update

scripts/nasa1.py

@@ -73,7 +73,9 @@ def scrape():
         # 解析 JSON 数据
         json_data = response.json()
         # 遍历数据并下载文件
-        for row in json_data['ROWS']:
+        print("total:" + str(json_data['RECORDS']))
+        for index, row in enumerate(json_data['ROWS']):
+            print("index:"+str(index))
             part_number = row[0]  # 部件编号
             file_links_str = row[4]  # 文件链接
 
@@ -209,7 +211,7 @@ def scrape():
                         file_response = requests.get(file_url)
                         file_response.raise_for_status()
 
-                        # 保存文件
+                        # 保存文件1685+431+314
                         file_path = os.path.join(folder_path, os.path.basename(file_url))
                         with open(file_path, 'wb') as file:
                             file.write(file_response.content)
@@ -226,15 +228,19 @@ def scrape():
             device_batch=None
             manufacturer=row[2]
             experiment_date=row[3]
-            data_db = [get_md5(row[0]), 'Crawler', datetime.now(), None, None, None,
+            origin_data = ','.join(row)
+
+            data_db = [get_md5(''.join([device_name,device_function,manufacturer])), 'Crawler', datetime.now(), None, None, None,
                        device_type,
                        device_name, device_mode,
                        device_function,
                        device_batch, manufacturer,
                        experiment_date,
-                       'NASA', None, None, ','.join(upload_ids)
+                       'NASA', None, None, str(upload_ids),origin_data
                        ]
             save_to_db_import_record(nasa1_connection, data_db)
+    except Exception as e:
+        print(e)
     finally:
         # 关闭游标和连接
         nasa1_connection.close()