python爬虫应用——爬取中关村在线的多个品牌多个交换机设备信息

结果如下

代码

import requests
from bs4 import BeautifulSoup as bs4
def main(name):
   name=name
   url="https://detail.zol.com.cn/switches/{}/".format(name)

   response=requests.get(url=url)
   dict1={}
   html_text=bs4(response.text,'lxml')
   sw_url=html_text.select('.pro-intro')[:3]

   for i in sw_url:
       for j in i.select('h3'):
           name=j.text[1:-1]
           for k in j.select('a'):
               dict1[name]='https://detail.zol.com.cn'+k.attrs['href']
   return dict1



def get_info(items):
   import requests
   from bs4 import BeautifulSoup as bs4
   url=items[1]
   rp=requests.get(url=url).text
   bs4_obj=bs4(rp,'lxml')
   tr=bs4_obj.select('.enterprise-level_table tr')

   dict_info={}
   list_info=[]
   for i in tr:
       for j in i.select('td')[1]:
           list_info.append(j.text)

   dict_info[items[0]]=list_info
   return dict_info

import csv
for n in ['huawei','h3c','ruijie','cisco']:
   for i in main(n).items():
       for j in get_info(i).items():
           with open("./info.csv", 'a', encoding='utf-8', newline='') as f:
               f_csv = csv.writer(f)
               f_csv.writerow([j[0]]+j[1][:8])
           print(j[0],' '.join(j[1][:8]))