Update app.py

app.py

@@ -1,5 +1,5 @@
 import gradio as gr
-from newspaper import Article
+import trafilatura
 from transformers import pipeline
 import pytesseract
 from PIL import Image
@@ -20,14 +20,13 @@ def extract_text_from_image_url(img_url):
         return f"❌ OCR Error: {e}"
 
 # Extract blog
-def extract_text_from_url(url):
-    try:
-        article = Article(url)
-        article.download()
-        article.parse()
-        return article.text
-    except Exception as e:
-        return f"❌ Blog Error: {e}"
+def extract_text_from_url(url): 
+    downloaded = trafilatura.fetch_url(url)
+    if downloaded:
+        return trafilatura.extract(downloaded)
+    else:
+        return "❌ Blog Error: Could not fetch content from the URL."
+
 
 # Review line-by-line
 def review_lines(text):