修改证监会name加上.pdf

comData/noticeReport/证监会-公告.py

-import json
+import json
@@ -53,7 +53,7 @@ def uptoOBS(pdf_url,pdf_name,type_id,social_code):
     page_size = 0
     for i in range(0, 3):
         try:
-            name = pdf_name + '.pdf'
+            name = pdf_name
             now_time = time.strftime("%Y-%m")
             result = obsClient.putContent('zzsn', 'QYNotice/'+name, content=response.content)
             with fitz.open(stream=response.content, filetype='pdf') as doc:
@@ -89,7 +89,8 @@ def uptoOBS(pdf_url,pdf_name,type_id,social_code):
 def secrchATT(item_id, name, type_id,order_by):
     sel_sql = '''select id from clb_sys_attachment where item_id = %s and name = %s and type_id=%s and order_by=%s '''
     cursor_.execute(sel_sql, (item_id, name, type_id,order_by))
-    selects = cursor_.fetchone()
+    select = cursor_.fetchall()
+    selects = select[-1]
     return selects
 
 # 插入到att表 返回附件id
@@ -124,7 +125,7 @@ def tableUpdate(retData, com_name, year, pdf_name, num):
         cnx_.commit()  # 提交
     except Exception as e:
         print(e)
-    log.info("更新完成:{}".format(Upsql))
+    log.info(f"更新完成:{item_id}===={pdf_name}")
     selects = secrchATT(item_id, pdf_name, type_id,order_by)
     id = selects[0]
     return id
@@ -282,7 +283,7 @@ def GetContent(pdf_url, pdf_name, social_code, year, pub_time, start_time,com_na
     #判断文件是否已经存在obs服务器中
     # file_path = 'QYNotice//浙江国祥股份有限公司首次公开发行股票并在主板上市暂缓发行公告'
     now_time = time.strftime("%Y-%m")
-    file_path = 'QYNotice/'+pdf_name+'.pdf'
+    file_path = 'QYNotice/'+pdf_name
     response = obsClient.getObjectMetadata('zzsn', file_path)
     if response.status >= 300:
         log.info('=====文件不存在obs=====')
@@ -410,7 +411,7 @@ def SpiderByZJH(url, payload, dic_info, start_time,num):  # dic_info 数据库
             pdf_url_info = td_list[2]
             # print(pdf_url)
             pdf_url = pdf_url_info['onclick'].strip('downloadPdf1(').split(',')[0].strip('\'')
-            name_pdf = pdf_url_info['onclick'].strip('downloadPdf1(').split('\',')[1].strip('\'')
+            name_pdf = pdf_url_info['onclick'].strip('downloadPdf1(').split('\',')[1].strip('\'') + '.pdf'
 
             pub_time = pdf_url_info['onclick'].strip('downloadPdf1(').split('\',')[2].strip('\'')
             #todo:判断发布日期是否是日期格式
@@ -489,7 +490,7 @@ if __name__ == '__main__':
         start_time = time.time()
         # 获取企业信息
         # social_code = baseCore.redicPullData('NoticeEnterprise:gnqy_socialCode')
-        social_code = '91440500617540496Q'
+        social_code = '91110108740053589U'
         # 判断 如果Redis中已经没有数据，则等待
         if social_code == None:
             time.sleep(20)
@@ -531,6 +532,7 @@ if __name__ == '__main__':
             count += 1
             runType = 'NoticeReportCount'
             baseCore.updateRun(social_code, runType, count)
+        break
     cursor.close()
     cnx.close()
     baseCore.close()