Sample data and code for the article on MarkItDown

python-markitdown/README.md

@@ -0,0 +1,3 @@
+# Python MarkItDown: Convert Documents Into LLM-Ready Markdown
+
+This folder provides the code examples for the Real Python tutorial [Python MarkItDown: Convert Documents Into LLM-Ready Markdown](https://realpython.com/python-markitdown/).

python-markitdown/batch_converter.py

@@ -0,0 +1,33 @@
+from pathlib import Path
+
+from markitdown import MarkItDown
+
+
+def main(
+    input_dir,
+    output_dir="output",
+    target_formats=(".docx", ".xlsx", ".pdf"),
+):
+    input_path = Path(input_dir)
+    output_path = Path(output_dir)
+    output_path.mkdir(parents=True, exist_ok=True)
+
+    md = MarkItDown()
+
+    for file_path in input_path.glob("*"):
+        if file_path.suffix in target_formats:
+            try:
+                result = md.convert(file_path)
+            except Exception as e:
+                print(f"✗ Error converting {file_path.name}: {e}")
+                continue
+
+            output_file = (
+                output_path / f"{file_path.stem}{file_path.suffix}.md"
+            )
+            output_file.write_text(result.markdown, encoding="utf-8")
+            print(f"✓ Converted {file_path.name} → {output_file.name}")
+
+
+if __name__ == "__main__":
+    main("data", "output")

python-markitdown/convert_files.py

@@ -0,0 +1,5 @@
+from markitdown import MarkItDown
+
+md = MarkItDown()
+result = md.convert("./data/sample_DOCX.docx")
+print(result)

python-markitdown/data/employees.csv

@@ -0,0 +1,9 @@
+First Name,Last Name,Department,Position,Start Date
+Alice,Johnson,Marketing,Marketing Coordinator,1/15/2022
+Bob,Williams,Human Resources,HR Generalist,6/1/2021
+Carol,Davis,Engineering,Software Engineer,3/20/2023
+David,Brown,Sales,Sales Representative,9/10/2022
+Eve,Miller,Finance,Financial Analyst,11/5/2021
+Frank,Garcia,Customer Service,Customer Support Specialist,7/1/2023
+Grace,Rodriguez,Research & Development,Research Scientist,4/25/2022
+Henry,Martinez,Operations,Operations Manager,2/14/2021

python-markitdown/data/zen-of-python.txt

@@ -0,0 +1,22 @@
+<h2>The Zen of Python, by Tim Peters</h2>
+<ul>
+  <li>Beautiful is better than ugly.</li>
+  <li>Explicit is better than implicit.</li>
+  <li>Simple is better than complex.</li>
+  <li>Complex is better than complicated.</li>
+  <li>Flat is better than nested.</li>
+  <li>Sparse is better than dense.</li>
+  <li>Readability counts.</li>
+  <li>Special cases aren't special enough to break the rules.</li>
+  <li>Although practicality beats purity.</li>
+  <li>Errors should never pass silently.</li>
+  <li>Unless explicitly silenced.</li>
+  <li>In the face of ambiguity, refuse the temptation to guess.</li>
+  <li>There should be one-- and preferably only one --obvious way to do it.</li>
+  <li>Although that way may not be obvious at first unless you're Dutch.</li>
+  <li>Now is better than never.</li>
+  <li>Although never is often better than <em>right</em> now.</li>
+  <li>If the implementation is hard to explain, it's a bad idea.</li>
+  <li>If the implementation is easy to explain, it may be a good idea.</li>
+  <li>Namespaces are one honking great idea -- let's do more of those!</li>
+</ul>

python-markitdown/img_description.py

@@ -0,0 +1,11 @@
+from markitdown import MarkItDown
+from openai import OpenAI
+
+client = OpenAI()
+md = MarkItDown(
+    llm_client=client,
+    llm_model="gpt-4o",
+)
+
+result = md.convert("./data/real-python.png")
+print(result.markdown)

python-markitdown/ocr.py

@@ -0,0 +1,12 @@
+from markitdown import MarkItDown
+from openai import OpenAI
+
+client = OpenAI()
+md = MarkItDown(
+    llm_client=client,
+    llm_model="gpt-4o",
+    llm_prompt="Extract text from image with OCR and return Markdown.",
+)
+
+result = md.convert("./data/zen-of-python.png")
+print(result.markdown)