Initial work to port #55 to MarkItDown 0.1.X

Author: afourney

README.md

@@ -17,6 +17,7 @@ At present, MarkItDown supports:
 - PowerPoint
 - Word
 - Excel
+- OneNote
 - Images (EXIF metadata and OCR)
 - Audio (EXIF metadata and speech transcription)
 - HTML
@@ -82,6 +83,7 @@ At the moment, the following optional dependencies are available:
 * `[xls]` Installs dependencies for older Excel files
 * `[pdf]` Installs dependencies for PDF files
 * `[outlook]` Installs dependencies for Outlook messages
+* `[onenote]` Installs dependencies for OneNote .one files
 * `[az-doc-intel]` Installs dependencies for Azure Document Intelligence
 * `[audio-transcription]` Installs dependencies for audio transcription of wav and mp3 files
 * `[youtube-transcription]` Installs dependencies for fetching YouTube video transcription

packages/markitdown/pyproject.toml

@@ -45,14 +45,16 @@ all = [
   "SpeechRecognition",
   "youtube-transcript-api",
   "azure-ai-documentintelligence",
-  "azure-identity"
+  "azure-identity",
+  "one-extract",
 ]
 pptx = ["python-pptx"]
 docx = ["mammoth"]
 xlsx = ["pandas", "openpyxl"]
 xls = ["pandas", "xlrd"]
 pdf = ["pdfminer.six"]
 outlook = ["olefile"]
+onenote = ["one-extract"]
 audio-transcription = ["pydub", "SpeechRecognition"]
 youtube-transcription = ["youtube-transcript-api"]
 az-doc-intel = ["azure-ai-documentintelligence", "azure-identity"]

packages/markitdown/src/markitdown/_markitdown.py

@@ -30,6 +30,7 @@
     BingSerpConverter,
     PdfConverter,
     DocxConverter,
+    OneNoteConverter,
     XlsxConverter,
     XlsConverter,
     PptxConverter,
@@ -158,6 +159,7 @@ def enable_builtins(self, **kwargs) -> None:
             self.register_converter(YouTubeConverter())
             self.register_converter(BingSerpConverter())
             self.register_converter(DocxConverter())
+            self.register_converter(OneNoteConverter())
             self.register_converter(XlsxConverter())
             self.register_converter(XlsConverter())
             self.register_converter(PptxConverter())

packages/markitdown/src/markitdown/converters/__init__.py

@@ -11,6 +11,7 @@
 from ._bing_serp_converter import BingSerpConverter
 from ._pdf_converter import PdfConverter
 from ._docx_converter import DocxConverter
+from ._onenote_converter import OneNoteConverter
 from ._xlsx_converter import XlsxConverter, XlsConverter
 from ._pptx_converter import PptxConverter
 from ._image_converter import ImageConverter
@@ -29,6 +30,7 @@
     "BingSerpConverter",
     "PdfConverter",
     "DocxConverter",
+    "OneNoteConverter",
     "XlsxConverter",
     "XlsConverter",
     "PptxConverter",

packages/markitdown/src/markitdown/converters/_onenote_converter.py

@@ -0,0 +1,87 @@
+import sys
+
+from typing import BinaryIO, Any
+
+from ._html_converter import HtmlConverter
+from .._base_converter import DocumentConverter, DocumentConverterResult
+from .._stream_info import StreamInfo
+from .._exceptions import MissingDependencyException, MISSING_DEPENDENCY_MESSAGE
+
+# Try loading optional (but in this case, required) dependencies
+# Save reporting of any exceptions for later
+_dependency_exc_info = None
+try:
+    import one_extract
+except ImportError:
+    # Preserve the error and stack trace for later
+    _dependency_exc_info = sys.exc_info()
+
+
+ACCEPTED_MIME_TYPE_PREFIXES = []
+
+ACCEPTED_FILE_EXTENSIONS = [".one"]
+
+
+class OneNoteConverter(DocumentConverter):
+    """
+    Converts OneNote files to Markdown.
+    """
+
+    def __init__(self):
+        super().__init__()
+        self._html_converter = HtmlConverter()
+
+    def accepts(
+        self,
+        file_stream: BinaryIO,
+        stream_info: StreamInfo,
+        **kwargs: Any,  # Options to pass to the converter
+    ) -> bool:
+        mimetype = (stream_info.mimetype or "").lower()
+        extension = (stream_info.extension or "").lower()
+
+        if extension in ACCEPTED_FILE_EXTENSIONS:
+            return True
+
+        for prefix in ACCEPTED_MIME_TYPE_PREFIXES:
+            if mimetype.startswith(prefix):
+                return True
+
+        return False
+
+    def convert(
+        self,
+        file_stream: BinaryIO,
+        stream_info: StreamInfo,
+        **kwargs: Any,  # Options to pass to the converter
+    ) -> DocumentConverterResult:
+        # Check: the dependencies
+        if _dependency_exc_info is not None:
+            raise MissingDependencyException(
+                MISSING_DEPENDENCY_MESSAGE.format(
+                    converter=type(self).__name__,
+                    extension=".one",
+                    feature="onenote",
+                )
+            ) from _dependency_exc_info[
+                1
+            ].with_traceback(  # type: ignore[union-attr]
+                _dependency_exc_info[2]
+            )
+
+        # Perform the conversion
+        md_content = ""
+        notebook = one_extract.Notebook(file_stream)
+        for section in notebook.sections:
+            md_content += f"\n\n# {section.name}\n"
+            for page in section.pages:
+                md_content += f"\n\n## {page.name}\n"
+                md_content += (
+                    self._html_converter.convert_string(page.content).markdown.strip()
+                    + "\n\n"
+                )
+
+        return DocumentConverterResult(
+            title=None,
+            text_content=md_content.strip(),
+        )