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.

Merge pull request #580 from kaifcodec/feat/add-3-new-username-scan-modules

Kaif46686c3b91dc
diff --git a/user_scanner/user_scan/community/hive_blog.py b/user_scanner/user_scan/community/hive_blog.py
new file mode 100644
index 0000000..258b896
--- /dev/null
+++ b/user_scanner/user_scan/community/hive_blog.py
@@ -0,0 +1,72 @@
+import json
+import re
+from user_scanner.core.orchestrator import generic_validate
+from user_scanner.core.result import Result
+
+
+def validate_hive_blog(user: str) -> Result:
+ """Validate a username on Hive Blog (hive.blog)."""
+ url = f"https://hive.blog/@{user}"
+ show_url = f"https://hive.blog/@{user}"
+ headers = {
+ "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
+ }
+
+ def process(response):
+ response_text_lower = response.text.lower()
+
+ # 1. Explicit check for available / not-found state (HTTP 404 or explicit title marker)
+ if response.status_code == 404 or "user not found - hive" in response_text_lower or "user not found" in response_text_lower:
+ return Result.available(url=show_url)
+
+ # 2. Explicit verification of 200 OK + site marker
+ if response.status_code == 200 and "hive" in response_text_lower:
+ script_match = re.search(
+ r'<script[^>]*>(\{"community":[\s\S]+?)</script>',
+ response.text,
+ )
+ if script_match:
+ try:
+ data = json.loads(script_match.group(1))
+ profiles = data.get("userProfiles", {}).get("profiles", {})
+ user_key = user.lower()
+
+ if user_key in profiles and isinstance(profiles[user_key], dict):
+ user_info = profiles[user_key]
+ metadata = user_info.get("metadata", {}).get("profile", {})
+ stats = user_info.get("stats", {})
+
+ extra = {}
+ media = {}
+ if name := metadata.get("name"):
+ if str(name).strip():
+ extra["name"] = str(name).strip()
+ if about := metadata.get("about"):
+ if str(about).strip():
+ extra["about"] = str(about).strip()
+ if website := metadata.get("website"):
+ if str(website).strip():
+ extra["website"] = str(website).strip()
+ if location := metadata.get("location"):
+ if str(location).strip():
+ extra["location"] = str(location).strip()
+ if avatar := metadata.get("profile_image"):
+ if str(avatar).strip():
+ media["avatar"] = str(avatar).strip()
+
+ if followers := stats.get("followers"):
+ extra["followers"] = str(followers)
+ if following := stats.get("following"):
+ extra["following"] = str(following)
+ if post_count := user_info.get("post_count"):
+ extra["post_count"] = str(post_count)
+
+ return Result.taken(extra=extra, media=media, url=show_url)
+ except Exception:
+ return Result.error("Failed to parse userProfiles JSON on Hive Blog", url=show_url)
+ return Result.error("Could not find userProfiles script tag on Hive Blog", url=show_url)
+
+ # 3. Graceful error for unexpected status codes (No bare else!)
+ return Result.error(f"Unexpected response status: {response.status_code}", url=show_url)
+
+ return generic_validate(url, process, headers=headers, show_url=show_url, follow_redirects=True)
diff --git a/user_scanner/user_scan/creator/bio_site.py b/user_scanner/user_scan/creator/bio_site.py
new file mode 100644
index 0000000..46f1a18
--- /dev/null
+++ b/user_scanner/user_scan/creator/bio_site.py
@@ -0,0 +1,53 @@
+import json
+import re
+from user_scanner.core.orchestrator import generic_validate
+from user_scanner.core.result import Result
+
+
+def validate_bio_site(user: str) -> Result:
+ """Validate a username on Bio Site (bio.site)."""
+ url = f"https://bio.site/{user}"
+ show_url = f"https://bio.site/{user}"
+ headers = {
+ "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
+ }
+
+ def process(response):
+ response_text_lower = response.text.lower()
+
+ # 1. Explicit verification of available / not-found state (HTTP 404 or explicit text marker)
+ if response.status_code == 404 or "this bio site doesn’t exist" in response_text_lower or "this bio site doesn't exist" in response_text_lower:
+ return Result.available(url=show_url)
+
+ # 2. Explicit verification of taken state + deep data extraction
+ if response.status_code == 200 and "bio.site" in response_text_lower:
+ state_match = re.search(
+ r"window\.initial_state=({[\s\S]+?});\s*window\.additional",
+ response.text,
+ )
+ if state_match:
+ try:
+ state_data = json.loads(state_match.group(1))
+ metadata = state_data.get("metadata", {})
+ header = state_data.get("header", {})
+
+ handle = metadata.get("handle")
+ if handle and str(handle).lower() == user.lower():
+ extra = {}
+ media = {}
+ if name := header.get("name"):
+ extra["name"] = str(name).strip()
+ if bio := header.get("bio"):
+ extra["bio"] = str(bio).strip()
+ if photo := (header.get("profilePhoto") or header.get("profile_photo")):
+ media["avatar"] = str(photo).strip()
+
+ return Result.taken(extra=extra, media=media, url=show_url)
+ except Exception:
+ return Result.error("Failed to parse initial_state JSON on Bio Site", url=show_url)
+ return Result.error("Could not find profile initial_state on Bio Site", url=show_url)
+
+ # 3. Graceful error for unexpected status codes or unhandled states (No bare else!)
+ return Result.error(f"Unexpected response status: {response.status_code}", url=show_url)
+
+ return generic_validate(url, process, headers=headers, show_url=show_url, follow_redirects=True)
diff --git a/user_scanner/user_scan/dev/cssbattle.py b/user_scanner/user_scan/dev/cssbattle.py
new file mode 100644
index 0000000..29c0c0a
--- /dev/null
+++ b/user_scanner/user_scan/dev/cssbattle.py
@@ -0,0 +1,56 @@
+import json
+import re
+from user_scanner.core.orchestrator import generic_validate
+from user_scanner.core.result import Result
+
+
+def validate_cssbattle(user: str) -> Result:
+ """Validate a username on CSSBattle (cssbattle.dev)."""
+ url = f"https://cssbattle.dev/player/{user}"
+ show_url = f"https://cssbattle.dev/player/{user}"
+ headers = {
+ "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
+ }
+
+ def process(response):
+ # 1. Explicit check for 404
+ if response.status_code == 404:
+ return Result.available(url=show_url)
+
+ # 2. Explicit verification of 200 OK + site marker
+ if response.status_code == 200 and "cssbattle" in response.text.lower():
+ next_data_match = re.search(
+ r'<script id="__NEXT_DATA__" type="application/json">([\s\S]+?)</script>',
+ response.text,
+ )
+ if next_data_match:
+ try:
+ data = json.loads(next_data_match.group(1))
+ page_props = data.get("props", {}).get("pageProps", {})
+ player = page_props.get("player")
+
+ # CSSBattle returns 200 with player: null in __NEXT_DATA__ payload for nonexistent players
+ if player is None:
+ return Result.available(url=show_url)
+
+ if isinstance(player, dict):
+ extra = {}
+ media = {}
+ if name := player.get("displayName"):
+ if str(name).strip() and str(name).lower() != "user":
+ extra["name"] = str(name).strip()
+ if username := player.get("username"):
+ extra["username"] = str(username).strip()
+ if avatar := player.get("avatar"):
+ if str(avatar).strip():
+ media["avatar"] = str(avatar).strip()
+
+ return Result.taken(extra=extra, media=media, url=show_url)
+ except Exception:
+ return Result.error("Failed to parse __NEXT_DATA__ JSON on CSSBattle", url=show_url)
+ return Result.error("Could not find __NEXT_DATA__ script tag on CSSBattle", url=show_url)
+
+ # 3. Graceful error for unexpected status codes (No bare else!)
+ return Result.error(f"Unexpected response status: {response.status_code}", url=show_url)
+
+ return generic_validate(url, process, headers=headers, show_url=show_url, follow_redirects=True)