File size: 4,900 Bytes
0094fbb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
import base64
import io
import os
import threading
import time
import zipfile
from dash import Dash, dcc, html, Input, Output, State, ctx
import dash_bootstrap_components as dbc
from pdf2docx import Converter
import tempfile

app = Dash(__name__, external_stylesheets=[dbc.themes.BOOTSTRAP])

# Global variables
uploaded_files = {}
converted_files = {}
conversion_progress = {}

def convert_pdf_to_docx(pdf_path, docx_path):
    cv = Converter(pdf_path)
    cv.convert(docx_path)
    cv.close()

def process_contents(contents, filename):
    content_type, content_string = contents.split(',')
    decoded = base64.b64decode(content_string)
    return io.BytesIO(decoded)

def convert_files(filenames):
    global conversion_progress, converted_files
    total_files = len(filenames)
    for i, filename in enumerate(filenames):
        pdf_file = uploaded_files[filename]
        with tempfile.NamedTemporaryFile(delete=False, suffix='.pdf') as temp_pdf:
            temp_pdf.write(pdf_file.getvalue())
            temp_pdf_path = temp_pdf.name

        docx_filename = os.path.splitext(filename)[0] + '.docx'
        with tempfile.NamedTemporaryFile(delete=False, suffix='.docx') as temp_docx:
            temp_docx_path = temp_docx.name

        convert_pdf_to_docx(temp_pdf_path, temp_docx_path)

        with open(temp_docx_path, 'rb') as docx_file:
            converted_files[docx_filename] = io.BytesIO(docx_file.read())

        os.unlink(temp_pdf_path)
        os.unlink(temp_docx_path)

        conversion_progress[filename] = (i + 1) / total_files * 100

    conversion_progress['overall'] = 100

app.layout = dbc.Container([
    dbc.Card(
        dbc.CardBody([
            html.H1("PDF to DOCX Converter", className="text-center mb-4"),
            dcc.Upload(
                id='upload-data',
                children=html.Div([
                    'Drag and Drop or ',
                    html.A('Select PDF Files')
                ]),
                style={
                    'width': '100%',
                    'height': '60px',
                    'lineHeight': '60px',
                    'borderWidth': '1px',
                    'borderStyle': 'dashed',
                    'borderRadius': '5px',
                    'textAlign': 'center',
                    'margin': '10px'
                },
                multiple=True
            ),
            html.Div(id='upload-output'),
            dbc.Button("Convert and Download", id="convert-button", color="primary", className="mt-3 mb-3", disabled=True),
            html.Div(id='conversion-output'),
            dcc.Download(id="download-zip")
        ]),
        className="mt-3"
    )
], fluid=True)

@app.callback(
    Output('upload-output', 'children'),
    Output('convert-button', 'disabled'),
    Input('upload-data', 'contents'),
    State('upload-data', 'filename'),
    prevent_initial_call=True
)
def update_output(list_of_contents, list_of_names):
    if list_of_contents is not None:
        global uploaded_files
        uploaded_files.clear()
        children = []
        for content, name in zip(list_of_contents, list_of_names):
            if name.lower().endswith('.pdf'):
                uploaded_files[name] = process_contents(content, name)
                children.append(html.Div(f"Uploaded: {name}"))
            else:
                children.append(html.Div(f"Skipped: {name} (Not a PDF file)", style={'color': 'red'}))
        return children, False
    return [], True

@app.callback(
    Output('conversion-output', 'children'),
    Output('download-zip', 'data'),
    Input('convert-button', 'n_clicks'),
    prevent_initial_call=True
)
def convert_and_download(n_clicks):
    if n_clicks is None:
        return [], None

    global conversion_progress, converted_files
    conversion_progress.clear()
    converted_files.clear()
    conversion_progress['overall'] = 0

    threading.Thread(target=convert_files, args=(list(uploaded_files.keys()),)).start()

    while conversion_progress.get('overall', 0) < 100:
        time.sleep(0.1)
        progress_bars = [
            dbc.Progress(value=conversion_progress.get(filename, 0), label=f"{filename}: {conversion_progress.get(filename, 0):.0f}%", className="mb-3")
            for filename in uploaded_files.keys()
        ]
        yield progress_bars, None

    with io.BytesIO() as zip_buffer:
        with zipfile.ZipFile(zip_buffer, 'w', zipfile.ZIP_DEFLATED) as zip_file:
            for filename, file_content in converted_files.items():
                zip_file.writestr(filename, file_content.getvalue())
        
        return [html.Div("Conversion complete! Downloading ZIP file...")], dcc.send_bytes(zip_buffer.getvalue(), "converted_files.zip")

if __name__ == '__main__':
    print("Starting the Dash application...")
    app.run(debug=True, host='0.0.0.0', port=7860)
    print("Dash application has finished running.")