Markitdown

from markitdown import MarkItDown

md = MarkItDown()

# Convert PDF paper
result = md.convert("research_paper.pdf")
with open("paper.md", "w") as f:
    f.write(result.text_content)

from markitdown import MarkItDown

md = MarkItDown()
result = md.convert("data.xlsx")

# Result will be in Markdown table format
print(result.text_content)

from markitdown import MarkItDown
import os
from pathlib import Path

md = MarkItDown()

# Process all PDFs in a directory
pdf_dir = Path("papers/")
output_dir = Path("markdown_output/")
output_dir.mkdir(exist_ok=True)

for pdf_file in pdf_dir.glob("*.pdf"):
    result = md.convert(str(pdf_file))
    output_file = output_dir / f"{pdf_file.stem}.md"
    output_file.write_text(result.text_content)
    print(f"Converted: {pdf_file.name}")

from markitdown import MarkItDown
from openai import OpenAI

# Use OpenRouter for access to multiple AI models
client = OpenAI(
    api_key="your-openrouter-api-key",
    base_url="https://openrouter.ai/api/v1"
)

md = MarkItDown(
    llm_client=client,
    llm_model="anthropic/claude-sonnet-4.5",  # recommended for presentations
    llm_prompt="Describe this slide image in detail, focusing on key visual elements and data"
)

result = md.convert("presentation.pptx")
with open("presentation.md", "w") as f:
    f.write(result.text_content)

from markitdown import MarkItDown
from pathlib import Path

md = MarkItDown()

# Files to convert
files = [
    "document.pdf",
    "spreadsheet.xlsx",
    "presentation.pptx",
    "notes.docx"
]

for file in files:
    try:
        result = md.convert(file)
        output = Path(file).stem + ".md"
        with open(output, "w") as f:
            f.write(result.text_content)
        print(f"✓ Converted {file}")
    except Exception as e:
        print(f"✗ Error converting {file}: {e}")

from markitdown import MarkItDown

md = MarkItDown()

# Convert YouTube video to transcript
result = md.convert("https://www.youtube.com/watch?v=VIDEO_ID")
print(result.text_content)

# Build image
docker build -t markitdown:latest .

# Run conversion
docker run --rm -i markitdown:latest < ~/document.pdf > output.md

from markitdown import MarkItDown

md = MarkItDown()

try:
    result = md.convert("document.pdf")
    print(result.text_content)
except FileNotFoundError:
    print("File not found")
except Exception as e:
    print(f"Conversion error: {e}")

from markitdown import MarkItDown

md = MarkItDown()

# For large files, use streaming
with open("large_file.pdf", "rb") as f:
    result = md.convert_stream(f, file_extension=".pdf")
    
    # Process in chunks or save directly
    with open("output.md", "w") as out:
        out.write(result.text_content)

from markitdown import MarkItDown
import re

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

# Clean up extra whitespace
clean_text = re.sub(r'\n{3,}', '\n\n', result.text_content)
clean_text = clean_text.strip()

print(clean_text)

from markitdown import MarkItDown
from pathlib import Path

md = MarkItDown()

# Convert all papers in literature folder
papers_dir = Path("literature/pdfs")
output_dir = Path("literature/markdown")
output_dir.mkdir(exist_ok=True)

for paper in papers_dir.glob("*.pdf"):
    result = md.convert(str(paper))
    
    # Save with metadata
    output_file = output_dir / f"{paper.stem}.md"
    content = f"# {paper.stem}\n\n"
    content += f"**Source**: {paper.name}\n\n"
    content += "---\n\n"
    content += result.text_content
    
    output_file.write_text(content)

# For AI-enhanced conversion with figures
from openai import OpenAI

client = OpenAI(
    api_key="your-openrouter-api-key",
    base_url="https://openrouter.ai/api/v1"
)

md_ai = MarkItDown(
    llm_client=client,
    llm_model="anthropic/claude-sonnet-4.5",
    llm_prompt="Describe scientific figures with technical precision"
)

from markitdown import MarkItDown
import re

md = MarkItDown()
result = md.convert("data_tables.xlsx")

# Markdown tables can be parsed or used directly
print(result.text_content)