联系人正则补充优化

BiddingKG/dl/interface/Preprocessing.py

@@ -1078,9 +1078,11 @@ def segment(soup,final=True):
     text = re.sub("(?<=[\u4e00-\u9fa5]),|,(?=[\u4e00-\u9fa5])","，",text)
     #替换为中文分号
     text = re.sub("(?<=[\u4e00-\u9fa5]);|;(?=[\u4e00-\u9fa5])","；",text)
+    # 感叹号替换为中文句号
+    text = re.sub("(?<=[\u4e00-\u9fa5])[!！]|[!！](?=[\u4e00-\u9fa5])","。",text)
     #替换"？"为 " " ,update:2021/7/20
     text = re.sub("？"," ",text)
-         
+
 
     #替换"""为"“",否则导入deepdive出错
     text = text.replace('"',"“").replace("\r","").replace("\n","，")
@@ -1925,10 +1927,11 @@ def get_preprocessed_entitys(list_sentences,useselffool=True,cost_time=dict()):
 
             # "联系人"正则补充提取  2021/11/15 新增
             list_person_text = [entity.entity_text for entity in list_sentence_entitys if entity.entity_type=='person']
-            error_text = ['传真','网址','电子邮','联系','联系电','联系地','采购代','邮政编','邮政','电话','手机','手机号','联系人','地址','地点','邮箱','邮编','联系方','招标','招标人','代理','代理人','采购','附件']
+            error_text = ['交易','机构','教育','项目','公司','中标','开标','截标','监督','政府','国家','中国','技术','投标','传真','网址','电子邮',
+                          '联系','联系电','联系地','采购代','邮政编','邮政','电话','手机','手机号','联系人','地址','地点','邮箱','邮编','联系方','招标','招标人','代理','代理人','采购','附件']
             list_person_text = set(list_person_text + error_text)
-            re_person = re.compile("联系人[:：]([\u4e00-\u9fa5]{2,3})(?=联系)|"
-                                   "联系人[:：]([\u4e00-\u9fa5]工)|"
+            re_person = re.compile("联系人[:：]([\u4e00-\u9fa5]工)|"
+                                   "联系人[:：]([\u4e00-\u9fa5]{2,3})(?=联系)|"
                                    "联系人[:：]([\u4e00-\u9fa5]{2,3})")
             list_person = []
             for match_result in re_person.finditer(sentence_text):
@@ -1937,6 +1940,9 @@ def get_preprocessed_entitys(list_sentences,useselffool=True,cost_time=dict()):
                 wordOffset_begin = match_result.start() + 4
                 wordOffset_end = match_result.end()
                 # print(text[wordOffset_begin:wordOffset_end])
+                # 排除一些不为人名的实体
+                if re.search("^[\u4e00-\u9fa5]{7,}([，。]|$)",sentence_text[wordOffset_begin:wordOffset_begin+20]):
+                    continue
                 if entity_text not in list_person_text and entity_text[:2] not in list_person_text:
                     _person = dict()
                     _person['body'] = entity_text

BiddingKG/dl/interface/getAttributes.py

@@ -1129,10 +1129,10 @@ def findAttributeAfterEntity(PackDict,roleSet,PackageList,PackageSet,list_entity
                 if not re.search("电，?话", phone_left):
                     last_phone_mask = False
                     continue
-            if re.search("帐，?号|编，?号|报，?价|证，?号|价，?格|[\(（]万?元[\)）]", phone_left):
+            if re.search("注册[证号]|帐，?号|编，?[号码]|报，?价|证，?号|价，?格|[\(\（]万?元[\)\）]|[a-zA-Z]+\d*$", phone_left):
                 last_phone_mask = False
                 continue
-            if re.search("^\d{0,4}[.,]\d{2,}", phone_right):
+            if re.search("^\d{0,4}[.,]\d{2,}|^[0-9a-zA-Z\.]*@|^\d*[a-zA-Z]+", phone_right):
                 last_phone_mask = False
                 continue
             # if:上一个phone实体不符合条件

BiddingKG/dl/test/test4.py

@@ -68,7 +68,8 @@ if __name__=="__main__":
     # '''
     # print(predict("12",content,title="关于人防工程技术咨询服务项目【重新招标】单一来源谈判的通知"))
     # print(predict("12", text))
+    print(predict("12", content))
     # test("12",text)
-    test("12",content)
+    # test("12",content)
     print("takes",time.time()-_time1)
     pass

BiddingKG/dl/test/测试整个要素提取流程.py

@@ -427,6 +427,8 @@ if __name__=="__main__":
     # 传真：0769-81216222，邮编：523000。(三)，采购人：东莞市道滘镇教育管理中心，地址：广东省东莞市道滘镇花园街1号，联系人：李先生，联系电话：0769-81332303，传真：/，邮编：523000，各有关当事人对中标、成交结果有异议的，可以在中标、成交公告发布之日起7个工作日内以书面形式向(政府采购代理机构)(或采购人)提出质疑，逾期将依法不予受理，'''
     text = codecs.open("C:\\Users\\Administrator\\Desktop\\test12354.txt", "r", encoding="utf8").read()
     content = str(BeautifulSoup(text).find("div", id="pcontent"))
+    from BiddingKG.dl.interface.Preprocessing import tableToText
+    # print("tableToText:",tableToText(BeautifulSoup(re.sub("<html>|</html>|<body>|</body>","",content),"lxml")))
 #     text = '''
 # 采购代理机构：山东立行建设项目管理有限公司地址：山东省临沂市兰山县(区)柳青广州路与蒙河路交汇大官苑社区西沿街A区三楼南侧号，联系方式：17862288900，
 # '''