Skip to content

Python tool for converting files and office documents to Markdown.

feat: Add IpynbConverter

Om Guptaa3208f2bd059
diff --git a/src/markitdown/_markitdown.py b/src/markitdown/_markitdown.py
index 96997cf3..746e5577 100644
--- a/src/markitdown/_markitdown.py
+++ b/src/markitdown/_markitdown.py
@@ -390,6 +390,63 @@ class YouTubeConverter(DocumentConverter):
return ret
return None
+class IpynbConverter(DocumentConverter):
+ """Converts Jupyter Notebook (.ipynb) files to Markdown."""
+
+ def convert(
+ self, local_path: str, **kwargs: Any
+ ) -> Union[None, DocumentConverterResult]:
+ # Bail if not ipynb
+ extension = kwargs.get("file_extension", "")
+ if extension.lower() != ".ipynb":
+ return None
+
+ # Parse and convert the notebook
+ result = None
+ with open(local_path, "rt", encoding="utf-8") as fh:
+ notebook_content = json.load(fh)
+ result = self._convert(notebook_content)
+
+ return result
+
+ def _convert(self, notebook_content: dict) -> Union[None, DocumentConverterResult]:
+ """Helper function that converts notebook JSON content to Markdown."""
+ try:
+ md_output = []
+ title = None
+
+ for cell in notebook_content.get("cells", []):
+ cell_type = cell.get("cell_type", "")
+ source_lines = cell.get("source", [])
+
+ if cell_type == "markdown":
+ md_output.append("".join(source_lines))
+
+ # Extract the first # heading as title if not already found
+ if title is None:
+ for line in source_lines:
+ if line.startswith("# "):
+ title = line.lstrip("# ").strip()
+ break
+
+ elif cell_type == "code":
+ # Code cells are wrapped in Markdown code blocks
+ md_output.append(f"```python\n{''.join(source_lines)}\n```")
+ elif cell_type == "raw":
+ md_output.append(f"```\n{''.join(source_lines)}\n```")
+
+ md_text = "\n\n".join(md_output)
+
+ # Check for title in notebook metadata
+ title = notebook_content.get("metadata", {}).get("title", title)
+
+ return DocumentConverterResult(
+ title=title,
+ text_content=md_text,
+ )
+
+ except Exception as e:
+ raise FileConversionException(f"Error converting .ipynb file: {str(e)}") from e
class BingSerpConverter(DocumentConverter):
"""
@@ -879,6 +936,7 @@ class MarkItDown:
self.register_page_converter(WavConverter())
self.register_page_converter(Mp3Converter())
self.register_page_converter(ImageConverter())
+ self.register_page_converter(IpynbConverter())
self.register_page_converter(PdfConverter())
def convert(
diff --git a/tests/test_files/test_notebook.ipynb b/tests/test_files/test_notebook.ipynb
new file mode 100644
index 00000000..62db0faa
--- /dev/null
+++ b/tests/test_files/test_notebook.ipynb
@@ -0,0 +1,89 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "id": "0f61db80",
+ "metadata": {},
+ "source": [
+ "# Test Notebook"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "id": "3f2a5bbd",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "markitdown\n"
+ ]
+ }
+ ],
+ "source": [
+ "print('markitdown')"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "9b9c0468",
+ "metadata": {},
+ "source": [
+ "## Code Cell Below"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "id": "37d8088a",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "42\n"
+ ]
+ }
+ ],
+ "source": [
+ "# comment in code\n",
+ "print(42)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "2e3177bd",
+ "metadata": {},
+ "source": [
+ "End\n",
+ "\n",
+ "---"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.12.8"
+ },
+ "title": "Test Notebook Title"
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}