伯乐在线资讯URL

• 伯乐资讯URL

• # encoding: utf-8
  import requests
  from bs4 import BeautifulSoup
  import csv
  import time
  
  
  base_url = 'http://top.jobbole.com/page/'
  
  session = requests.session()
  inum=0
  
  def zhuqu(page):
      url_list = []
      url = base_url+str(page)+"/"
      # print(url)
      res = session.get(url=url)
      soup = BeautifulSoup(res.text, 'html.parser')
  
      post_nodes = soup.select(".list-posts .media .media-body h3 a")
  
      for post_node in post_nodes:
          post_url = post_node.get("href")
          url_list.append([post_url])
          # i+=1
          # print(i,post_url)
      print(url_list)
      return url_list
  # zhuqu(2)
  
  
  with open("伯乐资讯", 'w', newline="", encoding='utf-8') as csv_out:
          writer = csv.writer(csv_out)
          for i in range(355):
              if i%10==0:
                  time.sleep(1)
              row =zhuqu(i)
              if not row:
                  print("有错误")
                  continue
              else:
                  writer.writerows(row)
                  print(inum,"成功")
                  inum+=1

  代码如上

• 问题：把广告也抓进来了，不知道怎么用css选择来避免抓取这种情况，懂的朋友给提示下。