extract_count加分修改

BiddingKG/dl/interface/extract.py

@@ -80,6 +80,9 @@ def extractCount(extract_dict,page_attachments,web_source_name):
     dict_pack = _extract.get("prem",{})
     extract_count = 0
     list_code = _extract.get("code",[])
+    word_count = _extract.get("word_count",{})
+    if word_count.get("正文",0)>500:
+        extract_count += 3
     if len(list_code)>0:
         project_code = list_code[0]
     else:
@@ -102,10 +105,12 @@ def extractCount(extract_dict,page_attachments,web_source_name):
                 if _role[0]=="tenderee":
                     tenderee = _role[1]
                 if _role[0]=="win_tenderer":
+                    if _role[1] is not None and _role[1]!="":
+                        extract_count += 2
                     if  win_tenderer=="":
                         win_tenderer = _role[1]
                     if _role[2]!='' and float(_role[2])>0:
-                        extract_count += 1
+                        extract_count += 2
                         if win_bid_price=="":
                             win_bid_price = str(float(_role[2]))
                 if _role[0]=="agency":
@@ -118,15 +123,18 @@ def extractCount(extract_dict,page_attachments,web_source_name):
                 if _role.get("role_name")=="tenderee":
                     tenderee = _role["role_text"]
                 if _role.get("role_name")=="win_tenderer":
+                    if _role["role_text"] is not None and _role["role_text"]!="":
+                        extract_count += 2
                     if  win_tenderer=="":
                         win_tenderer = _role["role_text"]
                     if "role_money" in _role:
                         if str(_role["role_money"]["money"])!='' and float(_role["role_money"]["money"])>0:
-                            extract_count += 1
+                            extract_count += 2
                             if win_bid_price=="":
                                 win_bid_price = str(float(_role["role_money"]["money"]))
                 if _role["role_name"]=="agency":
                     agency = _role["role_text"]
+
                 linklist = _role.get("linklist",[])
                 for link in linklist:
                     for l in link:
@@ -504,7 +512,7 @@ def predict(doc_id,text,title="",page_time="",web_source_no='',web_source_name="
     return _extract_json#, list_articles[0].content, get_ent_context(list_sentences, list_entitys)
 
 
-def test(name,content):
+def test1(name,content):
     user = {
         "content": content,
         "id":name