Bläddra i källkod

修改当products有提取时原product只保留标题中产品

lsm 7 månader sedan
förälder
incheckning
92d6f08c84
1 ändrade filer med 3 tillägg och 1 borttagningar
  1. 3 1
      BiddingKG/dl/interface/extract.py

+ 3 - 1
BiddingKG/dl/interface/extract.py

@@ -455,7 +455,7 @@ def predict(doc_id,text,title="",page_time="",web_source_no='',web_source_name="
 
     # data_res = Preprocessing.union_result(Preprocessing.union_result(codeName, prem),list_punish_dic)[0]
     # data_res = Preprocessing.union_result(Preprocessing.union_result(Preprocessing.union_result(codeName, prem),list_punish_dic), list_channel_dic)[0]
-    version_date = {'version_date': '2024-11-07'}
+    version_date = {'version_date': '2024-11-08'}
     data_res = dict(codeName[0], **prem[0], **channel_dic, **product_attrs[0], **product_attrs[1], **payment_way_dic, **fail_reason, **industry, **district, **candidate_dic, **version_date, **all_moneys, **pb_json)
 
     if original_docchannel == 302:
@@ -476,6 +476,8 @@ def predict(doc_id,text,title="",page_time="",web_source_no='',web_source_name="
                 data_res['prem'].pop('Project')
 
     # 把产品属性里面的产品补充到产品列表
+    if len(data_res['product_attrs']['data']) > 0: # 20241108 如果产品单价数量提取到产品的,原来提取的产品只保留标题中的
+        data_res['product'] = [it for it in data_res['product'] if it in title]
     for d in data_res['product_attrs']['data']:
         if isinstance(d['product'], str) and d['product'] not in data_res['product']:
             data_res['product'].append(d['product'])