selenium批量诚信通会员，重复一条数据

测试积点老人

遍历页面，没有获取全部数据没有报错，获取了第一条数据，没有全部数据

1. <span style="font-weight: normal;">from selenium import webdriver
   
2. from selenium.webdriver.support import expected_conditions as EC
   
3. from selenium.webdriver.support.ui import WebDriverWait
   
4. from selenium.webdriver.common.by import By
   
5. import time
   
6. import pandas as pd
   
7. 
   
8. 
   
9. driver = webdriver.Chrome()
   
10. #发送请求
    
11. driver.get("https://sale.1688.com/factory/home.html")
    
12. wait = WebDriverWait(driver,5)
    
13. #重要：暂停1分钟进行预登陆，此处填写账号密码及验证
    
14. time.sleep(60)
    
15. 
    
16. 
    
17. driver.find_element(By.XPATH,'//*[@id="home-header-searchbox"]').send_keys('诚信通')
    
18. driver.find_element(By.XPATH,'//*[@id="root"]/div[2]/div/div[1]/div/div/div/div[1]/form/fieldset/div/div[2]/button').click()
    
19. time.sleep(1)
    
20. 
    
21. 
    
22. #人为移动driver
    
23. driver.switch_to.window(driver.window_handles[1])
    
24. 
    
25. name = []
    
26. keeptime = []
    
27. nodes =  driver.find_elements(By.CSS_SELECTOR,'#app > div > div.space-company-offer-list-temp > div.offerlist > div')
    
28. for i in range(0,len(nodes),1):
    
29.     name.append(nodes[i].find_element(By.CSS_SELECTOR,'#app > div > div.space-company-offer-list-temp > div.offerlist > div > div:nth-child(1) > a > div.left-container > div.main-content > div.title-container > div.title').text)
    
30.     keeptime.append(nodes[i].find_element(By.CSS_SELECTOR,'#app > div > div.space-company-offer-list-temp > div.offerlist > div > div:nth-child(1) > a > div.left-container > div.main-content > div.desc-container > div.identity-container > div.credit-tag.identity-tag').text)
    
31. 
    
32. for page in range(3):
    
33.     try:
    
34.         print(page)
    
35.     # 定位下一页按钮
    
36.         nextpage_button = driver.find_element(By.LINK_TEXT,'下一页')
    
37.         #点击按键
    
38.         driver.execute_script("arguments[0].click();", nextpage_button)
    
39.         wait = WebDriverWait(driver,5)
    
40.         nodes1 =  driver.find_elements(By.CSS_SELECTOR,'#app > div > div.space-company-offer-list-temp > div.offerlist > div')
    
41.         for i in range(0,len(nodes1),1):
    
42.             name.append(nodes[i].find_element(By.CSS_SELECTOR,'#app > div > div.space-company-offer-list-temp > div.offerlist > div > div:nth-child(1) > a > div.left-container > div.main-content > div.title-container > div.title').text)
    
43.             keeptime.append(nodes[i].find_element(By.CSS_SELECTOR,'#app > div > div.space-company-offer-list-temp > div.offerlist > div > div:nth-child(1) > a > div.left-container > div.main-content > div.desc-container > div.identity-container > div.credit-tag.identity-tag').text)
    
44.     except:
    
45.         pass
    
46. '''保存数据'''
    
47. data = pd.DataFrame({'诚信通会员名称':name,'诚信通开通':keeptime})
    
48. data.to_excel("weibo.xlsx")</span>
    

复制代码

jingzizx

依次断电进行