爬取2019主要城市房价工资比为空列表

601971945

小白一枚  照猫画虎写的代码  爬取出来是空列表  在网上没找到解决办法
求大佬帮着看一下

爬取的url:http://www.szfce.com/gn/27107.html

1. import requests
   
2. from bs4 import BeautifulSoup
   
3. import re
   
4. import openpyxl
   
5. 
   
6. def open_url(url):
   
7.     headers = {
   
8.         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36'
   
9.     }
   
10. 
    
11.     res = requests.get(url, headers = headers)
    
12.     res.encoding = 'utf-8'
    
13.     return res
    
14. 
    
15. 
    
16. def find_data(res):
    
17.     data = []
    
18.     soup = BeautifulSoup(res.text,'lxml')
    
19.     content = soup.find('article',class_="article-content")
    
20.     targets = content.find_all('p')
    
21.     targets = iter(targets)
    
22.     for each in targets:
    
23.         if each.text.isnumeric():
    
24.             data.append([
    
25.                 re.search(r'\[(.+)\]',next(targets).text).group(1),
    
26.                 re.search(r'\d.*',next(targets).text).group(),
    
27.                 re.search(r'\d.*',next(targets).text).group(),
    
28.                 re.search(r'\d.*',next(targets).text).group()
    
29.             ])
    
30.    
    
31.     return data
    
32. 
    
33. 
    
34. def to_excel(data):
    
35.     wb = openpyxl.Workbook()
    
36.     wb.guess_types = True
    
37.     ws = wb.active
    
38.     ws.append(['城市','平均房价','平均工资','房价工资比'])
    
39.     for each in data:
    
40.         ws.append(each)
    
41. 
    
42.     wb.save("2019全国各大主要城市房价、工资排行榜.xlsx")
    
43. 
    
44. 
    
45. def main():
    
46.     url = 'http://www.szfce.com/gn/27107.html'
    
47.     # url = 'https://news.house.qq.com/a/20170702/003985.htm'
    
48.     res = open_url(url)
    
49.     data = find_data(res)
    
50.     to_excel(data)
    
51. 
    
52. if __name__ == "__main__":
    
53.     main()

复制代码

snaker

给你重写了一下

1. import requests
   
2. from bs4 import BeautifulSoup
   
3. import re
   
4. import openpyxl
   
5. 
   
6. def open_url(url):
   
7.     headers = {
   
8.         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36'
   
9.     }
   
10. 
    
11.     res = requests.get(url, headers = headers)
    
12.     res.encoding = 'utf-8'
    
13.     return res
    
14. 
    
15. 
    
16. def find_data(res):
    
17.     data = []
    
18.     soup = BeautifulSoup(res.text,'lxml')
    
19.     content = soup.find('article',class_="article-content")
    
20.     targets = content.find_all('p')[8:-13]
    
21.     for i in range(len(targets)//5):
    
22.         data.append([
    
23.                 re.findall(r'\[(.+)\]',targets[i*5+1].text)[0],
    
24.                 re.findall(r'\d.*',targets[i*5+2].text)[0],
    
25.                 re.findall(r'\d.*',targets[i*5+3].text)[0],
    
26.                 re.findall(r'\d.*',targets[i*5+4].text)[0]
    
27.             ])
    
28.     return data
    
29. 
    
30. 
    
31. def to_excel(data):
    
32.     wb = openpyxl.Workbook()
    
33.     wb.guess_types = True
    
34.     ws = wb.active
    
35.     ws.append(['城市','平均房价','平均工资','房价工资比'])
    
36.     for each in data:
    
37.         ws.append(each)
    
38. 
    
39.     wb.save("2019全国各大主要城市房价、工资排行榜.xlsx")
    
40. 
    
41. 
    
42. def main():
    
43.     url = 'http://www.szfce.com/gn/27107.html'
    
44.     # url = 'https://news.house.qq.com/a/20170702/003985.htm'
    
45.     res = open_url(url)
    
46.     data = find_data(res)
    
47.     to_excel(data)
    
48. 
    
49. if __name__ == "__main__":
    
50.     main()
    

复制代码

601971945

snaker 发表于 2020-3-23 15:23
给你重写了一下

谢谢 老哥

601971945

snaker 发表于 2020-3-23 15:23
给你重写了一下

话说老哥你知道我那种写发为啥爬出来是空的么？