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.

feature: add new dating category for username modules, add 5 Estonian dating site modules (#621)

Kristo Isberg68491a130b4e
diff --git a/user_scanner/user_scan/adult/iha.py b/user_scanner/user_scan/adult/iha.py
new file mode 100644
index 0000000..2aea155
--- /dev/null
+++ b/user_scanner/user_scan/adult/iha.py
@@ -0,0 +1,135 @@
+import html
+import re
+from urllib.parse import quote
+
+import httpx
+
+from user_scanner.core.orchestrator import generic_validate
+from user_scanner.core.result import Result
+
+FIELD_NAMES = {
+ "Konto tĂĽĂĽp": "account_type",
+ "Nimi": "name",
+ "SĂĽnniaeg": "birth_date",
+ "Riik": "country",
+ "Elukoht": "location",
+ "Kodulinn": "hometown",
+ "Kasv": "height_cm",
+ "Kaal": "weight_kg",
+ "Kehaehitus": "body_type",
+ "Juuste värv": "hair_color",
+ "Silmade värv": "eye_color",
+ "Orientatsioon": "orientation",
+ "Soovin tutvuda": "looking_for",
+ "Soovitud vanus": "desired_age",
+ "Tutvumise eesmärk": "intent",
+ "Mina (me) oleme": "relationship_status",
+ "Kas sa oled abielus?": "marital_status",
+ "Kas sul on lapsi?": "children",
+ "Keeled": "languages",
+ "Haridus": "education",
+ "Kool/Ülikool kus õppisin": "school",
+ "Hobid": "hobbies",
+ "Avalik e-maili aadress": "public_email",
+ "Kas sa suitsetad?": "smoking",
+ "Suhe alkoholi": "alcohol",
+ "Suhe narkootikumidesse": "drug_use",
+ "Sissetulek": "income",
+ "Minu roll seksis": "sexual_role",
+ "Kui tihti soovin seksida": "sexual_frequency",
+ "Mind erutab": "turn_ons",
+ "Kas sulle meeldib masturbeerida": "masturbation",
+ "BDSM": "bdsm",
+ "Liiklusvahend": "vehicle",
+ "Mind jahutab maha": "turn_offs",
+ "Muusika, mis meeldib": "favorite_music",
+ "Minu magamistoast leiad": "bedroom_items",
+ "Mis muudab minu jaoks seksi kvaliteetseks?": "sexual_preferences",
+ "Lemmikraamat": "favorite_book",
+ "Lemmikfilm": "favorite_movie",
+ "Ametikoht": "occupation",
+ "Minu ettekujutus ideaalsest esimesest kohtingust": "ideal_first_date",
+ "Mida õppisin oma viimasest suhtest": "relationship_lessons",
+}
+
+
+def validate_iha(user: str) -> Result:
+ username = user.strip()
+ url = f"https://www.iha.ee/users/{quote(username, safe='')}"
+
+ def process(response: httpx.Response) -> Result:
+ if response.status_code != 200:
+ return Result.error(f"Unexpected response status: {response.status_code}")
+
+ match = re.search(
+ r'<div class="member_username"[^>]*>\s*([^<]+)', response.text
+ )
+ if match:
+ profile_user = html.unescape(match.group(1)).strip()
+ if profile_user.casefold() != username.casefold():
+ return Result.error(
+ "Profile response does not match the requested handle"
+ )
+ user_id = re.search(r'<form[^>]+(?:name|id)="_(\d+)"', response.text)
+ extra = _fields(response.text)
+ if user_id:
+ extra["user_id"] = int(user_id.group(1))
+ return Result.taken(
+ extra=extra,
+ media=_media(response.text, user_id.group(1) if user_id else None),
+ )
+
+ if re.search(
+ r"<title>\s*Iha\.ee - Seksikate inimeste kohtumispaik\s*</title>",
+ response.text,
+ ) and (
+ 'id="online_list"' in response.text
+ or "Sellist kasutajat ei leitud" in response.text
+ ):
+ return Result.available()
+
+ return Result.error("Could not verify profile page")
+
+ return generic_validate(url, process, show_url=url)
+
+
+def _fields(page: str) -> dict[str, object]:
+ pairs = re.findall(
+ r'<div class="member_form_opt1">\s*<div[^>]*>(.*?)</div>\s*</div>\s*'
+ r'<div class="member_form_opt2">\s*<div[^>]*>(.*?)</div>\s*</div>',
+ page,
+ re.DOTALL,
+ )
+ fields: dict[str, object] = {}
+ for raw_label, raw_value in pairs:
+ label = _text(raw_label)
+ value = _text(raw_value)
+ if label not in FIELD_NAMES or not value:
+ continue
+ field = FIELD_NAMES[label]
+ if field == "birth_date":
+ value = re.sub(r"\s+\(\d+\)$", "", value)
+ fields[field] = value
+ return fields
+
+
+def _media(page: str, user_id: str | None) -> dict[str, str]:
+ if not user_id:
+ return {}
+ photos = list(
+ dict.fromkeys(
+ html.unescape(url)
+ for url in re.findall(r"https://img2\.iha\.ee/[^\"'? )]+", page)
+ if f"/{user_id}e" in url
+ )
+ )
+ if not photos:
+ return {}
+ return {
+ "avatar": photos[0],
+ **{f"photo_{index}": url for index, url in enumerate(photos[1:], 1)},
+ }
+
+
+def _text(value: str) -> str:
+ return re.sub(r"\s+", " ", html.unescape(re.sub(r"<[^>]+>", " ", value))).strip()
diff --git a/user_scanner/user_scan/dating/__init__.py b/user_scanner/user_scan/dating/__init__.py
new file mode 100644
index 0000000..8b13789
--- /dev/null
+++ b/user_scanner/user_scan/dating/__init__.py
@@ -0,0 +1 @@
+
diff --git a/user_scanner/user_scan/dating/amoremi.py b/user_scanner/user_scan/dating/amoremi.py
new file mode 100644
index 0000000..8490c6a
--- /dev/null
+++ b/user_scanner/user_scan/dating/amoremi.py
@@ -0,0 +1,75 @@
+import html
+import re
+from urllib.parse import quote
+
+import httpx
+
+from user_scanner.core.orchestrator import generic_validate
+from user_scanner.core.result import Result
+
+GENDERS = {"mehega": "male", "naisega": "female"}
+
+
+def validate_amoremi(user: str) -> Result:
+ username = user.strip()
+ url = f"https://www.amoremi.ee/user/{quote(username, safe='')}"
+
+ def process(response: httpx.Response) -> Result:
+ if response.status_code == 404 and (
+ "<title>LehekĂĽlge ei leitud</title>" in response.text
+ or f'Kasutajat nimega "{html.escape(username)}" ei eksisteeri.'
+ in response.text
+ ):
+ return Result.available()
+ if response.status_code != 200:
+ return Result.error(f"Unexpected response status: {response.status_code}")
+
+ match = re.search(
+ r'<div class="profile-title text-center">\s*'
+ r'<div class=(?:"page-title"|page-title)>\s*([^<]+)',
+ response.text,
+ )
+ if not match:
+ return Result.error("Could not verify profile page")
+
+ profile_user = html.unescape(match.group(1)).strip()
+ if profile_user.casefold() != username.casefold():
+ return Result.error("Profile response does not match the requested handle")
+
+ extra: dict[str, object] = {}
+ breadcrumb = re.search(
+ r'<li class="breadcrumb-item active">\s*[^<]*?\s+(\d+)\s+a\.',
+ response.text,
+ )
+ if breadcrumb:
+ extra["age"] = int(breadcrumb.group(1))
+ if profile_type := re.search(
+ r'<a href="/tutvus/([^"/]+)">\s*([^<]+)</a>', response.text
+ ):
+ extra["profile_type"] = html.unescape(profile_type.group(2)).strip()
+ if profile_gender := GENDERS.get(profile_type.group(1)):
+ extra["gender"] = profile_gender
+ if description := re.search(
+ r"<div class=profile-description>.*?"
+ r'<div class="short-desc">(.*?)</div>',
+ response.text,
+ re.DOTALL,
+ ):
+ extra["bio"] = _text(description.group(1))
+ if seeking := re.search(
+ r"Tutvun\s+(mehega|naisega)\s+(\d+)-(\d+)\s+a\.", response.text
+ ):
+ extra["looking_for"] = GENDERS[seeking.group(1)]
+ extra["desired_age"] = f"{seeking.group(2)}-{seeking.group(3)}"
+ if title := re.search(r"<title>(.*?)</title>", response.text, re.DOTALL):
+ extra["headline"] = (
+ html.unescape(title.group(1)).strip().removesuffix(f" - {profile_user}")
+ )
+
+ return Result.taken(extra=extra)
+
+ return generic_validate(url, process, show_url=url)
+
+
+def _text(value: str) -> str:
+ return re.sub(r"\s+", " ", html.unescape(re.sub(r"<[^>]+>", " ", value))).strip()
diff --git a/user_scanner/user_scan/dating/neanky.py b/user_scanner/user_scan/dating/neanky.py
new file mode 100644
index 0000000..68041bc
--- /dev/null
+++ b/user_scanner/user_scan/dating/neanky.py
@@ -0,0 +1,95 @@
+import html
+import re
+from urllib.parse import quote, urljoin
+
+import httpx
+
+from user_scanner.core.orchestrator import generic_validate, make_request
+from user_scanner.core.result import Result
+
+
+def validate_neanky(user: str) -> Result:
+ username = user.strip()
+ url = f"https://neanky.ee/user/{quote(username, safe='')}"
+
+ def process_profile(response: httpx.Response) -> Result:
+ if (
+ response.status_code == 404
+ and "<title>Kasutajat ei leitud | Neanky" in response.text
+ ):
+ return Result.available()
+ if response.status_code != 200:
+ return Result.error(f"Unexpected response status: {response.status_code}")
+
+ if pending := re.search(
+ r"Soovitud kasutaja ei ole hetkel veel aktiveeritud!<br>\s*"
+ r"Konto registreeritud:\s*([^<]+)<br>",
+ response.text,
+ ):
+ return Result.taken(
+ extra={
+ "account_status": "pending_activation",
+ "registered_at": pending.group(1).strip(),
+ }
+ )
+
+ match = re.search(
+ r'<h1 class="u-box-name-txt-b text-white">(.*?)</h1>',
+ response.text,
+ re.DOTALL,
+ )
+ if not match:
+ return Result.taken()
+
+ profile_user = _text(match.group(1))
+ if profile_user.casefold() != username.casefold():
+ return Result.error("Profile response does not match the requested handle")
+
+ extra: dict[str, object] = {}
+ if name := re.search(r"Nimi:\s*<strong>(.*?)</strong>", response.text):
+ extra["name"] = _text(name.group(1))
+ if gender := re.search(r"Sugu:\s*<img[^>]*>\s*([^<]+)<br", response.text):
+ extra["gender"] = html.unescape(gender.group(1)).strip()
+ if user_id := re.search(r'\bvar vsID="(\d+)"', response.text):
+ extra["user_id"] = int(user_id.group(1))
+ if online_status := re.search(
+ r'<span[^>]+title="(online|offline)"', match.group(1)
+ ):
+ extra["online_status"] = online_status.group(1)
+ media: dict[str, str] = {}
+ avatar = re.search(
+ r"u-box-avatar-Pic[^>]+background-image:url\([\'\"]?([^\'\")]+)",
+ response.text,
+ )
+ if avatar and not avatar.group(1).endswith("/images/avatar.svg"):
+ media["avatar"] = urljoin("https://neanky.ee", avatar.group(1))
+ return Result.taken(extra=extra, media=media)
+
+ def process_availability(response: httpx.Response) -> Result:
+ if response.status_code != 200:
+ return Result.error(f"Unexpected response status: {response.status_code}")
+ data = response.json()
+ if data.get("user", {}).get("username", "").casefold() != username.casefold():
+ return Result.error(
+ "Availability response does not match the requested handle"
+ )
+ if data.get("state") == 1:
+ return Result.available()
+ if data.get("state") != 0:
+ return Result.error("Could not verify username availability")
+ try:
+ return process_profile(make_request(url))
+ except httpx.HTTPError as exc:
+ return Result.error(exc)
+
+ return generic_validate(
+ "https://neanky.ee/p/register",
+ process_availability,
+ method="POST",
+ data={"username": username, "type": "validateusername"},
+ show_url=url,
+ )
+
+
+def _text(value: str) -> str:
+ return re.sub(r"\s+", " ", html.unescape(re.sub(r"<[^>]+>", " ", value))).strip()
diff --git a/user_scanner/user_scan/dating/svenvaher.py b/user_scanner/user_scan/dating/svenvaher.py
new file mode 100644
index 0000000..c3382e1
--- /dev/null
+++ b/user_scanner/user_scan/dating/svenvaher.py
@@ -0,0 +1,148 @@
+import html
+import re
+from urllib.parse import quote
+
+import httpx
+
+from user_scanner.core.orchestrator import generic_validate
+from user_scanner.core.result import Result
+
+PROFILE_FIELDS = {
+ "Orientatsioon": "orientation",
+ "Pikkus cm": "height_cm",
+ "Kaal kg": "weight_kg",
+ "Turvaline seks?": "safe_sex",
+ "Otsin": "looking_for",
+ "Vanusevahemikus": "desired_age",
+ "Avalik e-mail": "public_email",
+}
+
+
+def validate_svenvaher(user: str) -> Result:
+ username = user.strip()
+ url = f"https://svenvaher.ee/{quote(username, safe='')}"
+
+ def process(response: httpx.Response) -> Result:
+ if (
+ response.status_code == 403
+ and "<title>Attention Required! | Cloudflare</title>" in response.text
+ and "Sorry, you have been blocked" in response.text
+ ):
+ return Result.error("Blocked by SvenVaher Cloudflare security")
+ if (
+ response.status_code == 404
+ and "<title>404 Ei leitud</title>" in response.text
+ ):
+ return Result.available()
+ if response.status_code != 200:
+ return Result.error(f"Unexpected response status: {response.status_code}")
+
+ match = re.search(
+ r'<div class="profile-name-wrapper">\s*<a[^>]*>(.*?)</a>',
+ response.text,
+ re.DOTALL,
+ )
+ if not match:
+ return Result.error("Could not verify profile page")
+
+ profile_user = _text(match.group(1))
+ if profile_user.casefold() != username.casefold():
+ return Result.error("Profile response does not match the requested handle")
+
+ extra = _about(response.text)
+
+ stat_names = {"Postitused": "posts", "Fotod": "photos", "Videod": "videos"}
+ for count, label in re.findall(
+ r"(\d+)\s+(Postitused|Fotod|Videod)", response.text
+ ):
+ extra[stat_names[label]] = int(count)
+
+ avatar = re.search(
+ r'<div class="profile-avatar-wrapper">\s*'
+ r'<img[^>]+\bdata-image="([^"]+)"',
+ response.text,
+ )
+ media: dict[str, str] = {}
+ if avatar:
+ media["avatar"] = html.unescape(avatar.group(1))
+ if cover := re.search(
+ r'<div class="profile-cover-wrapper">.*?'
+ r'<img class="js_position-cover-full[^"]*" src="([^"]+)"',
+ response.text,
+ re.DOTALL,
+ ):
+ media["cover"] = html.unescape(cover.group(1))
+ return Result.taken(extra=extra, media=media)
+
+ return generic_validate(url, process, show_url=url)
+
+
+def _about(page: str) -> dict[str, object]:
+ extra: dict[str, object] = {}
+ if bio := re.search(
+ r'<div class="about-bio">.*?'
+ r'<div class="js_readmore[^"]*">(.*?)</div>',
+ page,
+ re.DOTALL,
+ ):
+ extra["bio"] = _text(bio.group(1))
+
+ about = re.search(r'<ul class="about-list">(.*?)</ul>', page, re.DOTALL)
+ if about:
+ items = re.findall(
+ r'<div class="about-list-item">(.*?)</div>\s*</li>',
+ about.group(1),
+ re.DOTALL,
+ )
+ relationships = {
+ "Ăśksik",
+ "Suhtes",
+ "Abielus",
+ "See on keeruline",
+ "Lahus",
+ "Lahutatud",
+ "Lesk",
+ }
+ for raw_item in items:
+ item = _text(raw_item)
+ if item.startswith("Elab "):
+ extra["location"] = item.removeprefix("Elab ")
+ elif item.startswith("Pärit "):
+ extra["hometown"] = item.removeprefix("Pärit ")
+ elif item in {"Mees", "Naine", "Muu"}:
+ extra["gender"] = item
+ elif item in relationships:
+ extra["relationship_status"] = item
+ elif birth_date := re.fullmatch(r"(\d{2})/(\d{2})/(\d{4})", item):
+ extra["birth_date"] = "-".join(reversed(birth_date.groups()))
+ elif followers := re.fullmatch(r"Jälgib\s+(\d+)\s+inimes(?:t|ed)", item):
+ extra["followers"] = int(followers.group(1))
+
+ for raw_label, raw_value in re.findall(
+ r"<li>\s*<strong>(.*?)</strong><br>(.*?)</li>", page, re.DOTALL
+ ):
+ field = PROFILE_FIELDS.get(_text(raw_label))
+ if not field:
+ continue
+ if field == "public_email":
+ if protected := re.search(r'data-cfemail="([0-9a-f]+)"', raw_value):
+ extra[field] = _decode_cfemail(protected.group(1))
+ elif value := _text(raw_value):
+ extra[field] = value
+
+ if pronouns := re.search(
+ r'class="profile-pronouns[^"]*">\s*\((.*?)\)\s*</span>', page
+ ):
+ extra["pronouns"] = _text(pronouns.group(1))
+ if 'class="verified-badge"' in page:
+ extra["verified"] = True
+ return extra
+
+
+def _text(value: str) -> str:
+ return re.sub(r"\s+", " ", html.unescape(re.sub(r"<[^>]+>", " ", value))).strip()
+
+
+def _decode_cfemail(value: str) -> str:
+ key = int(value[:2], 16)
+ return bytes(byte ^ key for byte in bytes.fromhex(value[2:])).decode()
diff --git a/user_scanner/user_scan/social/tinder.py b/user_scanner/user_scan/dating/tinder.py
similarity index 100%
rename from user_scanner/user_scan/social/tinder.py
rename to user_scanner/user_scan/dating/tinder.py
diff --git a/user_scanner/user_scan/dating/tutvused.py b/user_scanner/user_scan/dating/tutvused.py
new file mode 100644
index 0000000..7233229
--- /dev/null
+++ b/user_scanner/user_scan/dating/tutvused.py
@@ -0,0 +1,106 @@
+import html
+import re
+from urllib.parse import quote, unquote, urlsplit
+
+import httpx
+
+from user_scanner.core.orchestrator import generic_validate
+from user_scanner.core.result import Result
+
+
+def validate_tutvused(user: str) -> Result:
+ username = user.strip()
+ url = f"https://tutvused.net/vendor/{quote(username, safe='')}/"
+
+ def process(response: httpx.Response) -> Result:
+ if (
+ "<title>One moment, please...</title>" in response.text
+ and "Please wait while your request is being verified..." in response.text
+ ):
+ return Result.error("Blocked by Tutvused bot challenge")
+ if (
+ response.status_code == 404
+ and "<title>Page not found - Tutvused</title>" in response.text
+ ):
+ return Result.available()
+ if response.status_code != 200:
+ return Result.error(f"Unexpected response status: {response.status_code}")
+
+ canonical = re.search(
+ r"https://tutvused\.net/vendor/([^/\"'?]+)/", response.text
+ )
+ profile = re.search(
+ r'<aside[^>]+class="[^"]*hp-vendor--view-page[^"]*".*?</aside>',
+ response.text,
+ re.DOTALL,
+ )
+ if not canonical or not profile:
+ return Result.error("Could not verify profile page")
+ if unquote(canonical.group(1)).casefold() != username.casefold():
+ return Result.error("Profile response does not match the requested handle")
+
+ extra: dict[str, object] = {}
+ listing_count = len(
+ re.findall(r'<article class="[^"]*hp-listing--view-block', response.text)
+ )
+ if listing_count:
+ extra["listing_count"] = listing_count
+ if name := re.search(
+ r'<h3 class="hp-vendor__name">.*?<span>(.*?)</span>\s*</h3>',
+ response.text,
+ re.DOTALL,
+ ):
+ extra["name"] = _text(name.group(1))
+ if joined := re.search(
+ r'<time class="[^"]*hp-vendor__registered-date[^"]*"\s+'
+ r'datetime="([^"]+)"',
+ response.text,
+ ):
+ extra["joined"] = joined.group(1)
+ if description := re.search(
+ r'<div class="hp-vendor__description">(.*?)</div>',
+ response.text,
+ re.DOTALL,
+ ):
+ extra["bio"] = _text(description.group(1))
+ if last_seen := re.search(
+ r'class="hp-vendor__online-badge[^"]*"\s+title="Last seen ([^"]+)"',
+ response.text,
+ ):
+ extra["last_seen"] = html.unescape(last_seen.group(1)).strip()
+ if links := _external_links(profile.group(0)):
+ extra["links"] = links
+
+ avatar = re.search(
+ r'<div class="hp-vendor__image">\s*<img[^>]+src="([^"]+)"',
+ response.text,
+ )
+ media = (
+ {"avatar": html.unescape(avatar.group(1))}
+ if avatar and "/placeholders/" not in avatar.group(1)
+ else {}
+ )
+ return Result.taken(extra=extra, media=media)
+
+ return generic_validate(url, process, show_url=url)
+
+
+def _external_links(profile: str) -> list[str]:
+ links: list[str] = []
+ for raw_url in re.findall(r'<a[^>]+href=["\']([^"\']+)', profile):
+ url = html.unescape(raw_url).strip()
+ parsed = urlsplit(url)
+ host = (parsed.hostname or "").removeprefix("www.")
+ if parsed.scheme not in {"http", "https", "mailto", "tel"}:
+ continue
+ if parsed.scheme in {"http", "https"} and (
+ host == "tutvused.net" or host.endswith(".tutvused.net")
+ ):
+ continue
+ if url not in links:
+ links.append(url)
+ return links
+
+
+def _text(value: str) -> str:
+ return re.sub(r"\s+", " ", html.unescape(re.sub(r"<[^>]+>", " ", value))).strip()