统计淘宝销量

cyy6666

import requests
import re
import json
import random

def url_open(url,keyword,s):
    params={'q':keyword,'sort':'sale-desc', 's':str(s)}
    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/',
            'cookie':''
             }
    r=requests.get(url,headers=headers,params=params)
    return r

def get_ip():
    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'}
    r=requests.get('',headers=headers)
    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,}'
    iplist=re.findall(p,r.text)
    return iplist

def proxy_url_open(url,ip,keyword,s):
    params={'q':keyword,'sort':'sale-desc', 's':str(s)}
    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/',
            'cookie':''
             }
    rip=random.choice(ip)
    proxies={'http':rip}
    while True:
        try:
            r=requests.get(url,headers=headers,params=params,proxies=proxies)
        except:
            print('wait')
            rip=random.choice(ip)
            proxies={'http':rip}
        else:
            break
    return r

def taobao():
    proxy=input("1使用代理;0不使用代理:")
    proxy=int(proxy)
    keyword=input('搜索关键词:')
    key=input('统计关键词:')
    url='https://s.taobao.com/search'
    ip=get_ip()
    count=0
    if proxy==0:
        r=url_open(url,keyword,0)        
    else:
        r=proxy_url_open(url,ip,keyword,0)
    html=re.search(r'g_page_config = (.{,});\n',r.text)
    html=json.loads(html.group(1))
    pages=html['mods']['pager']['data']['totalPage']
    pages=int(pages)
    print(pages)
    html=html['mods']['itemlist']['data']['auctions']
    i=1
    while i < pages:
        for each in html:
            if key in each['title']:
                count+=int(re.search(r'\d{,}',each['view_sales']).group())
        print(str(i)+':'+str(count))
        if proxy==0:
            r=url_open(url,keyword,i*44)        
        else:
            r=proxy_url_open(url,ip,keyword,i*44)
        html=re.search(r'g_page_config = (.{,});\n',r.text)
        html=json.loads(html.group(1))
        html=html['mods']['itemlist']['data']['auctions']
        i=i+1
    for each in html:
        if key in each['title']:
            count+=int(re.search(r'\d{,}',each['view_sales']).group())
    print(str(i)+':'+str(count))

if __name__=='__main__':
    taobao()

层次分析

import re
import json

def geten(le):
    return '  '*le+'-'
def getex(le):
    return '  '*le+'+'

def find(ta,le):
    keys=iter(ta)
    for each in keys:
        if type(ta[each]) is not dict:
            print(geten(le)+each)
        else:
            print(getex(le)+each)
            find(ta[each],le+1)

def taobaotest():
    with open('taobao.txt','r',encoding='utf-8') as f:
        result=re.search(r'g_page_config = (.{,});\n',f.read())
        result=json.loads(result.group(1))
    find(result,0)
    
if __name__=='__main__':
    taobaotest()

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！