init code

山西路桥客户数据处理/API.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Tue Aug 25 11:07:18 2020
+
+@author: rico
+"""
+
+import requests
+
+
+
+def zgc_api(func,data):
+    
+    headers = {
+    'Connection': 'Keep-Alive'
+    }
+    
+    key = 'eRo1#ZFHY5N&GEzV'
+    
+    api = f"http://59.110.219.171:8000/{func}/"
+    print(api)
+    
+    data.update({'key':key})
+    session = requests.session()
+    result = session.post(api,json=data,headers=headers,timeout=600).json()
+    
+    
+    return result

山西路桥客户数据处理/db.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Sep  7 23:08:30 2020
+
+@author: rico
+"""
+
+import pymssql
+
+class MSSQL:
+    
+    def __init__(self,host,db):
+        
+        self.host = host
+        self.db = db
+        
+        self._conn = self.GetConnect()
+        if(self._conn):
+            self._cur = self._conn.cursor()
+            
+    #连接数据库    
+    def GetConnect(self):
+        conn = False
+        
+        if self.host == '123.57.45.119':
+            user = 'zgcprice'
+            pwd = 'zgcprice20200708'
+        elif self.host == '123.56.115.207':
+            user = 'zgcindex'
+            pwd = 'jiayou202006'
+        elif self.host == '10.0.120.131':
+            user = 'sa'
+            pwd = '1qaz@WSX'
+        elif self.host == '10.0.120.79':
+            user = 'sa'
+            pwd = '1qaz@WSX'
+        
+        try:
+            conn = pymssql.connect(
+                host=self.host,
+                user=user,
+                password=pwd,
+                database =self.db,
+                autocommit=True
+            )
+        except Exception as err:
+            print("连接数据库失败, %s" % err)
+        else:
+            return conn
+ 
+    #获取连接信息
+    def GetConnectInfo(self):
+        print( "连接信息：" )
+        print( "服务器:%s , 用户名:%s , 数据库:%s " % (self.host,self.user,self.db))
+    
+    def Close(self):
+        
+        self._cur.close()
+        self._conn.close()
+
+                
+'''
+ms = MSSQL('123.56.115.207','zdindex')
+conn = ms._conn
+cursor = ms._cur
+
+cursor.execute(f"select top 10 *  from zd_week_price")
+cursor.fetchall()
+
+ms.Close()
+
+cursor.close()
+conn.close()
+'''
\ No newline at end of file

山西路桥客户数据处理/name_hash.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Nov 13 11:42:04 2020
+
+@author: rico
+"""
+
+import hashlib
+from API import zgc_api
+from db import MSSQL
+import pandas as pd
+from public_function import *
+'''
+#加载数据
+def LoadData():
+   
+    #创建数据库链接
+    mssql = MSSQL('123.57.45.119','ZI_Service')
+    cursor_zi_service = mssql._cur
+    
+    cursor_zi_service.execute("select * from product_all where sku is Null")
+    df = pd.DataFrame(cursor_zi_service.fetchall(), columns=[tuple[0] for tuple in cursor_zi_service.description])
+    
+    mssql.Close()
+    return df
+'''
+
+def hash_name(name):
+    
+    m = hashlib.md5(name.encode("utf8"))
+    hasn_name = m.hexdigest()
+    
+    return hasn_name
+
+def get_pre_deal():
+    
+    #创建数据库链接
+    mssql = MSSQL('123.57.45.119','ZI_Service')
+    cursor_zi_service = mssql._cur
+    
+    cursor_zi_service.execute("select * from product_all where sku is Null")
+    df = pd.DataFrame(cursor_zi_service.fetchall(), columns=[tuple[0] for tuple in cursor_zi_service.description])
+    
+    #创建数据库链接
+    mssql_new = MSSQL('123.56.115.207','ZI_NEW')
+    cursor_zi_new = mssql_new._cur
+    
+    cursor_zi_new.execute("select * from p_brand where id not in (select pid from p_brand)")
+    brand_df = pd.DataFrame(cursor_zi_new.fetchall(), columns=[tuple[0] for tuple in cursor_zi_new.description]).fillna('无品牌信息')
+    
+    cursor_zi_new.execute("select * from p_category where id not in (select pid from p_category)")
+    category_df = pd.DataFrame(cursor_zi_new.fetchall(), columns=[tuple[0] for tuple in cursor_zi_new.description])
+    
+    #hash产品名称至SKU
+    df['sku'] = df['name'].apply(lambda x: hash_name(x))
+    
+    name_list = df['name'].tolist()
+    #获取预测类别结果
+    data = {
+          "category_info": {
+            "cust_name_list": name_list,
+            "url_name_list":name_list
+          }
+        }
+    res = zgc_api("GetPredictCategory",data)
+    df['predict_cat'] = res['category_list']
+    df['predict_cat_code'] = res['categoryCode_list']
+    
+    #实例化进度条
+    index_ = Index()
+    counter = 1
+    
+    for index,row in df.iterrows():
+        
+        id_ = row['id']
+        sku = row['sku']
+        name = row['name'].strip().upper()
+        
+        print(index_(counter, len(df)-1), end='%')
+        counter += 1
+        
+        pre_cat = row['predict_cat']
+        pre_cat_code = row['predict_cat_code']
+        
+        zi_brandname = '未抽取到数据'
+        zi_brandcode = '未抽取到数据'
+        zi_categoryname = '未抽取到数据'
+        zi_categorycode = '未抽取到数据'
+
+        #抽取品牌
+        search_name = name.split(' ')[0]
+        for index_b,row_brand in brand_df.iterrows():
+            
+            brandcode = row_brand['id']
+            brandname = row_brand['name']
+            cname = row_brand['cname']
+            ename = row_brand['ename'].upper()
+            
+            if len(cname) == 1 or len(ename) == 1:
+                continue
+
+            if len(re.findall(r"[\u4e00-\u9fa5]", search_name)) == 0:
+                
+                if ename in search_name:
+            
+                    zi_brandname = brandname
+                    zi_brandcode = brandcode
+                    break
+            else:
+
+                if cname in search_name:
+                
+                    zi_brandname = brandname
+                    zi_brandcode = brandcode
+                    break
+
+        #抽取类别
+        for index_c,row_cat in category_df.iterrows():
+
+            categorycode = row_cat['id']
+            categoryname = row_cat['name']
+            categoryname_list = row_cat['name'].split('/')
+            
+            for category in categoryname_list:
+                
+                if category in name:
+                    
+                    zi_categoryname = categoryname
+                    zi_categorycode = categorycode
+                    break
+
+        if zi_categoryname == '未抽取到数据':
+            zi_categoryname = pre_cat
+            zi_categorycode = pre_cat_code
+            
+        cursor_zi_service.execute(f"update product_all set zi_brandname = '{zi_brandname}',zi_brandcode = {zi_brandcode},\
+                                  zi_subcategoryname = '{zi_categoryname}',zi_subcategorycode = {zi_categorycode}, \
+                                  predict_category = '{pre_cat}',predict_category_code = {pre_cat_code},sku = '{sku}' where id = {id_}")
+        
+                
+                
+                
+        
+    
+    
+    
+    
\ No newline at end of file

山西路桥客户数据处理/多供应商SKU排重.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Dec 18 11:11:31 2020
+
+@author: rico
+"""
+
+
+from db import MSSQL
+from API import zgc_api
+import math
+import pandas as pd
+import numpy as np
+from public_function import *
+
+
+df = pd.read_excel("/Users/rico/project/中信银行/5000条/中信5000测试数据.xlsx",converters = {'供应商SKU':str})
+
+
+supplier_list = df['供应商名称'].unique().tolist()
+engine = 'SQL'
+df_list = []
+for supplier in supplier_list:
+
+    sup_df = df[df['供应商名称'] == supplier]
+    
+
+    sku_list = sup_df['供应商SKU'].tolist()
+
+
+    #获取SKU匹配结果
+    data = {
+      "params_info": {
+          "channelAlias": f"{supplier}",
+          "cust_sku_list": sku_list,
+          "engine":f"{engine}"
+              }
+          }
+    res = zgc_api("GetSKUMatchResInfo",data)
+    
+    if res['code'] == 0:
+        res_list = [False for i in range(len(sup_df))]
+    else:
+        res_list = [res['res_dict'][sku] for sku in sku_list]
+            
+    sup_df['productcode'] = res_list
+    
+    df_list.append(sup_df)
+    
+result_df = pd.concat(df_list)
+
+result_df.to_excel("中信银行5000条.xlsx")
\ No newline at end of file

山西路桥客户数据处理/录入价格.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Wed Sep 16 14:27:52 2020
+
+@author: rico
+"""
+
+import pandas as pd
+from API import zgc_api
+import pymssql
+from public_function import *
+
+df = pd.read_excel("/Users/rico/Downloads/京东重复链接（修正后链接）.xls",sheet_name = "保留",converters = {'productcode':str})
+
+sku_list = df['productcode'].tolist()
+source_name_list = df['productname'].tolist()
+price_list = df['参考价'].tolist()
+url_list = df['goods_url'].tolist()
+channelId_list = ['DS-JD' for i in range(len(df))]
+
+
+
+
+
+#价格关系入库
+data = {
+          "params_info": {
+            "sku_list": sku_list,
+            "url_name_list": source_name_list,
+            "url_price_list":price_list,
+            "url_list": url_list,
+            "channelId_list": channelId_list
+          }
+        }
+
+res = zgc_api("Stock-InPriceInfo",data)
+
+
+
+
+conn = pymssql.connect(host='123.56.115.207', user='zgcprice3311',password='zgcprice20200628',database= 'zdindex',autocommit=True)
+cursor = conn.cursor()
+
+ 
+cursor.execute(f"select id,goods_id from zd_electricity_price where mall_id ='DS-JD' and (periods = '20200917' or periods = '20200921') and goods_url is Null")
+data = cursor.fetchall()
+df = pd.DataFrame(data, columns=[tuple[0] for tuple in cursor.description])
+
+index_ = Index()
+counter = 1
+        
+           
+            
+            
+
+
+
+
+for index,row in df.iterrows():
+    
+    print(index_(counter, len(df)-1), end='%')
+    counter += 1
+    
+    id_ = row['id']
+    code = row['goods_id']
+    
+    cursor.execute(f"select goods_url from zd_electricity_price where goods_id = '{code}' and periods = '20200914' and mall_id = 'DS-JD'")
+
+    try:
+        url = cursor.fetchone()[0]
+    except:
+        continue
+    cursor.execute(f"update zd_electricity_price set goods_url = '{url}' where id = {id_}")
+   
+    

山西路桥客户数据处理/非重点类建库.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Sep 14 10:11:38 2020
+
+@author: rico
+"""
+
+
+import pymssql
+import pandas as pd
+from API import zgc_api
+
+
+df = pd.read_excel("/Users/rico/project/路桥项目/JD数据/反馈-JD未匹配数据处理基本信息确认0909.xlsx",sheet_name = '建库')
+
+
+conn_zi_lq = pymssql.connect(host='123.57.45.119', user='zgcprice', password='zgcprice20200708',database= f"SXLQ_JD",autocommit=True)
+cursor_zi_lq = conn_zi_lq.cursor()
+
+
+#新建品牌
+newbrand_df = df[df['zi_brandcode'] == "空"][['id','zi_brandname']]
+newbrand_list = newbrand_df['zi_brandname'].apply(lambda x : x.replace("新建品牌：","").strip()).unique().tolist()
+
+
+data = {
+      "params_info": {
+        "brand_list": newbrand_list
+      }
+    }
+
+res = zgc_api("Stock-InbrandInfo",data)
+brand_dict = res['res_dict']
+
+#更新product_all表
+for index,row in newbrand_df.iterrows():
+    
+    _id = row['id']
+    zi_brand_dict = brand_dict[row['zi_brandname'].replace("新建品牌：","").strip()]
+    
+    zi_brand = [key for key in zi_brand_dict][0]
+    zi_brandcode = zi_brand_dict[zi_brand]
+    
+    cursor_zi_lq.execute(f"update product_all set zi_brandname = '{zi_brand}',zi_brandcode = {zi_brandcode} where id = {_id}")
+
+
+#入库
+id_list =  df['id'].tolist()
+
+cust_sku_list = df['sku'].tolist()
+
+channelAlias_list = df['channel_alias'].apply(lambda x:x.replace("SXLQ_","")).tolist()
+
+source_name_list = df['name'].tolist()
+
+price_list = df['price'].apply(lambda x:str(x)).tolist()
+
+url_list = df['url'].tolist()
+
+channelId_list = ["DS-JD" for i in range(len(df))]
+
+brand_list = df['zi_brandname'].tolist()
+
+brandId_list = df['zi_brandcode'].apply(lambda x:str(x)).tolist()
+
+category_list = df['zi_subcategoryname'].tolist()
+
+categoryId_list = df['zi_subcategorycode'].apply(lambda x:str(x)).tolist()
+
+params_list = df['params'].apply(lambda x: eval(x)).tolist()
+
+name_list = df['productname'].apply(lambda x: x.replace("'","''")).tolist()
+
+
+'''
+for params,category in zip(params_list,category_list):
+    
+    cust_paramsAttr_list = [key for key in params]
+
+
+    data = {
+          "params_info": {
+            "category": category,
+            "cust_paramsAttr_list": cust_paramsAttr_list
+          }
+        }
+    res = zgc_api("GetZGCParamsInfo",data)
+    res['paramsAttr_dict']
+'''
+
+
+data = {
+      "params_info": {
+        "brand_list": brand_list,
+        "brandId_list": brandId_list,
+        "category_list": category_list,
+        "categoryId_list": categoryId_list,
+        "params_list": params_list,
+        "name_list": name_list
+      }
+    }
+res = zgc_api("Stock-InProductInfo",data)
+sku_list = res['sku_list']
+
+#更新product_all表
+for _id,sku in zip(id_list,sku_list):
+    
+    cursor_zi_lq.execute(f"update product_all set productcode = '{sku}',remark = Null,state = '9' where id = {_id}")
+    
+    
+#价格关系入库
+data = {
+          "params_info": {
+            "sku_list": sku_list,
+            "url_name_list": source_name_list,
+            "url_price_list":price_list,
+            "url_list": url_list,
+            "channelId_list": channelId_list
+          }
+        }
+res = zgc_api("Stock-InPriceInfo",data)
+
+
+
+
+#对应关系入库
+data = {
+          "params_info": {
+            "cust_sku_list": cust_sku_list,
+            "sku_list": sku_list,
+            "channelAlias_list": channelAlias_list
+          }
+        }
+res = zgc_api("Stock-InSkuRelationshipInfo",data)
+
+
+

常规客户数据处理/API.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Tue Aug 25 11:07:18 2020
+
+@author: rico
+"""
+
+import requests
+
+
+
+def zgc_api(func,data):
+    
+    headers = {
+    'Connection': 'Keep-Alive'
+    }
+    
+    key = 'eRo1#ZFHY5N&GEzV'
+    
+    api = f"http://59.110.219.171:8000/{func}/"
+    print(api)
+    
+    data.update({'key':key})
+    session = requests.session()
+    result = session.post(api,json=data,headers=headers,timeout=600).json()
+    
+    
+    return result

常规客户数据处理/db.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Sep  7 23:08:30 2020
+
+@author: rico
+"""
+
+import pymssql
+
+class MSSQL:
+    
+    def __init__(self,host,db):
+        
+        self.host = host
+        self.db = db
+        
+        self._conn = self.GetConnect()
+        if(self._conn):
+            self._cur = self._conn.cursor()
+            
+    #连接数据库    
+    def GetConnect(self):
+        conn = False
+        
+        if self.host == '123.57.45.119':
+            user = 'zgcprice'
+            pwd = 'zgcprice20200708'
+        elif self.host == '123.56.115.207':
+            user = 'zgcindex'
+            pwd = 'jiayou202006'
+        elif self.host == '10.0.120.131':
+            user = 'sa'
+            pwd = '1qaz@WSX'
+        elif self.host == '10.0.120.79':
+            user = 'sa'
+            pwd = '1qaz@WSX'
+        
+        try:
+            conn = pymssql.connect(
+                host=self.host,
+                user=user,
+                password=pwd,
+                database =self.db,
+                autocommit=True
+            )
+        except Exception as err:
+            print("连接数据库失败, %s" % err)
+        else:
+            return conn
+ 
+    #获取连接信息
+    def GetConnectInfo(self):
+        print( "连接信息：" )
+        print( "服务器:%s , 用户名:%s , 数据库:%s " % (self.host,self.user,self.db))
+    
+    def Close(self):
+        
+        self._cur.close()
+        self._conn.close()
+
+                
+'''
+ms = MSSQL('123.56.115.207','zdindex')
+conn = ms._conn
+cursor = ms._cur
+
+cursor.execute(f"select top 10 *  from zd_week_price")
+cursor.fetchall()
+
+ms.Close()
+
+cursor.close()
+conn.close()
+'''
\ No newline at end of file

常规客户数据处理/多供应商SKU排重.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Dec 18 11:11:31 2020
+
+@author: rico
+"""
+
+
+from db import MSSQL
+from API import zgc_api
+import math
+import pandas as pd
+import numpy as np
+from public_function import *
+
+
+df = pd.read_excel("/Users/rico/project/中信银行/5000条/中信5000测试数据.xlsx",converters = {'供应商SKU':str})
+
+
+supplier_list = df['供应商名称'].unique().tolist()
+engine = 'SQL'
+df_list = []
+for supplier in supplier_list:
+
+    sup_df = df[df['供应商名称'] == supplier]
+    
+
+    sku_list = sup_df['供应商SKU'].tolist()
+
+
+    #获取SKU匹配结果
+    data = {
+      "params_info": {
+          "channelAlias": f"{supplier}",
+          "cust_sku_list": sku_list,
+          "engine":f"{engine}"
+              }
+          }
+    res = zgc_api("GetSKUMatchResInfo",data)
+    
+    if res['code'] == 0:
+        res_list = [False for i in range(len(sup_df))]
+    else:
+        res_list = [res['res_dict'][sku] for sku in sku_list]
+            
+    sup_df['productcode'] = res_list
+    
+    df_list.append(sup_df)
+    
+result_df = pd.concat(df_list)
+
+result_df.to_excel("中信银行5000条.xlsx")
\ No newline at end of file