每日一爬之爬取自定义车型和价位的汽车（好久没爬了哈哈哈~）

snail:)

1. import requests
   
2. import bs4
   
3. import re
   
4. import openpyxl
   
5. def open_url(url):
   
6. 
   
7.     headers = {'user-agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'}
   
8.     html = requests.get(url,headers = headers)
   
9.     '''
   
10.     with open('car.txt','w',encoding = html.encoding)as f:
    
11.         f.write(html.text)
    
12.     '''
    
13.     return [html,url]
    
14. 
    
15. def find_data(html):
    
16.     soup = bs4.BeautifulSoup(html.text,'html.parser')
    
17.     bs4_data = soup.find_all('p',class_='price')
    
18.     car_data_list = []
    
19.    
    
20.     for each in bs4_data:
    
21.         car_data_list.append([re.search(r'(.+)报价',each.a['title'].strip()).group(1),re.search(r'(.+)万元',each.text.strip()).group(1)])
    
22.         
    
23.     return car_data_list
    
24. def save_as_excel(data,name):
    
25.     wb = openpyxl.Workbook()
    
26.     ws = wb.active
    
27. 
    
28.     ws['A1'] = '品牌'
    
29.     ws['B1'] = '车价'
    
30.     for each in data:
    
31.         ws.append(each)
    
32.     wb.save(name)
    
33. def main():
    
34.     car = {'2':'小型车','4':'中型车','6':'大型车'}
    
35.     url_data1 = input('请输入车型[小型：2，中型：4，大型：6]：')
    
36.     url_data2 = input('请输入价位(万元)[n_m]：')
    
37.     first_url = 'http://db.auto.sina.com.cn'
    
38. 
    
39.     url = first_url + '/list-' + url_data1 + '-0-' + url_data2 + '-0-0-0-0-0-9-0-1.html'
    
40.     html = open_url(url)[0]
    
41.    
    
42.     name = car[url_data1] + url_data2 + '万元价位汇总.xlsx'
    
43.     data = find_data(html)
    
44.     save_as_excel(data,name)
    
45.    
    
46. if __name__ == '__main__':
    
47.     main()

复制代码

焰虎

大佬你好，你这个写入xlsx没有数据是什么问题