python - BeautifulSoup 简单爬虫示例（以 csdn 为例）

谁践踏了优雅 2024-03-22 09:33 38阅读 0赞

## 爬取标题内容 ##

import requests
    from bs4 import BeautifulSoup
    
    url = 'https://lfsun666.blog.csdn.net/article/details/129893244'
    response = requests.get(url)
    
    soup = BeautifulSoup(response.text, 'html.parser')
    title = soup.find('h1', class_='title-article').text.strip()
    content = soup.find('article', class_='baidu_pl').text.strip()
    
    print(title)
    print(content)

## 爬取内容并保存到md文档 ##

import requests
    from bs4 import BeautifulSoup
    
    url = 'https://lfsun666.blog.csdn.net/article/details/129893244'
    
    # 发送GET请求，获取CSDN博客文章的内容
    response = requests.get(url)
    html_content = response.text
    
    # 使用beautifulsoup库解析html内容
    soup = BeautifulSoup(html_content, 'html.parser')
    
    # 获取文章标题和正文内容
    title = soup.find('h1').text.strip() # 标题
    article_content = soup.find('article').text.strip() # 正文内容
    
    # 将文章内容保存为md文档
    filename = title + '.md'
    with open(filename, 'w', encoding='utf-8') as f:
        f.write('# ' + title + '\n\n' + article_content)
    
    print('文章已保存为：' + filename)

## 爬取页面内容 ##

import requests
    from bs4 import BeautifulSoup
    
    url = 'https://lfsun666.blog.csdn.net/article/details/129893244'
    
    # 获取页面内容
    response = requests.get(url)
    html_content = response.content
    
    # 解析html内容并提取文章信息
    soup = BeautifulSoup(html_content, 'html.parser')
    title = soup.find('h1', {
        'class': 'title-article'}).text.strip()
    author = soup.find('a', {
        'class': 'follow-nickName'}).text.strip()
    time = soup.find('span', {
        'class': 'time'}).text.strip()
    zan_count = soup.find('span', {
        'id': 'spanCount'}).text.strip()
    fav_count = soup.find('span', {
        'id': 'get-collection'}).text.strip()
    views_count = soup.find('span', {
        'class': 'read-count'}).text.strip()
    
    # 输出文章信息
    print('标题：', title)
    print('作者：', author)
    print('发布时间：', time)
    print('点赞数：', zan_count)
    print('收藏数：', fav_count)
    print('浏览量：', views_count)

![在这里插入图片描述][d7adb4c06f784f43a016d5fe8afffb29.png]  
由于评论数是动态加载的需要用到selenium，这里不过多展示

[d7adb4c06f784f43a016d5fe8afffb29.png]: https://image.dandelioncloud.cn/pgy_files/images/2024/03/22/c9de7662a96f41ce9f9f8f2eaf4b71ea.png