Skip to content

πŸ•΅οΈβ€β™‚οΈ (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(bdsmlr): resolve blogs through the site API

Bruno Leonardo Michels77d4b9103e6e
diff --git a/user_scanner/user_scan/adult/bdsmlr.py b/user_scanner/user_scan/adult/bdsmlr.py
index 4ece7ce..57f1695 100644
--- a/user_scanner/user_scan/adult/bdsmlr.py
+++ b/user_scanner/user_scan/adult/bdsmlr.py
@@ -1,52 +1,72 @@
-import re
-from user_scanner.core.orchestrator import generic_validate, Result
+import json
+
+from user_scanner.core.orchestrator import generic_validate
+from user_scanner.core.result import Result
+
+# bdsmlr.com is a client-rendered SPA: every /blog/<name> URL serves the same
+# empty shell, so only this backend call distinguishes a real blog. It is
+# POST-only β€” a GET answers 404 regardless of the handle.
+API_URL = "https://api-prod.bdsmlr.com/v2/api/get-blog"
+
+EMPTY_DESCRIPTIONS = ("", "no description")
def validate_bdsmlr(user):
- user = user.replace(".", "")
- url = f"https://{user}.bdsmlr.com"
- show_url = f"https://{user}.bdsmlr.com"
+ show_url = f"https://bdsmlr.com/blog/{user}"
def process(response):
- if response.status_code == 200 and "login" in response.text:
- extra = {}
- media = {}
-
- # Extract blog title
- title_match = re.search(
- r"<title>(.*?)</title>", response.text, re.IGNORECASE)
- if title_match:
- title_val = title_match.group(1).strip()
- if title_val.lower() != "no title":
- extra["fullname"] = title_val
- else:
- extra["fullname"] = user.capitalize()
-
- # Extract avatar image (if not default)
- image_match = re.search(
- r'<meta\s+property="og:image"\s+content="([^"]+)"', response.text, re.IGNORECASE)
- if image_match and "default_avatar" not in image_match.group(1):
- media["image"] = image_match.group(1).strip()
-
- # Extract description
- desc_match = re.search(
- r'<meta\s+property="og:description"\s+content="([^"]+)"', response.text, re.IGNORECASE)
- if desc_match:
- desc_val = desc_match.group(1).strip()
- if desc_val.lower() != "no description":
- extra["bio"] = desc_val
-
- # Extract blog ID
- blog_id_match = re.search(
- r'/followersblogs/(\d+)', response.text, re.IGNORECASE)
- if blog_id_match:
- extra["blog_id"] = blog_id_match.group(1)
-
- return Result.taken(extra=extra, media=media, url=show_url)
-
- if "This blog doesn't exist." in response.text or response.status_code == 404:
+ try:
+ data = response.json()
+ except ValueError:
+ return Result.error(f"Unexpected response body (HTTP {response.status_code})", url=show_url)
+
+ error = data.get("error")
+
+ blog = data.get("blog")
+ if isinstance(blog, dict) and blog.get("name"):
+ return Result.taken(extra=_extra(blog), media=_media(blog), url=show_url)
+
+ if error == "blog not found":
return Result.available(url=show_url)
- return Result.error(f"Unexpected response code/body: {response.status_code}", url=show_url)
+ # "blog gone" is a deleted blog: the name is neither free nor backed by
+ # a profile, so it must not become a verdict.
+ return Result.error(error or f"Unexpected response body (HTTP {response.status_code})", url=show_url)
+
+ return generic_validate(
+ API_URL,
+ process,
+ show_url=show_url,
+ method="POST",
+ headers={"Content-Type": "application/json", "Accept": "application/json"},
+ content=json.dumps({"blog_name": user}),
+ )
+
+
+def _extra(blog: dict) -> dict:
+ # A renamed blog still resolves under its old handle, so the canonical name
+ # is reported to make that visible rather than silently labelling the
+ # requested handle with another blog's metadata.
+ extra = {
+ "username": blog.get("name"),
+ "blog_id": blog.get("id"),
+ "owner_user_id": blog.get("ownerUserId"),
+ "fullname": blog.get("title"),
+ "posts": blog.get("postsCount"),
+ "followers": blog.get("followersCount"),
+ }
+
+ description = blog.get("description") or ""
+ if description.strip().lower() not in EMPTY_DESCRIPTIONS:
+ extra["bio"] = description
+
+ labels = (blog.get("personals") or {}).get("labels")
+ if labels:
+ extra["personals"] = ", ".join(sorted(labels))
+
+ return extra
+
- return generic_validate(url, process, show_url=show_url)
+def _media(blog: dict) -> dict:
+ # Both URLs are signed and expire; they are reported as-is.
+ return {"avatar": blog.get("avatarUrl") or "", "cover": blog.get("coverUrl") or ""}