企业基本信息更新

comData/Tyc/baseinfo0227_tyc.py

@@ -8,7 +8,7 @@ import pymongo
 import requests
 from bs4 import BeautifulSoup
 from kafka import KafkaProducer
-
+from selenium.webdriver.edge.service import Service
 import urllib3
 from selenium.webdriver.support.wait import WebDriverWait
 
@@ -38,7 +38,7 @@ from selenium.webdriver.common.by import By
 
 def create_driver():
     path = r'D:\soft\msedgedriver.exe'
-
+    service = Service(path)
     # options = webdriver.EdgeOptions()
     options = {
         "browserName": "MicrosoftEdge",
@@ -47,7 +47,7 @@ def create_driver():
         }
     }
 
-    session = webdriver.Edge(executable_path=path, capabilities=options)
+    session = webdriver.Edge(service=service, capabilities=options)
     return session
 
 
@@ -142,7 +142,7 @@ def redaytowork(com_name, social_code, securitiesCode, securitiesShortName, list
                 else:
                     return count
             except Exception as e:
-                log.info(f'====={social_code}=====获取基本信息失败，重新放入redis=====')
+                log.info(f'====={social_code}=====获取基本信息失败，重新放入redis====={e}')
                 # baseCore.r.lpush('BaseInfoEnterprise:gnqy_socialCode', company_field)
                 Lreputredis(company_field)
                 token.updateTokeen(id_cookie, 2)
@@ -162,7 +162,7 @@ def ifbeforename(company_url):
         try:
             name = businessinfo.find('span', class_='index_history-gray-tags__o8mkl').text
             value = \
-                businessinfo.find('span', class_='index_copy-text__ri7W6').text.replace('展开', '').replace(' ',
+                businessinfo.find('div', class_='index_history-container__VywXO').find('span', class_='index_copy-text__ri7W6').text.replace('展开', '').replace(' ',
                                                                                                           '').replace(
                     '…', '').replace('\n', '').replace('复制', '').split('（')[0]
         except:
@@ -209,8 +209,11 @@ def spiderinfo(company_url, securitiesCode, securitiesShortName, listingDate, ca
     econKind = script['companyOrgType']
     termStart = int(script['fromTime'])
     termStart = datetime.datetime.fromtimestamp(termStart / 1000).strftime('%Y-%m-%d %H:%M:%S')
+    try:
         termEnd = script['toTime']
         termEnd = datetime.datetime.fromtimestamp(termEnd / 1000).strftime('%Y-%m-%d %H:%M:%S')
+    except:
+        termEnd = '无固定期限'
     taxpayerType = script['taxQualification']
     subIndustry = script['industryInfo']['nameLevel3']
     belogOrg = script['regInstitute']
@@ -275,7 +278,7 @@ def spiderinfo(company_url, securitiesCode, securitiesShortName, listingDate, ca
         if value == 'None':
             aa_dic[key] = None
     # 发送kafka
-    # sendkafka(aa_dic)
+    sendkafka(aa_dic)
 
 
 def remove_parentheses(text):
@@ -305,7 +308,7 @@ def spiderwork(soup, receptname, securitiesCode, securitiesShortName, listingDat
         info_t = compamy.find('div', class_='index_name__qEdWi')
         getname = info_t.find('span').text
         log.info(f'接收到的企业名称--{receptname}---采到的企业名称--{getname}')
-        if receptname and getname == receptname:
+        if receptname and (getname == receptname):
             company_url = info_t.find('a')['href']
             break
         elif not receptname:
@@ -404,7 +407,7 @@ if __name__ == '__main__':
         start_time = time.time()
         # 获取企业信息
         # company_field = baseCore.redicPullData('BaseInfoEnterprise:gnqy_socialCode')
-        company_field = '|北京华信瑞德信息技术有限公司|北京华信瑞德信息技术有限公司|||||||||||||1|中国内地|||||||'
+        company_field = '|江苏协昌电子科技股份有限公司|江苏协昌电子科技股份有限公司|||||||||||||1|中国内地|||||||'
 
         if company_field == 'end':
             # 本轮处理完毕，需要发送邮件，并且进入下一轮