Spaces:
Paused
Paused
Upload app.py with huggingface_hub
Browse files
app.py
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# -*- coding: utf-8 -*-
|
| 2 |
+
import os
|
| 3 |
+
import fitz # PyMuPDF
|
| 4 |
+
import gradio as gr
|
| 5 |
+
from gradio_theme_fenix import apply_fenix_theme, FENIX_CSS, fenix_header, fenix_footer
|
| 6 |
+
|
| 7 |
+
def extract_text(pdf_path):
|
| 8 |
+
"""Extract text from a PDF file located at pdf_path."""
|
| 9 |
+
doc = fitz.open(pdf_path)
|
| 10 |
+
text = ""
|
| 11 |
+
for page in doc:
|
| 12 |
+
text += page.get_text()
|
| 13 |
+
doc.close()
|
| 14 |
+
return text
|
| 15 |
+
|
| 16 |
+
with gr.Blocks(css=FENIX_CSS, theme=apply_fenix_theme(), title="PDF Reader") as demo:
|
| 17 |
+
fenix_header("PDF Reader", "Extract text from PDF files")
|
| 18 |
+
with gr.Row():
|
| 19 |
+
pdf_input = gr.File(label="Upload PDF", type="filepath")
|
| 20 |
+
extract_btn = gr.Button("Extract")
|
| 21 |
+
output_box = gr.Textbox(label="Extracted Text", lines=20, interactive=False)
|
| 22 |
+
extract_btn.click(fn=extract_text, inputs=pdf_input, outputs=output_box)
|
| 23 |
+
fenix_footer()
|
| 24 |
+
|
| 25 |
+
demo.launch()
|