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(user_scan): update albicla, threads, tumblr, codepen, linuxquimper, bucket and retire dead modules (#707)

Kaif3518f8430219
diff --git a/user_scanner/user_scan/dev/bitquery.py b/abandoned/user_scan/dev/bitquery.py
similarity index 100%
rename from user_scanner/user_scan/dev/bitquery.py
rename to abandoned/user_scan/dev/bitquery.py
diff --git a/user_scanner/user_scan/dev/gumloop.py b/abandoned/user_scan/dev/gumloop.py
similarity index 100%
rename from user_scanner/user_scan/dev/gumloop.py
rename to abandoned/user_scan/dev/gumloop.py
diff --git a/user_scanner/user_scan/dev/rhasspy.py b/abandoned/user_scan/dev/rhasspy.py
similarity index 100%
rename from user_scanner/user_scan/dev/rhasspy.py
rename to abandoned/user_scan/dev/rhasspy.py
diff --git a/user_scanner/user_scan/dev/strapi.py b/abandoned/user_scan/dev/strapi.py
similarity index 100%
rename from user_scanner/user_scan/dev/strapi.py
rename to abandoned/user_scan/dev/strapi.py
diff --git a/user_scanner/user_scan/social/lemmy_metapowers_org.py b/abandoned/user_scan/social/lemmy_metapowers_org.py
similarity index 100%
rename from user_scanner/user_scan/social/lemmy_metapowers_org.py
rename to abandoned/user_scan/social/lemmy_metapowers_org.py
diff --git a/user_scanner/user_scan/dev/bucket.py b/user_scanner/user_scan/dev/bucket.py
index 1a02f76..1b9f994 100644
--- a/user_scanner/user_scan/dev/bucket.py
+++ b/user_scanner/user_scan/dev/bucket.py
@@ -1,6 +1,5 @@
import urllib.parse
-from user_scanner.core.helpers import get_random_user_agent
from user_scanner.core.orchestrator import Result, generic_validate
@@ -9,7 +8,7 @@ def validate_bucket(user: str) -> Result:
url = "https://bucket.miraheze.org/w/api.php"
show_url = f"https://bucket.miraheze.org/wiki/User:{encoded_user}"
headers = {
- "User-Agent": get_random_user_agent(),
+ "User-Agent": "user-scanner/1.0",
"Accept": "application/json",
}
params = {
diff --git a/user_scanner/user_scan/dev/casiohacking.py b/user_scanner/user_scan/dev/casiohacking.py
index 91f5160..0949f42 100644
--- a/user_scanner/user_scan/dev/casiohacking.py
+++ b/user_scanner/user_scan/dev/casiohacking.py
@@ -1,6 +1,5 @@
import urllib.parse
-from user_scanner.core.helpers import get_random_user_agent
from user_scanner.core.orchestrator import Result, generic_validate
@@ -9,7 +8,7 @@ def validate_casiohacking(user: str) -> Result:
url = "https://casiohacking.miraheze.org/w/api.php"
show_url = f"https://casiohacking.miraheze.org/wiki/User:{encoded_user}"
headers = {
- "User-Agent": get_random_user_agent(),
+ "User-Agent": "user-scanner/1.0",
"Accept": "application/json",
}
params = {
diff --git a/user_scanner/user_scan/dev/codepen.py b/user_scanner/user_scan/dev/codepen.py
index c2e9bb7..a4d84e7 100644
--- a/user_scanner/user_scan/dev/codepen.py
+++ b/user_scanner/user_scan/dev/codepen.py
@@ -2,7 +2,7 @@ import html
import re
from urllib.parse import quote
-from user_scanner.core.orchestrator import generic_validate, make_request
+from user_scanner.core.impersonate import impersonate_request, impersonate_validate
from user_scanner.core.result import Result
@@ -49,7 +49,7 @@ def _enrichment(
return extra, {}
try:
- response = make_request(
+ response = impersonate_request(
"https://codepen.io/graphql",
method="POST",
headers={"referer": profile_url, "x-csrf-token": csrf_token},
@@ -100,4 +100,4 @@ def validate_codepen(user: str) -> Result:
extra, media = _enrichment(user, document, url)
return Result.taken(extra=extra, media=media)
- return generic_validate(url, process, show_url=url, follow_redirects=True)
+ return impersonate_validate(url, process, show_url=url, allow_redirects=True)
diff --git a/user_scanner/user_scan/dev/codepenteams.py b/user_scanner/user_scan/dev/codepenteams.py
index 3eb205b..cbf7d73 100644
--- a/user_scanner/user_scan/dev/codepenteams.py
+++ b/user_scanner/user_scan/dev/codepenteams.py
@@ -2,7 +2,7 @@ import html
import re
from urllib.parse import quote
-from user_scanner.core.orchestrator import generic_validate, make_request
+from user_scanner.core.impersonate import impersonate_request, impersonate_validate
from user_scanner.core.result import Result
@@ -49,7 +49,7 @@ def _enrichment(
return extra, {}
try:
- response = make_request(
+ response = impersonate_request(
"https://codepen.io/graphql",
method="POST",
headers={"referer": profile_url, "x-csrf-token": csrf_token},
@@ -100,4 +100,4 @@ def validate_codepenteams(user: str) -> Result:
extra, media = _enrichment(user, document, url)
return Result.taken(extra=extra, media=media)
- return generic_validate(url, process, show_url=url, follow_redirects=True)
+ return impersonate_validate(url, process, show_url=url, allow_redirects=True)
diff --git a/user_scanner/user_scan/dev/linuxquimper.py b/user_scanner/user_scan/dev/linuxquimper.py
index b48c02a..ea0b5b2 100644
--- a/user_scanner/user_scan/dev/linuxquimper.py
+++ b/user_scanner/user_scan/dev/linuxquimper.py
@@ -1,6 +1,5 @@
import urllib.parse
-from user_scanner.core.helpers import get_random_user_agent
from user_scanner.core.orchestrator import Result, generic_validate
@@ -9,7 +8,7 @@ def validate_linuxquimper(user: str) -> Result:
url = f"https://forum.linuxquimper.org/u/{encoded_user}.json"
show_url = f"https://forum.linuxquimper.org/u/{encoded_user}"
headers = {
- "User-Agent": get_random_user_agent(),
+ "User-Agent": "user-scanner/1.0",
"Accept": "application/json",
}
diff --git a/user_scanner/user_scan/social/albicla.py b/user_scanner/user_scan/social/albicla.py
index 6ca6e1f..52a2f8d 100644
--- a/user_scanner/user_scan/social/albicla.py
+++ b/user_scanner/user_scan/social/albicla.py
@@ -1,9 +1,14 @@
+import re
+
from user_scanner.core.helpers import get_random_user_agent
from user_scanner.core.orchestrator import Result, generic_validate
-def validate_albicla(user):
- url = f"https://albicla.com/{user}/post/1"
+def validate_albicla(user: str) -> Result:
+ if not re.fullmatch(r"[A-Za-z0-9_.-]{1,50}", user):
+ return Result.error("Invalid username format")
+
+ url = f"https://albicla.com/{user}"
show_url = f"https://albicla.com/{user}"
headers = {
@@ -11,15 +16,17 @@ def validate_albicla(user):
}
def process(response):
- if (
- response.status_code == 500
- or "500 Post tymczasowo niedostępny" in response.text
+ if response.status_code == 404 and (
+ "nie ma takiej strony" in response.text.lower()
):
- return Result.taken()
-
- if "404 Nie znaleziono użytkownika" in response.text:
return Result.available()
+ if response.status_code == 200 and (
+ "document.location.href='/login'" in response.text
+ or 'document.location.href="/login"' in response.text
+ ):
+ return Result.taken()
+
return Result.error(f"Unexpected status: {response.status_code}")
- return generic_validate(url, process, show_url=show_url, headers=headers)
+ return generic_validate(url, process, show_url=show_url, headers=headers, follow_redirects=False)
diff --git a/user_scanner/user_scan/social/threads.py b/user_scanner/user_scan/social/threads.py
index 3b93c7c..404cf96 100644
--- a/user_scanner/user_scan/social/threads.py
+++ b/user_scanner/user_scan/social/threads.py
@@ -1,22 +1,77 @@
-from user_scanner.core.helpers import get_random_user_agent
-from user_scanner.core.orchestrator import status_validate
-
-
-def validate_threads(user):
- url = "https://www.threads.net/api/v1/users/web_profile_info/"
- show_url = f"https://www.threads.net/@{user}"
-
- headers = {
- "User-Agent": get_random_user_agent(),
- "X-IG-App-ID": "936619743392459",
- "Accept": "application/json, text/javascript, */*; q=0.01",
- "Accept-Encoding": "gzip, deflate, br",
- "Accept-Language": "en-US,en;q=0.9",
- "X-Requested-With": "XMLHttpRequest",
- "Referer": f"https://www.threads.net/@{user}",
- }
-
- return status_validate(
- url, 404, 200, show_url=show_url, headers=headers, http2=True,
- params={"username": user},
- )
+from html import unescape
+import re
+
+from user_scanner.core.impersonate import impersonate_validate
+from user_scanner.core.result import Result
+
+
+def validate_threads(user: str) -> Result:
+ if not (1 <= len(user) <= 30):
+ return Result.error("Length must be between 1 and 30 characters")
+
+ if not re.fullmatch(r"[A-Za-z0-9._]+", user):
+ return Result.error("Threads usernames can only use letters, numbers, underscores, and periods")
+
+ url = f"https://www.threads.net/@{user}"
+
+ def process(response) -> Result:
+ if response.status_code != 200:
+ return Result.error(f"Unexpected status: {response.status_code}")
+
+ og_title_match = re.search(r'<meta[^>]*property="og:title"[^>]*content="([^"]*)"', response.text)
+ title_tag_match = re.search(r"<title[^>]*>(.*?)</title>", response.text, re.IGNORECASE)
+ title_text = unescape(
+ og_title_match.group(1) if og_title_match else (title_tag_match.group(1) if title_tag_match else "")
+ ).strip()
+
+ # Non-existent handles render the Threads login landing page
+ if any(marker in title_text for marker in ("Threads • Log in", "Threads \u2022 Log in", "Log in \u2022 Threads")):
+ return Result.available()
+
+ if f"@{user.lower()}" in title_text.lower():
+ extra, media = _extract_threads(response.text, user)
+ return Result.taken(extra=extra, media=media)
+
+ return Result.error("Unexpected response title format")
+
+ return impersonate_validate(url, process, show_url=url, allow_redirects=True)
+
+
+def _extract_threads(html: str, user: str) -> tuple[dict, dict]:
+ extra: dict[str, str] = {}
+ media: dict[str, str] = {}
+
+ og_title = re.search(r'<meta[^>]*property="og:title"[^>]*content="([^"]*)"', html)
+ if og_title:
+ title_text = unescape(og_title.group(1)).strip()
+ m = re.search(r"^(.*?)\s*\(@([A-Za-z0-9._]+)\)", title_text)
+ if m:
+ name = m.group(1).strip()
+ if name and name.lower() != user.lower():
+ extra["name"] = name
+
+ og_desc = re.search(r'<meta[^>]*property="og:description"[^>]*content="([^"]*)"', html)
+ if og_desc:
+ desc_text = unescape(og_desc.group(1)).strip()
+ desc_text = re.sub(
+ r"\s*See the latest conversations with\s+@[A-Za-z0-9._]+\.?\s*$", "", desc_text, flags=re.IGNORECASE
+ ).strip()
+ parts = [p.strip() for p in desc_text.split(" • ") if p.strip()]
+ bio_parts = []
+ for part in parts:
+ if re.search(r"^\d+[\d.,]*[KMkm]?\s+Followers?$", part, re.IGNORECASE):
+ extra["followers"] = part.split()[0]
+ elif re.search(r"^\d+[\d.,]*[KMkm]?\s+Threads?$", part, re.IGNORECASE):
+ extra["threads"] = part.split()[0]
+ else:
+ bio_parts.append(part)
+ if bio_parts:
+ extra["bio"] = " • ".join(bio_parts)
+
+ og_img = re.search(r'<meta[^>]*property="og:image"[^>]*content="([^"]*)"', html)
+ if og_img:
+ img_url = unescape(og_img.group(1)).strip()
+ if img_url and not any(k in img_url for k in ("rsrc.php", "kHwIMM5b8PW")):
+ media["avatar"] = img_url
+
+ return extra, media
diff --git a/user_scanner/user_scan/social/tumblr.py b/user_scanner/user_scan/social/tumblr.py
index 3971aa9..076592b 100644
--- a/user_scanner/user_scan/social/tumblr.py
+++ b/user_scanner/user_scan/social/tumblr.py
@@ -74,6 +74,29 @@ def _find_blog(html: str, user: str) -> dict | None:
The page carries sibling blog objects for recommendation rails, so the
first match is not necessarily the requested one.
"""
+ # 1. Primary modern method: parse ___INITIAL_STATE___
+ m = re.search(r'<script[^>]*id="___INITIAL_STATE___"[^>]*>(.*?)</script>', html, re.DOTALL)
+ if m:
+ try:
+ state = json.loads(m.group(1))
+ for q in state.get("queries", {}).get("queries", []):
+ qkey = q.get("queryKey")
+ if isinstance(qkey, list) and len(qkey) >= 2 and qkey[0] == "blog-info":
+ if str(qkey[1]).lower() == user.lower():
+ blog_data = q.get("state", {}).get("data")
+ if isinstance(blog_data, dict):
+ return blog_data
+
+ objects = state.get("PeeprRoute", {}).get("initialTimeline", {}).get("objects", [])
+ for obj in objects:
+ if isinstance(obj, dict):
+ blog = obj.get("blog")
+ if isinstance(blog, dict) and blog.get("name", "").lower() == user.lower():
+ return blog
+ except Exception:
+ pass
+
+ # 2. Fallback to scanning for "blog": markers
decoder = json.JSONDecoder()
index = html.find(BLOG_MARKER)
while index != -1: