Spaces:
Running
Running
Upload 2 files
Browse files- app.py +21 -0
- requirements.txt +3 -0
app.py
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import gradio as gr
|
| 2 |
+
from newspaper import Article
|
| 3 |
+
|
| 4 |
+
def extraer_texto(url):
|
| 5 |
+
try:
|
| 6 |
+
articulo = Article(url, language='es')
|
| 7 |
+
articulo.download()
|
| 8 |
+
articulo.parse()
|
| 9 |
+
return articulo.text
|
| 10 |
+
except Exception as e:
|
| 11 |
+
return f"[Error al extraer texto]: {str(e)}"
|
| 12 |
+
|
| 13 |
+
demo = gr.Interface(
|
| 14 |
+
fn=extraer_texto,
|
| 15 |
+
inputs=gr.Textbox(label="Pega la URL de la noticia"),
|
| 16 |
+
outputs="text",
|
| 17 |
+
title="Extractor de Texto de Noticias",
|
| 18 |
+
description="Extrae el texto plano de una noticia desde su enlace. Solo pega el enlace."
|
| 19 |
+
)
|
| 20 |
+
|
| 21 |
+
demo.launch()
|
requirements.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
gradio
|
| 2 |
+
newspaper3k
|
| 3 |
+
lxml_html_clean
|