python-pdf2txt/app.py

from flask import Flask, request, send_from_directory, abort
import os
from pdf_to_word import pdf_to_word
import logging

# Configure logging
logging.basicConfig(level=logging.DEBUG, filename='/app/logs/app.log', filemode='w',
                    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')

app = Flask(__name__)
UPLOAD_FOLDER = '/app/uploads'
OUTPUT_FOLDER = '/app/outputs'

if not os.path.exists(UPLOAD_FOLDER):
    os.makedirs(UPLOAD_FOLDER)
if not os.path.exists(OUTPUT_FOLDER):
    os.makedirs(OUTPUT_FOLDER)

@app.route('/upload-pdf', methods=['POST'])
def upload_pdf():
    file = request.files['file']
    if file and file.filename.endswith('.pdf'):
        pdf_path = os.path.join(UPLOAD_FOLDER, file.filename)
        file.save(pdf_path)
        logging.info(f'File uploaded and saved to {pdf_path}')
        output_path = pdf_to_word(pdf_path, OUTPUT_FOLDER, lang='fas+eng')
        if output_path:
            logging.info(f'Sending file {output_path}')
            return send_from_directory(OUTPUT_FOLDER, os.path.basename(output_path), as_attachment=True)
        else:
            logging.error('Conversion failed.')
            abort(500, 'Conversion failed.')
    else:
        logging.warning('Invalid file type or no file uploaded.')
        abort(400, 'Invalid file type or no file uploaded.')

if __name__ == '__main__':
    app.run(debug=True, host='0.0.0.0', port=5000)