不会写代码 用DeepSeek实现爬虫

<div class="post_title_wrapper">    <h2 class="m-t-xs text-ellipsis index-post-title text-title"><a href="https://blog.bbskali.cn/4234.html">Homeassistant界面美化</a></h2>
</div>

import requests
from bs4 import BeautifulSoup
import csv
import re
import time

def get_post_details(url, headers):
   try:
       response = requests.get(url, headers=headers)
       response.raise_for_status()
   except Exception as e:
       print(f"获取文章详情失败：{url}，错误：{str(e)}")
       return None, None, None

   soup = BeautifulSoup(response.text, 'html.parser')
   
   # 解析发文时间
   date_li = soup.find('li', class_='meta-date')
   post_date = date_li.find('time').text.strip() if date_li else ''

   # 解析阅读量
   views_li = soup.find('li', class_='meta-views')
   views = 0
   if views_li:
       views_text = views_li.find('span', class_='meta-value').text
       match = re.search(r'(\d+)', views_text.replace(' ', ' '))
       views = match.group(1) if match else 0

   # 解析评论量
   comments_li = soup.find('li', class_='meta-comments')
   comments = 0
   if comments_li:
       comments_tag = comments_li.find('a', class_='meta-value') or comments_li.find('span', class_='meta-value')
       if comments_tag:
           match = re.search(r'(\d+)', comments_tag.text)
           comments = match.group(1) if match else 0

   return post_date, views, comments

def get_all_posts():
   base_url = "https://blog.bbskali.cn"
   headers = {
       'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'
   }
   
   all_data = []
   page_num = 1
   
   while True:
       # 构造分页URL
       url = f"{base_url}/page/{page_num}/" if page_num > 1 else base_url
       
       try:
           response = requests.get(url, headers=headers)
           response.raise_for_status()
       except Exception as e:
           print(f"停止在第 {page_num} 页，错误：{str(e)}")
           break

       soup = BeautifulSoup(response.text, 'html.parser')
       posts = soup.find_all('div', class_='post_title_wrapper')
       
       if not posts:
           break

       for post in posts:
           h2_tag = post.find('h2', class_='index-post-title')
           if not h2_tag:
               continue

           a_tag = h2_tag.find('a')
           if a_tag and a_tag.has_attr('href'):
               title = a_tag.text.strip()
               link = a_tag['href']
               
               # 获取文章详细信息
               post_date, views, comments = get_post_details(link, headers)
               
               # 收集数据
               all_data.append([
                   title,
                   link,
                   post_date,
                   views,
                   comments
               ])
               # 礼貌性延迟
               time.sleep(0.5)

       print(f"已处理第 {page_num} 页，累计文章数：{len(all_data)}")
       page_num += 1

   # 保存数据
   with open('blog_posts_full.csv', 'w', newline='', encoding='utf-8-sig') as f:
       writer = csv.writer(f)
       writer.writerow(['标题', '链接', '发布日期', '阅读量', '评论数'])
       writer.writerows(all_data)
   
   return len(all_data)

if __name__ == "__main__":
   count = get_all_posts()
   print(f"完整数据已保存到 blog_posts_full.csv，总计 {count} 篇文章")

# 执行示例输出
"""
已处理第 1 页，累计文章数：10
已处理第 2 页，累计文章数：20
...
完整数据已保存到 blog_posts_full.csv，总计 56 篇文章
"""