Create app.py

app.py

@@ -0,0 +1,119 @@
+import gradio as gr
+import fitz  # PyMuPDF
+import os
+import tempfile
+import shutil
+import zipfile
+
+def extract_text(pdf_file):
+    doc = fitz.open(stream=pdf_file.read(), filetype="pdf")
+    text = ""
+    for page in doc:
+        text += page.get_text()
+    return text
+
+def extract_images(pdf_file):
+    doc = fitz.open(stream=pdf_file.read(), filetype="pdf")
+    output_dir = tempfile.mkdtemp()
+    img_count = 0
+    for page_num in range(len(doc)):
+        page = doc.load_page(page_num)
+        image_list = page.get_images(full=True)
+        for img_index, img in enumerate(image_list):
+            xref = img[0]
+            try:
+                base_image = doc.extract_image(xref)
+                image_bytes = base_image["image"]
+                image_ext = base_image["ext"]
+                image_filename = os.path.join(output_dir, f"image_{page_num+1}_{img_index+1}_{xref}.{image_ext}")
+                with open(image_filename, "wb") as image_file:
+                    image_file.write(image_bytes)
+                img_count += 1
+            except Exception as e:
+                continue
+
+    if img_count == 0:
+        return "No images found in the PDF.", None
+
+    # Zip all extracted images
+    zip_path = os.path.join(output_dir, "images.zip")
+    with zipfile.ZipFile(zip_path, "w") as zipf:
+        for fname in os.listdir(output_dir):
+            if fname.endswith((".png", ".jpg", ".jpeg")):
+                zipf.write(os.path.join(output_dir, fname), fname)
+
+    return f"{img_count} images extracted.", zip_path
+
+def merge_pdfs(pdf_files):
+    merged_pdf = fitz.open()
+    for pdf_file in pdf_files:
+        with fitz.open(stream=pdf_file.read(), filetype="pdf") as doc:
+            merged_pdf.insert_pdf(doc)
+    temp_path = tempfile.mktemp(suffix=".pdf")
+    merged_pdf.save(temp_path)
+    return temp_path
+
+def split_pdf(pdf_file):
+    doc = fitz.open(stream=pdf_file.read(), filetype="pdf")
+    output_dir = tempfile.mkdtemp()
+    for page_num in range(len(doc)):
+        new_doc = fitz.open()
+        new_doc.insert_pdf(doc, from_page=page_num, to_page=page_num)
+        page_path = os.path.join(output_dir, f"page_{page_num+1}.pdf")
+        new_doc.save(page_path)
+
+    zip_path = os.path.join(output_dir, "split_pages.zip")
+    with zipfile.ZipFile(zip_path, "w") as zipf:
+        for fname in os.listdir(output_dir):
+            if fname.endswith(".pdf"):
+                zipf.write(os.path.join(output_dir, fname), fname)
+    return zip_path
+
+def pdf_tool(task, pdf_input1=None, pdf_input2=None):
+    if task == "Extract Text":
+        if not pdf_input1:
+            return "Please upload a PDF file.", None
+        return extract_text(pdf_input1), None
+
+    elif task == "Extract Images":
+        if not pdf_input1:
+            return "Please upload a PDF file.", None
+        msg, zip_path = extract_images(pdf_input1)
+        return msg, zip_path
+
+    elif task == "Merge PDFs":
+        if not pdf_input1 or not pdf_input2:
+            return "Please upload two PDF files to merge.", None
+        merged_path = merge_pdfs([pdf_input1, pdf_input2])
+        return "PDFs merged successfully.", merged_path
+
+    elif task == "Split PDF":
+        if not pdf_input1:
+            return "Please upload a PDF file.", None
+        zip_path = split_pdf(pdf_input1)
+        return "PDF split into separate pages.", zip_path
+
+    else:
+        return "Invalid task selected.", None
+
+with gr.Blocks() as demo:
+    gr.Markdown("## 🛠️ PDF Utility Tool")
+    task = gr.Radio(choices=["Extract Text", "Extract Images", "Merge PDFs", "Split PDF"], label="Select a Task")
+
+    with gr.Row():
+        pdf_input1 = gr.File(label="PDF File 1", file_types=[".pdf"])
+        pdf_input2 = gr.File(label="PDF File 2 (for Merge only)", file_types=[".pdf"], visible=True)
+
+    task.change(lambda t: gr.update(visible=(t == "Merge PDFs")), inputs=task, outputs=pdf_input2)
+
+    run_button = gr.Button("Run")
+    output_text = gr.Textbox(label="Output Text")
+    output_file = gr.File(label="Download Result", file_types=[".pdf", ".zip"], visible=False)
+
+    def process(task, pdf_input1, pdf_input2):
+        result_text, result_file = pdf_tool(task, pdf_input1, pdf_input2)
+        return result_text, gr.update(value=result_file, visible=bool(result_file))
+
+    run_button.click(process, inputs=[task, pdf_input1, pdf_input2], outputs=[output_text, output_file])
+
+demo.launch()