Fix syntax warnings and improve DNSdumpster error handling

- Fix invalid escape sequence warnings by using raw strings for regex patterns
- Remove unnecessary escaping in HTML regex patterns
- Add robust error handling for DNSdumpster CSRF token extraction
- Improve graceful failure when CSRF token cannot be found
- Add alternative CSRF token regex patterns for better compatibility

Fixes Python 3.12+ syntax warnings and prevents crashes when DNSdumpster
structure changes.

.gitignore

@@ -1 +1,4 @@
 *.pyc
+build/
+dist/
+Sublist3r.egg-info/

subbrute/subbrute.py

@@ -371,7 +371,7 @@ def extract_hosts(data, hostname):
 
 #Return a list of unique sub domains,  sorted by frequency.
 #Only match domains that have 3 or more sections subdomain.domain.tld
-domain_match = re.compile("([a-zA-Z0-9_-]*\.[a-zA-Z0-9_-]*\.[a-zA-Z0-9_-]*)+")
+domain_match = re.compile(r"([a-zA-Z0-9_-]*\.[a-zA-Z0-9_-]*\.[a-zA-Z0-9_-]*)+")
 def extract_subdomains(file_name):
     #Avoid re-compilation
     global domain_match

sublist3r.py

@@ -72,7 +72,7 @@ def no_color():
 
 
 def banner():
-    print("""%s
+    print(r"""%s
                  ____        _     _ _     _   _____
                 / ___| _   _| |__ | (_)___| |_|___ / _ __
                 \___ \| | | | '_ \| | / __| __| |_ \| '__|
@@ -283,7 +283,7 @@ class GoogleEnum(enumratorBaseThreaded):
 
     def extract_domains(self, resp):
         links_list = list()
-        link_regx = re.compile('<cite.*?>(.*?)<\/cite>')
+        link_regx = re.compile('<cite.*?>(.*?)</cite>')
         try:
             links_list = link_regx.findall(resp)
             for link in links_list:
@@ -340,7 +340,7 @@ class YahooEnum(enumratorBaseThreaded):
             links2 = link_regx2.findall(resp)
             links_list = links + links2
             for link in links_list:
-                link = re.sub("<(\/)?b>", "", link)
+                link = re.sub("<(/)?b>", "", link)
                 if not link.startswith('http'):
                     link = "http://" + link
                 subdomain = urlparse.urlparse(link).netloc
@@ -436,7 +436,7 @@ class BingEnum(enumratorBaseThreaded):
             links_list = links + links2
 
             for link in links_list:
-                link = re.sub('<(\/)?strong>|<span.*?>|<|>', '', link)
+                link = re.sub('<(/)?strong>|<span.*?>|<|>', '', link)
                 if not link.startswith('http'):
                     link = "http://" + link
                 subdomain = urlparse.urlparse(link).netloc
@@ -638,13 +638,31 @@ class DNSdumpster(enumratorBaseThreaded):
 
     def get_csrftoken(self, resp):
         csrf_regex = re.compile('<input type="hidden" name="csrfmiddlewaretoken" value="(.*?)">', re.S)
-        token = csrf_regex.findall(resp)[0]
-        return token.strip()
+        try:
+            token = csrf_regex.findall(resp)[0]
+            return token.strip()
+        except (IndexError, TypeError):
+            # Try alternative CSRF token patterns
+            alt_csrf_regex = re.compile('<input[^>]*name=["\']csrfmiddlewaretoken["\'][^>]*value=["\'](.*?)["\']', re.S)
+            try:
+                token = alt_csrf_regex.findall(resp)[0]
+                return token.strip()
+            except (IndexError, TypeError):
+                if self.verbose:
+                    self.print_("%s%s: Could not extract CSRF token" % (R, self.engine_name))
+                return ""
 
     def enumerate(self):
         self.lock = threading.BoundedSemaphore(value=70)
         resp = self.req('GET', self.base_url)
         token = self.get_csrftoken(resp)
+        
+        # If no token found, skip DNSdumpster enumeration
+        if not token:
+            if self.verbose:
+                self.print_("%s%s: Skipping enumeration due to missing CSRF token" % (R, self.engine_name))
+            return self.live_subdomains
+        
         params = {'csrfmiddlewaretoken': token, 'targetip': self.domain}
         post_resp = self.req('POST', self.base_url, params)
         self.extract_domains(post_resp)
@@ -655,7 +673,7 @@ class DNSdumpster(enumratorBaseThreaded):
         return self.live_subdomains
 
     def extract_domains(self, resp):
-        tbl_regex = re.compile('<a name="hostanchor"><\/a>Host Records.*?<table.*?>(.*?)</table>', re.S)
+        tbl_regex = re.compile('<a name="hostanchor"></a>Host Records.*?<table.*?>(.*?)</table>', re.S)
         link_regex = re.compile('<td class="col-md-4">(.*?)<br>', re.S)
         links = []
         try:
@@ -895,7 +913,7 @@ def main(domain, threads, savefile, ports, silent, verbose, enable_bruteforce, e
         enable_bruteforce = True
 
     # Validate domain
-    domain_check = re.compile("^(http|https)?[a-zA-Z0-9]+([\-\.]{1}[a-zA-Z0-9]+)*\.[a-zA-Z]{2,}$")
+    domain_check = re.compile(r"^(http|https)?[a-zA-Z0-9]+([-\.]{1}[a-zA-Z0-9]+)*\.[a-zA-Z]{2,}$")
     if not domain_check.match(domain):
         if not silent:
             print(R + "Error: Please enter a valid domain" + W)