Update body_analyzer.py

body_analyzer.py

@@ -1,5 +1,6 @@
 import requests
 import os
+import re
 
 HF_API_KEY = os.getenv("HF_API_KEY")  # Hugging Face free account
 HF_HEADERS = {"Authorization": f"Bearer {HF_API_KEY}"}
@@ -10,36 +11,71 @@ MODELS = {
     "spam": "mrm8488/bert-tiny-finetuned-sms-spam-detection",
 }
 
+# Suspicious patterns to look for
+SUSPICIOUS_PATTERNS = [
+    r"verify your account",
+    r"urgent action",
+    r"click here",
+    r"reset (your )?password",
+    r"confirm (your )?identity",
+    r"bank account",
+    r"invoice",
+    r"payment (required|overdue|failed|method expired)",
+    r"unauthorized login",
+    r"compromised",
+    r"final reminder",
+    r"account (suspended|deactivated|locked)",
+    r"update your (information|details|billing)",
+    r"legal action",
+]
+
 def query_hf(model, text):
     url = f"https://api-inference.huggingface.co/models/{model}"
-    res = requests.post(url, headers=HF_HEADERS, json={"inputs": text[:1000]})
-    return res.json()
+    try:
+        res = requests.post(url, headers=HF_HEADERS, json={"inputs": text[:1000]})
+        return res.json()
+    except Exception:
+        return None
 
 def analyze_body(text):
     findings = []
+    score = 0
+    body_lower = text.lower()
 
-    # 1. AI-generated detection
-    try:
-        result = query_hf(MODELS["ai_detector"], text)
-        if isinstance(result, list):
-            findings.append(f"Body: AI Detector → {result[0]['label']} (confidence {result[0]['score']:.2f})")
-    except:
-        findings.append("Body: AI detection failed")
+    # --- 1. Suspicious keyword detection ---
+    for pattern in SUSPICIOUS_PATTERNS:
+        matches = re.findall(pattern, body_lower)
+        for match in matches:
+            findings.append(f"Suspicious phrase detected: \"{match}\"")
+            score += 20  # weight for suspicious phrase
 
-    # 2. Sentiment / Tone
-    try:
-        result = query_hf(MODELS["sentiment"], text)
-        if isinstance(result, list):
-            findings.append(f"Body: Sentiment → {result[0]['label']} (confidence {result[0]['score']:.2f})")
-    except:
-        findings.append("Body: Sentiment analysis failed")
+    # --- 2. AI-generated text detection ---
+    result = query_hf(MODELS["ai_detector"], text)
+    if result and isinstance(result, list) and len(result) > 0:
+        label = result[0]["label"]
+        confidence = result[0]["score"]
+        findings.append(f"Body: AI Detector → {label} (confidence {confidence:.2f})")
+        # No score impact yet (just informational)
 
-    # 3. Spam vs Ham
-    try:
-        result = query_hf(MODELS["spam"], text)
-        if isinstance(result, list):
-            findings.append(f"Body: Spam Detector → {result[0]['label']} (confidence {result[0]['score']:.2f})")
-    except:
-        findings.append("Body: Spam detection failed")
+    # --- 3. Sentiment analysis ---
+    result = query_hf(MODELS["sentiment"], text)
+    if result and isinstance(result, list) and len(result) > 0:
+        label = result[0]["label"]
+        confidence = result[0]["score"]
+        findings.append(f"Body: Sentiment → {label} (confidence {confidence:.2f})")
+        if label.lower() in ["negative"]:
+            score += 10  # negative/urgent tone adds risk
+
+    # --- 4. Spam vs Ham detection ---
+    result = query_hf(MODELS["spam"], text)
+    if result and isinstance(result, list) and len(result) > 0:
+        label = result[0]["label"]
+        confidence = result[0]["score"]
+        findings.append(f"Body: Spam Detector → {label} (confidence {confidence:.2f})")
+        if label.lower() == "spam":
+            score += 20  # spam classification increases risk
+
+    if not findings:
+        return ["No suspicious content detected in body."], 0
 
-    return findings
+    return findings, score