Merge branch 'main' into dev

.devcontainer/devcontainer.json

@@ -6,7 +6,10 @@
 		// Sets the run context to one level up instead of the .devcontainer folder.
 		"context": "..",
 		// Update the 'dockerFile' property if you aren't using the standard 'Dockerfile' filename.
-		"dockerfile": "../Dockerfile"
+		"dockerfile": "../Dockerfile",
+		"args": {
+			"INSTALL_GIT": "true"
+		}
 	},
 
 	// Features to add to the dev container. More info: https://containers.dev/features.

.github/dependabot.yml

@@ -0,0 +1,6 @@
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"

.github/workflows/pre-commit.yml

@@ -5,9 +5,9 @@ jobs:
   pre-commit:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       - name: Set up Python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v5
         with:
           python-version: "3.x"
 

.github/workflows/tests.yml

@@ -5,8 +5,8 @@ jobs:
   tests:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
-      - uses: actions/setup-python@v4
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: |
             3.10
@@ -14,7 +14,7 @@ jobs:
             3.12
       - name: Set up pip cache
         if: runner.os == 'Linux'
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: ~/.cache/pip
           key: ${{ runner.os }}-pip-${{ hashFiles('pyproject.toml') }}

.gitignore

@@ -1,3 +1,5 @@
+.vscode
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]

Dockerfile

@@ -2,6 +2,11 @@ FROM python:3.13-slim-bullseye
 
 USER root
 
+ARG INSTALL_GIT=false
+RUN if [ "$INSTALL_GIT" = "true" ]; then \
+    apt-get update && apt-get install -y git && rm -rf /var/lib/apt/lists/*; \
+    fi
+
 # Runtime dependency
 RUN apt-get update && apt-get install -y --no-install-recommends \
     ffmpeg \

README.md

@@ -1,8 +1,11 @@
+> [!IMPORTANT]
+> (12/19/24) Hello! MarkItDown team members will be resting and recharging with family and friends over the holiday period. Activity/responses on the project may be delayed during the period of Dec 21-Jan 06. We will be excited to engage with you in the new year!
+
 # MarkItDown
 
 [![PyPI](https://img.shields.io/pypi/v/markitdown.svg)](https://pypi.org/project/markitdown/)
 ![PyPI - Downloads](https://img.shields.io/pypi/dd/markitdown)
-
+[![Built by AutoGen Team](https://img.shields.io/badge/Built%20by-AutoGen%20Team-blue)](https://github.com/microsoft/autogen)
 
 
 MarkItDown is a utility for converting various files to Markdown (e.g., for indexing, text analysis, etc).
@@ -27,6 +30,12 @@ To install MarkItDown, use pip: `pip install markitdown`. Alternatively, you can
 markitdown path-to-file.pdf > document.md
 ```
 
+Or use `-o` to specify the output file:
+
+```bash
+markitdown path-to-file.pdf -o document.md
+```
+
 You can also pipe content:
 
 ```bash
@@ -63,6 +72,42 @@ print(result.text_content)
 docker build -t markitdown:latest .
 docker run --rm -i markitdown:latest < ~/your-file.pdf > output.md
 ```
+<details>
+    
+<summary>Batch Processing Multiple Files</summary>
+
+This example shows how to convert multiple files to markdown format in a single run. The script processes all supported files in a directory and creates corresponding markdown files.
+
+
+```python convert.py
+from markitdown import MarkItDown
+from openai import OpenAI
+import os
+client = OpenAI(api_key="your-api-key-here")
+md = MarkItDown(llm_client=client, llm_model="gpt-4o-2024-11-20")
+supported_extensions = ('.pptx', '.docx', '.pdf', '.jpg', '.jpeg', '.png')
+files_to_convert = [f for f in os.listdir('.') if f.lower().endswith(supported_extensions)]
+for file in files_to_convert:
+    print(f"\nConverting {file}...")
+    try:
+        md_file = os.path.splitext(file)[0] + '.md'
+        result = md.convert(file)
+        with open(md_file, 'w') as f:
+            f.write(result.text_content)
+        
+        print(f"Successfully converted {file} to {md_file}")
+    except Exception as e:
+        print(f"Error converting {file}: {str(e)}")
+
+print("\nAll conversions completed!")
+```
+2. Place the script in the same directory as your files
+3. Install required packages: like openai
+4. Run script ```bash python convert.py ```
+
+Note that original files will remain unchanged and new markdown files are created with the same base name.
+
+</details>
    
 ## Contributing
 
@@ -78,6 +123,20 @@ This project has adopted the [Microsoft Open Source Code of Conduct](https://ope
 For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or
 contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additional questions or comments.
 
+### How to Contribute
+
+You can help by looking at issues or helping review PRs. Any issue or PR is welcome, but we have also marked some as 'open for contribution' and 'open for reviewing' to help facilitate community contributions. These are ofcourse just suggestions and you are welcome to contribute in any way you like.
+
+
+<div align="center">
+
+|                       | All                                      | Especially Needs Help from Community                                                                 |
+|-----------------------|------------------------------------------|------------------------------------------------------------------------------------------|
+| **Issues**            | [All Issues](https://github.com/microsoft/markitdown/issues) | [Issues open for contribution](https://github.com/microsoft/markitdown/issues?q=is%3Aissue+is%3Aopen+label%3A%22open+for+contribution%22) |
+| **PRs**               | [All PRs](https://github.com/microsoft/markitdown/pulls)     | [PRs open for reviewing](https://github.com/microsoft/markitdown/pulls?q=is%3Apr+is%3Aopen+label%3A%22open+for+reviewing%22)               |
+
+</div>
+
 ### Running Tests and Checks
 
 - Install `hatch` in your environment and run tests:

pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "hatchling.build"
 [project]
 name = "markitdown"
 dynamic = ["version"]
-description = ''
+description = 'Utility tool for converting various files to Markdown'
 readme = "README.md"
 requires-python = ">=3.10"
 license = "MIT"

src/markitdown/__main__.py

@@ -1,16 +1,20 @@
 # SPDX-FileCopyrightText: 2024-present Adam Fourney <adamfo@microsoft.com>
 #
 # SPDX-License-Identifier: MIT
-import sys
 import argparse
-from ._markitdown import MarkItDown
+import sys
+from textwrap import dedent
+from .__about__ import __version__
+from ._markitdown import MarkItDown, DocumentConverterResult
 
 
 def main():
     parser = argparse.ArgumentParser(
         description="Convert various file formats to markdown.",
+        prog="markitdown",
         formatter_class=argparse.RawDescriptionHelpFormatter,
-        usage="""
+        usage=dedent(
+            """
             SYNTAX:
 
                 markitdown <OPTIONAL: FILENAME>
@@ -27,19 +31,50 @@ EXAMPLE:
                 OR
 
                 markitdown < example.pdf
-""".strip(),
+                
+                OR to save to a file use
+    
+                markitdown example.pdf -o example.md
+                
+                OR
+                
+                markitdown example.pdf > example.md
+            """
+        ).strip(),
+    )
+
+    parser.add_argument(
+        "-v",
+        "--version",
+        action="version",
+        version=f"%(prog)s {__version__}",
+        help="show the version number and exit",
     )
 
     parser.add_argument("filename", nargs="?")
+    parser.add_argument(
+        "-o",
+        "--output",
+        help="Output file name. If not provided, output is written to stdout.",
+    )
     args = parser.parse_args()
 
     if args.filename is None:
         markitdown = MarkItDown()
         result = markitdown.convert_stream(sys.stdin.buffer)
-        print(result.text_content)
+        _handle_output(args, result)
     else:
         markitdown = MarkItDown()
         result = markitdown.convert(args.filename)
+        _handle_output(args, result)
+
+
+def _handle_output(args, result: DocumentConverterResult):
+    """Handle output to stdout or file"""
+    if args.output:
+        with open(args.output, "w", encoding="utf-8") as f:
+            f.write(result.text_content)
+    else:
         print(result.text_content)
 
 

src/markitdown/_markitdown.py

@@ -15,6 +15,7 @@ import traceback
 import zipfile
 from xml.dom import minidom
 from typing import Any, Dict, List, Optional, Union
+from pathlib import Path
 from urllib.parse import parse_qs, quote, unquote, urlparse, urlunparse
 from warnings import warn, resetwarnings, catch_warnings
 
@@ -1289,11 +1290,11 @@ class MarkItDown:
         self.register_page_converter(ZipConverter())
 
     def convert(
-        self, source: Union[str, requests.Response], **kwargs: Any
+        self, source: Union[str, requests.Response, Path], **kwargs: Any
     ) -> DocumentConverterResult:  # TODO: deal with kwargs
         """
         Args:
-            - source: can be a string representing a path or url, or a requests.response object
+            - source: can be a string representing a path either as string pathlib path object or url, or a requests.response object
             - extension: specifies the file extension to use when interpreting the file. If None, infer from source (path, uri, content-type, etc.)
         """
 
@@ -1310,10 +1311,14 @@ class MarkItDown:
         # Request response
         elif isinstance(source, requests.Response):
             return self.convert_response(source, **kwargs)
+        elif isinstance(source, Path):
+            return self.convert_local(source, **kwargs)
 
     def convert_local(
-        self, path: str, **kwargs: Any
+        self, path: Union[str, Path], **kwargs: Any
     ) -> DocumentConverterResult:  # TODO: deal with kwargs
+        if isinstance(path, Path):
+            path = str(path)
         # Prepare a list of extensions to try (in order of priority)
         ext = kwargs.get("file_extension")
         extensions = [ext] if ext is not None else []

tests/test_markitdown.py

@@ -131,6 +131,17 @@ LLM_TEST_STRINGS = [
 ]
 
 
+# --- Helper Functions ---
+def validate_strings(result, expected_strings, exclude_strings=None):
+    """Validate presence or absence of specific strings."""
+    text_content = result.text_content.replace("\\", "")
+    for string in expected_strings:
+        assert string in text_content
+    if exclude_strings:
+        for string in exclude_strings:
+            assert string not in text_content
+
+
 @pytest.mark.skipif(
     skip_remote,
     reason="do not run tests that query external urls",
@@ -163,73 +174,53 @@ def test_markitdown_local() -> None:
 
     # Test XLSX processing
     result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.xlsx"))
-    for test_string in XLSX_TEST_STRINGS:
-        text_content = result.text_content.replace("\\", "")
-        assert test_string in text_content
+    validate_strings(result, XLSX_TEST_STRINGS)
 
     # Test DOCX processing
     result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.docx"))
-    for test_string in DOCX_TEST_STRINGS:
-        text_content = result.text_content.replace("\\", "")
-        assert test_string in text_content
+    validate_strings(result, DOCX_TEST_STRINGS)
 
     # Test DOCX processing, with comments
     result = markitdown.convert(
         os.path.join(TEST_FILES_DIR, "test_with_comment.docx"),
         style_map="comment-reference => ",
     )
-    for test_string in DOCX_COMMENT_TEST_STRINGS:
-        text_content = result.text_content.replace("\\", "")
-        assert test_string in text_content
+    validate_strings(result, DOCX_COMMENT_TEST_STRINGS)
 
     # Test DOCX processing, with comments and setting style_map on init
     markitdown_with_style_map = MarkItDown(style_map="comment-reference => ")
     result = markitdown_with_style_map.convert(
         os.path.join(TEST_FILES_DIR, "test_with_comment.docx")
     )
-    for test_string in DOCX_COMMENT_TEST_STRINGS:
-        text_content = result.text_content.replace("\\", "")
-        assert test_string in text_content
+    validate_strings(result, DOCX_COMMENT_TEST_STRINGS)
 
     # Test PPTX processing
     result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.pptx"))
-    for test_string in PPTX_TEST_STRINGS:
-        text_content = result.text_content.replace("\\", "")
-        assert test_string in text_content
+    validate_strings(result, PPTX_TEST_STRINGS)
 
     # Test HTML processing
     result = markitdown.convert(
         os.path.join(TEST_FILES_DIR, "test_blog.html"), url=BLOG_TEST_URL
     )
-    for test_string in BLOG_TEST_STRINGS:
-        text_content = result.text_content.replace("\\", "")
-        assert test_string in text_content
+    validate_strings(result, BLOG_TEST_STRINGS)
 
     # Test ZIP file processing
     result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test_files.zip"))
-    for test_string in DOCX_TEST_STRINGS:
-        text_content = result.text_content.replace("\\", "")
-        assert test_string in text_content
+    validate_strings(result, XLSX_TEST_STRINGS)
 
     # Test Wikipedia processing
     result = markitdown.convert(
         os.path.join(TEST_FILES_DIR, "test_wikipedia.html"), url=WIKIPEDIA_TEST_URL
     )
     text_content = result.text_content.replace("\\", "")
-    for test_string in WIKIPEDIA_TEST_EXCLUDES:
-        assert test_string not in text_content
-    for test_string in WIKIPEDIA_TEST_STRINGS:
-        assert test_string in text_content
+    validate_strings(result, WIKIPEDIA_TEST_STRINGS, WIKIPEDIA_TEST_EXCLUDES)
 
     # Test Bing processing
     result = markitdown.convert(
         os.path.join(TEST_FILES_DIR, "test_serp.html"), url=SERP_TEST_URL
     )
     text_content = result.text_content.replace("\\", "")
-    for test_string in SERP_TEST_EXCLUDES:
-        assert test_string not in text_content
-    for test_string in SERP_TEST_STRINGS:
-        assert test_string in text_content
+    validate_strings(result, SERP_TEST_STRINGS, SERP_TEST_EXCLUDES)
 
     # Test RSS processing
     result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test_rss.xml"))
@@ -239,9 +230,7 @@ def test_markitdown_local() -> None:
 
     ## Test non-UTF-8 encoding
     result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test_mskanji.csv"))
-    text_content = result.text_content.replace("\\", "")
-    for test_string in CSV_CP932_TEST_STRINGS:
-        assert test_string in text_content
+    validate_strings(result, CSV_CP932_TEST_STRINGS)
 
 
 @pytest.mark.skipif(