爬取淘宝商品的时候输出不了结果

chunguang

利用selenium爬取淘宝商品的时候输出不了结果，求大神：

1. import re
   
2. from selenium import webdriver
   
3. from selenium.common.exceptions import TimeoutException
   
4. from selenium.webdriver.common.by import By
   
5. from selenium.webdriver.support import expected_conditions as EC
   
6. from selenium.webdriver.support.wait import WebDriverWait
   
7. from pyquery import PyQuery as pq
   
8. 
   
9. browser=webdriver.Chrome()
   
10. wait=WebDriverWait(browser,10)
    
11. 
    
12. def search():
    
13.     try:
    
14.         browser.get('https://www.taobao.com')
    
15.         input=wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#q')))
    
16.         submit=wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,'#J_TSearchForm > div.search-button > button')))
    
17.         input.send_keys('手机')
    
18.         submit.click()
    
19.         total=wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#spulist-pager > div > div > div > div.total')))
    
20.         return total.text
    
21.     except TimeoutException:
    
22.         return search()
    
23. 
    
24. def next_page(page_number):
    
25.     try:
    
26.         input = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#spulist-pager > div > div > div > div.form > input')))
    
27.         submit = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, '#spulist-pager > div > div > div > div.form > span.btn.J_Submit')))
    
28.         input.clear()
    
29.         input.send_keys(page_number)
    
30.         submit.click()
    
31.         wait.until(EC.text_to_be_present_in_element((By.CSS_SELECTOR,'#spulist-pager > div > div > div > ul > li.item.active > span'),str(page_number)))
    
32.     except TimeoutException:
    
33.         next_page(page_number)
    
34. 
    
35. def get_products():
    
36.     wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#spulist-grid .grid-container row .grid-item col')))
    
37.     html=browser.page_source
    
38.     doc=pq(html)
    
39.     items=doc('#spulist-grid .grid-container row  .grid-item col').items()
    
40.     for item in items:
    
41.         products={
    
42.                 'images':item.find('.img-box .img').attr('src'),
    
43.                 'price':item.find('.price').text(),
    
44.                 'deal':item.find('.week-sale').text(),
    
45.                 'title':item.find('.feature').text(),
    
46.                 'screen':item.find('.important-key').text()
    
47.         }
    
48.         print(products)
    
49. 
    
50. def main():
    
51.     total=search()
    
52.     total=int(re.compile('(\d+)').search(total).group(1))
    
53.     for i in range(2,total+1):
    
54.         next_page(i)
    
55. 
    
56. if __name__=='__main__':
    
57.     main()

复制代码

凌九霄

1、首先要检查服务器返回是否200
2、检查正则表达式无误

chunguang

凌九霄 发表于 2018-8-17 20:27
1、首先要检查服务器返回是否200
2、检查正则表达式无误

没问题呀，应该是网页的ID、class什么的