Add files

app.py

@@ -0,0 +1,157 @@
+import os
+import gradio as gr
+from PyPDF2 import PdfWriter, PdfReader
+import zipfile
+import tempfile
+import fitz  # PyMuPDF
+
+def merge_pdfs(pdf_files):
+    if not pdf_files:
+        return "❌ No PDF files uploaded.", None
+
+    output_dir = tempfile.mkdtemp()
+    output_file = os.path.join(output_dir, "merged.pdf")
+
+    doc_out = fitz.open()
+    a4_rect = fitz.paper_rect("a4")
+
+    for file in pdf_files:
+        src = fitz.open(file.name)
+        for page in src:
+            page_out = doc_out.new_page(width=a4_rect.width, height=a4_rect.height)
+            page_out.show_pdf_page(a4_rect, src, page.number, keep_proportion=True)
+        src.close()
+
+    doc_out.save(output_file)
+    doc_out.close()
+    return "✅ PDFs merged successfully.", output_file
+
+
+def compress_pdf(file, dpi_threshold, dpi_target, quality):
+    input_path = file.name
+
+    # Create a unique temporary file for the compressed output
+    temp_dir = tempfile.mkdtemp()
+    output_path = os.path.join(temp_dir, "compressed_output.pdf")
+
+    doc = fitz.open(input_path)
+
+    # Recompress images above dpi_threshold to target DPI with JPEG at quality
+    doc.rewrite_images(
+        dpi_threshold=dpi_threshold,
+        dpi_target=dpi_target,
+        quality=quality,
+        lossy=True,
+        lossless=True,
+        bitonal=True,
+        color=True,
+        gray=True,
+        set_to_gray=False,
+    )
+
+    # Subset fonts and apply full garbage collection + stream compression
+    doc.subset_fonts()
+    doc.save(output_path,
+             garbage=3,
+             deflate=True,
+             use_objstms=True)
+
+    status = f"✅ PDF compressed successfully!"
+    return status, output_path
+
+
+def split_pdf(file_path, start_page, end_page):
+    file_name = os.path.basename(file_path)
+    base_name = file_name[:-4]  # Remove .pdf extension
+    output_dir = tempfile.mkdtemp()
+    zip_path = os.path.join(output_dir, f"{base_name}_split_pages.zip")
+
+    input_pdf = PdfReader(open(file_path, "rb"))
+    total_pages = len(input_pdf.pages)
+
+    # Clamp values within range
+    start_page = max(0, min(start_page, total_pages - 1))
+    end_page = max(start_page, min(end_page, total_pages - 1))
+
+    zipf = zipfile.ZipFile(zip_path, 'w', zipfile.ZIP_DEFLATED)
+
+    for i in range(start_page, end_page + 1):
+        writer = PdfWriter()
+        writer.add_page(input_pdf.pages[i])
+        split_pdf_path = os.path.join(output_dir, f"{base_name}-page{i+1}.pdf")
+        with open(split_pdf_path, "wb") as f_out:
+            writer.write(f_out)
+        zipf.write(split_pdf_path, arcname=os.path.basename(split_pdf_path))
+
+    zipf.close()
+    return zip_path, start_page + 1, end_page + 1
+
+def process_pdf(file, start_page, end_page):
+    if file is None:
+        return "❌ No file uploaded.", None
+    zip_file_path, actual_start, actual_end = split_pdf(file.name, start_page, end_page)
+    status = f"✅ File '{file.name}' split from page {actual_start} to {actual_end}."
+    return status, zip_file_path
+
+with gr.Blocks(title="PDF Utility") as demo:
+    gr.Markdown("# 📄 PDF Utility App")
+
+    with gr.Tabs():
+        with gr.TabItem("Split PDF"):
+            gr.Markdown("Upload a PDF, select page range, and click **Split PDF** to download a ZIP of split pages.")
+            with gr.Row():
+                file_input = gr.File(label="Upload PDF", file_types=[".pdf"])
+
+            with gr.Row():
+                start_page = gr.Number(label="Start Page (0-based)", value=0, precision=0)
+                end_page = gr.Number(label="End Page (0-based)", value=0, precision=0)
+
+            split_button = gr.Button("🚀 Split PDF")
+
+            status_text = gr.Textbox(label="Status", lines=2)
+            download_link = gr.File(label="Download ZIP")
+
+            split_button.click(
+                fn=process_pdf,
+                inputs=[file_input, start_page, end_page],
+                outputs=[status_text, download_link]
+            )
+            
+        with gr.TabItem("Compress PDF"):
+            gr.Markdown("Upload a PDF and click **Compress PDF** to download the compressed version.")
+            with gr.Row():
+                file_input_compress = gr.File(label="Upload PDF", file_types=[".pdf"])
+            
+            with gr.Row():
+                dpi_threshold = gr.Number(label="DPI Threshold", value=100, precision=0)
+                dpi_target = gr.Number(label="Target DPI", value=72, precision=0)
+                quality = gr.Number(label="JPEG Quality (1-100)", value=60, precision=0)
+                
+            compress_button = gr.Button("🚀 Compress PDF")
+            
+            status_text_compress = gr.Textbox(label="Status", lines=2)
+            download_link_compress = gr.File(label="Download compressed PDF")
+
+            compress_button.click(
+                fn=compress_pdf,
+                inputs=[file_input_compress, dpi_threshold, dpi_target, quality],
+                outputs=[status_text_compress, download_link_compress]
+            )
+            
+        with gr.TabItem("Merge PDFs"):
+            gr.Markdown("Upload multiple PDFs and click **Merge PDFs** to download the merged version.")
+            pdf_uploads = gr.File(label="Upload PDFs", file_types=[".pdf"], file_count="multiple")
+
+            merge_button = gr.Button("📎 Merge PDF Files")
+
+            merge_status = gr.Textbox(label="Status", lines=2)
+            merged_file = gr.File(label="Download Merged PDF")
+
+            merge_button.click(
+                fn=merge_pdfs,
+                inputs=[pdf_uploads],
+                outputs=[merge_status, merged_file]
+            )
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio
+PyMuPDF
+PyPDF2