Skip to content

🕵️‍♂️ (2-in-1) Email & Username OSINT suite featuring native MCP support for deep data extraction just from a single Email/Username. Analyzes 2720+ actively maintained scan vectors (210+ email / 2510+ username) for security research, investigations, and digital footprinting.

fix(stackb): enrich profile metadata from public pages (#636)

Kristo Isberga412c6d1ac48
diff --git a/user_scanner/email_scan/gaming/stackb.py b/user_scanner/email_scan/gaming/stackb.py
index 13f0e04..98302a0 100644
--- a/user_scanner/email_scan/gaming/stackb.py
+++ b/user_scanner/email_scan/gaming/stackb.py
@@ -3,25 +3,16 @@ import re
import httpx
-from user_scanner.core.helpers import get_random_user_agent
+from user_scanner.core.helpers import get_global_timeout
from user_scanner.core.result import Result
-async def _check(email: str) -> Result:
+async def validate_stackb(email: str) -> Result:
show_url = "https://stackb.net"
login_url = f"{show_url}/login"
- headers = {
- "User-Agent": get_random_user_agent(),
- "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
- "Accept-Language": "ru,en-US;q=0.9,en;q=0.8",
- }
try:
- async with httpx.AsyncClient(
- timeout=15.0,
- headers=headers,
- follow_redirects=True,
- ) as client:
+ async with httpx.AsyncClient(timeout=get_global_timeout() or 15.0) as client:
login_response = await client.get(login_url)
if login_response.status_code != 200:
return Result.error(
@@ -34,8 +25,8 @@ async def _check(email: str) -> Result:
login_response.text,
)
snapshot_match = re.search(
- r'<div[^>]*wire:snapshot="([^"]+)"'
- r'[^>]*x-data="loginFormCaptcha',
+ r'<div(?=[^>]*wire:name="login-form")'
+ r'(?=[^>]*wire:snapshot="([^"]+)")[^>]*>',
login_response.text,
)
if not csrf_match or not snapshot_match:
@@ -46,7 +37,6 @@ async def _check(email: str) -> Result:
csrf_token = html.unescape(csrf_match.group(1))
payload = {
- "_token": csrf_token,
"components": [
{
"snapshot": html.unescape(snapshot_match.group(1)),
@@ -54,19 +44,13 @@ async def _check(email: str) -> Result:
"identifier": email,
"password": "StackB-not-the-password-12345",
},
- "calls": [
- {"path": "", "method": "submitLogin", "params": []}
- ],
+ "calls": [{"path": "", "method": "submitLogin", "params": []}],
}
],
}
login_check = await client.post(
f"{show_url}/livewire/update",
headers={
- "Accept": "application/json",
- "Content-Type": "application/json",
- "Origin": show_url,
- "Referer": login_url,
"X-CSRF-TOKEN": csrf_token,
"X-Livewire": "true",
},
@@ -79,23 +63,12 @@ async def _check(email: str) -> Result:
url=show_url,
)
- components = login_check.json().get("components", [])
- login_messages = " ".join(
- str(dispatch.get("params", {}).get("message", ""))
- for component in components
- for dispatch in component.get("effects", {}).get(
- "dispatches", []
- )
- )
+ login_messages = str(login_check.json().get("components", []))
if "Таких пользователей не нашлось" in login_messages:
return Result.available(url=show_url)
if "Пароль введен неверно" in login_messages:
return Result.taken(url=show_url)
return Result.error("Unexpected login check response", url=show_url)
- except Exception as exc:
+ except (httpx.HTTPError, ValueError, AttributeError) as exc:
return Result.error(exc, url=show_url)
-
-
-async def validate_stackb(email: str) -> Result:
- return await _check(email)
diff --git a/user_scanner/user_scan/gaming/stackb.py b/user_scanner/user_scan/gaming/stackb.py
index 63c4da3..5723e44 100644
--- a/user_scanner/user_scan/gaming/stackb.py
+++ b/user_scanner/user_scan/gaming/stackb.py
@@ -3,131 +3,119 @@ import json
import re
from urllib.parse import quote
-from user_scanner.core.helpers import get_random_user_agent
-from user_scanner.core.orchestrator import make_request
+from user_scanner.core.orchestrator import generic_validate
from user_scanner.core.result import Result
+def _text(markup: str) -> str:
+ return " ".join(html.unescape(re.sub(r"<[^>]*>", " ", markup)).split())
+
+
+def _extract_profile(response_text: str, profile: dict) -> tuple[dict, dict]:
+ extra = {
+ "username": str(profile.get("identifier", "")).removeprefix("@"),
+ "display_name": profile.get("name"),
+ "bio": profile.get("description"),
+ }
+ media = {"avatar": profile.get("image")}
+
+ description_match = re.search(
+ r'<meta\s[^>]*property=["\']og:description["\'][^>]*content=["\']([^"\']*)',
+ response_text,
+ re.IGNORECASE,
+ )
+ stats_text = html.unescape(description_match.group(1)) if description_match else ""
+ if rank_match := re.search(r"Ранг:\s*([^\.]+)", stats_text):
+ extra["rank"] = rank_match.group(1).strip()
+ if followers_match := re.search(r"Подписчики:\s*(\d+)", stats_text):
+ extra["followers"] = int(followers_match.group(1))
+ if following_match := re.search(
+ r'href="[^"]+/follows">\s*<span[^>]*>(\d+)</span>',
+ response_text,
+ ):
+ extra["following"] = int(following_match.group(1))
+
+ if user_id_match := re.search(
+ r'<div\s+wire:key="(\d+)"[^>]*wire:name="profile"', response_text
+ ):
+ extra["user_id"] = int(user_id_match.group(1))
+
+ if demographics_match := re.search(
+ r"<div\b(?=[^>]*\bdata-profile-demographics\b)[^>]*>(.*?)</div>\s*</div>",
+ response_text,
+ re.DOTALL,
+ ):
+ demographics = _text(demographics_match.group(1))
+ if match := re.fullmatch(r"(.+?)(?:\s+(\d+))?\s*•\s*(\S+)", demographics):
+ extra["gender"] = match.group(1)
+ extra["age"] = int(match.group(2)) if match.group(2) else None
+ extra["region"] = match.group(3)
+
+ identity_match = re.search(
+ r"data-profile-name-row\b[^>]*>.*?</h1>", response_text, re.DOTALL
+ )
+ extra["verified"] = bool(identity_match and "<svg" in identity_match.group(0))
+
+ if badge_match := re.search(
+ r"<button\b(?=[^>]*\bdata-profile-badge\b)[^>]*>(.*?)</button>",
+ response_text,
+ re.DOTALL,
+ ):
+ extra["badge"] = _text(badge_match.group(1))
+
+ if (
+ website_tag := re.search(
+ r"<a\b(?=[^>]*\bdata-profile-website\b)[^>]*>", response_text
+ )
+ ) and (href_match := re.search(r'href=["\']([^"\']+)', website_tag.group(0))):
+ extra["website"] = html.unescape(href_match.group(1)).removeprefix(
+ "https://stackb.net/redirect/"
+ )
+
+ if games := [
+ _text(match)
+ for match in re.findall(
+ r"<a\b(?=[^>]*class=[\"\'][^\"\']*\bgame-card\b)[^>]*>(.*?)</a>",
+ response_text,
+ re.DOTALL,
+ )
+ ]:
+ extra["games"] = games
+
+ if cover_tag := re.search(
+ r"<div\b(?=[^>]*\bdata-profile-cover\b)[^>]*>", response_text
+ ):
+ decoded_tag = html.unescape(cover_tag.group(0))
+ if cover_match := re.search(
+ r"background-image:\s*url\(['\"]?([^'\")]+)", decoded_tag
+ ):
+ media["banner"] = cover_match.group(1)
+
+ return extra, media
+
+
def validate_stackb(user: str) -> Result:
- profile_url = f"https://stackb.net/@{user}"
url = f"https://stackb.net/@{quote(user, safe='')}"
- login_url = "https://stackb.net/login"
+ show_url = f"https://stackb.net/@{user}"
- headers = {
- "User-Agent": get_random_user_agent(),
- "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
- "Accept-Language": "ru,en-US;q=0.9,en;q=0.8",
- }
+ def process(response):
+ if response.status_code == 404 and "Ошибка 404" in response.text:
+ return Result.available()
- try:
- login_response = make_request(login_url, headers=headers, follow_redirects=True)
- if login_response.status_code != 200:
- return Result.error(f"Unexpected login status: {login_response.status_code}", url=url)
+ if response.status_code != 200:
+ return Result.error(f"Unexpected profile status: {response.status_code}")
- login_text = login_response.text
- csrf_match = re.search(r'<meta name="csrf-token" content="([^"]+)"', login_text)
- snapshot_match = re.search(
- r'<div[^>]*wire:snapshot="([^"]+)"[^>]*x-data="loginFormCaptcha',
- login_text,
- )
- if not csrf_match or not snapshot_match:
- return Result.error("Could not find login form tokens", url=url)
-
- csrf_token = html.unescape(csrf_match.group(1))
- snapshot = html.unescape(snapshot_match.group(1))
- payload = {
- "_token": csrf_token,
- "components": [
- {
- "snapshot": snapshot,
- "updates": {
- "identifier": user,
- "password": "StackB-not-the-password-12345",
- },
- "calls": [{"path": "", "method": "submitLogin", "params": []}],
- }
- ],
- }
- login_check = make_request(
- "https://stackb.net/livewire/update",
- method="POST",
- headers={
- **headers,
- "Accept": "application/json",
- "Content-Type": "application/json",
- "Origin": "https://stackb.net",
- "Referer": login_url,
- "X-CSRF-TOKEN": csrf_token,
- "X-Livewire": "true",
- },
- json=payload,
+ match = re.search(
+ r'<script[^>]*type="application/ld\+json"[^>]*>(.*?)</script>',
+ response.text,
+ re.DOTALL,
)
+ data = json.loads(html.unescape(match.group(1))) if match else {}
+ profile = data.get("mainEntity") if data.get("@type") == "ProfilePage" else None
+ if isinstance(profile, dict) and profile.get("@type") == "Person":
+ extra, media = _extract_profile(response.text, profile)
+ return Result.taken(extra=extra, media=media)
+
+ return Result.error("Unexpected profile response")
- if login_check.status_code != 200:
- return Result.error(f"Unexpected login check status: {login_check.status_code}", url=url)
-
- try:
- login_data = login_check.json()
- login_messages = " ".join(
- str(dispatch.get("params", {}).get("message", ""))
- for component in login_data.get("components", [])
- for dispatch in component.get("effects", {}).get("dispatches", [])
- )
- except (ValueError, AttributeError):
- return Result.error("Unexpected login check response", url=url)
-
- if "Максимальная длина никнейма" in login_messages:
- return Result.available(
- "Username format rejected by StackB",
- url=url,
- )
- if "Таких пользователей не нашлось" in login_messages:
- return Result.available(url=url)
- if "Пароль введен неверно" not in login_messages:
- return Result.error("Unexpected login check response", url=url)
-
- extra = {}
- media = {}
-
- try:
- profile_response = make_request(
- url,
- headers=headers,
- show_url=url,
- follow_redirects=True,
- )
- response_text = profile_response.text
- profile = {}
- for json_match in re.finditer(r'<script[^>]*type="application/ld\+json"[^>]*>(.*?)</script>', response_text, re.DOTALL):
- try:
- data = json.loads(html.unescape(json_match.group(1)))
- except json.JSONDecodeError:
- continue
-
- if data.get("@type") == "ProfilePage":
- entity = data.get("mainEntity")
- if isinstance(entity, dict):
- profile = entity
- break
-
- if profile:
- description_match = re.search(r'<meta [^>]*property=["\']og:description["\'][^>]*content=["\']([^"\']*)', response_text, re.IGNORECASE)
- stats_text = html.unescape(description_match.group(1)).strip() if description_match else None
-
- if name := profile.get("name"): extra["display_name"] = name
- if description := profile.get("description"): extra["bio"] = description
- if image := profile.get("image"): media["avatar"] = image
-
- if stats_text:
- if rank_match := re.search(r"Ранг:\s*([^\.]+)", stats_text):
- extra["rank"] = rank_match.group(1).strip()
- if followers_match := re.search(r"Подписчики:\s*(\d+)", stats_text):
- extra["followers"] = int(followers_match.group(1))
-
- extra["profile_url"] = profile_url
- except Exception:
- pass
-
- return Result.taken(extra=extra, media=media, url=url)
- except Exception as exc:
- return Result.error(exc, url=url)
+ return generic_validate(url, process, show_url=show_url, follow_redirects=True)