batch-convert

SKILL.md

Batch Convert Skill

Overview

This skill enables batch conversion of documents between multiple formats using a unified pipeline. Convert hundreds of files at once with consistent settings, automatic format detection, and parallel processing for maximum efficiency.

How to Use

Specify the source folder or files

Choose target format(s)

Optionally configure conversion options

I'll process all files with progress tracking

Example prompts:

"Convert all PDFs in this folder to Word documents"

"Batch convert these markdown files to PDF and HTML"

"Process all Office files and convert to Markdown"

"Convert this folder of images to a single PDF"

Domain Knowledge

Supported Format Matrix

From
To: DOCX
To: PDF
To: MD
To: HTML
To: PPTX

DOCX
-
✅
✅
✅
-

PDF
✅
-
✅
✅
-

MD
✅
✅
-
✅
✅

HTML
✅
✅
✅
-
-

XLSX
-
✅
✅
✅
-

PPTX
-
✅
✅
✅
-

Core Pipeline

from pathlib import Path
from concurrent.futures import ThreadPoolExecutor, as_completed
import subprocess
import os

class DocumentConverter:
    """Unified document conversion pipeline."""
    
    def __init__(self, max_workers=4):
        self.max_workers = max_workers
        self.converters = {
            ('md', 'docx'): self._md_to_docx,
            ('md', 'pdf'): self._md_to_pdf,
            ('md', 'html'): self._md_to_html,
            ('md', 'pptx'): self._md_to_pptx,
            ('docx', 'pdf'): self._docx_to_pdf,
            ('docx', 'md'): self._docx_to_md,
            ('pdf', 'docx'): self._pdf_to_docx,
            ('pdf', 'md'): self._pdf_to_md,
            ('xlsx', 'pdf'): self._xlsx_to_pdf,
            ('xlsx', 'md'): self._xlsx_to_md,
            ('pptx', 'pdf'): self._pptx_to_pdf,
            ('pptx', 'md'): self._pptx_to_md,
            ('html', 'md'): self._html_to_md,
            ('html', 'pdf'): self._html_to_pdf,
        }
    
    def convert(self, input_path, output_format, output_dir=None):
        """Convert single file to target format."""
        input_path = Path(input_path)
        input_format = input_path.suffix[1:].lower()
        
        if output_dir:
            output_path = Path(output_dir) / f"{input_path.stem}.{output_format}"
        else:
            output_path = input_path.with_suffix(f".{output_format}")
        
        converter_key = (input_format, output_format)
        if converter_key not in self.converters:
            raise ValueError(f"Conversion not supported: {input_format} -> {output_format}")
        
        converter = self.converters[converter_key]
        return converter(input_path, output_path)
    
    def batch_convert(self, input_dir, output_format, output_dir=None, 
                      file_pattern="*", recursive=False):
        """Batch convert all matching files."""
        input_path = Path(input_dir)
        output_path = Path(output_dir) if output_dir else input_path / "converted"
        output_path.mkdir(exist_ok=True)
        
        # Find files
        if recursive:
            files = list(input_path.rglob(file_pattern))
        else:
            files = list(input_path.glob(file_pattern))
        
        # Filter to supported formats
        supported_ext = ['.md', '.docx', '.pdf', '.xlsx', '.pptx', '.html']
        files = [f for f in files if f.suffix.lower() in supported_ext]
        
        results = []
        
        with ThreadPoolExecutor(max_workers=self.max_workers) as executor:
            future_to_file = {
                executor.submit(self.convert, f, output_format, output_path): f
                for f in files
            }
            
            for future in as_completed(future_to_file):
                file = future_to_file[future]
                try:
                    result = future.result()
                    results.append({'file': str(file), 'status': 'success', 'output': str(result)})
                except Exception as e:
                    results.append({'file': str(file), 'status': 'error', 'error': str(e)})
        
        return results

Converter Implementations

# Markdown conversions (using Pandoc)
def _md_to_docx(self, input_path, output_path):
    subprocess.run(['pandoc', str(input_path), '-o', str(output_path)], check=True)
    return output_path

def _md_to_pdf(self, input_path, output_path):
    subprocess.run(['pandoc', str(input_path), '-o', str(output_path)], check=True)
    return output_path

def _md_to_html(self, input_path, output_path):
    subprocess.run(['pandoc', str(input_path), '-s', '-o', str(output_path)], check=True)
    return output_path

def _md_to_pptx(self, input_path, output_path):
    subprocess.run(['marp', str(input_path), '-o', str(output_path)], check=True)
    return output_path

# Office to Markdown (using markitdown)
def _docx_to_md(self, input_path, output_path):
    from markitdown import MarkItDown
    md = MarkItDown()
    result = md.convert(str(input_path))
    with open(output_path, 'w') as f:
        f.write(result.text_content)
    return output_path

def _xlsx_to_md(self, input_path, output_path):
    from markitdown import MarkItDown
    md = MarkItDown()
    result = md.convert(str(input_path))
    with open(output_path, 'w') as f:
        f.write(result.text_content)
    return output_path

def _pptx_to_md(self, input_path, output_path):
    from markitdown import MarkItDown
    md = MarkItDown()
    result = md.convert(str(input_path))
    with open(output_path, 'w') as f:
        f.write(result.text_content)
    return output_path

# PDF conversions
def _pdf_to_docx(self, input_path, output_path):
    from pdf2docx import Converter
    cv = Converter(str(input_path))
    cv.convert(str(output_path))
    cv.close()
    return output_path

def _pdf_to_md(self, input_path, output_path):
    from markitdown import MarkItDown
    md = MarkItDown()
    result = md.convert(str(input_path))
    with open(output_path, 'w') as f:
        f.write(result.text_content)
    return output_path

# Office to PDF (using LibreOffice)
def _docx_to_pdf(self, input_path, output_path):
    subprocess.run([
        'soffice', '--headless', '--convert-to', 'pdf',
        '--outdir', str(output_path.parent), str(input_path)
    ], check=True)
    return output_path

def _xlsx_to_pdf(self, input_path, output_path):
    subprocess.run([
        'soffice', '--headless', '--convert-to', 'pdf',
        '--outdir', str(output_path.parent), str(input_path)
    ], check=True)
    return output_path

def _pptx_to_pdf(self, input_path, output_path):
    subprocess.run([
        'soffice', '--headless', '--convert-to', 'pdf',
        '--outdir', str(output_path.parent), str(input_path)
    ], check=True)
    return output_path

Progress Tracking

from tqdm import tqdm

def batch_convert_with_progress(converter, input_dir, output_format, output_dir=None):
    """Batch convert with progress bar."""
    input_path = Path(input_dir)
    files = list(input_path.glob('*'))
    
    results = []
    for file in tqdm(files, desc=f"Converting to {output_format}"):
        try:
            result = converter.convert(file, output_format, output_dir)
            results.append({'file': str(file), 'status': 'success'})
        except Exception as e:
            results.append({'file': str(file), 'status': 'error', 'error': str(e)})
    
    return results

Best Practices

Test Sample First: Convert a few files before batch processing

Check Disk Space: Ensure sufficient space for output

Use Parallel Processing: Speed up with multiple workers

Handle Errors Gracefully: Log failures, continue processing

Verify Output: Spot-check converted files

Common Patterns

Format Detection Pipeline

def detect_and_convert(file_path, target_format):
    """Automatically detect format and convert."""
    import mimetypes
    
    mime_type, _ = mimetypes.guess_type(str(file_path))
    
    format_map = {
        'application/pdf': 'pdf',
        'application/vnd.openxmlformats-officedocument.wordprocessingml.document': 'docx',
        'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet': 'xlsx',
        'application/vnd.openxmlformats-officedocument.presentationml.presentation': 'pptx',
        'text/markdown': 'md',
        'text/html': 'html',
    }
    
    source_format = format_map.get(mime_type, Path(file_path).suffix[1:])
    
    converter = DocumentConverter()
    return converter.convert(file_path, target_format)

Multi-Format Output

def convert_to_multiple_formats(input_file, output_formats, output_dir):
    """Convert one file to multiple formats."""
    converter = DocumentConverter()
    results = {}
    
    for fmt in output_formats:
        try:
            output = converter.convert(input_file, fmt, output_dir)
            results[fmt] = {'status': 'success', 'path': str(output)}
        except Exception as e:
            results[fmt] = {'status': 'error', 'error': str(e)}
    
    return results

# Convert README to multiple formats
results = convert_to_multiple_formats(
    'README.md',
    ['docx', 'pdf', 'html'],
    './exports'
)

Examples

Example 1: Documentation Export

from pathlib import Path
import json

def export_documentation(docs_dir, export_dir):
    """Export all documentation to multiple formats."""
    
    converter = DocumentConverter(max_workers=8)
    docs_path = Path(docs_dir)
    export_path = Path(export_dir)
    
    # Create format directories
    for fmt in ['pdf', 'docx', 'html']:
        (export_path / fmt).mkdir(parents=True, exist_ok=True)
    
    all_results = {}
    
    # Find all markdown files
    md_files = list(docs_path.rglob('*.md'))
    
    for md_file in md_files:
        file_results = {}
        
        for fmt in ['pdf', 'docx', 'html']:
            output_dir = export_path / fmt
            try:
                output = converter.convert(md_file, fmt, output_dir)
                file_results[fmt] = 'success'
            except Exception as e:
                file_results[fmt] = f'error: {e}'
        
        all_results[str(md_file)] = file_results
        print(f"Processed: {md_file.name}")
    
    # Save report
    with open(export_path / 'export_report.json', 'w') as f:
        json.dump(all_results, f, indent=2)
    
    return all_results

results = export_documentation('./docs', './exports')

Example 2: Legacy Document Migration

def migrate_legacy_docs(source_dir, target_dir):
    """Migrate legacy documents to modern formats."""
    
    converter = DocumentConverter(max_workers=4)
    
    # Migration rules
    migrations = [
        ('*.doc', 'docx'),   # Old Word to new
        ('*.xls', 'xlsx'),   # Old Excel to new
        ('*.ppt', 'pptx'),   # Old PowerPoint to new
        ('*.rtf', 'docx'),   # RTF to Word
    ]
    
    source_path = Path(source_dir)
    target_path = Path(target_dir)
    target_path.mkdir(exist_ok=True)
    
    total_migrated = 0
    errors = []
    
    for pattern, target_format in migrations:
        files = list(source_path.glob(pattern))
        
        for file in files:
            try:
                # Use LibreOffice for legacy formats
                subprocess.run([
                    'soffice', '--headless',
                    '--convert-to', target_format,
                    '--outdir', str(target_path),
                    str(file)
                ], check=True)
                
                total_migrated += 1
                print(f"Migrated: {file.name}")
                
            except Exception as e:
                errors.append({'file': str(file), 'error': str(e)})
    
    print(f"\nMigration complete: {total_migrated} files")
    print(f"Errors: {len(errors)}")
    
    return {'migrated': total_migrated, 'errors': errors}

Example 3: Report Generation Pipeline

def generate_reports_pipeline(data_files, template_dir, output_dir):
    """Generate reports from data files using templates."""
    
    from datetime import datetime
    
    converter = DocumentConverter()
    output_path = Path(output_dir)
    output_path.mkdir(exist_ok=True)
    
    timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
    
    reports = []
    
    for data_file in data_files:
        # Load data
        data_path = Path(data_file)
        
        # Generate markdown report
        md_content = f"""---
title: Report - {data_path.stem}
date: {datetime.now().strftime('%Y-%m-%d')}
---

# {data_path.stem} Report

Generated: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}

## Data Summary

"""
        
        # Add data content (simplified)
        if data_path.suffix == '.xlsx':
            from markitdown import MarkItDown
            md = MarkItDown()
            result = md.convert(str(data_path))
            md_content += result.text_content
        
        # Save markdown
        md_file = output_path / f"{data_path.stem}_{timestamp}.md"
        with open(md_file, 'w') as f:
            f.write(md_content)
        
        # Convert to PDF and DOCX
        for fmt in ['pdf', 'docx']:
            try:
                output = converter.convert(md_file, fmt, output_path)
                reports.append({'source': str(data_file), 'output': str(output), 'format': fmt})
            except Exception as e:
                print(f"Error converting {data_file} to {fmt}: {e}")
    
    return reports

Limitations

Some format combinations not supported

Complex formatting may be lost in conversion

Large files may require more time

Some conversions need external tools (LibreOffice, Pandoc)

Quality varies by source document complexity

Installation

# Core dependencies
pip install pdf2docx markitdown python-docx openpyxl

# Pandoc (for MD conversions)
brew install pandoc  # macOS
apt install pandoc   # Ubuntu

# Marp (for PPTX)
npm install -g @marp-team/marp-cli

# LibreOffice (for Office formats)
brew install libreoffice  # macOS
apt install libreoffice   # Ubuntu

Resources

Pandoc Documentation

markitdown GitHub

pdf2docx Documentation

LibreOffice CLI