app.py

# -*- encoding: utf-8 -*-
# @Author: SWHL
# @Contact: [email protected]
import gradio as gr
from gradio_pdf import PDF

from rapidocr_pdf import RapidOCRPDF

pdf_extracter = RapidOCRPDF()


def get_pdf_result(pdf_path: str, page_num: int = 0):
    return pdf_extracter(pdf_path, page_num_list=[page_num])


with gr.Blocks(title="RapidOCR 📄 PDF", theme=gr.themes.Soft()) as demo:
    gr.HTML(
        """
        <h1 style='text-align: center;'><a href="https://github.com/RapidAI/RapidOCRPDF">RapidOCR 📄 PDF</a></h1>

        <div style="display: flex; justify-content: center; gap: 10px;">
            <a href=""><img src="https://img.shields.io/badge/Python->=3.6-aff.svg"></a>
            <a href=""><img src="https://img.shields.io/badge/OS-Linux%2C%20Win%2C%20Mac-pink.svg"></a>
            <a href="https://pypi.org/project/rapidocr-pdf/"><img alt="PyPI" src="https://img.shields.io/pypi/v/rapidocr-pdf"></a>
            <a href="https://pepy.tech/project/rapidocr-pdf"><img src="https://static.pepy.tech/personalized-badge/rapidocr-pdf?period=total&units=abbreviation&left_color=grey&right_color=blue&left_text=Downloads"></a>
            <a href="https://semver.org/"><img alt="SemVer2.0" src="https://img.shields.io/badge/SemVer-2.0-brightgreen"></a>
            <a href="https://github.com/psf/black"><img src="https://img.shields.io/badge/code%20style-black-000000.svg"></a>
            <a href="https://choosealicense.com/licenses/apache-2.0/"><img alt="GitHub" src="https://img.shields.io/github/license/RapidAI/RapidOCRPDF"></a>
        </div>
    """
    )

    pdf_path = PDF(label="Upload a PDF", interactive=True)
    page_num = gr.Number(value=0, label="Select Extract Page", minimum=0, maximum=5)
    btn = gr.Button("Run")
    results = gr.Dataframe(
        label="PDF Extract Results",
        headers=["Index", "Txt", "Score"],
        datatype=["number", "str", "number"],
        show_copy_button=True,
        show_fullscreen_button=True,
    )
    btn.click(get_pdf_result, inputs=[pdf_path, page_num], outputs=[results])

    examples = gr.Examples(
        examples=[
            ["./files/direct_and_image.pdf", 0],
            ["./files/direct_extract.pdf", 0],
        ],
        examples_per_page=5,
        inputs=[pdf_path, page_num],
        fn=get_pdf_result,
        outputs=[results],
        cache_examples=False,
    )


if __name__ == "__main__":
    demo.launch()