Office To Md

from markitdown import MarkItDown
# Initialize convertermd = MarkItDown()
# Convert fileresult = md.convert("document.docx")print(result.text_content)
# Save to filewith open("output.md", "w") as f:    f.write(result.text_content)

from markitdown import MarkItDown
# Simple conversionmd = MarkItDown()result = md.convert("document.docx")
# Access contentmarkdown_text = result.text_content
# With optionsmd = MarkItDown(    llm_client=None,      # Optional LLM for enhanced processing    llm_model=None        # Model name if using LLM)

from markitdown import MarkItDown
md = MarkItDown()
# Convert Word documentresult = md.convert("report.docx")
# Output preserves:# - Headings (as # headers)# - Bold/italic formatting# - Lists (bulleted and numbered)# - Tables (as markdown tables)# - Hyperlinks
print(result.text_content)

from markitdown import MarkItDown
md = MarkItDown()result = md.convert("data.xlsx")
# Each sheet becomes a section# Data becomes markdown tablesprint(result.text_content)

from markitdown import MarkItDown
md = MarkItDown()result = md.convert("presentation.pptx")
# Each slide becomes a section# Speaker notes included if presentprint(result.text_content)

from markitdown import MarkItDown
md = MarkItDown()result = md.convert("document.pdf")
# Extracts text content# Tables converted where detectedprint(result.text_content)

from markitdown import MarkItDownimport anthropic
# Use Claude for image descriptionclient = anthropic.Anthropic()
md = MarkItDown(    llm_client=client,    llm_model="claude-sonnet-4-20250514")
result = md.convert("diagram.png")print(result.text_content)
# Output: Description of the image content

from markitdown import MarkItDownfrom pathlib import Path
def batch_convert(input_dir, output_dir):    """Convert all Office files to Markdown."""    md = MarkItDown()    input_path = Path(input_dir)    output_path = Path(output_dir)    output_path.mkdir(exist_ok=True)        extensions = ['.docx', '.xlsx', '.pptx', '.pdf']        for ext in extensions:        for file in input_path.glob(f'*{ext}'):            try:                result = md.convert(str(file))                output_file = output_path / f"{file.stem}.md"                                with open(output_file, 'w') as f:                    f.write(result.text_content)                                print(f"Converted: {file.name}")            except Exception as e:                print(f"Error converting {file.name}: {e}")
batch_convert('./documents', './markdown')

import osfrom datetime import datetimefrom markitdown import MarkItDown
def archive_document(doc_path, archive_dir):    """Convert and archive Office document to Markdown."""    md = MarkItDown()    result = md.convert(doc_path)        # Create archive structure    date_str = datetime.now().strftime('%Y-%m-%d')    filename = os.path.basename(doc_path)    base_name = os.path.splitext(filename)[0]        # Save with metadata    output_content = f"""---source: {filename}converted: {date_str}---
{result.text_content}"""        output_path = os.path.join(archive_dir, f"{base_name}.md")    with open(output_path, 'w') as f:        f.write(output_content)        return output_path

from markitdown import MarkItDownfrom pathlib import Pathimport json
def create_ai_corpus(doc_folder, output_file):    """Convert documents to JSON corpus for AI training/RAG."""    md = MarkItDown()    corpus = []        for doc in Path(doc_folder).glob('**/*'):        if doc.suffix in ['.docx', '.pdf', '.pptx', '.xlsx']:            try:                result = md.convert(str(doc))                corpus.append({                    'source': str(doc),                    'filename': doc.name,                    'content': result.text_content,                    'type': doc.suffix[1:]                })            except Exception as e:                print(f"Skipped {doc.name}: {e}")        with open(output_file, 'w') as f:        json.dump(corpus, f, indent=2)        print(f"Created corpus with {len(corpus)} documents")    return corpus

from markitdown import MarkItDownfrom pathlib import Path
def convert_docs_to_wiki(docs_folder, wiki_folder):    """Convert all Office docs to markdown wiki structure."""    md = MarkItDown()    docs_path = Path(docs_folder)    wiki_path = Path(wiki_folder)        # Create wiki structure    wiki_path.mkdir(exist_ok=True)        # Create index    index_content = "# Documentation Index\n\n"        for doc in sorted(docs_path.glob('**/*.docx')):        try:            result = md.convert(str(doc))                        # Create relative path in wiki            rel_path = doc.relative_to(docs_path)            output_file = wiki_path / rel_path.with_suffix('.md')            output_file.parent.mkdir(parents=True, exist_ok=True)                        # Write markdown            with open(output_file, 'w') as f:                f.write(result.text_content)                        # Add to index            link = str(rel_path.with_suffix('.md')).replace('\\', '/')            index_content += f"- [{doc.stem}]({link})\n"                        print(f"Converted: {doc.name}")                    except Exception as e:            print(f"Error: {doc.name} - {e}")        # Write index    with open(wiki_path / 'index.md', 'w') as f:        f.write(index_content)
convert_docs_to_wiki('./company_docs', './wiki')

from markitdown import MarkItDownimport refrom datetime import datetime
def process_meeting_notes(pptx_path):    """Extract and structure meeting notes from PowerPoint."""    md = MarkItDown()    result = md.convert(pptx_path)        # Parse the markdown    content = result.text_content        # Extract sections    sections = {        'attendees': [],        'agenda': [],        'decisions': [],        'action_items': []    }        current_section = None        for line in content.split('\n'):        line_lower = line.lower()                if 'attendee' in line_lower or 'participant' in line_lower:            current_section = 'attendees'        elif 'agenda' in line_lower:            current_section = 'agenda'        elif 'decision' in line_lower:            current_section = 'decisions'        elif 'action' in line_lower:            current_section = 'action_items'        elif line.strip().startswith(('-', '*', '•')) and current_section:            sections[current_section].append(line.strip()[1:].strip())        # Generate structured output    output = f"""# Meeting Notes
**Date:** {datetime.now().strftime('%Y-%m-%d')}**Source:** {pptx_path}
## Attendees{chr(10).join('- ' + a for a in sections['attendees'])}
## Agenda{chr(10).join('- ' + a for a in sections['agenda'])}
## Decisions Made{chr(10).join('- ' + d for d in sections['decisions'])}
## Action Items{chr(10).join('- [ ] ' + a for a in sections['action_items'])}"""        return output
notes = process_meeting_notes('team_meeting.pptx')print(notes)

from markitdown import MarkItDown
def excel_to_data_dictionary(xlsx_path):    """Convert Excel data model to data dictionary documentation."""    md = MarkItDown()    result = md.convert(xlsx_path)        # Add documentation structure    doc = f"""# Data Dictionary
Generated from: `{xlsx_path}`
{result.text_content}
## Usage Notes
- All tables are derived from the source Excel file- Review data types and constraints before use- Contact data team for clarifications
## Change Log
| Date | Change | Author ||------|--------|--------|| {datetime.now().strftime('%Y-%m-%d')} | Initial generation | Auto |"""        return doc
documentation = excel_to_data_dictionary('data_model.xlsx')with open('data_dictionary.md', 'w') as f:    f.write(documentation)