Add support to extract offsets of embedded files in case someone needs it.

pyOneNote/FileNode.py

@@ -544,7 +544,9 @@ def __str__(self):
 
 class FileDataStoreObject:
     def __init__(self, file, fileNodeChunkReference):
-        self.guidHeader, self.cbLength, self.unused, self.reserved = struct.unpack('<16sQ4s8s', file.read(36))
+        size_of_header = 36
+        self.guidHeader, self.cbLength, self.unused, self.reserved = struct.unpack('<16sQ4s8s', file.read(size_of_header))
+        self.FileOffset = fileNodeChunkReference.stp + size_of_header
         self.FileData, = struct.unpack('{}s'.format(self.cbLength), file.read(self.cbLength))
         file.seek(fileNodeChunkReference.stp + fileNodeChunkReference.cb - 16)
         self.guidFooter, = struct.unpack('16s', file.read(16))

pyOneNote/Main.py

@@ -55,6 +55,7 @@ def process_onenote_file(file, output_dir, extension, json_output):
         for name, file in data['files'].items():
             print('{}{} ({}):'.format(indent, name, file['identity']))
             print('\t{}Extension: {}'.format(indent, file['extension']))
+            print('\t{}At offset: {} ({} bytes)'.format(indent, file['offset'], len(file['content'])))
             if(file['identity'] in file_metadata):
                 for property_name, property_val in file_metadata[file['identity']].items():
                     print('{}{}: {}'.format(indent+'\t', property_name, str(property_val)))

pyOneNote/OneDocument.py

@@ -51,13 +51,14 @@ def get_files(self):
             if hasattr(node, "data") and node.data:
                 if isinstance(node.data, FileDataStoreObjectReferenceFND):
                     if not str(node.data.guidReference) in self._files:
-                        self._files[str(node.data.guidReference)] = {"extension": "", "content": "", "identity": ""}
+                        self._files[str(node.data.guidReference)] = {"extension": "", "content": "", "identity": "", "offset": 0}
                     self._files[str(node.data.guidReference)]["content"] = node.data.fileDataStoreObject.FileData
+                    self._files[str(node.data.guidReference)]["offset"] = node.data.fileDataStoreObject.FileOffset
                 elif isinstance(node.data, ObjectDeclarationFileData3RefCountFND):
                     guid = node.data.FileDataReference.StringData.replace("<ifndf>{", "").replace("}", "")
                     guid = guid.lower()
                     if not guid in self._files:
-                        self._files[guid] = {"extension": "", "content": "", "identity": ""}
+                        self._files[guid] = {"extension": "", "content": "", "identity": "", "offset": 0}
                     self._files[guid]["extension"] = node.data.Extension.StringData
                     self._files[guid]["identity"] = str(node.data.oid)
         return self._files
@@ -71,6 +72,7 @@ def get_json(self):
         for key, file in self.get_files().items():
             files_in_hex[key] = {'extension': file['extension'],
                                  'content': file['content'].hex(),
+                                 'offset': file['offset'],
                                  'identity': file['identity']}
 
         res = {