app.py

import spaces
import gradio as gr
import fitz  # PyMuPDF

@spaces.GPU
def convert(pdf_file):
    doc = fitz.open(pdf_file)
    markdown_output = ""

    for page in doc:
        blocks = page.get_text("dict")["blocks"]
        elements = []

        for b in blocks:
            if b["type"] == 0:  # texto
                for line in b["lines"]:
                    for span in line["spans"]:
                        elements.append((span["bbox"][1], span["text"]))  # y, texto
            elif b["type"] == 1:  # imagen
                y_pos = b["bbox"][1]
                elements.append((y_pos, "[imagen]()"))

        # Ordenar por posición vertical
        elements.sort(key=lambda x: x[0])

        for _, content in elements:
            markdown_output += content.strip() + "\n\n"

    return markdown_output.strip(), {}

gr.Interface(
    convert,
    inputs=[
        gr.File(label="Upload PDF", type="filepath"),
    ],
    outputs=[
        gr.Text(label="Markdown"),
        gr.JSON(label="Metadata"),
    ],
).launch()