Add email format and DNS validation to detect invalid emails before sending

backend/routers/email.py

@@ -8,6 +8,7 @@ from sendgrid.helpers.mail import Mail, Attachment, FileContent, FileName, FileT
 import base64
 import uuid
 from backend.utils.pdf_generator import generate_certificate_pdf
+from backend.utils.email_validator import validate_email
 
 router = APIRouter()
 
@@ -84,6 +85,32 @@ def send_email_task(
     
     if not name or not email:
         print(f"Skipping row with missing name or email")
+        if job_id in email_progress:
+            email_progress[job_id]["sent"] += 1
+            email_progress[job_id]["failed"] += 1
+            if "failed_emails" not in email_progress[job_id]:
+                email_progress[job_id]["failed_emails"] = []
+            email_progress[job_id]["failed_emails"].append({
+                "email": email or "(empty)",
+                "name": name or "(empty)",
+                "error": "Missing name or email"
+            })
+        return
+
+    # Validate email format and domain BEFORE generating PDF
+    is_valid, validation_error = validate_email(email)
+    if not is_valid:
+        print(f"Invalid email skipped: {email} - {validation_error}")
+        if job_id in email_progress:
+            email_progress[job_id]["sent"] += 1
+            email_progress[job_id]["failed"] += 1
+            if "failed_emails" not in email_progress[job_id]:
+                email_progress[job_id]["failed_emails"] = []
+            email_progress[job_id]["failed_emails"].append({
+                "email": email,
+                "name": name,
+                "error": validation_error
+            })
         return
 
     print(f"Starting email task for: {name} ({email})")

backend/utils/email_validator.py

@@ -0,0 +1,70 @@
+"""
+Email validation utilities - Format and DNS validation
+"""
+import re
+import socket
+from typing import Tuple
+
+def validate_email_format(email: str) -> Tuple[bool, str]:
+    """
+    Validate email format using regex.
+    Returns (is_valid, error_message)
+    """
+    if not email or not email.strip():
+        return False, "Email is empty"
+    
+    email = email.strip().lower()
+    
+    # Basic email regex pattern
+    pattern = r'^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$'
+    
+    if not re.match(pattern, email):
+        return False, f"Invalid email format: {email}"
+    
+    return True, ""
+
+
+def validate_email_domain(email: str) -> Tuple[bool, str]:
+    """
+    Validate that the email domain has valid MX or A records.
+    Returns (is_valid, error_message)
+    """
+    try:
+        domain = email.split('@')[1]
+        
+        # Try to get MX records first
+        try:
+            socket.getaddrinfo(domain, None, socket.AF_INET)
+            return True, ""
+        except socket.gaierror:
+            pass
+        
+        # If no A record, try with 'mail.' prefix (common mail server)
+        try:
+            socket.getaddrinfo(f"mail.{domain}", None, socket.AF_INET)
+            return True, ""
+        except socket.gaierror:
+            pass
+        
+        return False, f"Domain does not exist: {domain}"
+        
+    except Exception as e:
+        return False, f"Domain validation error: {str(e)}"
+
+
+def validate_email(email: str) -> Tuple[bool, str]:
+    """
+    Full email validation - format and domain.
+    Returns (is_valid, error_message)
+    """
+    # First check format
+    is_valid, error = validate_email_format(email)
+    if not is_valid:
+        return False, error
+    
+    # Then check domain
+    is_valid, error = validate_email_domain(email)
+    if not is_valid:
+        return False, error
+    
+    return True, ""