2023/8/12

comData/annualReport_ZJH/fbs_annualreport.py

@@ -92,11 +92,18 @@ def SpiderByZJH(url, payload, dic_info, num, start_time):
     short_name = dic_info[4]
     soup = RequestUrl(url, payload, item_id, start_time)
     if soup == '':
-        return
+        return False
     # 先获取页数
-
+    page = 0
+    try:
         page = soup.find('div', class_='pages').find('ul', class_='g-ul').text
-
+    except:
+        e = f"该企业没有{dic_parms['Catagory2']}数据"
+        state = 0
+        takeTime = baseCore.getTimeCost(start_time, time.time())
+        baseCore.recordLog(social_code, taskType, state, takeTime, dic_parms['url'], f'{e}')
+        return False
+    if page != 0:
         total = re.findall(r'\d+', page)[0]
         r_page = int(total) % 15
         if r_page == 0:
@@ -220,7 +227,7 @@ def SpiderByZJH(url, payload, dic_info, num, start_time):
                             continue
                 else:
                         continue
-
+        return True
 
 def getUrl(code, url_parms, Catagory2_parms):
     # 深市

comData/noticeReport_ZJH/fbs_notice.py

@@ -261,14 +261,16 @@ def SpiderByZJH(url, payload, dic_info, start_time):  # dic_info 数据库中获
     if soup == '':
         return False
     # 先获取页数
+    page = 0
     try:
         page = soup.find('div', class_='pages').find('ul', class_='g-ul').text
     except:
         e = f"该企业没有{dic_parms['Catagory2']}数据"
         state = 0
         takeTime = baseCore.getTimeCost(start_time, time.time())
-        baseCore.recordLog(social_code, taskType, state, takeTime, dic_parms['url'], 'Kafka操作失败')
+        baseCore.recordLog(social_code, taskType, state, takeTime, dic_parms['url'], f'{e}')
         return False
+    if page != 0:
         total = re.findall(r'\d+', page)[0]
 
         r_page = int(total) % 15