pdf2txt/app.py

from flask import Flask, request, jsonify
import fitz  # PyMuPDF
import os

app = Flask(__name__)

# Define the upload folder
UPLOAD_FOLDER = 'uploads'
if not os.path.exists(UPLOAD_FOLDER):
    os.makedirs(UPLOAD_FOLDER)

@app.route('/upload', methods=['POST'])
def upload_file():
    # Check if the post request has the file part
    if 'file' not in request.files:
        return jsonify({'error': 'No file part in the request'}), 400

    file = request.files['file']

    # If the user does not select a file, the browser submits an
    # empty file without a filename.
    if file.filename == '':
        return jsonify({'error': 'No selected file'}), 400

    if file and allowed_file(file.filename):
        filepath = os.path.join(UPLOAD_FOLDER, file.filename)
        file.save(filepath)

        # Extract text from the PDF
        text = extract_text_from_pdf(filepath)

        # Optionally, remove the file after processing
        os.remove(filepath)

        return jsonify({'text': text}), 200
    else:
        return jsonify({'error': 'Invalid file type. Only PDF files are allowed.'}), 400

def allowed_file(filename):
    return '.' in filename and filename.rsplit('.', 1)[1].lower() == 'pdf'

def extract_text_from_pdf(filepath):
    document = fitz.open(filepath)
    text = ""
    for page_num in range(len(document)):
        page = document.load_page(page_num)
        text += page.get_text("text")
    return text

if __name__ == '__main__':
    app.run(debug=True)