爬取当当电子书排名

qq1084799589

1. from selenium import webdriver
   
2. import time
   
3. from bs4 import BeautifulSoup
   
4. import re
   
5. from openpyxl import Workbook
   
6. 
   
7. browser = webdriver.Firefox(executable_path="C:\\Program Files\\Mozilla Firefox\\geckodriver.exe")
   
8. #   保存到表格
   
9. wb = Workbook()
   
10. ws = wb.active
    
11. ws.title = "Sheet1"
    
12. Project = [
    
13.     '排名','书名','作者','价格','内容介绍'
    
14. 
    
15. ]
    
16. for i in range(len(Project)):
    
17.     ws.cell(1, i + 1, Project[i])
    
18. url = 'http://e.dangdang.com/rank_detail_page.html?listType=ddds_sale&channelType=all'
    
19. browser.get (url)
    
20. time.sleep(3)
    
21. browser.find_element_by_xpath('//div[contains(text(),"新书榜")]').click()
    
22. [hide]time.sleep(5)
    
23. for i in range(10):
    
24.     browser.execute_script('window.scrollTo(0,document.body.scrollHeight)')
    
25.     time.sleep(3)
    
26. html = browser.page_source
    
27. bs4_html = BeautifulSoup(html,'html.parser')
    
28. n = 2
    
29. for d in bs4_html.find_all(class_='book'):
    
30.     f = []
    
31.     index = re.sub('、','',d.find(class_='index').text)
    
32.     BookName = d.find(class_='tit').text
    
33.     monye = re.findall('￥[0-9].*',d.find(class_='price').text)
    
34.     book = d.find(class_='auth').text
    
35.     summury = d.find(class_='summury').text
    
36.     f.append(index)
    
37.     f.append(BookName)
    
38.     f.append(book)
    
39.     f.append(monye[0])
    
40.     f.append(summury)
    
41.     for i in range(len(f)):
    
42.         ws.cell(n, i + 1, str(f[i]))
    
43.         wb.save("当当网电子书新书排名.xlsx")
    
44.     n +=1

复制代码

[/hide][/hide]