app.py

import gradio as gr
from pdfitdown.pdfconversion import Converter
import fitz
from typing import List
from PIL import Image
from loadimg import load_img
import io
from markitdown import MarkItDown
from docx import Document
import pdfplumber

converter = Converter()
md = MarkItDown()


def convert_file_to_pdf(filename: str) -> str:
    """
    Converts a markdown file to PDF format.

    Args:
        filename: str
            The path to the markdown file to be converted.

    Returns:
        str: The file path of the generated PDF file.
    """
    output_path = filename.name.rsplit(".", 1)[0] + ".pdf"
    converter.convert(filename.name, output_path)
    return output_path


def convert_file_to_img(image_file: str = None, txt: str = "") -> List[Image.Image]:
    """
    Convert an image file to PDF format.

    Args:
        image_file: A file object containing the image to be converted.
                    The file must be in a format supported by the converter
                    (e.g., PNG, JPG, JPEG).

    Returns:
        str: The file path of the generated PDF file. The output filename will be
             the same as the input filename but with a .pdf extension.
    """
    img_list = []
    if txt != "":
        img_list.append(load_img(txt, output_type="pil"))
    if image_file is not None:
        output_path = image_file.name.rsplit(".", 1)[0] + ".pdf"
        converter.convert(image_file.name, output_path)
        doc = fitz.open(output_path)
        for page in doc:
            page_bytes = page.get_pixmap().tobytes("png")
            img_list.append(load_img(Image.open(io.BytesIO(page_bytes))).convert("RGB"))
    doc.close()
    return img_list


def convert_file_to_markdown(filename: str) -> str:
    """
    Converts a file to markdown format using markitdown.
    Args:
        filename: str
            The path to the file to be converted.
    Returns:
        str: The markdown representation of the file.
    """
    return md.convert(filename.name).text_content


def convert_pdf_to_word(filename: str) -> str:
    """
    Converts a PDF file to Word format.

    Args:
        filename: str
            The path to the PDF file to be converted.

    Returns:
        str: The file path of the generated Word file.
    """
    output_path = filename.name.rsplit(".", 1)[0] + ".docx"
    doc = Document()

    with pdfplumber.open(filename.name) as pdf:
        for page in pdf.pages:
            text = page.extract_text()
            if text:
                doc.add_paragraph(text)

    doc.save(output_path)
    return output_path


# Create individual interfaces
file_to_pdf = gr.Interface(
    fn=convert_file_to_pdf,
    inputs=gr.File(label="Upload README/Markdown file"),
    outputs=gr.File(label="Converted PDF"),
    title="File to PDF Converter",
    description="Convert your files to PDF format",
)

file_to_image = gr.Interface(
    fn=convert_file_to_img,
    inputs=[gr.File(label="Upload Image"), gr.Textbox(label="base64, url")],
    outputs=gr.Gallery(label="Converted Images"),
    title="File to Images Converter",
    description="Convert your images to an image format",
)

file_to_markdown = gr.Interface(
    fn=convert_file_to_markdown,
    inputs=gr.File(label="Upload File"),
    outputs=gr.Textbox(label="Converted Markdown"),
    title="File to Markdown Converter",
    description="Convert your files to markdown format",
)

pdf_to_word = gr.Interface(
    fn=convert_pdf_to_word,
    inputs=gr.File(label="Upload PDF file"),
    outputs=gr.File(label="Converted Word Document"),
    title="PDF to Word Converter",
    description="Convert your PDF files to Word format",
)

# Create tabbed interface
demo = gr.TabbedInterface(
    [file_to_pdf, file_to_image, file_to_markdown, pdf_to_word],
    ["File to PDF", "File to Image", "File to Markdown", "PDF to Word"],
)

if __name__ == "__main__":
    demo.launch(server_name="0.0.0.0", server_port=7860, debug=True, mcp_server=True)