修复特殊站源中标表达

BiddingKG/dl/interface/Preprocessing.py

@@ -2293,6 +2293,8 @@ def get_preprocessed_article(articles,cost_time = dict(),useselffool=True):
         article_processed = re.sub('备选中标人', '第二候选人', article_processed)  # 341344142 # 2023/7/17 特殊表达修改
         if web_source_no.startswith('DX002756-'):
             article_processed = re.sub('状态：(进行中|已结束)单位', '，项目单位', article_processed)  # 376225646
+        if web_source_no.startswith('DX006116-') and re.search('结果公告如下：.{5,50}，单位名称：', article_processed):  # 2023/11/20 特殊处理 381591924 381592533 这种提取不到情况
+            article_processed = re.sub('，单位名称：', '，供应商名称：', article_processed)
         ser = re.search('(采购|招标|比选)人(名称)?/(采购|招标|比选)?代理机构(名称)?：(?P<tenderee>[\w（）]{4,25}(/[\w（）]{4,25})?)/(?P<agency>[\w（）]{4,25})[，。]', article_processed)
         if ser:
             article_processed = article_processed.replace(ser.group(0), '采购人名称：%s，采购代理机构名称：%s，' % (ser.group('tenderee'), ser.group('agency')))

BiddingKG/dl/interface/extract.py

@@ -342,7 +342,7 @@ 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': '2023-11-17'}
+    version_date = {'version_date': '2023-11-20'}
     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)
 
     '''最终检查修正招标、中标金额'''