update according new product database

README.md

@@ -4,14 +4,16 @@ ZOL爬虫补惨
 
 1、实体化对象
     
-    参数：指数类别编码 string
+    参数：指数类别名称 string
     
-    CRAWLER('0506')
+    CRAWLER('空调')
 
 2、调用对象爬取方法，返回结果字典
 
     方法：crawl_zol()
     
     参数：要补参产品的品牌型号 string
+    crawl_zol('格力（GREE）KFR-72GW/(72558)NHAD-3')
     
-    返回：{param:value}
\ No newline at end of file
+    返回：{param:value}
+    {'产品系列': '绿嘉园系列', '产品型号': '爬取不到数据', '空调类别': '壁挂式空调', '冷暖类型': '冷暖电辅', '能效等级': '三级能效', '匹数': '大3.0P', '变频/定频': '定频'}
\ No newline at end of file

ZOL_Crawler.py

@@ -13,11 +13,11 @@ from lxml import etree
 
 class CRAWLER:
     
-    def __init__(self, categorycode):
+    def __init__(self, zgc_categoryname):
         
-        self.conn = pymssql.connect('123.56.115.207','zgcindex','jiayou2017+2018','ZI_DataBase')
-        self.zol_rel_data = self.get_zol_attribute_relation(categorycode)
-        self.necessary_attrs = self.get_necessary_attrs(categorycode)
+        self.conn = pymssql.connect(host='123.56.115.207', user='zgcprice3311',password='admin@2018@)!*',database= 'ZI_NEW',autocommit=True)
+        self.zol_rel_data = self.get_zol_attribute_relation(zgc_categoryname)
+        self.necessary_attrs = self.get_necessary_attrs(zgc_categoryname)
         
         self.headers = {
                     'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36',
@@ -32,18 +32,18 @@ class CRAWLER:
                 }
         self.basic_url = "http://detail.zol.com.cn/index.php?c=SearchList&keyword="
         
-    def get_zol_attribute_relation(self,zgc_category_code):
+    def get_zol_attribute_relation(self,zgc_categoryname):
         '''
         获取ZOL参数对应关系
         '''
         try:
             zol_rel_data = pd.DataFrame()
             cursor = self.conn.cursor()
-            cursor.execute("SELECT * FROM Product_Relation_Attribute_SubTitle where ZI_SubCategoryCode = '"+zgc_category_code+"' and Source = 'ZOL'")
+            cursor.execute(f"SELECT * FROM p_skusubtitle_out_map where categoryname = '{zgc_categoryname}' and frm = 'ZOL'")
             try:
                 data_source = [v for v in cursor.fetchall()]
             except:
-                print(str(zgc_category_code) + " 该类别产品参数项无zol对应关系")
+                print(str(zgc_categoryname) + " 该类别产品参数项无zol对应关系")
                 return zol_rel_data
             zol_rel_data = pd.DataFrame(data_source,columns=[tuple[0] for tuple in cursor.description])
             
@@ -53,17 +53,17 @@ class CRAWLER:
 
         except:
             print('链接失败,重新链接')
-            return self.get_zol_attribute_relation(zgc_category_code)
+            return self.get_zol_attribute_relation(zgc_categoryname)
     
-    def get_necessary_attrs(self,zgc_category_code):
+    def get_necessary_attrs(self,zgc_categoryname):
         '''
         获取对应类别参数项
         '''
         try:
             cursor = self.conn.cursor()
-            cursor.execute("select distinct SubTitle from vw_relation_property where SubCategoryCode = '"+zgc_category_code+"' and (ISimportant = 1 or ispeijian = 1)")
+            cursor.execute(f"select subtitle from vw_property where name = '{zgc_categoryname}' and left(identy,1) = 1")
             data_source = [v for v in cursor.fetchall()]
-            attribute_data_list = pd.DataFrame(data_source,columns=[tuple[0] for tuple in cursor.description])['SubTitle'].tolist()
+            attribute_data_list = pd.DataFrame(data_source,columns=[tuple[0] for tuple in cursor.description])['subtitle'].tolist()
             
             cursor.close()     
             self.conn.close()  
@@ -72,7 +72,7 @@ class CRAWLER:
         
         except:
             print('链接失败,重新链接')
-            return self.get_necessary_attrs(zgc_category_code)
+            return self.get_necessary_attrs(zgc_categoryname)
         
     def get_reponse(self,url):
         '''
@@ -164,7 +164,7 @@ class CRAWLER:
         #create zol relationship attribute dict
         dic = dict()
         for attr in self.necessary_attrs:
-            dic[attr] = [v if "，" not in str(v) else [v_ for v_ in v.split("，")] for v in self.zol_rel_data[self.zol_rel_data['ZI_SubTitle'] == attr]['Other_SubTitle'].unique().tolist()]
+            dic[attr] = [v if "，" not in str(v) else [v_ for v_ in v.split("，")] for v in self.zol_rel_data[self.zol_rel_data['subtitle'] == attr]['outsubtitle'].unique().tolist()]
 
         #get need data
         get_data_list = []
@@ -200,5 +200,6 @@ class CRAWLER:
     
 if __name__ == '__main__':
 
-    crawler = CRAWLER('0506')
-    res = crawler.crawl_zol('东芝2823am')
\ No newline at end of file
+    crawler = CRAWLER('空调')
+    res = crawler.crawl_zol('格力（GREE）KFR-72GW/(72558)NHAD-3')
+    print(res)
\ No newline at end of file