Commit ·
928c304
1
Parent(s): 3511fa6
Add application file
Browse files- app.py +36 -0
- requirements.txt +4 -0
app.py
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import gradio as gr
|
| 2 |
+
import json
|
| 3 |
+
from docx import Document # from python-docx
|
| 4 |
+
|
| 5 |
+
def docx_to_json(file_obj):
|
| 6 |
+
if file_obj is None:
|
| 7 |
+
return "No file uploaded", "{}"
|
| 8 |
+
|
| 9 |
+
# Load docx
|
| 10 |
+
document = Document(file_obj.name)
|
| 11 |
+
|
| 12 |
+
# Very simple example: collect paragraphs as a list
|
| 13 |
+
paragraphs = [p.text for p in document.paragraphs if p.text.strip() != ""]
|
| 14 |
+
|
| 15 |
+
# Build a JSON structure (customize to your needs)
|
| 16 |
+
data = {
|
| 17 |
+
"paragraphs": paragraphs,
|
| 18 |
+
"paragraph_count": len(paragraphs),
|
| 19 |
+
}
|
| 20 |
+
|
| 21 |
+
return json.dumps(data, indent=2)
|
| 22 |
+
|
| 23 |
+
with gr.Blocks() as demo:
|
| 24 |
+
gr.Markdown("# DOCX → JSON & DB Sync (Prototype)")
|
| 25 |
+
|
| 26 |
+
with gr.Row():
|
| 27 |
+
file_input = gr.File(label="Upload Word (.docx)")
|
| 28 |
+
|
| 29 |
+
json_output = gr.Code(label="Extracted JSON", language="json")
|
| 30 |
+
|
| 31 |
+
btn = gr.Button("Convert to JSON")
|
| 32 |
+
|
| 33 |
+
btn.click(fn=docx_to_json, inputs=file_input, outputs=json_output)
|
| 34 |
+
|
| 35 |
+
if __name__ == "__main__":
|
| 36 |
+
demo.launch()
|
requirements.txt
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
gradio
|
| 2 |
+
python-docx
|
| 3 |
+
deepdiff
|
| 4 |
+
mysql-connector-python # or psycopg2 / sqlalchemy depending on your DB
|