Update: Refactor to absolute imports, fix QPS limits, and enhance Gitea sync with SQLite support

2026-07-21 10:25:29 +08:00
parent ef04fc5627
commit 97d9d98b4c
67 changed files with 1691 additions and 457 deletions
@@ -0,0 +1,73 @@
+
+import os
+import base64
+import requests
+import json
+from pathlib import Path
+
+def get_access_token(api_key, secret_key):
+    url = f"https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id={api_key}&client_secret={secret_key}"
+    response = requests.request("POST", url)
+    return response.json().get("access_token")
+
+def test_table_v2(image_path, api_key, secret_key):
+    # 表格识别V2接口
+    request_url = "https://aip.baidubce.com/rest/2.0/ocr/v1/table"
+    
+    with open(image_path, "rb") as f:
+        img = base64.b64encode(f.read())
+
+    params = {
+        "image": img,
+        "is_sync": "true",
+        "request_type": "excel"
+    }
+    access_token = get_access_token(api_key, secret_key)
+    request_url = request_url + "?access_token=" + access_token
+    headers = {'content-type': 'application/x-www-form-urlencoded'}
+    response = requests.post(request_url, data=params, headers=headers)
+    
+    return response.json()
+
+if __name__ == "__main__":
+    api_key = "kIehdWbbVD85K18qZYz6SeUf"
+    secret_key = "RCXTgmVjJJkNNMhfY5ASab0xY3mvF6d7"
+    
+    input_dir = Path(r"F:\Administrator\桌面\OCR系统_Release\data\input")
+    images = list(input_dir.glob("*.jpg")) + list(input_dir.glob("*.png"))
+    
+    if not images:
+        print("错误: 桌面 Release 目录下没有找到图片文件")
+    else:
+        latest_image = max(images, key=os.path.getmtime)
+        print(f"正在使用【表格识别V2】接口测试图片: {latest_image.name}")
+        
+        result = test_table_v2(str(latest_image), api_key, secret_key)
+        
+        # 打印表格外的文字（header/footer）
+        if "tables_result" in result:
+            print("\n--- 表格识别结果 ---")
+            for table in result["tables_result"]:
+                print("\n[Header 区域]:")
+                header = table.get("header", [])
+                for cell in header:
+                    print(f"- {cell.get('words')}")
+                
+                print("\n[Footer 区域]:")
+                footer = table.get("footer", [])
+                for cell in footer:
+                    print(f"- {cell.get('words')}")
+        elif "result" in result and "tables_result" in result["result"]:
+            print("\n--- 表格识别结果 (嵌套结构) ---")
+            for table in result["result"]["tables_result"]:
+                print("\n[Header 区域]:")
+                header = table.get("header", [])
+                for cell in header:
+                    print(f"- {cell.get('words')}")
+                
+                print("\n[Footer 区域]:")
+                footer = table.get("footer", [])
+                for cell in footer:
+                    print(f"- {cell.get('words')}")
+        else:
+            print(f"识别失败或未找到表格: {json.dumps(result, indent=2, ensure_ascii=False)[:500]}")