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(unsplash): resolve users through the site's profile API

Bruno Leonardo Michels7326363cf977
diff --git a/user_scanner/user_scan/creator/unsplash.py b/user_scanner/user_scan/creator/unsplash.py
index ba14146..b0bca2c 100644
--- a/user_scanner/user_scan/creator/unsplash.py
+++ b/user_scanner/user_scan/creator/unsplash.py
@@ -1,39 +1,99 @@
-import re
-import html
-import httpx
+import json
+
+from user_scanner.core.impersonate import impersonate_request, impersonate_validate
from user_scanner.core.result import Result
-from user_scanner.core.orchestrator import make_request
-def validate_unsplash(username: str) -> Result:
- """Validate a username on Unsplash."""
- url = f"https://unsplash.com/@{username}"
- show_url = f"https://unsplash.com/@{username}"
-
+BASE_URL = "https://unsplash.com"
+# The site's own profile API. It answers with the full user object for a real
+# handle and a distinct not-found payload otherwise, unlike the profile page,
+# which is client-rendered and identical either way.
+API_URL = f"{BASE_URL}/napi/users"
+NOT_FOUND_MARKER = "Couldn't find User"
+
+FIELDS = {
+ "name": "name",
+ "id": "id",
+ "numeric_id": "numeric_id",
+ "bio": "bio",
+ "location": "location",
+ "portfolio_url": "portfolio",
+ "instagram_username": "instagram",
+ "twitter_username": "twitter",
+}
+COUNTS = {
+ "total_photos": "photos",
+ "total_illustrations": "illustrations",
+ "total_collections": "collections",
+ "total_likes": "likes",
+}
+
+
+def validate_unsplash(user: str) -> Result:
+ show_url = f"{BASE_URL}/@{user}"
+
+ def process(response) -> Result:
+ if response.status_code == 404 and NOT_FOUND_MARKER in response.text:
+ return Result.available()
+ if response.status_code != 200:
+ return Result.error(f"Unexpected response status: {response.status_code}")
+
+ try:
+ profile = json.loads(response.text)
+ except json.JSONDecodeError:
+ return Result.error("Malformed JSON response, report it on Github")
+
+ if str(profile.get("username", "")).lower() != user.lower():
+ return Result.error("Profile payload does not match the requested handle")
+
+ return Result.taken(extra=_extract_profile(profile), media=_extract_media(profile))
+
+ return impersonate_validate(
+ f"{API_URL}/{user}", process, show_url=show_url, allow_redirects=True)
+
+
+def _extract_profile(profile: dict) -> dict:
+ extra: dict[str, str | bool | int] = {}
+
+ for field, label in FIELDS.items():
+ value = profile.get(field)
+ if value in (None, ""):
+ continue
+ extra[label] = value if isinstance(value, (bool, int)) else str(value).strip()
+
+ for field, label in COUNTS.items():
+ value = profile.get(field)
+ if isinstance(value, int):
+ extra[label] = value
+
+ badge = profile.get("badge") or {}
+ if badge.get("title"):
+ extra["badge"] = badge["title"]
+
+ if profile.get("for_hire"):
+ extra["for_hire"] = True
+
+ downloads = _total_downloads(profile["username"])
+ if downloads is not None:
+ extra["downloads"] = downloads
+
+ return extra
+
+
+def _total_downloads(user: str) -> int | None:
+ """The user object carries a `downloads` key that is 0 for every account;
+ the real lifetime figure only comes from the statistics endpoint."""
try:
- # We pass headers={} to use httpx's default user-agent,
- # as Unsplash blocks/redirects the default browser user-agent.
- response = make_request(url, headers={}, follow_redirects=True)
- response_text = response.text
-
- # Verify status code 200 AND check unique Unsplash strings in the response body to prevent false positives
- if response.status_code == 200 and "unsplash" in response_text.lower() and "page not found" not in response_text.lower():
- extra = {}
- title_match = re.search(r"<title>(.*?)</title>", response_text, re.IGNORECASE)
- if title_match:
- title = html.unescape(title_match.group(1).strip())
- title_clean = title.split(" | ")[0]
- match = re.search(r"^(.*?)\s*\((?:@" + re.escape(username) + r")\)", title_clean, re.IGNORECASE)
- if match:
- name = match.group(1).strip()
- name = re.sub(r"'\s*s (?:Collections|Photos|Likes|Stats)$", "", name, flags=re.IGNORECASE)
- name = re.sub(r"'\''s (?:Collections|Photos|Likes|Stats)$", "", name, flags=re.IGNORECASE)
- extra["name"] = name
- return Result.taken(extra=extra, url=show_url)
- elif response.status_code == 404 or "page not found" in response_text.lower():
- return Result.available(url=show_url)
- else:
- return Result.error(f"Unexpected status: {response.status_code}", url=show_url)
- except httpx.TimeoutException:
- return Result.skipped("Connection timed out")
- except Exception as e:
- return Result.error(e, url=show_url)
+ response = impersonate_request(
+ f"{API_URL}/{user}/statistics", allow_redirects=True)
+ if response.status_code != 200:
+ return None
+ total = json.loads(response.text).get("downloads", {}).get("total")
+ except Exception:
+ return None
+ return total if isinstance(total, int) else None
+
+
+def _extract_media(profile: dict) -> dict:
+ images = profile.get("profile_image") or {}
+ avatar = images.get("large") or images.get("medium") or images.get("small")
+ return {"avatar": avatar} if avatar else {}