hindi-ocr-api / app.py
badman99dev
πŸ› οΈ Updated OCR files with PDF support
279020a
from flask import Flask, request, jsonify
from flask_cors import CORS
import pytesseract
from PIL import Image
import fitz # PyMuPDF
import os
app = Flask(__name__)
CORS(app)
@app.route("/")
def home():
return "πŸš€ Hindi OCR API is running!"
@app.route("/api/ocr", methods=["POST"])
def ocr():
if "file" not in request.files:
return jsonify({"error": "❌ No file uploaded"}), 400
file = request.files["file"]
filename = file.filename
if filename.endswith(".pdf"):
doc = fitz.open(stream=file.read(), filetype="pdf")
text = ""
for page in doc:
pix = page.get_pixmap()
img_path = "temp.png"
pix.save(img_path)
img = Image.open(img_path)
text += pytesseract.image_to_string(img, lang="hin+eng") + "\n"
os.remove("temp.png")
return jsonify({"text": text.strip()})
elif filename.endswith((".png", ".jpg", ".jpeg")):
img = Image.open(file.stream)
text = pytesseract.image_to_string(img, lang="hin+eng")
return jsonify({"text": text.strip()})
else:
return jsonify({"error": "❌ Unsupported file type"}), 400
if __name__ == "__main__":
app.run(host="0.0.0.0", port=7860)