From 3fd0956c0f92b1fc3468eac5223552519ed066c6 Mon Sep 17 00:00:00 2001
From: Bruno Leonardo Michels <brunolm7@gmail.com>
Date: Sat, 18 Jul 2026 20:56:10 -0300
Subject: [PATCH] feat: add Tube8 email scan module

Add email-based Tube8 account check via the register/verify_email endpoint
(email_scan/adult), following the same Aylo create-account flow as YouPorn
and RedTube. Includes the shared is_valid_email helper used to guard the
"requirements" response, matching the helper introduced alongside RedTube.
---
 user_scanner/core/helpers.py           | 18 ++++++
 user_scanner/email_scan/adult/tube8.py | 77 ++++++++++++++++++++++++++
 2 files changed, 95 insertions(+)
 create mode 100644 user_scanner/email_scan/adult/tube8.py

diff --git a/user_scanner/core/helpers.py b/user_scanner/core/helpers.py
index ddb86e1c..38707d37 100644
--- a/user_scanner/core/helpers.py
+++ b/user_scanner/core/helpers.py
@@ -7,6 +7,7 @@
 import json
 import os
 import random
+import re
 import threading
 import functools
 import asyncio
@@ -15,6 +16,14 @@
 
 import httpx
 
+# Pragmatic RFC 5322 / email-validator-style syntax check: an unquoted
+# dot-atom local part, a dotted host name, and an alphabetic TLD. It does not
+# accept quoted local parts, IP-address literals, or internationalized (IDN)
+# domains — none of which the scanners target.
+_EMAIL_LOCAL = r"[A-Za-z0-9!#$%&'*+/=?^_`{|}~-]+(?:\.[A-Za-z0-9!#$%&'*+/=?^_`{|}~-]+)*"
+_EMAIL_LABEL = r"[A-Za-z0-9](?:[A-Za-z0-9-]{0,61}[A-Za-z0-9])?"
+EMAIL_RE = re.compile(rf"{_EMAIL_LOCAL}@(?:{_EMAIL_LABEL}\.)+[A-Za-z]{{2,63}}")
+
 LOUD_MODULES: Dict[str, List[str]] = {
     "user": [],
     "email": [
@@ -55,6 +64,15 @@ class ScanConfig:
     verbose: bool = False
 
 
+def is_valid_email(email: str) -> bool:
+    if not email or len(email) > 254:
+        return False
+    local, _, domain = email.rpartition("@")
+    if len(local) > 64 or len(domain) > 253:
+        return False
+    return bool(EMAIL_RE.fullmatch(email))
+
+
 def get_site_name(module) -> str:
     name = module.__name__.split(".")[-1].capitalize().replace("_", ".")
     if name == "X":
diff --git a/user_scanner/email_scan/adult/tube8.py b/user_scanner/email_scan/adult/tube8.py
new file mode 100644
index 00000000..ce6922a2
--- /dev/null
+++ b/user_scanner/email_scan/adult/tube8.py
@@ -0,0 +1,77 @@
+import httpx
+import re
+from user_scanner.core.helpers import is_valid_email
+from user_scanner.core.result import Result
+
+RATE_LIMITED_MSG = "Rate limited, wait for a few minutes"
+
+
+async def _check(email: str) -> Result:
+    base_url = "https://www.tube8.com"
+    show_url = "https://tube8.com"
+    register_url = f"{base_url}/register"
+    check_api = f"{base_url}/register/verify_email"
+
+    headers = {
+        "User-Agent": "Mozilla/5.0 (Linux; Android 10; K) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/143.0.0.0 Mobile Safari/537.36",
+        "X-Requested-With": "XMLHttpRequest",
+        "Origin": base_url,
+        "Referer": register_url,
+        "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
+    }
+
+    async with httpx.AsyncClient(http2=True, follow_redirects=True, timeout=15.0) as client:
+        try:
+            landing_resp = await client.get(register_url, headers=headers)
+            token_match = re.search(
+                r'page_params\.token\s*=\s*"([^"]+)"', landing_resp.text
+            )
+
+            if not token_match:
+                return Result.error("Failed to extract dynamic token from HTML")
+
+            token = token_match.group(1)
+
+            params = {"token": token}
+            payload = {"token": token, "email": email}
+
+            response = await client.post(
+                check_api,
+                params=params,
+                headers=headers,
+                data=payload,
+            )
+
+            if response.status_code == 429:
+                return Result.error(RATE_LIMITED_MSG)
+
+            if response.status_code != 200:
+                return Result.error(f"HTTP Error: {response.status_code}")
+
+            data = response.json()
+
+            if data.get("success") is True:
+                return Result.available(url=show_url)
+
+            messages = data.get("messages", [])
+            message = " ".join(messages) if isinstance(messages, list) else str(messages)
+
+            # A well-formed address that fails the requirements check is Tube8's
+            # way of reporting an existing account rather than saying it's taken.
+            if "does not meet our registration requirements" in message:
+                if is_valid_email(email):
+                    return Result.taken(url=show_url)
+                return Result.available(url=show_url, reason=message)
+
+            # A stale or over-used token answers "Not available." instead of a verdict.
+            if "not available" in message.lower():
+                return Result.error(RATE_LIMITED_MSG)
+
+            return Result.error(f"Unexpected API response: {message}")
+
+        except Exception as e:
+            return Result.error(e)
+
+
+async def validate_tube8(email: str) -> Result:
+    return await _check(email)