Spaces:
Starting
Starting
Update app.py
Browse files
app.py
CHANGED
@@ -18,50 +18,13 @@ def extract_text_from_url(url):
|
|
18 |
return f"An error occurred: {e}"
|
19 |
|
20 |
# Gradio interface
|
21 |
-
|
22 |
-
|
23 |
-
gr.
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
with gr.Row():
|
29 |
-
dataset_url = gr.Textbox(
|
30 |
-
label="Dataset URL",
|
31 |
-
placeholder="Enter the dataset URL",
|
32 |
-
lines=1
|
33 |
-
)
|
34 |
-
|
35 |
-
extracted_texts = gr.Textbox(
|
36 |
-
label="Extracted Texts",
|
37 |
-
lines=20,
|
38 |
-
placeholder="Extracted texts will appear here",
|
39 |
-
interactive=False,
|
40 |
-
elem_id="extracted-texts" # Add unique ID for JavaScript targeting
|
41 |
-
)
|
42 |
-
|
43 |
-
with gr.Row():
|
44 |
-
extract_button = gr.Button("Extract Texts")
|
45 |
-
# Add custom HTML for copy functionality
|
46 |
-
copy_button_html = gr.HTML("""
|
47 |
-
<button id="copy-btn" style="padding: 10px; background-color: #007bff; color: white; border: none; cursor: pointer;">
|
48 |
-
Copy All
|
49 |
-
</button>
|
50 |
-
<script>
|
51 |
-
document.getElementById("copy-btn").addEventListener("click", function() {
|
52 |
-
const text = document.getElementById("extracted-texts").value;
|
53 |
-
navigator.clipboard.writeText(text).then(function() {
|
54 |
-
alert("Texts copied to clipboard!");
|
55 |
-
}).catch(function(err) {
|
56 |
-
alert("Failed to copy text: " + err);
|
57 |
-
});
|
58 |
-
});
|
59 |
-
</script>
|
60 |
-
""")
|
61 |
|
62 |
-
# Define the interaction for extracting text
|
63 |
-
extract_button.click(extract_text_from_url, inputs=dataset_url, outputs=extracted_texts)
|
64 |
-
|
65 |
-
# Launch the app
|
66 |
if __name__ == "__main__":
|
67 |
-
|
|
|
18 |
return f"An error occurred: {e}"
|
19 |
|
20 |
# Gradio interface
|
21 |
+
interface = gr.Interface(
|
22 |
+
fn=extract_text_from_url,
|
23 |
+
inputs=gr.Textbox(label="Dataset URL", placeholder="Enter the dataset URL"),
|
24 |
+
outputs=gr.Textbox(label="Extracted Texts", lines=20, placeholder="Extracted texts will appear here"),
|
25 |
+
title="Extract Text from Hugging Face Dataset",
|
26 |
+
description="Enter the URL of a Hugging Face dataset to extract and display the 'text' fields. https://datasets-server.huggingface.co/rows?dataset=pszemraj%2Fmidjourney-messages-cleaned&config=deduped&split=train&length=100&offset=0"
|
27 |
+
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
|
|
|
|
|
|
|
|
|
29 |
if __name__ == "__main__":
|
30 |
+
interface.launch()
|