app.py

import gradio as gr
import os
import cv2
import numpy as np
from paddleocr import PPStructure,save_structure_res
from paddleocr.ppstructure.recovery.recovery_to_doc import sorted_layout_boxes, convert_info_docx

# Chinese image
table_engine = PPStructure(recovery=True)

# English image
# table_engine = PPStructure(recovery=True, lang='en')


def find_layout(image):
    save_folder = './output'
    # img = cv2.imread(image)
    img = np.array(image)
    result = table_engine(img)
    save_structure_res(result, save_folder, os.path.basename("result").split('.')[0])

    final_text = []
    for line in result:
        line.pop('img')
        print(line)
        final_text.append(line)

    h, w, _ = img.shape
    res = sorted_layout_boxes(result, w)
    convert_info_docx(img, res, save_folder, os.path.basename("result").split('.')[0])

    return final_text

iface = gr.Interface(fn=find_layout, inputs=[gr.Image(type="pil")], outputs="text")
iface.launch()