统计淘宝销量

cyy6666

1. import requests
   
2. import re
   
3. import json
   
4. import random
   
5. 
   
6. def url_open(url,keyword,s):
   
7.     params={'q':keyword,'sort':'sale-desc', 's':str(s)}
   
8.     headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.141 Safari/537.36 Edg/87.0.664.75','referer':'https://s.taobao.com/',
   
9.             'cookie':''
   
10.              }
    
11.     r=requests.get(url,headers=headers,params=params)
    
12.     return r
    
13. 
    
14. def get_ip():
    
15.     headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.141 Safari/537.36 Edg/87.0.664.75'}
    
16.     r=requests.get('',headers=headers)
    
17.     p=r'(?:(?:25[0-5]|2[0-4]\d|[01]{0,1}\d{0,1}\d)\.){3}(?:25[0-5]|2[0-4]\d|[01]{0,1}\d{0,1}\d):[^@]{1,}'
    
18.     iplist=re.findall(p,r.text)
    
19.     return iplist
    
20. 
    
21. def proxy_url_open(url,ip,keyword,s):
    
22.     params={'q':keyword,'sort':'sale-desc', 's':str(s)}
    
23.     headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.141 Safari/537.36 Edg/87.0.664.75','referer':'https://s.taobao.com/',
    
24.             'cookie':''
    
25.              }
    
26.     rip=random.choice(ip)
    
27.     proxies={'http':rip}
    
28.     while True:
    
29.         try:
    
30.             r=requests.get(url,headers=headers,params=params,proxies=proxies)
    
31.         except:
    
32.             print('wait')
    
33.             rip=random.choice(ip)
    
34.             proxies={'http':rip}
    
35.         else:
    
36.             break
    
37.     return r
    
38. 
    
39. def taobao():
    
40.     proxy=input("1使用代理;0不使用代理:")
    
41.     proxy=int(proxy)
    
42.     keyword=input('搜索关键词:')
    
43.     key=input('统计关键词:')
    
44.     url='https://s.taobao.com/search'
    
45.     ip=get_ip()
    
46.     count=0
    
47.     if proxy==0:
    
48.         r=url_open(url,keyword,0)        
    
49.     else:
    
50.         r=proxy_url_open(url,ip,keyword,0)
    
51.     html=re.search(r'g_page_config = (.{,});\n',r.text)
    
52.     html=json.loads(html.group(1))
    
53.     pages=html['mods']['pager']['data']['totalPage']
    
54.     pages=int(pages)
    
55.     print(pages)
    
56.     html=html['mods']['itemlist']['data']['auctions']
    
57.     i=1
    
58.     while i < pages:
    
59.         for each in html:
    
60.             if key in each['title']:
    
61.                 count+=int(re.search(r'\d{,}',each['view_sales']).group())
    
62.         print(str(i)+':'+str(count))
    
63.         if proxy==0:
    
64.             r=url_open(url,keyword,i*44)        
    
65.         else:
    
66.             r=proxy_url_open(url,ip,keyword,i*44)
    
67.         html=re.search(r'g_page_config = (.{,});\n',r.text)
    
68.         html=json.loads(html.group(1))
    
69.         html=html['mods']['itemlist']['data']['auctions']
    
70.         i=i+1
    
71.     for each in html:
    
72.         if key in each['title']:
    
73.             count+=int(re.search(r'\d{,}',each['view_sales']).group())
    
74.     print(str(i)+':'+str(count))
    
75. 
    
76. if __name__=='__main__':
    
77.     taobao()

复制代码

层次分析

1. import re
   
2. import json
   
3. 
   
4. def geten(le):
   
5.     return '  '*le+'-'
   
6. def getex(le):
   
7.     return '  '*le+'+'
   
8. 
   
9. def find(ta,le):
   
10.     keys=iter(ta)
    
11.     for each in keys:
    
12.         if type(ta[each]) is not dict:
    
13.             print(geten(le)+each)
    
14.         else:
    
15.             print(getex(le)+each)
    
16.             find(ta[each],le+1)
    
17. 
    
18. def taobaotest():
    
19.     with open('taobao.txt','r',encoding='utf-8') as f:
    
20.         result=re.search(r'g_page_config = (.{,});\n',f.read())
    
21.         result=json.loads(result.group(1))
    
22.     find(result,0)
    
23.    
    
24. if __name__=='__main__':
    
25.     taobaotest()

复制代码

现在淘宝需要cookie，需要我们登录账号，刷新页面就可以获取cookie，cookie很快就会失效，需要退出账号重新登陆

更新cookie还挺麻烦的，不知道大佬们有什么好方法

本来想发图的，好像没有这个选项

新人，请大佬指教

zhiweng07

果然厉害！佩服佩服！

cyy6666

zhiweng07 发表于 2021-2-16 08:46
果然厉害！佩服佩服！