[已解决]正则搜索出来的数据只能加载一条

Ygh6688

1. <div class="blockcode"><blockquote>import requests
   
2. import re
   
3. from lxml import etree
   
4. 
   
5. def get_url(url):
   
6.     headers = {
   
7.         'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36'
   
8. 
   
9.     }
   
10.     page_text = requests.get(url,headers=headers).text
    
11.     return page_text
    
12. 
    
13. 
    
14. def get_page(html):
    
15.     tittle = re.compile(r'<ul class="gl-warp.*?class="p-price">.*?<i>(\d+).\d+</i>.*?class="p-name.*?<em>([^￥^/^-].*?)</em>',re.S)
    
16. 
    
17.     # tittle = re.compile('<i>(\d+).\d+</i>',re.S)
    
18.     # tittle = re.compile('<em>([^￥^/^-].*?)</em>',re.S)
    
19.     shangpin = re.findall(tittle,html)
    
20.     for i in shangpin:
    
21.       yield{
    
22.         '价格':i[0],
    
23.         '商品':i[1],
    
24.       }
    
25.     print(shangpin)
    
26. 
    
27. 
    
28. def write_file(team):
    
29.       pass
    
30. 
    
31. 
    
32. def main():
    
33.     url = 'https://list.jd.com/list.html?cat=9987,653,655'
    
34.     html = get_url(url)
    
35.     team = get_page(html)
    
36.     for i in team:
    
37.         write_file(i)
    
38. 
    
39. 
    
40. if __name__ == "__main__":
    
41.       main()
    
42. 
    
43. 
    

复制代码

如果我正常分开的打印价格和商品名称就可以出来所有信息，但是合并在一起就只能打印出一条信息求求大佬指出是我正则的的问题还是其他的

最佳答案

月排行榜 / 总排行榜

suchocolate

2020-12-17 15:54:24

1. import requests
   
2. from lxml import etree
   
3. 
   
4. 
   
5. def main():
   
6.     url = 'https://list.jd.com/list.html?cat=9987,653,655'
   
7.     headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) '
   
8.                              'Chrome/72.0.3626.121 Safari/537.36'}
   
9.     r = requests.get(url, headers=headers)
   
10.     result = []
    
11.     html = etree.HTML(r.text)
    
12.     lis = html.xpath('//li[@class="gl-item"]')
    
13.     for li in lis:
    
14.         p_name = li.xpath('./div/div[4]/a/em/text()')[0]
    
15.         p_price = li.xpath('./div/div[3]/strong/i/text()')[0]
    
16.         print(p_name, p_price)
    
17. 
    
18. 
    
19. if __name__ == "__main__":
    
20.     main()

复制代码

跳转到最佳答案楼层

suchocolate

1. import requests
   
2. from lxml import etree
   
3. 
   
4. 
   
5. def main():
   
6.     url = 'https://list.jd.com/list.html?cat=9987,653,655'
   
7.     headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) '
   
8.                              'Chrome/72.0.3626.121 Safari/537.36'}
   
9.     r = requests.get(url, headers=headers)
   
10.     result = []
    
11.     html = etree.HTML(r.text)
    
12.     lis = html.xpath('//li[@class="gl-item"]')
    
13.     for li in lis:
    
14.         p_name = li.xpath('./div/div[4]/a/em/text()')[0]
    
15.         p_price = li.xpath('./div/div[3]/strong/i/text()')[0]
    
16.         print(p_name, p_price)
    
17. 
    
18. 
    
19. if __name__ == "__main__":
    
20.     main()

复制代码

Ygh6688

suchocolate 发表于 2020-12-17 15:54

牛