Update app.py
Browse files
app.py
CHANGED
@@ -1,40 +1,125 @@
|
|
1 |
from flask import Flask, request, jsonify, send_file
|
2 |
from flask_cors import CORS
|
3 |
import os
|
|
|
4 |
from pdf2docx import Converter
|
|
|
5 |
|
6 |
app = Flask(__name__)
|
7 |
CORS(app)
|
8 |
|
9 |
-
|
10 |
-
|
|
|
|
|
|
|
11 |
os.makedirs(UPLOAD_FOLDER, exist_ok=True)
|
12 |
os.makedirs(CONVERTED_FOLDER, exist_ok=True)
|
13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
@app.route("/", methods=["GET"])
|
15 |
def index():
|
16 |
return "✅ PDF to DOCX Converter is running!"
|
17 |
|
|
|
|
|
|
|
|
|
18 |
@app.route("/convert", methods=["POST"])
|
19 |
def convert_pdf_to_docx():
|
|
|
20 |
if "file" not in request.files:
|
21 |
return jsonify({"error": "No file uploaded"}), 400
|
22 |
-
|
23 |
pdf_file = request.files["file"]
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
try:
|
|
|
|
|
|
|
|
|
31 |
cv = Converter(pdf_path)
|
32 |
cv.convert(docx_path, start=0, end=None)
|
33 |
cv.close()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
except Exception as e:
|
|
|
|
|
|
|
35 |
return jsonify({"error": f"Conversion failed: {str(e)}"}), 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
|
37 |
-
|
|
|
|
|
38 |
|
39 |
if __name__ == "__main__":
|
40 |
-
|
|
|
|
|
|
1 |
from flask import Flask, request, jsonify, send_file
|
2 |
from flask_cors import CORS
|
3 |
import os
|
4 |
+
import tempfile
|
5 |
from pdf2docx import Converter
|
6 |
+
from werkzeug.utils import secure_filename
|
7 |
|
8 |
app = Flask(__name__)
|
9 |
CORS(app)
|
10 |
|
11 |
+
# Use system temp directory for better cross-platform compatibility
|
12 |
+
UPLOAD_FOLDER = os.path.join(tempfile.gettempdir(), "pdf_uploads")
|
13 |
+
CONVERTED_FOLDER = os.path.join(tempfile.gettempdir(), "pdf_converted")
|
14 |
+
|
15 |
+
# Create directories
|
16 |
os.makedirs(UPLOAD_FOLDER, exist_ok=True)
|
17 |
os.makedirs(CONVERTED_FOLDER, exist_ok=True)
|
18 |
|
19 |
+
# Configuration
|
20 |
+
app.config['MAX_CONTENT_LENGTH'] = 16 * 1024 * 1024 # 16MB max file size
|
21 |
+
ALLOWED_EXTENSIONS = {'pdf'}
|
22 |
+
|
23 |
+
def allowed_file(filename):
|
24 |
+
"""Check if file has allowed extension"""
|
25 |
+
return '.' in filename and \
|
26 |
+
filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
|
27 |
+
|
28 |
+
def cleanup_file(filepath):
|
29 |
+
"""Safely remove file if it exists"""
|
30 |
+
try:
|
31 |
+
if os.path.exists(filepath):
|
32 |
+
os.remove(filepath)
|
33 |
+
except Exception as e:
|
34 |
+
print(f"Warning: Could not remove file {filepath}: {e}")
|
35 |
+
|
36 |
@app.route("/", methods=["GET"])
|
37 |
def index():
|
38 |
return "✅ PDF to DOCX Converter is running!"
|
39 |
|
40 |
+
@app.route("/health", methods=["GET"])
|
41 |
+
def health_check():
|
42 |
+
return jsonify({"status": "healthy", "service": "PDF to DOCX Converter"})
|
43 |
+
|
44 |
@app.route("/convert", methods=["POST"])
|
45 |
def convert_pdf_to_docx():
|
46 |
+
# Check if file is present
|
47 |
if "file" not in request.files:
|
48 |
return jsonify({"error": "No file uploaded"}), 400
|
49 |
+
|
50 |
pdf_file = request.files["file"]
|
51 |
+
|
52 |
+
# Check if file is selected
|
53 |
+
if pdf_file.filename == '':
|
54 |
+
return jsonify({"error": "No file selected"}), 400
|
55 |
+
|
56 |
+
# Validate file type
|
57 |
+
if not allowed_file(pdf_file.filename):
|
58 |
+
return jsonify({"error": "Only PDF files are allowed"}), 400
|
59 |
+
|
60 |
+
# Secure the filename
|
61 |
+
filename = secure_filename(pdf_file.filename)
|
62 |
+
if not filename:
|
63 |
+
return jsonify({"error": "Invalid filename"}), 400
|
64 |
+
|
65 |
+
# Create unique paths to avoid conflicts
|
66 |
+
import time
|
67 |
+
timestamp = str(int(time.time()))
|
68 |
+
pdf_path = os.path.join(UPLOAD_FOLDER, f"{timestamp}_{filename}")
|
69 |
+
|
70 |
+
# Generate DOCX filename
|
71 |
+
docx_filename = os.path.splitext(filename)[0] + ".docx"
|
72 |
+
docx_path = os.path.join(CONVERTED_FOLDER, f"{timestamp}_{docx_filename}")
|
73 |
+
|
74 |
try:
|
75 |
+
# Save uploaded file
|
76 |
+
pdf_file.save(pdf_path)
|
77 |
+
|
78 |
+
# Convert PDF to DOCX
|
79 |
cv = Converter(pdf_path)
|
80 |
cv.convert(docx_path, start=0, end=None)
|
81 |
cv.close()
|
82 |
+
|
83 |
+
# Check if conversion was successful
|
84 |
+
if not os.path.exists(docx_path):
|
85 |
+
raise Exception("Conversion completed but output file not found")
|
86 |
+
|
87 |
+
# Send file and cleanup in finally block
|
88 |
+
return send_file(
|
89 |
+
docx_path,
|
90 |
+
as_attachment=True,
|
91 |
+
download_name=docx_filename,
|
92 |
+
mimetype='application/vnd.openxmlformats-officedocument.wordprocessingml.document'
|
93 |
+
)
|
94 |
+
|
95 |
except Exception as e:
|
96 |
+
# Cleanup on error
|
97 |
+
cleanup_file(pdf_path)
|
98 |
+
cleanup_file(docx_path)
|
99 |
return jsonify({"error": f"Conversion failed: {str(e)}"}), 500
|
100 |
+
|
101 |
+
finally:
|
102 |
+
# Schedule cleanup of uploaded file (converted file cleaned up after send)
|
103 |
+
try:
|
104 |
+
cleanup_file(pdf_path)
|
105 |
+
except:
|
106 |
+
pass
|
107 |
+
|
108 |
+
@app.after_request
|
109 |
+
def cleanup_converted_files(response):
|
110 |
+
"""Clean up converted files after response is sent"""
|
111 |
+
# This is a simple cleanup - in production you might want a more sophisticated approach
|
112 |
+
return response
|
113 |
+
|
114 |
+
@app.errorhandler(413)
|
115 |
+
def too_large(e):
|
116 |
+
return jsonify({"error": "File too large. Maximum size is 16MB"}), 413
|
117 |
|
118 |
+
@app.errorhandler(Exception)
|
119 |
+
def handle_exception(e):
|
120 |
+
return jsonify({"error": f"An unexpected error occurred: {str(e)}"}), 500
|
121 |
|
122 |
if __name__ == "__main__":
|
123 |
+
print(f"Upload folder: {UPLOAD_FOLDER}")
|
124 |
+
print(f"Converted folder: {CONVERTED_FOLDER}")
|
125 |
+
app.run(host="0.0.0.0", port=7860, debug=False)
|