Update app.py

app.py

@@ -16,8 +16,7 @@ import datasets
 from datasets import load_dataset, Image
 from PIL import Image
 from paddleocr import PaddleOCR
-from save_data import flag
-            
+
 """
 Paddle OCR
 """
@@ -63,58 +62,51 @@ def ocr_with_easy(img):
     bounds = reader.readtext('image.png',paragraph="False",detail = 0)
     bounds = ''.join(bounds)
     return bounds
-        
-"""
-Generate OCR
-"""
-def generate_ocr(Method,img):
-    
+
+def generate_ocr(Method, file):
     text_output = ''
-    if (img).any():
-        add_csv = []
-        image_id = 1
-        print("Method___________________",Method)
-        if Method == 'EasyOCR':
-            text_output = ocr_with_easy(img)
-        if Method == 'KerasOCR':
-            text_output = ocr_with_keras(img)
-        if Method == 'PaddleOCR':
-            text_output = ocr_with_paddle(img)
-       
-        try:
-            flag(Method,text_output,img)
-        except Exception as e:
-            print(e)
-        return text_output
+    if isinstance(file, bytes):  # Handle file uploaded as bytes
+        file = io.BytesIO(file)
+
+    if file.name.endswith('.pdf'):
+        # Convert PDF to images
+        images = convert_from_path(file)
+        for img in images:
+            img_np = np.array(img)
+            text_output += generate_text_from_image(Method, img_np) + "\n"
     else:
-        raise gr.Error("Please upload an image!!!!")
-    
-    # except Exception as e:
-    #     print("Error in ocr generation ==>",e)
-    #     text_output = "Something went wrong"
-    # return text_output
+        # Handle image file
+        img_np = np.array(Image.open(file))
+        text_output = generate_text_from_image(Method, img_np)
     
+    return text_output
 
-"""
-Create user interface for OCR demo
-"""
+def generate_text_from_image(Method, img):
+    text_output = ''
+    if Method == 'EasyOCR':
+        text_output = ocr_with_easy(img)
+    elif Method == 'KerasOCR':
+        text_output = ocr_with_keras(img)
+    elif Method == 'PaddleOCR':
+        text_output = ocr_with_paddle(img)
+    return text_output
+
+
+import gradio as gr
 
-# image = gr.Image(shape=(300, 300))
-image = gr.Image()
-method = gr.Radio(["PaddleOCR","EasyOCR", "KerasOCR"],value="PaddleOCR")
+image_or_pdf = gr.File(label="Upload an image or PDF")
+method = gr.Radio(["PaddleOCR", "EasyOCR", "KerasOCR"], value="PaddleOCR")
 output = gr.Textbox(label="Output")
 
 demo = gr.Interface(
     generate_ocr,
-    [method,image],
+    [method, image_or_pdf],
     output,
     title="Optical Character Recognition",
     css=".gradio-container {background-color: lightgray} #radio_div {background-color: #FFD8B4; font-size: 40px;}",
-    article = """<p style='text-align: center;'>Feel free to give us your thoughts on this demo and please contact us at 
-                    <a href="mailto:[email protected]" target="_blank">[email protected]</a> 
-                    <p style='text-align: center;'>Developed by: <a href="https://www.pragnakalp.com" target="_blank">Pragnakalp Techlabs</a></p>"""
-    
-
+    article="""<p style='text-align: center;'>Feel free to give us your thoughts on this demo and please contact us at 
+                <a href="mailto:[email protected]" target="_blank">[email protected]</a> 
+                <p style='text-align: center;'>Developed by: <a href="https://www.pragnakalp.com" target="_blank">Pragnakalp Techlabs</a></p>"""
 )
-# demo.launch(enable_queue = False)
+
 demo.launch(show_error=True)