🕵️♂️ (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.
Python cybersecuritycybersecurity-toolsemail-osintethical-hackingethical-hacking-toolsidentificationinfosecosintosint-emailosint-toolosint-toolsosint-usernamepentestingpythonredteam-toolsredteamingthreat-intelligence
feat: add Threadless email and username modules (#647)
Kristo Isbergaaeada966de0
diff --git a/user_scanner/email_scan/creator/threadless.py b/user_scanner/email_scan/creator/threadless.pynew file mode 100644index 0000000..a8c9402--- /dev/null+++ b/user_scanner/email_scan/creator/threadless.py@@ -0,0 +1,55 @@+"""Threadless email registration check via the public Artist Shops signup form."""++import re++from curl_cffi.requests.exceptions import RequestException++from user_scanner.core.impersonate import impersonate_request_async+from user_scanner.core.result import Result++SIGNUP_URL = "https://profile.threadless.com/artist/shops/"+CSRF_RE = re.compile(r"name=['\"]csrfmiddlewaretoken['\"]\s+value=['\"]([^'\"]+)")+++async def validate_threadless(email: str) -> Result:+ """Check Threadless without creating an account or sending email."""+ show_url = "https://www.threadless.com"++ try:+ page = await impersonate_request_async(SIGNUP_URL, allow_redirects=True)+ token = CSRF_RE.search(page.text)+ if page.status_code != 200 or not token:+ return Result.error(+ f"Could not read Threadless signup form (HTTP {page.status_code})",+ url=show_url,+ )++ response = await impersonate_request_async(+ SIGNUP_URL,+ "POST",+ headers={"x-requested-with": "XMLHttpRequest"},+ data={+ "validate": "true",+ "email": email,+ "csrfmiddlewaretoken": token.group(1),+ },+ )+ if response.status_code != 200:+ return Result.error(+ f"Unexpected Threadless response: HTTP {response.status_code}",+ url=show_url,+ )++ except RequestException as exc:+ return Result.error(exc, url=show_url)++ try:+ data = response.json()+ except ValueError:+ return Result.error("Invalid Threadless response", url=show_url)++ if data.get("is_valid") is False:+ return Result.taken(url=show_url)+ if data.get("is_valid") is True:+ return Result.available(url=show_url)+ return Result.error("Unexpected Threadless response", url=show_url)diff --git a/user_scanner/user_scan/creator/threadless.py b/user_scanner/user_scan/creator/threadless.pynew file mode 100644index 0000000..9a274b7--- /dev/null+++ b/user_scanner/user_scan/creator/threadless.py@@ -0,0 +1,140 @@+import html+import re+from urllib.parse import quote, urljoin++from curl_cffi.requests.exceptions import RequestException++from user_scanner.core.impersonate import impersonate_request, impersonate_validate+from user_scanner.core.result import Result++SIGNUP_URL = "https://profile.threadless.com/artist/shops/"+CSRF_RE = re.compile(r"name=['\"]csrfmiddlewaretoken['\"]\s+value=['\"]([^'\"]+)")+++def validate_threadless(user: str) -> Result:+ show_url = f"https://www.threadless.com/@{user}"++ def process(page):+ token = CSRF_RE.search(page.text)+ if page.status_code != 200 or not token:+ return Result.error(+ f"Could not read Threadless signup form (HTTP {page.status_code})"+ )++ response = impersonate_request(+ SIGNUP_URL,+ "POST",+ headers={"x-requested-with": "XMLHttpRequest"},+ data={+ "validate": "true",+ "username": user,+ "csrfmiddlewaretoken": token.group(1),+ },+ )+ if response.status_code != 200:+ return Result.error(+ f"Unexpected Threadless response: HTTP {response.status_code}"+ )++ match response.json():+ case {"is_valid": False}:+ extra, media = _profile(user)+ return Result.taken(extra=extra, media=media)+ case {"is_valid": True}:+ return Result.available()+ case _:+ return Result.error("Unexpected Threadless response")++ return impersonate_validate(+ SIGNUP_URL,+ process,+ show_url=show_url,+ allow_redirects=True,+ )+++def _profile(user: str) -> tuple[dict, dict]:+ try:+ response = impersonate_request(+ f"https://www.threadless.com/@{quote(user, safe='')}",+ allow_redirects=True,+ )+ except RequestException:+ return {}, {}++ if response.status_code != 200:+ return {}, {}++ document = response.text+ username = _text(r'var userName = "([^"]+)"', document)+ if not username or username.casefold() != user.casefold():+ return {}, {}++ shop = _text(r'<div class="artist-shop">(.*?)</div>', document) or ""+ shop_url = _text(r'<a href="([^"]+)" title="Visit my Artist Shop"', shop)+ links = re.findall(+ r'<a href="(https?://[^"]+)" target="_blank" title="[^"]+" rel="nofollow"',+ document,+ )+ website = _text(+ r'<div class="website">(?:(?!</div>).)*?<a href="([^"]+)"', document+ )+ shop_preview = _text(r'<img src="([^"]+)"', shop)+ return (+ {+ "id": _text(r"var profileId = (\d+);", document),+ "name": _text(r'<span class="name">\s*([^<]+)', document),+ "bio": _text(r'<div class="cover-statement">\s*<p>(.*?)</p>', document),+ "location": _text(+ r'<div class="location">\s*<h3>Location</h3>\s*([^<]+)', document+ ),+ "following": _text(r'/following"[^>]*>\s*<span>(\d+)</span>', document),+ "followers": _text(r'/followers"[^>]*>\s*<span>(\d+)</span>', document),+ "member_since": _text(r"Member since ([^<]+)", document),+ "artist_shop": urljoin("https://www.threadless.com", shop_url)+ if shop_url+ else None,+ "artist_shop_slug": _text(r'var artistSlug = "([^"]+)";', document),+ "artist_shop_name": _text(+ r'title="Visit my Artist Shop"[^>]*>\s*([^<]+)</a>',+ shop,+ ),+ "website": website,+ "links": ", ".join(map(html.unescape, links)),+ "threads_started": _number(r"([\d,]+) threads started", document),+ "designs_submitted": _number(r"([\d,]+) designs submitted", document),+ "designs_scored": _number(r"([\d,]+) designs scored", document),+ "avg_score_given": _text(r"Avg Score Given:\s*([\d.]+)", document),+ "is_printed_artist": _flag("isPrintedArtist", document),+ "is_submitted_artist": _flag("isSubmittedArtist", document),+ "is_shop_owner": _flag("isShopOwner", document),+ "facebook_connected": _flag("fbConnected", document),+ "is_hifiver": _flag("isHifiver", document),+ "is_shop_published": _flag("isShopPublished", document),+ "open_submissions": _flag("openSubs", document),+ "is_alumni": "is-alumni" in document,+ },+ {+ "avatar": _text(r'<meta property="og:image" content="([^"]+)"', document),+ "cover": _text(+ r'<header id="header" style="background-image: url\([\'\"]([^\'\"]+)',+ document,+ ),+ "artist_shop_preview": shop_preview,+ },+ )+++def _text(pattern: str, document: str) -> str | None:+ match = re.search(pattern, document, re.DOTALL)+ return html.unescape(match.group(1)).strip() if match else None+++def _number(pattern: str, document: str) -> int | None:+ value = _text(pattern, document)+ return int(value.replace(",", "")) if value else None+++def _flag(name: str, document: str) -> bool | None:+ value = _text(rf"var {name} = (true|false);", document)+ return value == "true" if value else Nonediff --git a/user_scanner/user_scan/creator/threadless_shop.py b/user_scanner/user_scan/creator/threadless_shop.pynew file mode 100644index 0000000..43dd943--- /dev/null+++ b/user_scanner/user_scan/creator/threadless_shop.py@@ -0,0 +1,182 @@+import html+import re++from curl_cffi.requests.exceptions import RequestException++from user_scanner.core.impersonate import impersonate_request, impersonate_validate+from user_scanner.core.result import Result++SIGNUP_URL = "https://profile.threadless.com/artist/shops/"+CSRF_RE = re.compile(r"name=['\"]csrfmiddlewaretoken['\"]\s+value=['\"]([^'\"]+)")+++def validate_threadless_shop(user: str) -> Result:+ shop = user.lower()+ show_url = f"https://{shop}.threadless.com/"+ if not re.fullmatch(r"[a-z0-9]{1,63}", shop):+ return Result.error(+ "Shop name must contain only lowercase letters and numbers",+ url=show_url,+ )++ def process(page):+ token = CSRF_RE.search(page.text)+ if page.status_code != 200 or not token:+ return Result.error(+ f"Could not read Threadless signup form (HTTP {page.status_code})"+ )++ response = impersonate_request(+ SIGNUP_URL,+ "POST",+ headers={"x-requested-with": "XMLHttpRequest"},+ data={+ "validate": "true",+ "shop_name": shop,+ "csrfmiddlewaretoken": token.group(1),+ },+ )+ if response.status_code != 200:+ return Result.error(+ f"Unexpected Threadless response: HTTP {response.status_code}"+ )++ match response.json():+ case {"is_valid": True}:+ return Result.available()+ case {"is_valid": False}:+ profile = _shop_profile(shop)+ if profile:+ extra, media = profile+ return Result.taken(extra=extra, media=media)+ return Result.error(+ "Shop name is unavailable but no public shop was found"+ )+ case _:+ return Result.error("Unexpected Threadless response")++ return impersonate_validate(+ SIGNUP_URL,+ process,+ show_url=show_url,+ allow_redirects=True,+ )+++def _shop_profile(shop: str) -> tuple[dict, dict] | None:+ try:+ response = impersonate_request(+ f"https://{shop}.threadless.com/", allow_redirects=True+ )+ except RequestException:+ return None++ if response.status_code != 200:+ return None++ document = response.text+ brand = _text(r'data-artist-brand="([^"]+)"', document)+ if not brand or brand.casefold() != shop.casefold():+ return None++ about = ""+ try:+ about_response = impersonate_request(+ f"https://{shop}.threadless.com/about", allow_redirects=True+ )+ if about_response.status_code == 200:+ about_brand = _text(r'data-artist-brand="([^"]+)"', about_response.text)+ if about_brand and about_brand.casefold() == shop.casefold():+ about = about_response.text+ except RequestException:+ pass++ social_links = []+ website = None+ for url, kind in re.findall(+ r'<a class="aboutSocial-cta" href="([^"]+)".*?'+ r'<em class="aboutSocial-title">\s*([^<]+)',+ about,+ re.DOTALL,+ ):+ url, kind = html.unescape(url), kind.strip().lower()+ if kind == "website":+ website = url+ else:+ social_links.append(f"{kind}: {url}")++ title = _text(r'<meta property="og:title"\s+content="([^"]+)"', document)+ name = title.split(" | ", 1)[0].removesuffix("'s Artist Shop") if title else None+ return (+ {+ "name": name,+ "description": _text(+ r'<meta property="og:description"\s+content="([^"]+)"',+ document,+ ),+ "owner_id": _number(r'data-to-follow="(\d+)"', document)+ or _number(r'data-shop-user-id="(\d+)"', document),+ "owner_name": _text(+ r'<strong class="aboutProfile-title">(.*?)</strong>', about+ ),+ "location": _text(r'<p class="aboutProfile-subtitle">(.*?)</p>', about),+ "headline": _clean(+ r'<h2 class="(?=[^"]*\baboutTitle\b)'+ r'(?![^"]*\b_is-hidden\b)[^"]*">(.*?)</h2>',+ about,+ ),+ "biography": _clean(r'<div class="aboutContent-bio">(.*?)</div>', about),+ "website": website,+ "social_links": ", ".join(social_links),+ "search_enabled": _has_link("search", document),+ "gift_cards_enabled": _has_link("gift-cards", document),+ "wholesale_enabled": _has_link("wholesale", document),+ "self_reported_shop_profiles": ", ".join(+ _clean_text(badge)+ for badge in re.findall(r'<div class="badge-title">\s*([^<]+)', about)+ ),+ },+ {+ "logo": _text(r'<img src="([^"]+)" alt="A logo image for', document),+ "cover": _text(+ r'<link rel="preload" media="\(min-width: 651px\)" href="([^"]+)"',+ document,+ ),+ "preview": _text(+ r'<meta property="og:image"\s+content="([^"]+)"', document+ ),+ "bio_photo": _text(+ r'<img class="aboutProfile aboutProfile--img" src="([^"]+)"',+ about,+ ),+ },+ )+++def _text(pattern: str, document: str) -> str | None:+ match = re.search(pattern, document, re.DOTALL)+ return html.unescape(match.group(1)).strip() if match else None+++def _number(pattern: str, document: str) -> int | None:+ value = _text(pattern, document)+ return int(value) if value else None+++def _has_link(path: str, document: str) -> bool:+ return bool(+ re.search(+ rf'<a\b[^>]*\bhref="(?:https?://[^/"]+)?/{re.escape(path)}/?'+ r'(?:\?[^"]*)?"',+ document,+ )+ )+++def _clean(pattern: str, document: str) -> str | None:+ value = _text(pattern, document)+ return _clean_text(value) if value else None+++def _clean_text(value: str) -> str:+ return " ".join(html.unescape(re.sub(r"<[^>]+>", " ", value)).split())