Spaces:
Running
Running
File size: 2,908 Bytes
0b4c299 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
# -*- encoding: utf-8 -*-
# @Author: SWHL
# @Contact: [email protected]
from typing import List
import gradio as gr
from gradio_pdf import PDF
from rapidocr_pdf import RapidOCRPDF
custom_css = """
body {font-family: body {font-family: 'Helvetica Neue', Helvetica;}
.gr-button {background-color: #4CAF50; color: white; border: none; padding: 10px 20px; border-radius: 5px;}
.gr-button:hover {background-color: #45a049;}
.gr-textbox {margin-bottom: 15px;}
.example-button {background-color: #1E90FF; color: white; border: none; padding: 8px 15px; border-radius: 5px; margin: 5px;}
.example-button:hover {background-color: #FF4500;}
.tall-radio .gr-radio-item {padding: 15px 0; min-height: 50px; display: flex; align-items: center;}
.tall-radio label {font-size: 16px;}
.output-image, .input-image, .image-preview {height: 300px !important}
"""
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", css="custom_css", theme=gr.themes.Soft()
) as demo:
gr.Markdown(
"<h1 style='text-align: center;'><a href='https://github.com/RapidAI/RapidOCRPDF' style='text-decoration: none;'>RapidOCR 📄 PDF</a></h1>"
)
gr.HTML(
"""
<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])
if __name__ == "__main__":
demo.launch()
|