π΅οΈββοΈ (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.
Python cybersecuritycybersecurity-toolsemail-osintethical-hackingethical-hacking-toolsidentificationinfosecosintosint-emailosint-toolosint-toolsosint-usernamepentestingpythonredteam-toolsredteamingthreat-intelligence
Merge pull request #542 from brunolm/fix/user-facebook
BrunoLM031800912db5
diff --git a/user_scanner/user_scan/social/facebook.py b/user_scanner/user_scan/social/facebook.pyindex 6975754..2b5ab80 100644--- a/user_scanner/user_scan/social/facebook.py+++ b/user_scanner/user_scan/social/facebook.py@@ -1,66 +1,87 @@+import htmlimport re-from urllib.error import HTTPError, URLError-from urllib.request import Request, urlopen+from user_scanner.core.impersonate import impersonate_validatefrom user_scanner.core.result import Result-PROFILE_TITLE_RE = re.compile(r'<meta property="og:title" content="[^"]+"')+PROFILE_TITLE_RE = re.compile(r'<meta property="og:title" content="([^"]+)"')PROFILE_URL_RE = re.compile(- r'<meta property="og:url" content="https://www\.facebook\.com/[^"]+"'+ r'<meta property="og:url" content="(https://www\.facebook\.com/[^"]+)"')-UNAVAILABLE_MARKER = "This content isn't available at the moment"+DESCRIPTION_RE = re.compile(r'<meta property="og:description" content="([^"]*)"')+COUNTS_RE = re.compile(+ r"^.*?\.\s*(?P<likes>[\d,.]+) likes"+ r"(?:\s*·\s*(?P<talking>[\d,.]+) talking about this)?\.\s*(?P<bio>.*)$",+ re.DOTALL,+)+# Facebook ships this error in two wordings ("at the moment" / "right now"),+# embedded in JSON where the apostrophe is backslash-escaped.+UNAVAILABLE_RE = re.compile(r"This content isn\\?'t available")+++def validate_facebook(user: str) -> Result:+ if not (1 <= len(user) <= 50):+ return Result.error("Length must be 1-50 characters")++ if not re.match(r"^[a-zA-Z0-9.]+$", user):+ return Result.error("Only letters, numbers and periods allowed")++ if user.isdigit():+ return Result.error("Username cannot be numbers only")-def _process_profile_response(status_code: int, html: str) -> Result:+ if user.startswith(".") or user.endswith("."):+ return Result.error("Username cannot start or end with a period")++ show_url = f"https://www.facebook.com/{user}"++ def process(response):+ return _process_profile_response(response.status_code, response.text)++ # A handle in non-canonical casing 302s to its canonical form; a miss does not.+ return impersonate_validate(show_url, process, show_url=show_url, allow_redirects=True)+++def _process_profile_response(status_code: int, body: str) -> Result:if status_code == 429:return Result.error("Rate limited by Facebook")if status_code >= 500:return Result.error(f"Facebook returned HTTP {status_code}")- has_profile_markers = bool(- PROFILE_TITLE_RE.search(html) and PROFILE_URL_RE.search(html)- )- has_unavailable_marker = UNAVAILABLE_MARKER in html+ title = PROFILE_TITLE_RE.search(body)+ canonical = PROFILE_URL_RE.search(body)+ has_unavailable_marker = bool(UNAVAILABLE_RE.search(body))- if has_profile_markers and not has_unavailable_marker:- return Result.taken()+ if title and canonical and not has_unavailable_marker:+ return Result.taken(extra=_extract(title.group(1), canonical.group(1), body))- if has_unavailable_marker and not has_profile_markers:+ if has_unavailable_marker and not (title and canonical):return Result.available()return Result.error("Unexpected response body, report it via GitHub issues.")-def validate_facebook(user: str) -> Result:- if not (1 <= len(user) <= 50):- return Result.error("Length must be 1-50 characters")+def _extract(title: str, canonical: str, body: str) -> dict:+ extra = {"name": html.unescape(title).strip()}- if not re.match(r"^[a-zA-Z0-9.]+$", user):- return Result.error("Only letters, numbers and periods allowed")+ # The canonical URL carries the handle's real casing, which the requested+ # one does not β Facebook resolves handles case-insensitively.+ handle = canonical.rsplit("/", 1)[-1]+ if handle:+ extra["handle"] = handle- if user.isdigit():- return Result.error("Username cannot be numbers only")+ description = DESCRIPTION_RE.search(body)+ if not description:+ return extra- if user.startswith(".") or user.endswith("."):- return Result.error("Username cannot start or end with a period")+ counts = COUNTS_RE.match(description.group(1))+ if not counts:+ return extra- show_url = f"https://www.facebook.com/{user}"- headers = {- "User-Agent": "Mozilla/5.0",- "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",- "Accept-Language": "en-US,en;q=0.9",- }-- request = Request(show_url, headers=headers)-- try:- with urlopen(request, timeout=8.0) as response:- html = response.read().decode("utf-8", "ignore")- return _process_profile_response(response.status, html).update(url=show_url)- except HTTPError as exc:- html = exc.read().decode("utf-8", "ignore")- return _process_profile_response(exc.code, html).update(url=show_url)- except URLError as exc:- return Result.error(exc, url=show_url)- except Exception as exc:- return Result.error(exc, url=show_url)+ extra["likes"] = counts.group("likes")+ if talking := counts.group("talking"):+ extra["talking_about"] = talking+ if bio := html.unescape(counts.group("bio")).strip():+ extra["bio"] = bio++ return extra