Update app.py

app.py

@@ -1,24 +1,109 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
 import requests
+from bs4 import BeautifulSoup
+import matplotlib.pyplot as plt
+import os
+
+# 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)
+
+# Initialize verdict counters
+verdict_counts = {"Authentic": 0, "Possibly Misinformation": 0}
+
+# Read API key from environment variable
+FACT_CHECK_API_KEY = os.getenv("FACT_CHECK_API_KEY")
+
+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]
+    except Exception as e:
+        return f"Error fetching URL: {e}"
+
+def update_chart():
+    labels = list(verdict_counts.keys())
+    sizes = list(verdict_counts.values())
+    fig, ax = plt.subplots()
+    ax.pie(sizes, labels=labels, autopct='%1.1f%%', startangle=90)
+    ax.set_title("Verdict Distribution")
+    return fig
 
 def fact_check_google_api(query, api_key):
+    if not api_key:
+        return "API key not found. Please set FACT_CHECK_API_KEY in environment."
     url = "https://factchecktools.googleapis.com/v1alpha1/claims:search"
     params = {
         "query": query,
         "languageCode": "en-US",
         "key": api_key
     }
-    response = requests.get(url, params=params)
-    if response.status_code == 200:
-        data = response.json()
-        if "claims" in data:
-            results = []
-            for claim in data["claims"]:
-                text = claim.get("text", "No claim text")
-                rating = claim.get("claimReview", [{}])[0].get("textualRating", "No rating")
-                publisher = claim.get("claimReview", [{}])[0].get("publisher", {}).get("name", "Unknown")
-                results.append(f"Claim: {text}\nRating: {rating}\nSource: {publisher}")
-            return "\n\n".join(results)
+    try:
+        response = requests.get(url, params=params)
+        if response.status_code == 200:
+            data = response.json()
+            if "claims" in data:
+                results = []
+                for claim in data["claims"]:
+                    text = claim.get("text", "No claim text")
+                    review = claim.get("claimReview", [{}])[0]
+                    rating = review.get("textualRating", "No rating")
+                    publisher = review.get("publisher", {}).get("name", "Unknown")
+                    results.append(f"Claim: {text}\nRating: {rating}\nSource: {publisher}")
+                return "\n\n".join(results)
+            else:
+                return "No fact-checks found for this query."
         else:
-            return "No fact-checks found for this query."
-    else:
-        return f"Error: {response.status_code} - {response.text}"
+            return f"Error: {response.status_code} - {response.text}"
+    except Exception as e:
+        return f"Error calling Fact Check API: {e}"
+
+def detect_misinformation(input_text, input_type):
+    if input_type == "URL":
+        input_text = extract_text_from_url(input_text)
+        if input_text.startswith("Error"):
+            return input_text, "Error", 0.0, update_chart(), "URL extraction failed."
+
+    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"
+        verdict_counts[verdict] += 1
+        fact_check_result = fact_check_google_api(input_text, FACT_CHECK_API_KEY)
+        return input_text[:1000], verdict, round(score * 100, 2), update_chart(), fact_check_result
+
+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 (%)")
+    chart = gr.Plot(label="Analytics Dashboard")
+    fact_check = gr.Textbox(label="Fact Check Results", lines=6)
+
+    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, chart, fact_check])
+
+demo.launch()