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: improve Gumroad email and username detection (#627)

Kristo Isberg261222f81a8b
diff --git a/user_scanner/email_scan/creator/gumroad.py b/user_scanner/email_scan/creator/gumroad.py
index 260fbb9..5061f39 100644
--- a/user_scanner/email_scan/creator/gumroad.py
+++ b/user_scanner/email_scan/creator/gumroad.py
@@ -1,83 +1,64 @@
-import httpx
import re
-from user_scanner.core.result import Result
-
-async def _check(email: str) -> Result:
- show_url = "https://gumroad.com"
- async with httpx.AsyncClient(timeout=15.0, http2=False, follow_redirects=True) as client:
- try:
- url1 = "https://gumroad.com/users/forgot_password/new"
- headers1 = {
- 'User-Agent': "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/144.0.0.0 Safari/537.36",
- 'Accept': "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8",
- 'Accept-Encoding': "identity",
- 'sec-ch-ua': '"Not(A:Brand";v="8", "Chromium";v="144", "Google Chrome";v="144"',
- 'sec-ch-ua-mobile': "?0",
- 'sec-ch-ua-platform': '"Linux"',
- 'upgrade-insecure-requests': "1",
- 'referer': "https://www.google.com/",
- 'accept-language': "en-US,en;q=0.9"
- }
+from user_scanner.core.impersonate import impersonate_request_async
+from user_scanner.core.result import Result
- res1 = await client.get(url1, headers=headers1)
- html = res1.text
+SIGNUP_URL = "https://gumroad.com/signup"
+CSRF_RE = re.compile(r'<meta name="csrf-token" content="([^"]+)"')
- csrf_match = re.search(
- r'authenticity_token&quot;:&quot;([^&]+)&quot;', html)
- if not csrf_match:
- csrf_match = re.search(
- r'name="csrf-token" content="([^"]+)"', html)
- if not csrf_match:
- return Result.error("Failed to extract CSRF token")
+async def validate_gumroad(email: str) -> Result:
+ show_url = "https://gumroad.com"
- csrf_token = csrf_match.group(1)
+ try:
+ page = await impersonate_request_async(SIGNUP_URL, allow_redirects=True)
+ if page.status_code != 200:
+ return Result.error(
+ f"Unexpected Gumroad signup response: {page.status_code}",
+ url=show_url,
+ )
- url2 = "https://gumroad.com/users/forgot_password"
+ token = CSRF_RE.search(page.text)
+ if not token or "Signup/New" not in page.text:
+ return Result.error("Could not read Gumroad signup form", url=show_url)
- payload = {
+ response = await impersonate_request_async(
+ SIGNUP_URL,
+ "POST",
+ json={
"user": {
- "email": email
- }
- }
+ "email": email,
+ # Gumroad rejects this three-character password after checking
+ # whether the email is already registered.
+ "password": "Q7~",
+ },
+ },
+ headers={
+ "accept": "text/html, application/xhtml+xml",
+ "origin": "https://gumroad.com",
+ "referer": SIGNUP_URL,
+ "x-csrf-token": token.group(1),
+ "x-inertia": "true",
+ "x-requested-with": "XMLHttpRequest",
+ },
+ allow_redirects=True,
+ )
+ if response.status_code != 200:
+ return Result.error(
+ f"Unexpected Gumroad signup response: {response.status_code}",
+ url=show_url,
+ )
- headers2 = {
- 'User-Agent': "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/144.0.0.0 Safari/537.36",
- 'Accept': "text/html, application/xhtml+xml",
- 'Accept-Encoding': "identity",
- 'Content-Type': "application/json",
- 'sec-ch-ua-platform': '"Linux"',
- 'x-csrf-token': csrf_token,
- 'sec-ch-ua': '"Not(A:Brand";v="8", "Chromium";v="144", "Google Chrome";v="144"',
- 'x-inertia': "true",
- 'sec-ch-ua-mobile': "?0",
- 'x-requested-with': "XMLHttpRequest",
- 'origin': "https://gumroad.com",
- 'sec-fetch-site': "same-origin",
- 'sec-fetch-mode': "cors",
- 'sec-fetch-dest': "empty",
- 'referer': "https://gumroad.com/users/forgot_password/new",
- 'accept-language': "en-US,en;q=0.9",
- 'priority': "u=1, i"
- }
+ data = response.json()
+ if data.get("component") != "Signup/New":
+ return Result.error("Unexpected Gumroad signup page", url=show_url)
- response = await client.post(url2, json=payload, headers=headers2)
-
- data = response.json()
- flash_msg = data.get("props", {}).get(
- "flash", {}).get("message", "")
-
- if "An account does not exist" in flash_msg:
- return Result.available(url=show_url)
- elif "An account does not exist" not in flash_msg:
- return Result.taken(url=show_url)
- else:
- return Result.error(f"Unexpected status: {response.status_code}")
-
- except Exception as e:
- return Result.error(f"unexpected exception: {e}")
-
-
-async def validate_gumroad(email: str) -> Result:
- return await _check(email)
+ flash = data.get("props", {}).get("flash") or {}
+ message = flash.get("message")
+ if message == "An account already exists with this email.":
+ return Result.taken(url=show_url)
+ if message == "Password is too short (minimum is 4 characters)":
+ return Result.available(url=show_url)
+ return Result.error("Unexpected Gumroad signup result", url=show_url)
+ except Exception as exc:
+ return Result.error(exc, url=show_url)
diff --git a/user_scanner/user_scan/creator/gumroad.py b/user_scanner/user_scan/creator/gumroad.py
index 2628a2b..243b9b6 100644
--- a/user_scanner/user_scan/creator/gumroad.py
+++ b/user_scanner/user_scan/creator/gumroad.py
@@ -1,28 +1,91 @@
+import html
+import json
import re
-from user_scanner.core.orchestrator import Result, make_request
+from typing import cast
+
+from user_scanner.core.orchestrator import generic_validate
+from user_scanner.core.result import Result
+
+NOT_FOUND = "<title>Page not found (404) - Gumroad</title>"
+
+
+def _links(value):
+ if isinstance(value, dict):
+ if isinstance(value.get("href"), str):
+ yield value["href"]
+ for item in value.values():
+ yield from _links(item)
+ elif isinstance(value, list):
+ for item in value:
+ yield from _links(item)
def validate_gumroad(user: str) -> Result:
- if not re.fullmatch(r"[a-z0-9]{3,20}", user):
+ username = user.lower()
+ if not re.fullmatch(r"(?=.*[a-z])[a-z0-9]{3,20}", username):
return Result.error(
- "Username must be between 3 and 20 lowercase alphanumeric characters"
+ "Username must be 3-20 lowercase letters and numbers, with at least one letter",
+ url="https://gumroad.com",
+ )
+
+ url = f"https://{username}.gumroad.com/"
+
+ def process(response) -> Result:
+ if response.status_code == 404 and NOT_FOUND in response.text:
+ return Result.available()
+
+ match = re.search(r'<div id="app" data-page="([^"]+)"', response.text)
+ if response.status_code != 200 or not match:
+ return Result.error(f"Unexpected Gumroad response: {response.status_code}")
+
+ try:
+ page = json.loads(html.unescape(match.group(1)))
+ except json.JSONDecodeError:
+ return Result.error("Invalid Gumroad profile data")
+
+ props = page.get("props", {})
+ profile = props.get("creator_profile")
+ if (
+ not isinstance(profile, dict)
+ or profile.get("subdomain") != f"{username}.gumroad.com"
+ ):
+ return Result.error("Gumroad profile did not match the requested username")
+
+ reputation = profile.get("reputation") or {}
+ preview = next(
+ (
+ tag.get("content")
+ for tag in props.get("_inertia_meta", [])
+ if tag.get("property") == "og:image"
+ ),
+ None,
+ )
+ links = list(
+ dict.fromkeys(
+ _links(
+ [
+ section.get("text")
+ for section in props.get("sections", [])
+ if section.get("type") == "SellerProfileRichTextSection"
+ ]
+ )
+ )
+ )
+ result = Result.taken(
+ extra={
+ "uid": profile.get("external_id"),
+ "name": profile.get("name"),
+ "bio": props.get("bio"),
+ "twitter_handle": profile.get("twitter_handle"),
+ "verified": profile.get("is_verified"),
+ "rating": reputation.get("average"),
+ "reviews": reputation.get("count"),
+ "products": reputation.get("products_count"),
+ },
+ media={"avatar": profile.get("avatar_url"), "preview": preview},
)
+ if links:
+ cast(dict, result.extra)["links"] = links
+ return result
- url = f"https://{user}.gumroad.com/"
- show_url = f"https://{user}.gumroad.com"
-
- try:
- response = make_request(url, follow_redirects=True)
- if response.status_code == 200:
- html = response.text
- extra = {}
- title = re.search(r'<title>([^\|]+)\|', html)
- if title:
- extra["name"] = title.group(1).strip()
- return Result.taken(extra=extra, url=show_url)
- elif response.status_code == 404:
- return Result.available(url=show_url)
- else:
- return Result.error(f"Unexpected status: {response.status_code}", url=show_url)
- except Exception as e:
- return Result.error(e, url=show_url)
+ return generic_validate(url, process, show_url=url, follow_redirects=True)