工具包注释fdfs方法

base/BaseCore.py

@@ -25,8 +25,8 @@ from DBUtils.PooledDB import PooledDB
 from fdfs_client.client import get_tracker_conf, Fdfs_client
 import uuid
 
-tracker_conf = get_tracker_conf('D:\\kkwork\\zzsn_spider\\base\\client.conf')
-client = Fdfs_client(tracker_conf)
+# tracker_conf = get_tracker_conf('D:\\kkwork\\zzsn_spider\\base\\client.conf')
+# client = Fdfs_client(tracker_conf)
 
 from obs import ObsClient
 import fitz
@@ -613,48 +613,48 @@ class BaseCore:
             self.r.expire(key, 3600)
             time.sleep(2)
 
-    # 上传至文件服务器,并解析pdf的内容和页数
-    def upLoadToServe(self, pdf_url, type_id, social_code):
-        headers = {}
-        retData = {'state': False, 'type_id': type_id, 'item_id': social_code, 'group_name': '', 'path': '',
-                   'full_path': '',
-                   'category': 'pdf', 'file_size': '', 'status': 1, 'create_by': 'XueLingKun',
-                   'create_time': '', 'page_size': '', 'content': ''}
-        headers['User-Agent'] = self.getRandomUserAgent()
-        for i in range(0, 3):
-            try:
-                resp_content = requests.get(pdf_url, headers=headers, verify=False, timeout=20).content
-                break
-            except:
-                time.sleep(3)
-                continue
-        page_size = 0
-
-        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():
-                        retData['content'] += page.get_text()
-                break
-            except:
-                time.sleep(3)
-                continue
-        if page_size < 1:
-            # pdf解析失败
-            print(f'======pdf解析失败=====')
-            return retData
-        else:
-            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
+    # # 上传至文件服务器,并解析pdf的内容和页数
+    # def upLoadToServe(self, pdf_url, type_id, social_code):
+    #     headers = {}
+    #     retData = {'state': False, 'type_id': type_id, 'item_id': social_code, 'group_name': '', 'path': '',
+    #                'full_path': '',
+    #                'category': 'pdf', 'file_size': '', 'status': 1, 'create_by': 'XueLingKun',
+    #                'create_time': '', 'page_size': '', 'content': ''}
+    #     headers['User-Agent'] = self.getRandomUserAgent()
+    #     for i in range(0, 3):
+    #         try:
+    #             resp_content = requests.get(pdf_url, headers=headers, verify=False, timeout=20).content
+    #             break
+    #         except:
+    #             time.sleep(3)
+    #             continue
+    #     page_size = 0
+    #
+    #     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():
+    #                     retData['content'] += page.get_text()
+    #             break
+    #         except:
+    #             time.sleep(3)
+    #             continue
+    #     if page_size < 1:
+    #         # pdf解析失败
+    #         print(f'======pdf解析失败=====')
+    #         return retData
+    #     else:
+    #         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, year, type_id):
         sel_sql = '''select id from clb_sys_attachment where item_id = %s and year = %s and type_id=%s '''