from markitdown import MarkItDown

md = MarkItDown()
result = md.convert("document.pdf")
print(result.text_content)

# Convert single file
markitdown document.pdf > output.md
markitdown document.pdf -o output.md

# Pipe input
cat document.pdf | markitdown

# Basic PDF conversion
md = MarkItDown()
result = md.convert("report.pdf")

# With Azure Document Intelligence (better quality)
md = MarkItDown(docintel_endpoint="<your-endpoint>")
result = md.convert("report.pdf")

# Word documents - preserves structure
result = md.convert("document.docx")

# Excel - converts tables to markdown tables
result = md.convert("spreadsheet.xlsx")

# PowerPoint - extracts slide content
result = md.convert("presentation.pptx")

# ✅ SECURE: Using environment variables for API keys
import os
from openai import OpenAI

api_key = os.getenv("OPENAI_API_KEY")
if not api_key:
    raise RuntimeError("OPENAI_API_KEY not set")

client = OpenAI(api_key=api_key)
md = MarkItDown(llm_client=client, llm_model="gpt-4o")
result = md.convert("diagram.jpg")  # Gets AI-generated description

from pathlib import Path

md = MarkItDown()
documents = Path(".").glob("*.pdf")

for doc in documents:
    result = md.convert(str(doc))
    output_path = doc.with_suffix(".md")
    output_path.write_text(result.text_content)

# Full installation (all features)
pip install 'markitdown[all]'

# Selective features
pip install 'markitdown[pdf, docx, pptx]'

# ❌ NEVER DO THIS
md = MarkItDown(llm_client=OpenAI(api_key="sk-hardcoded-key"))

# ✅ ALWAYS DO THIS
api_key = os.getenv("OPENAI_API_KEY")
md = MarkItDown(llm_client=OpenAI(api_key=api_key))

# ❌ Vulnerable to path traversal
user_input = "../../../etc/passwd"
md.convert(user_input)

# ✅ Validate and sanitize
from pathlib import Path
safe_path = Path(user_input).resolve()
if not safe_path.is_relative_to(allowed_dir):
    raise ValueError("Invalid path")
md.convert(str(safe_path))

# ❌ Can cause DoS
md.convert("huge_file.pdf")  # No size check

# ✅ Check size first
max_size = 50 * 1024 * 1024  # 50MB
if Path("file.pdf").stat().st_size > max_size:
    raise ValueError("File too large")