分类:", category)
            print("-" * 50)  # 打印分隔线以区分不同卡片的信息
    else:
        print(f"无法访问{url}，状态码：{response.status_code}")

# 示例：将你想要爬取的网页URL替换下面的'YOUR_TARGET_URL'
fetch_and_parse('https://www.xxx.com/vcat)