用python爬取浙江省统计局上的表格

snail:)

1. import requests
   
2. import bs4
   
3. import re
   
4. import openpyxl
   
5. def open_url(url):
   
6.     '''
   
7.     获取网页请求不解释了
   
8.     '''
   
9.     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'}
   
10.     html = requests.get(url,headers = headers)
    
11.     html.encoding = 'utf-8'
    
12.     #print(html.text)
    
13.     return html
    
14. def save_to_excel(data,name):
    
15.     '''
    
16.     将数据保存为EXCEL文件，传入的数据必须是列表的形式，其实是列表里面包含列表，传入是按行传的
    
17.     '''
    
18.     wb = openpyxl.Workbook()
    
19.     ws = wb.active
    
20.     for each in data:
    
21.         ws.append(each)
    
22.     wb.save(name)
    
23. def find_data(html):
    
24.     soup = bs4.BeautifulSoup(html.text,'html.parser')#用bs4模块获取网页结构
    
25.     data = soup.find_all('tr',style="height: 14.25pt")#抓取到需要的区域
    
26.     #print(data.text)
    
27.     data_list = []#用于保存数据
    
28.     for i in range(len(data)):
    
29.         each_ = data[i].text.strip().split('\n\n\n')#提取数据去空格，进行切片等
    
30.         data_list.append(each_)#添加到列表
    
31.     return data_list
    
32. def main():
    
33.     url = 'http://tjj.zj.gov.cn/tjsj/ydsj/gy/2017/201702/t20170224_192095.html'
    
34.     html = open_url(url)
    
35.     data = find_data(html)
    
36.     save_to_excel(data,'浙江工业.xlsx')
    
37. 
    
38. if __name__=='__main__':
    
39.     main()
    

复制代码