政策法规 10/17

comData/policylaw/BaseCore.py

@@ -20,9 +20,6 @@ from DBUtils.PooledDB import PooledDB
 # import sys
 # sys.path.append('D://zzsn_spider//base//fdfs_client')
 
-from fdfs_client.client import get_tracker_conf, Fdfs_client
-tracker_conf = get_tracker_conf('D:\\kkwork\\zzsn_spider\\comData\\policylaw\\client.conf')
-client = Fdfs_client(tracker_conf)
 
 from obs import ObsClient
 import fitz
@@ -444,72 +441,8 @@ class BaseCore:
     # def doc_page(self,file_path):
     #     doc = Document(file_path)
     #     return len(doc.sections)
-    def pdf_content(self,resp_content):
-        # 解析pdf文件内容
-        content = ''
-        for i in range(0, 3):
-            try:
-                result = client.upload_by_buffer(resp_content, file_ext_name='pdf')
-                with fitz.open(stream=resp_content, filetype='pdf') as doc:
-                    # page_size = doc.page_count
-                    for page in doc.pages():
-                        content += page.get_text()
-                break
-            except:
-                time.sleep(3)
-                continue
-        return content
 
-    # 替换为绝对路径之后，解析出来a.href
-    def uploadToserver(self,file_href,item_id):
-        category = os.path.splitext(file_href)[1]
-        # 上传至文件服务器
-        headers = {}
-        retData = {'state': False, 'type_id': 7, 'item_id': item_id, 'group_name': 'group1', 'path': '',
-                   'full_path': '',
-                   'category': category, 'file_size': '', 'status': 1, 'create_by': 'XueLingKun',
-                   'create_time': '', 'page_size': '', 'content': ''}
-        headers['User-Agent'] = self.getRandomUserAgent()
 
-        resp_content = ''
-        for i in range(0, 3):
-            try:
-                resp_content = requests.get(file_href, headers=headers, verify=False, timeout=20).content
-                break
-            except:
-                time.sleep(3)
-                continue
-        if resp_content:
-            pass
-        else:
-            return retData
-        # page_size = 0
-        # if category == '.doc' or category == '.docx':
-        #     # page_size = self.doc_page(file_href)
-        #     return retData
-        # if category == '.pdf' or category == '.PDF':
-        #     page_size = self.pdf_page(resp_content)
-        for i in range(0, 3):
-            try:
-                result = client.upload_by_buffer(resp_content,file_ext_name=category.replace('.',''))
-                self.getLogger().info('-------文件上传成功------')
-                break
-            except:
-                time.sleep(3)
-                continue
-        # if page_size>0:
-        #     pass
-        # else:
-        #     self.getLogger().info(f'======解析失败=====')
-        #     return retData
-        time_now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
-        retData['state'] = True
-        retData['path'] = bytes.decode(result['Remote file_id']).replace('group1', '')
-        retData['full_path'] = bytes.decode(result['Remote file_id'])
-        retData['file_size'] = result['Uploaded size']
-        retData['create_time'] = time_now
-        # retData['page_size'] = page_size
-        return retData
 
     def secrchATT(self,item_id,file_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 '''
@@ -518,7 +451,7 @@ class BaseCore:
         return selects
 
     #插入到att表 返回附件id
-    def tableUpdate(self,retData,com_name,file_name,num):
+    def tableUpdate(self,retData,com_name,file_name,num,pub_time):
             item_id = retData['item_id']
             type_id = retData['type_id']
             group_name = retData['group_name']
@@ -533,12 +466,12 @@ class BaseCore:
             order_by = num
 
 
-            Upsql = '''insert into clb_sys_attachment(name,type_id,item_id,group_name,path,full_path,category,file_size,order_by,status,create_by,create_time,object_key,bucket_name) values(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)'''
+            Upsql = '''insert into clb_sys_attachment(name,type_id,item_id,group_name,path,full_path,category,file_size,order_by,status,create_by,create_time,object_key,bucket_name,publish_time) values(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)'''
 
             values = (
                 file_name, type_id, item_id, group_name, path, full_path, category, file_size, order_by,
                 status, create_by,
-                create_time,path,'zzsn')
+                create_time,path,'zzsn',pub_time)
 
             self.cursor_.execute(Upsql, values)  # 插入
             self.cnx_.commit()  # 提交