it

providers/crtsh_provider.py

@@ -478,57 +478,56 @@ class CrtShProvider(BaseProvider):
         common_name = cert_data.get('common_name', '')
         if common_name:
             cleaned_cn = self._clean_domain_name(common_name)
-            if cleaned_cn and _is_valid_domain(cleaned_cn):
-                domains.add(cleaned_cn)
+            if cleaned_cn:
+                domains.update(cleaned_cn)
         
         # Extract from name_value field (contains SANs)
         name_value = cert_data.get('name_value', '')
         if name_value:
             # Split by newlines and clean each domain
             for line in name_value.split('\n'):
-                cleaned_domain = self._clean_domain_name(line.strip())
-                if cleaned_domain and _is_valid_domain(cleaned_domain):
-                    domains.add(cleaned_domain)
+                cleaned_domains = self._clean_domain_name(line.strip())
+                if cleaned_domains:
+                    domains.update(cleaned_domains)
         
         return domains
     
-    def _clean_domain_name(self, domain_name: str) -> str:
+    def _clean_domain_name(self, domain_name: str) -> List[str]:
         """
         Clean and normalize domain name from certificate data.
-        
-        Args:
-            domain_name: Raw domain name from certificate
-            
-        Returns:
-            Cleaned domain name or empty string if invalid
+        Now returns a list to handle wildcards correctly.
         """
         if not domain_name:
-            return ""
-        
-        # Remove common prefixes and clean up
+            return []
+
         domain = domain_name.strip().lower()
-        
+
         # Remove protocol if present
         if domain.startswith(('http://', 'https://')):
             domain = domain.split('://', 1)[1]
-        
+
         # Remove path if present
         if '/' in domain:
             domain = domain.split('/', 1)[0]
-        
+
         # Remove port if present
         if ':' in domain and not domain.count(':') > 1:  # Avoid breaking IPv6
             domain = domain.split(':', 1)[0]
-        
+
         # Handle wildcard domains
+        cleaned_domains = []
         if domain.startswith('*.'):
-            domain = domain[2:]
-        
-        # Remove any remaining invalid characters
-        domain = re.sub(r'[^\w\-\.]', '', domain)
-        
-        # Ensure it's not empty and doesn't start/end with dots or hyphens
-        if domain and not domain.startswith(('.', '-')) and not domain.endswith(('.', '-')):
-            return domain
-        
-        return ""
+            # Add both the wildcard and the base domain
+            cleaned_domains.append(domain)
+            cleaned_domains.append(domain[2:])
+        else:
+            cleaned_domains.append(domain)
+
+        # Remove any remaining invalid characters and validate
+        final_domains = []
+        for d in cleaned_domains:
+            d = re.sub(r'[^\w\-\.]', '', d)
+            if d and not d.startswith(('.', '-')) and not d.endswith(('.', '-')):
+                final_domains.append(d)
+
+        return [d for d in final_domains if _is_valid_domain(d)]