Create app.py

app.py

@@ -0,0 +1,59 @@
+import fitz  # PyMuPDF
+from PIL import Image
+import pytesseract
+from fpdf import FPDF
+import gradio as gr
+
+# Step 1: Convert PDF Pages to Images
+def pdf_to_images(pdf_path):
+    pdf_document = fitz.open(pdf_path)
+    images = []
+    for page_num in range(len(pdf_document)):
+        page = pdf_document[page_num]
+        pix = page.get_pixmap()  # Render the page as an image
+        image_path = f"page_{page_num + 1}.png"
+        pix.save(image_path)
+        images.append(image_path)
+    return images
+
+# Step 2: Extract Text Using Tesseract OCR
+def extract_text(images):
+    text_pages = []
+    for image_path in images:
+        text = pytesseract.image_to_string(Image.open(image_path))  # Perform OCR
+        text_pages.append(text)
+    return text_pages
+
+# Step 3: Replace Curved Text with Editable Text in a New PDF
+def create_editable_pdf(images, text_pages, output_pdf_path):
+    pdf = FPDF()
+    pdf.set_auto_page_break(auto=True, margin=15)
+    for text in text_pages:
+        pdf.add_page()
+        pdf.set_font("Arial", size=12)
+        pdf.multi_cell(0, 10, text)
+    pdf.output(output_pdf_path)
+
+# Main Function
+def process_pdf(file):
+    input_pdf_path = file.name
+    output_pdf_path = "Editable_Output.pdf"
+    
+    # Convert PDF to images and perform OCR
+    images = pdf_to_images(input_pdf_path)
+    text_pages = extract_text(images)
+    
+    # Create a new editable PDF
+    create_editable_pdf(images, text_pages, output_pdf_path)
+    return output_pdf_path
+
+# Gradio Interface
+iface = gr.Interface(
+    fn=process_pdf,
+    inputs=gr.File(label="Upload PDF"),
+    outputs=gr.File(label="Download Editable PDF"),
+    title="OCR PDF to Editable Text",
+    description="Upload a PDF to extract and replace text while preserving shapes and layout.",
+)
+
+iface.launch()