Update app.py

app.py

@@ -1,54 +1,59 @@
 import gradio as gr
-from transformers import pipeline
-from newspaper import Article
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+import requests
+from bs4 import BeautifulSoup
+# Load model and tokenizer
+model_name = "mrm8488/bert-tiny-finetuned-fake-news-detection"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
 
-# Load the model
-model = pipeline("text-classification", model="mrm8488/bert-tiny-finetuned-fake-news-detection")
-
-def analyze(input_text, input_type):
-    # Auto-detect if input is URL or text
-    if input_type == "Auto Detect":
-        if input_text.startswith("http://") or input_text.startswith("https://"):
-            input_type = "URL"
-        else:
-            input_type = "Text"
+def extract_text_from_url(url):
+    try:
+        response = requests.get(url, timeout=5)
+        soup = BeautifulSoup(response.text, "html.parser")
+        paragraphs = soup.find_all("p")
+        text = " ".join([p.get_text() for p in paragraphs])
+        return text.strip()[:3000]  # Limit to 3000 characters
+    except Exception as e:
+        return f"Error fetching URL: {e}"
 
+def detect_misinformation(input_text, input_type):
     if input_type == "URL":
-        try:
-            article = Article(input_text)
-            article.download()
-            article.parse()
-            text = article.text
-        except Exception as e:
-            return f"❌ Failed to extract article: {e}", 0
-    else:
-        text = input_text
-
-    if not text:
-        return "❌ No text provided", 0
+        input_text = extract_text_from_url(input_text)
+        if input_text.startswith("Error"):
+            return input_text, "Error", 0.0
 
-    try:
-        result = model(text)[0]
-        label = result["label"]
-        score = result["score"]
-        verdict = "Authentic" if label == "REAL" else "Possibly Misinformation"
-        authenticity_score = round(score * 100, 2)
-        return verdict, authenticity_score
-    except Exception as e:
-        return f"❌ Model inference failed: {e}", 0
-
-interface = gr.Interface(
-    fn=analyze,
-    inputs=[
-        gr.Textbox(lines=6, label="Paste article text or URL here"),
-        gr.Radio(["Auto Detect", "Text", "URL"], label="Input Type", value="Auto Detect")
-    ],
-    outputs=[
-        gr.Textbox(label="Verdict"),
-        gr.Number(label="Authenticity Score (%)")
-    ],
-    title="Misinformation Detection Dashboard",
-    description="Enter article text or a URL to detect whether the content is authentic or possibly misinformation."
-)
-
-interface.launch()
+    inputs = tokenizer(input_text, return_tensors="pt", truncation=True, padding=True)
+    with torch.no_grad():
+        outputs = model(**inputs)
+        probs = torch.nn.functional.softmax(outputs.logits, dim=1)
+        score = probs[0][1].item()
+        verdict = "Possibly Misinformation" if score > 0.5 else "Authentic"
+        return input_text[:1000], verdict, round(score * 100, 2)
+
+with gr.Blocks() as demo:
+    gr.Markdown("## 🧠 Misinformation Detection Dashboard")
+    gr.Markdown("Paste article text or a URL. Choose input type and get a verdict.")
+
+    with gr.Row():
+        input_text = gr.Textbox(label="Enter Text or URL", lines=6, placeholder="Paste article text or URL here...")
+        input_type = gr.Radio(["Auto Detect", "Text", "URL"], value="Auto Detect", label="Input Type")
+
+    output_text = gr.Textbox(label="Processed Text", lines=6)
+    verdict = gr.Label(label="Verdict")
+    score = gr.Label(label="Authenticity Score (%)")
+
+    btn = gr.Button("Analyze")
+
+    def handle_input(text, mode):
+        if mode == "Auto Detect":
+            if text.startswith("http://") or text.startswith("https://"):
+                mode = "URL"
+            else:
+                mode = "Text"
+        return detect_misinformation(text, mode)
+
+    btn.click(fn=handle_input, inputs=[input_text, input_type], outputs=[output_text, verdict, score])
+
+demo.launch()