lightpdf-aipdf-mcp 0.1.58__py3-none-any.whl → 0.1.60__py3-none-any.whl

lightpdf_aipdf_mcp/editor.py

@@ -20,6 +20,7 @@ class EditType(str, Enum):
     DECRYPT = "unlock"       # 解密PDF
     ADD_WATERMARK = "watermark"  # 添加水印
     REMOVE_MARGIN = "edit"   # 去除白边
+    EXTRACT_IMAGE = "extract"  # 提取图片
 
 @dataclass
 class EditResult(BaseResult):
@@ -381,6 +382,41 @@ class Editor(BaseApiClient):
         # 调用edit_pdf方法处理API请求
         return await self.edit_pdf(file_path, EditType.REMOVE_MARGIN, extra_params, password, original_name)
 
+    async def extract_images(self, file_path: str, format: str = "png", password: Optional[str] = None, original_name: Optional[str] = None) -> EditResult:
+        """从PDF文件中提取图片
+        
+        Args:
+            file_path: 要提取图片的PDF文件路径
+            format: 提取的图片格式，可选值为"bmp"/"png"/"gif"/"tif"/"jpg"，默认为"png"
+            password: 文档密码，如果文档受密码保护，则需要提供（可选）
+            original_name: 原始文件名（可选）
+            
+        Returns:
+            EditResult: 提取结果
+        """
+        # 验证输入文件是否为PDF
+        if not await self._validate_pdf_file(file_path):
+            return EditResult(success=False, file_path=file_path, error_message="非PDF文件", original_name=original_name)
+        
+        # 验证图片格式
+        valid_formats = {"bmp", "png", "gif", "tif", "jpg"}
+        if format not in valid_formats:
+            error_msg = f"无效的图片格式: {format}。有效值为: bmp, png, gif, tif, jpg"
+            await self.logger.error(error_msg)
+            return EditResult(success=False, file_path=file_path, error_message=error_msg, original_name=original_name)
+        
+        # 构建API参数
+        extra_params = {
+            "extract_type": "image",
+            "format": format
+        }
+        
+        # 记录操作描述
+        await self._log_operation("从PDF提取图片", f"格式: {format}")
+        
+        # 调用edit_pdf方法处理API请求
+        return await self.edit_pdf(file_path, EditType.EXTRACT_IMAGE, extra_params, password, original_name)
+
     async def edit_pdf(self, file_path: str, edit_type: EditType, extra_params: Dict[str, Any] = None, password: Optional[str] = None, original_name: Optional[str] = None) -> EditResult:
         """编辑PDF文件
         

lightpdf_aipdf_mcp/server.py

@@ -139,6 +139,17 @@ async def process_conversion_file(
             original_name
         )
     else:
+        # 处理extra_params
+        if extra_params is None:
+            extra_params = {}
+            
+        # 处理is_long_image参数，如果需要转换为长图，则添加merge_all=1参数
+        if extra_params.get("is_long_image") and format in ["jpg", "jpeg", "png"]:
+            extra_params["merge_all"] = 1
+            # 从extra_params中移除is_long_image，因为API不需要这个参数
+            if "is_long_image" in extra_params:
+                del extra_params["is_long_image"]
+                
         # 对于其他操作，使用convert_file方法
         return await converter.convert_file(file_path, format, extra_params, password, original_name)
 
@@ -232,6 +243,14 @@ async def process_edit_file(
             password=password,
             original_name=original_name
         )
+    elif edit_type == "extract_image":
+        # 调用extract_images方法提取图片
+        return await editor.extract_images(
+            file_path=file_path,
+            format=extra_params.get("format", "png"),
+            password=password,
+            original_name=original_name
+        )
     else:
         return EditResult(
             success=False, 
@@ -345,7 +364,7 @@ async def handle_list_tools() -> list[types.Tool]:
     return [
         types.Tool(
             name="convert_document",
-            description="文档格式转换工具。\n\nPDF可转换为：DOCX/XLSX/PPTX/图片/HTML/TXT；\n其他格式可转换为PDF：DOCX/XLSX/PPTX/图片/CAD/CAJ/OFD",
+            description="文档格式转换工具。\n\nPDF可转换为：DOCX/XLSX/PPTX/图片(长图)/HTML/TXT；\n其他格式可转换为PDF：DOCX/XLSX/PPTX/图片/CAD/CAJ/OFD",
             inputSchema={
                 "type": "object",
                 "properties": {
@@ -375,6 +394,11 @@ async def handle_list_tools() -> list[types.Tool]:
                         "type": "string",
                         "description": "目标格式",
                         "enum": ["pdf", "docx", "xlsx", "pptx", "jpg", "jpeg", "png", "html", "txt"]
+                    },
+                    "is_long_image": {
+                        "type": "boolean",
+                        "description": "是否需要转换为长图。仅当format为jpg/jpeg/png时有效",
+                        "default": False
                     }
                 },
                 "required": ["files", "format"]
@@ -776,7 +800,7 @@ async def handle_list_tools() -> list[types.Tool]:
         ),
         types.Tool(
             name="remove_margin",
-            description="去除PDF文件的白边（页边距）。",
+            description="去除PDF文件的白边（裁剪去掉页面边距）。",
             inputSchema={
                 "type": "object",
                 "properties": {
@@ -805,6 +829,44 @@ async def handle_list_tools() -> list[types.Tool]:
                 },
                 "required": ["files"]
             }
+        ),
+        types.Tool(
+            name="extract_images",
+            description="从PDF文件中提取图片资源。",
+            inputSchema={
+                "type": "object",
+                "properties": {
+                    "files": {
+                        "type": "array",
+                        "items": {
+                            "type": "object",
+                            "properties": {
+                                "path": {
+                                    "type": "string",
+                                    "description": "需要提取图片的PDF文件路径或URL"
+                                },
+                                "password": {
+                                    "type": "string",
+                                    "description": "PDF文档密码，如果文档受密码保护，则需要提供此参数"
+                                },
+                                "name": {
+                                    "type": "string",
+                                    "description": "文件的原始文件名"
+                                }
+                            },
+                            "required": ["path"]
+                        },
+                        "description": "需要提取图片的PDF文件列表，每个文件包含路径和可选的密码"
+                    },
+                    "format": {
+                        "type": "string",
+                        "description": "提取的图片格式",
+                        "enum": ["bmp", "png", "gif", "tif", "jpg"],
+                        "default": "png"
+                    }
+                },
+                "required": ["files"]
+            }
         )
     ]
 
@@ -871,6 +933,11 @@ async def handle_call_tool(name: str, arguments: dict | None) -> list[types.Text
         "remove_margin": {
             "edit_type": "remove_margin",  # 编辑类型
             "is_edit_operation": True,  # 标记为编辑操作
+        },
+        "extract_images": {
+            "edit_type": "extract_image",  # 编辑类型
+            "is_edit_operation": True,  # 标记为编辑操作
+            "param_keys": ["format"]  # 需要从arguments获取的参数
         }
     }
     
@@ -886,7 +953,8 @@ async def handle_call_tool(name: str, arguments: dict | None) -> list[types.Text
         "split_type": "page",
         "merge_all": 1,
         "angle": 90,
-        "pages": "all"  # 更新默认值为"all"
+        "pages": "all",  # 更新默认值为"all"
+        "format": "png"  # 提取图片的默认格式
     }
     
     if name in TOOL_CONFIG:
@@ -932,6 +1000,12 @@ async def handle_call_tool(name: str, arguments: dict | None) -> list[types.Text
             if name == "protect_pdf" and "password" in arguments:
                 operation_config["extra_params"]["password"] = arguments.get("password")
         
+        # 处理convert_document工具的is_long_image参数
+        if name == "convert_document" and "is_long_image" in arguments:
+            if operation_config.get("extra_params") is None:
+                operation_config["extra_params"] = {}
+            operation_config["extra_params"]["is_long_image"] = arguments.get("is_long_image", False)
+            
         # 特殊处理merge_pdfs工具
         if name == "merge_pdfs":
             # 创建编辑器
@@ -1058,4 +1132,4 @@ def cli_main():
         sys.exit(1)
 
 if __name__ == "__main__":
-    cli_main()
+    cli_main()

{lightpdf_aipdf_mcp-0.1.58.dist-info → lightpdf_aipdf_mcp-0.1.60.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lightpdf-aipdf-mcp
-Version: 0.1.58
+Version: 0.1.60
 Summary: MCP Server for LightPDF AI-PDF
 Author: LightPDF Team
 License: Proprietary

lightpdf_aipdf_mcp-0.1.60.dist-info/RECORD

@@ -0,0 +1,9 @@
+lightpdf_aipdf_mcp/__init__.py,sha256=PPnAgpvJLYLVOTxnHDmJAulFnHJD6wuTwS6tRGjqq6s,141
+lightpdf_aipdf_mcp/common.py,sha256=-7LU6gm-As_F8Ly68ssy15Vc9Zt_eNSnvDLEtVZDwlI,6633
+lightpdf_aipdf_mcp/converter.py,sha256=d90pNUT8pQn93u1fJSlu4f2KyLDzhOdTrqyBkSTRFBE,14450
+lightpdf_aipdf_mcp/editor.py,sha256=Dsgp_WUCj4Ke17KCm3RzltiTnQmg8u5LVEuhz_kNCRo,26426
+lightpdf_aipdf_mcp/server.py,sha256=uC08VViQGFYumPS9uvH1rGX-4YZ1leGNrgC4WKa2gDg,46912
+lightpdf_aipdf_mcp-0.1.60.dist-info/METADATA,sha256=BQOwhWIVRCwa7oATdteJy7mL4xO1aK9i9RKYJxc-k58,7826
+lightpdf_aipdf_mcp-0.1.60.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+lightpdf_aipdf_mcp-0.1.60.dist-info/entry_points.txt,sha256=X7TGUe52N4sYH-tYt0YUGApeJgw-efQlZA6uAZmlmr4,63
+lightpdf_aipdf_mcp-0.1.60.dist-info/RECORD,,

lightpdf_aipdf_mcp-0.1.58.dist-info/RECORD

@@ -1,9 +0,0 @@
-lightpdf_aipdf_mcp/__init__.py,sha256=PPnAgpvJLYLVOTxnHDmJAulFnHJD6wuTwS6tRGjqq6s,141
-lightpdf_aipdf_mcp/common.py,sha256=-7LU6gm-As_F8Ly68ssy15Vc9Zt_eNSnvDLEtVZDwlI,6633
-lightpdf_aipdf_mcp/converter.py,sha256=d90pNUT8pQn93u1fJSlu4f2KyLDzhOdTrqyBkSTRFBE,14450
-lightpdf_aipdf_mcp/editor.py,sha256=fGzIiAp48uTXBBKWWlHcGT0nwgZQBpjvrsxSf6Ockk4,24730
-lightpdf_aipdf_mcp/server.py,sha256=E9F2aE52R2ZPdLyFdZJ02-dXrmE_VpAHk64J6qSd8KI,43447
-lightpdf_aipdf_mcp-0.1.58.dist-info/METADATA,sha256=EyhD4kqvzK_a8S1fjB2_9r37U4dmAXcXlQizuYbXs3k,7826
-lightpdf_aipdf_mcp-0.1.58.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-lightpdf_aipdf_mcp-0.1.58.dist-info/entry_points.txt,sha256=X7TGUe52N4sYH-tYt0YUGApeJgw-efQlZA6uAZmlmr4,63
-lightpdf_aipdf_mcp-0.1.58.dist-info/RECORD,,