Merge pull request #116 from aspose-pdf-cloud/develop

boiledgas · web-flow · commit 22ddec87824f · 2025-09-26T01:18:04.000+03:00
update to 25.9
diff --git a/README.md b/README.md
@@ -30,13 +30,10 @@ XLS, XLSX, PPTX, DOC, DOCX, MobiXML, JPEG, EMF, PNG, BMP, GIF, TIFF, Text
 ## Read PDF Formats
 MHT, PCL, PS, XSLFO, MD
 
-## Enhancements in Version 25.8
-- Implement document page resize functionality using the Pdf.Cloud API library.
+## Enhancements in Version 25.9
+- Implement PDF document page crop functionality using the Pdf.Cloud API library.
 - A new version of Aspose.PDF Cloud was prepared using the latest version of Aspose.PDF for .NET.
 
-## Bugs fixed in Version 25.8
-- Implement delete watermark from PDF document using the Pdf.Cloud API library.
-
 ## Requirements.
 Python 2.7 and 3.4+
 
diff --git a/Uses-Cases/Parser/get_fdf.py b/Uses-Cases/Parser/get_fdf.py
@@ -0,0 +1,22 @@
+from paresr_helpers import ParesrHelper
+from pathlib import Path
+import logging
+
+class ExportFormToFDF:
+    """Class for extracting PDF form fields into FDF using Aspose PDF Cloud API."""
+    def __init__(self, helper: ParesrHelper):
+        self.helper = helper
+
+    def Extract(self, documentName: str, outputFDFName: str, localFolder: Path, remoteFolder: str ):
+        self.helper.upload_document(documentName, remoteFolder)
+
+        fdfPath = str(Path.joinpath(Path(remoteFolder), outputFDFName))
+        opts = {
+            "folder": remoteFolder
+        }
+        response = self.helper.pdf_api.put_export_fields_from_pdf_to_fdf_in_storage(documentName, fdfPath, **opts)
+        if response.code != 200:
+            logging.error("ExportFormToFDF(): Unexpected error!")
+        else:
+            logging.info(f"ExportFormToFDF(): Pdf document '{documentName}' form fields successfully exported to '{outputFDFName}' file.")
+            self.helper.downloadFile(outputFDFName, outputFDFName, localFolder, remoteFolder, "")
diff --git a/Uses-Cases/Parser/get_images.py b/Uses-Cases/Parser/get_images.py
@@ -0,0 +1,26 @@
+from paresr_helpers import ParesrHelper
+from pathlib import Path
+import shutil
+import logging
+
+class GetImages:
+    """Class for extracting images from PDF document page using Aspose PDF Cloud API."""
+    def __init__(self, helper: ParesrHelper):
+        self.helper = helper
+
+    def Extract(self, documentName: str, pageNumber: int, localFolder: Path, remoteFolder: Path):
+        self.helper.upload_document(documentName, remoteFolder)
+
+        opts = {
+            "folder": remoteFolder
+        }
+        respImages = self.helper.pdf_api.get_images(documentName, pageNumber, **opts)
+        if respImages.code != 200:
+            logging.error("GetImages(): Unexpected error!")
+        else:
+            for img in respImages.images.list:
+                response = self.helper.pdf_api.get_image_extract_as_png(documentName, img.id, **opts)
+
+                logging.info(f"GetImages(): Images '{img.id}' successfully extracted from the document '{documentName}'.")
+                local_path = localFolder / ( img.id + '.png' )
+                shutil.move(response, str(local_path))
diff --git a/Uses-Cases/Parser/get_tables.py b/Uses-Cases/Parser/get_tables.py
@@ -0,0 +1,30 @@
+from paresr_helpers import ParesrHelper
+from pathlib import Path
+import json
+import logging
+
+class GetTables:
+    """Class for extracting tables from PDF document using Aspose PDF Cloud API."""
+    def __init__(self, helper: ParesrHelper):
+        self.helper = helper
+
+    def Extract(self, documentName: str, localFolder: Path, remoteFolder: Path):
+        self.helper.upload_document(documentName, remoteFolder)
+
+        opts = {
+            "folder": remoteFolder
+        }
+        respTables = self.helper.pdf_api.get_document_tables(documentName, **opts)
+        if respTables.code != 200:
+            logging.error("GetTables(): Unexpected error!")
+        else:
+            localJson = Path.joinpath(localFolder, "tables_objects.json")
+            with open(str(localJson), "w", encoding="utf-8") as localFile:
+                for tab in respTables.tables.list:
+                    response = self.helper.pdf_api.get_table(documentName, tab.id, **opts)
+                    if response.code != 200:
+                        logging.error("GetTextBoxes(): Unexpected error!")
+                    else:
+                        logging.info(f"GetTabels(): Table '{tab.id}' successfully extracted from the document '{documentName}'.")
+                        json.dump(tab, localFile, ensure_ascii=False,default=str)
+                        localFile.write("\n*********************\n")
diff --git a/Uses-Cases/Parser/get_textboxes.py b/Uses-Cases/Parser/get_textboxes.py
@@ -0,0 +1,30 @@
+from paresr_helpers import ParesrHelper
+from pathlib import Path
+import json
+import logging
+
+class GetTextBoxes:
+    """Class for extracting text boxes from PDF document using Aspose PDF Cloud API."""
+    def __init__(self, helper: ParesrHelper):
+        self.helper = helper
+
+    def Extract(self, documentName: str, localFolder: Path, remoteFolder: Path):
+        self.helper.upload_document(documentName, remoteFolder)
+
+        opts = {
+            "folder": remoteFolder
+        }
+        respTextBoxes = self.helper.pdf_api.get_document_text_box_fields(documentName, **opts)
+        if respTextBoxes.code != 200:
+            logging.error("GetTextBoxes(): Unexpected error!")
+        else:
+            localJson = Path.joinpath(localFolder, "text_box_objects.json")
+            with open(str(localJson), "w", encoding="utf-8") as localFile:
+                for textBox in respTextBoxes.fields.list:
+                    response = self.helper.pdf_api.get_text_box_field(documentName, textBox.full_name, **opts)
+                    if response.code != 200:
+                        logging.error("GetTextBoxes(): Unexpected error!")
+                    else:
+                        logging.info(f"GetTextBoxes(): TextBox field '{textBox.full_name}' successfully extracted from the document '{documentName}'.")
+                        json.dump(textBox, localFile, ensure_ascii=False,default=str)
+                        localFile.write("\n*********************\n")
diff --git a/Uses-Cases/Parser/get_xml.py b/Uses-Cases/Parser/get_xml.py
@@ -0,0 +1,22 @@
+from paresr_helpers import ParesrHelper, Config
+from pathlib import Path
+import logging
+
+class ExportFormToXXML:
+    """Class for extracting PDF form fields into XML using Aspose PDF Cloud API."""
+    def __init__(self, helper: ParesrHelper):
+        self.helper = helper
+
+    def Extract(self, documentName: str, outputXMLName: str, localFolder: Path, remoteFolder: str ):
+        self.helper.upload_document(documentName, remoteFolder)
+
+        xmlPath = str(Path.joinpath(Path(remoteFolder), outputXMLName))
+        opts = {
+            "folder": remoteFolder
+        }
+        response = self.helper.pdf_api.put_export_fields_from_pdf_to_xml_in_storage(documentName, xmlPath, **opts)
+        if response.code != 200:
+            logging.error("ExportFormToXM(): Unexpected error!")
+        else:
+            logging.info(f"ExportFormToXML(): Pdf document '{documentName}' form fields successfully exported to '{outputXMLName}' file.")
+            self.helper.downloadFile(outputXMLName, outputXMLName, localFolder, remoteFolder, "")
diff --git a/Uses-Cases/Parser/paresr_helpers.py b/Uses-Cases/Parser/paresr_helpers.py
@@ -0,0 +1,66 @@
+import shutil
+import json
+import logging
+from pathlib import Path
+from asposepdfcloud import ApiClient, PdfApi
+
+# Configure logging
+logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
+
+
+class Config:
+    """Configuration parameters."""
+    CREDENTIALS_FILE = Path(r"..s\\credentials.json")
+    LOCAL_FOLDER = Path(r"C:\Samples")
+    REMOTE_TEMP_FOLDER  = "TempPdfCloud"
+    PDF_DOCUMENT_NAME = "sample.pdf"
+    XML_OUTPUT_FILE = "output_sample.xml"
+    FDF_OUTPUT_FILE = "output_sample.fdf"
+    LOCAL_RESULT_DOCUMENT_NAME = "output_sample.pdf"
+    PAGE_NUMBER = 1
+
+
+class ParesrHelper:
+    """Class with helper methods and properties for Parser"""
+
+    def __init__(self, credentials_file: Path = Config.CREDENTIALS_FILE):
+        self.pdf_api = None
+        self._init_api(credentials_file)
+
+    def _init_api(self, credentials_file: Path):
+        """Initialize the API client."""
+        try:
+            with credentials_file.open("r", encoding="utf-8") as file:
+                credentials = json.load(file)
+                api_key, app_id = credentials.get("key"), credentials.get("id")
+                if not api_key or not app_id:
+                    raise ValueError("Error: Missing API keys in the credentials file.")
+                self.pdf_api = PdfApi(ApiClient(api_key, app_id))
+        except (FileNotFoundError, json.JSONDecodeError, ValueError) as e:
+            logging.error(f"Failed to load credentials: {e}")
+
+    def upload_document(self, documentName: str, remoteFolder: str):
+        """Upload a PDF document to the Aspose Cloud server."""
+        if self.pdf_api:
+            file_path = Config.LOCAL_FOLDER / documentName
+            try:
+                if remoteFolder == None:
+                    self.pdf_api.upload_file(documentName, str(file_path))
+                else:
+                    opts = { "folder": remoteFolder }
+                    self.pdf_api.upload_file(remoteFolder + '/' + documentName, file_path)
+                logging.info(f"File {documentName} uploaded successfully.")
+            except Exception as e:
+                logging.error(f"Failed to upload file: {e}")
+
+    def downloadFile(self, document: str, outputDocument: str, localFolder: Path, remoteFolder: str,  output_prefix: str):
+        """Download the processed PDF document from the Aspose Cloud server."""
+        if self.pdf_api:
+            try:
+                temp_file = self.pdf_api.download_file(remoteFolder + '/' + document)
+                local_path = localFolder / ( output_prefix + outputDocument )
+                shutil.move(temp_file, str(local_path))
+                logging.info(f"download_result(): File successfully downloaded: {local_path}")
+            except Exception as e:
+                logging.error(f"download_result(): Failed to download file: {e}")
+
diff --git a/Uses-Cases/Parser/parser_launch.py b/Uses-Cases/Parser/parser_launch.py
@@ -0,0 +1,24 @@
+from paresr_helpers import ParesrHelper, Config
+from get_xml import ExportFormToXXML
+from get_fdf import ExportFormToFDF
+from get_images import GetImages
+from get_tables import GetTables
+from get_textboxes import GetTextBoxes
+
+if __name__ == "__main__":
+	helper = ParesrHelper(Config.CREDENTIALS_FILE)
+
+	xmlExtractor = ExportFormToXXML(helper)
+	xmlExtractor.Extract(Config.PDF_DOCUMENT_NAME, Config.XML_OUTPUT_FILE,  Config.LOCAL_FOLDER, Config.REMOTE_TEMP_FOLDER)
+
+	fdfExtractor = ExportFormToFDF(helper)
+	fdfExtractor.Extract(Config.PDF_DOCUMENT_NAME, Config.FDF_OUTPUT_FILE,  Config.LOCAL_FOLDER, Config.REMOTE_TEMP_FOLDER)
+
+	getImages = GetImages(helper)
+	getImages.Extract(Config.PDF_DOCUMENT_NAME, Config.PAGE_NUMBER, Config.LOCAL_FOLDER, Config.REMOTE_TEMP_FOLDER)
+
+	getTables = GetTables(helper)
+	getTables.Extract(Config.PDF_DOCUMENT_NAME, Config.LOCAL_FOLDER, Config.REMOTE_TEMP_FOLDER)
+
+	getTextBoxes = GetTextBoxes(helper)
+	getTextBoxes.Extract(Config.PDF_DOCUMENT_NAME, Config.LOCAL_FOLDER, Config.REMOTE_TEMP_FOLDER)
diff --git a/asposepdfcloud/api_client.py b/asposepdfcloud/api_client.py
@@ -83,7 +83,7 @@ def __init__(self, app_key, app_sid, host=None, self_host=False):
         self.rest_client = RESTClientObject()
         self.default_headers = {}
         self.default_headers['x-aspose-client'] = 'python sdk'
-        self.default_headers['x-aspose-client-version'] = '25.8.0'
+        self.default_headers['x-aspose-client-version'] = '25.9.0'
         
         self.self_host = self_host
         self.app_key = app_key
diff --git a/asposepdfcloud/apis/pdf_api.py b/asposepdfcloud/apis/pdf_api.py
@@ -24907,6 +24907,136 @@ def post_document_page_number_stamps_with_http_info(self, name, stamp, **kwargs)
                                         _request_timeout=params.get('_request_timeout'),
                                         collection_formats=collection_formats)
 
+    def post_document_pages_crop(self, name, pages, rect, **kwargs):
+        """
+        Crop PDF document pages.
+        This method makes a synchronous HTTP request by default. To make an
+        asynchronous HTTP request, please define a `callback` function
+        to be invoked when receiving the response.
+        >>> def callback_function(response):
+        >>>     pprint(response)
+        >>>
+        >>> thread = api.post_document_pages_crop(name, pages, rect, callback=callback_function)
+
+        :param callback function: The callback function
+            for asynchronous request. (optional)
+        :param str name: The document name. (required)
+        :param str pages: Comma separated list of pages and page ranges. (Example: 1,3-5,8) (required)
+        :param Rectangle rect: Rectangle of document area. (required)
+        :param str storage: The document storage.
+        :param str folder: The document folder.
+        :param str password: Base64 encoded password.
+        :return: AsposeResponse
+                 If the method is called asynchronously,
+                 returns the request thread.
+        """
+        kwargs['_return_http_data_only'] = True
+        if kwargs.get('callback'):
+            return self.post_document_pages_crop_with_http_info(name, pages, rect, **kwargs)
+        else:
+            (data) = self.post_document_pages_crop_with_http_info(name, pages, rect, **kwargs)
+            return data
+
+    def post_document_pages_crop_with_http_info(self, name, pages, rect, **kwargs):
+        """
+        Crop PDF document pages.
+        This method makes a synchronous HTTP request by default. To make an
+        asynchronous HTTP request, please define a `callback` function
+        to be invoked when receiving the response.
+        >>> def callback_function(response):
+        >>>     pprint(response)
+        >>>
+        >>> thread = api.post_document_pages_crop_with_http_info(name, pages, rect, callback=callback_function)
+
+        :param callback function: The callback function
+            for asynchronous request. (optional)
+        :param str name: The document name. (required)
+        :param str pages: Comma separated list of pages and page ranges. (Example: 1,3-5,8) (required)
+        :param Rectangle rect: Rectangle of document area. (required)
+        :param str storage: The document storage.
+        :param str folder: The document folder.
+        :param str password: Base64 encoded password.
+        :return: AsposeResponse
+                 If the method is called asynchronously,
+                 returns the request thread.
+        """
+
+        all_params = ['name', 'pages', 'rect', 'storage', 'folder', 'password']
+        all_params.append('callback')
+        all_params.append('_return_http_data_only')
+        all_params.append('_preload_content')
+        all_params.append('_request_timeout')
+
+        params = locals()
+        for key, val in iteritems(params['kwargs']):
+            if key not in all_params:
+                raise TypeError(
+                    "Got an unexpected keyword argument '%s'"
+                    " to method post_document_pages_crop" % key
+                )
+            params[key] = val
+        del params['kwargs']
+        # verify the required parameter 'name' is set
+        if ('name' not in params) or (params['name'] is None):
+            raise ValueError("Missing the required parameter `name` when calling `post_document_pages_crop`")
+        # verify the required parameter 'pages' is set
+        if ('pages' not in params) or (params['pages'] is None):
+            raise ValueError("Missing the required parameter `pages` when calling `post_document_pages_crop`")
+        # verify the required parameter 'rect' is set
+        if ('rect' not in params) or (params['rect'] is None):
+            raise ValueError("Missing the required parameter `rect` when calling `post_document_pages_crop`")
+
+
+        collection_formats = {}
+
+        path_params = {}
+        if 'name' in params:
+            path_params['name'] = params['name']
+
+        query_params = []
+        if 'pages' in params:
+            query_params.append(('pages', params['pages']))
+        if 'storage' in params:
+            query_params.append(('storage', params['storage']))
+        if 'folder' in params:
+            query_params.append(('folder', params['folder']))
+        if 'password' in params:
+            query_params.append(('password', params['password']))
+
+        header_params = {}
+
+        form_params = []
+        local_var_files = {}
+
+        body_params = None
+        if 'rect' in params:
+            body_params = params['rect']
+        # HTTP header `Accept`
+        header_params['Accept'] = self.api_client.\
+            select_header_accept(['application/json'])
+
+        # HTTP header `Content-Type`
+        header_params['Content-Type'] = self.api_client.\
+            select_header_content_type(['application/json'])
+
+        # Authentication setting
+        auth_settings = ['JWT']
+
+        return self.api_client.call_api('/pdf/{name}/crop', 'POST',
+                                        path_params,
+                                        query_params,
+                                        header_params,
+                                        body=body_params,
+                                        post_params=form_params,
+                                        files=local_var_files,
+                                        response_type='AsposeResponse',
+                                        auth_settings=auth_settings,
+                                        callback=params.get('callback'),
+                                        _return_http_data_only=params.get('_return_http_data_only'),
+                                        _preload_content=params.get('_preload_content', True),
+                                        _request_timeout=params.get('_request_timeout'),
+                                        collection_formats=collection_formats)
+
     def post_document_pages_resize(self, name, height, width, pages, **kwargs):
         """
         Rsize PDF document.
diff --git a/asposepdfcloud/configuration.py b/asposepdfcloud/configuration.py
diff --git a/docs/PdfApi.md b/docs/PdfApi.md
diff --git a/setup.py b/setup.py
diff --git a/test/pdf_test.py b/test/pdf_test.py
