Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -1,9 +1,8 @@
|
|
1 |
import os
|
2 |
from flask import Flask, request, jsonify
|
3 |
-
from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer
|
4 |
from werkzeug.utils import secure_filename
|
|
|
5 |
from pdf2image import convert_from_path
|
6 |
-
import pytesseract
|
7 |
from PIL import Image
|
8 |
|
9 |
# Initialize Flask app
|
@@ -14,24 +13,36 @@ UPLOAD_FOLDER = 'uploads'
|
|
14 |
os.makedirs(UPLOAD_FOLDER, exist_ok=True)
|
15 |
app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
|
16 |
|
17 |
-
#
|
18 |
-
|
19 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
|
21 |
-
# Function to extract text from a PDF resume
|
22 |
def extract_text_from_pdf(pdf_path):
|
|
|
23 |
images = convert_from_path(pdf_path)
|
24 |
extracted_text = ""
|
25 |
|
26 |
for img in images:
|
27 |
-
text =
|
28 |
extracted_text += text + "\n"
|
29 |
|
30 |
return extracted_text.strip()
|
31 |
|
32 |
-
# Route: Upload Resume & Generate Report
|
33 |
@app.route('/upload', methods=['POST'])
|
34 |
-
def
|
|
|
35 |
if 'file' not in request.files:
|
36 |
return jsonify({"error": "No file uploaded"}), 400
|
37 |
|
@@ -39,25 +50,21 @@ def upload_resume():
|
|
39 |
if file.filename == '':
|
40 |
return jsonify({"error": "No file selected"}), 400
|
41 |
|
|
|
|
|
|
|
42 |
# Save uploaded file
|
43 |
filename = secure_filename(file.filename)
|
44 |
file_path = os.path.join(app.config['UPLOAD_FOLDER'], filename)
|
45 |
file.save(file_path)
|
46 |
|
47 |
-
#
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
ai_evaluation = text_gen_pipeline(prompt, max_length=150, num_return_sequences=1)[0]["generated_text"]
|
53 |
-
|
54 |
-
# Return response
|
55 |
-
response = {
|
56 |
-
"resume_text": extracted_text[:1000], # Limit to 1000 chars for display
|
57 |
-
"ai_evaluation": ai_evaluation
|
58 |
-
}
|
59 |
|
60 |
-
return jsonify(
|
61 |
|
62 |
# Run Flask App
|
63 |
if __name__ == '__main__':
|
|
|
1 |
import os
|
2 |
from flask import Flask, request, jsonify
|
|
|
3 |
from werkzeug.utils import secure_filename
|
4 |
+
from transformers import pipeline
|
5 |
from pdf2image import convert_from_path
|
|
|
6 |
from PIL import Image
|
7 |
|
8 |
# Initialize Flask app
|
|
|
13 |
os.makedirs(UPLOAD_FOLDER, exist_ok=True)
|
14 |
app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
|
15 |
|
16 |
+
# Allowed file extensions
|
17 |
+
ALLOWED_EXTENSIONS = {'png', 'jpg', 'jpeg', 'pdf'}
|
18 |
+
|
19 |
+
# Load TrOCR Model
|
20 |
+
ocr_pipeline = pipeline("image-to-text", model="microsoft/trocr-small-printed")
|
21 |
+
|
22 |
+
def allowed_file(filename):
|
23 |
+
"""Check if the file has an allowed extension."""
|
24 |
+
return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
|
25 |
+
|
26 |
+
def extract_text_from_image(image_path):
|
27 |
+
"""Extract text from a single image using TrOCR."""
|
28 |
+
image = Image.open(image_path).convert("RGB")
|
29 |
+
text = ocr_pipeline(image)[0]['generated_text']
|
30 |
+
return text
|
31 |
|
|
|
32 |
def extract_text_from_pdf(pdf_path):
|
33 |
+
"""Convert PDF to images and extract text from each page."""
|
34 |
images = convert_from_path(pdf_path)
|
35 |
extracted_text = ""
|
36 |
|
37 |
for img in images:
|
38 |
+
text = extract_text_from_image(img)
|
39 |
extracted_text += text + "\n"
|
40 |
|
41 |
return extracted_text.strip()
|
42 |
|
|
|
43 |
@app.route('/upload', methods=['POST'])
|
44 |
+
def upload_file():
|
45 |
+
"""Handle file upload and text extraction."""
|
46 |
if 'file' not in request.files:
|
47 |
return jsonify({"error": "No file uploaded"}), 400
|
48 |
|
|
|
50 |
if file.filename == '':
|
51 |
return jsonify({"error": "No file selected"}), 400
|
52 |
|
53 |
+
if not allowed_file(file.filename):
|
54 |
+
return jsonify({"error": "Invalid file type. Allowed: PNG, JPG, JPEG, PDF."}), 400
|
55 |
+
|
56 |
# Save uploaded file
|
57 |
filename = secure_filename(file.filename)
|
58 |
file_path = os.path.join(app.config['UPLOAD_FOLDER'], filename)
|
59 |
file.save(file_path)
|
60 |
|
61 |
+
# Process image or PDF
|
62 |
+
if filename.lower().endswith(".pdf"):
|
63 |
+
extracted_text = extract_text_from_pdf(file_path)
|
64 |
+
else:
|
65 |
+
extracted_text = extract_text_from_image(file_path)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
|
67 |
+
return jsonify({"extracted_text": extracted_text})
|
68 |
|
69 |
# Run Flask App
|
70 |
if __name__ == '__main__':
|