Self-hosted OSINT exposure checker — is your email, username, phone or password leaked? Keyless sources: breaches, infostealer logs, COMB credentials, HIBP k-anonymity, 200-platform username grid. Docker one-command install, no API keys, no AI, Apache-2.0.
PHP breach-checkcredential-exposuredata-breachdigital-footprintemail-osintfree-osinthaveibeenpwnedip-reputationleaked-credentialsleaked-dataosintosint-apiosint-toolsphone-lookupprivacy-toolspublic-datapwned-passwordsself-hostedusername-checkusername-osint
<?php
declare(strict_types=1);
namespace App\Modules\Osint\Sources;
/**
* Bot-CIDR context (v1.2.0, S32 — CrawlerScope-inspired bot attribution).
* ============================================================
*
* OFFLINE source: zero HTTP requests. Answers one question for IP checks:
* "is this IP part of an operator-PUBLISHED crawler network range?"
*
* Why it matters (exposure-check context):
* - IN range: traffic from this IP is verifiable crawler traffic
* (Googlebot/Bingbot/Meta/Apple); verify via the documented PTR
* pattern before blocking or reporting it.
* - NOT in range: any user-agent CLAIMING to be those crawlers from
* this IP is spoofed — classic scanner-evasion / scraping signal.
*
* Honesty rules (same as the whole tool):
* - The table is a SNAPSHOT of operator-published prefixes (2026-10).
* A MISS is never proof of "not a crawler" — operators add ranges
* over time. The card says exactly that.
* - IPv6 inputs return a clean "not assessed (IPv4 ranges only)" —
* no silent wrong answers.
*/
class BotCidrSource implements OsintSource
{
/**
* Operator-published crawler prefixes (snapshot 2026-10).
* format: prefix => [operator, kind, ptr_hint]
*/
private const RANGES = [
// Google — publishes the live list at
// developers.google.com/search/apis/ipranges/googlebot.json
'66.249.64.0/19' => ['Google (Googlebot)', 'search_crawler', '*.googlebot.com / *.google.com'],
'64.233.160.0/19' => ['Google (Googlebot)', 'search_crawler', '*.googlebot.com / *.google.com'],
'72.14.192.0/18' => ['Google (Googlebot)', 'search_crawler', '*.googlebot.com / *.google.com'],
'209.85.128.0/17' => ['Google (Googlebot)', 'search_crawler', '*.googlebot.com / *.google.com'],
'216.239.32.0/19' => ['Google (Googlebot)', 'search_crawler', '*.googlebot.com / *.google.com'],
'74.125.0.0/16' => ['Google (Googlebot)', 'search_crawler', '*.googlebot.com / *.google.com'],
// Microsoft — bing.com/toolbox/bingbot.json
'157.55.39.0/24' => ['Microsoft (Bingbot)', 'search_crawler', '*.search.msn.com'],
'40.77.167.0/24' => ['Microsoft (Bingbot)', 'search_crawler', '*.search.msn.com'],
'207.46.12.0/23' => ['Microsoft (Bingbot)', 'search_crawler', '*.search.msn.com'],
// Meta — developers.facebook.com/docs/sharing/webmasters/crawler/
'69.171.224.0/19' => ['Meta (Facebook Crawler)', 'social_crawler', '*.facebook.com / *.tfbnw.net'],
'66.220.144.0/20' => ['Meta (Facebook Crawler)', 'social_crawler', '*.facebook.com / *.tfbnw.net'],
'173.252.64.0/18' => ['Meta (Facebook Crawler)', 'social_crawler', '*.facebook.com / *.tfbnw.net'],
// Apple — developers.apple.com/applebot/
'17.249.0.0/16' => ['Apple (Applebot)', 'ai_crawler', '*.applebot.apple.com / *.apple.com'],
'17.252.57.0/24' => ['Apple (Applebot)', 'ai_crawler', '*.applebot.apple.com / *.apple.com'],
];
public function key(): string
{
return 'botcidr';
}
public function label(): string
{
return 'Bot CIDR Attribution — Crawler Network Check';
}
public function category(): string
{
return 'infra';
}
public function supports(string $type): bool
{
return $type === 'ip';
}
/**
* Offline source: no HTTP requests are ever issued.
*
* @return array<int, array<string, mixed>>
*/
public function requests(string $type, string $identifier): array
{
return [];
}
public function parse(string $type, string $identifier, array $responses): array
{
$ip = trim($identifier);
if (!filter_var($ip, FILTER_VALIDATE_IP, FILTER_FLAG_IPV4)) {
return [
'status' => 'unavailable',
'summary' => 'Bot-CIDR attribution applies to IPv4 addresses only.',
'data' => ['note' => 'IPv6 crawler ranges are not covered by the offline snapshot.'],
'severity' => 'info',
];
}
$hit = $this->lookup($ip);
if ($hit !== null) {
return [
'status' => 'hit',
'summary' => "Verified {$hit['operator']} crawler network range ({$hit['network']}).",
'data' => [
'Operator' => $hit['operator'],
'Published range' => $hit['network'],
'Crawler kind' => $hit['kind'],
'Verify via reverse DNS' => $hit['ptr_hint'],
'What it means' => 'Traffic from this IP is crawler infrastructure. A website HOSTED here is unusual (likely a DNS misconfiguration). Requests FROM this range claiming the operator\'s user-agent are legitimate.',
],
'severity' => 'info',
];
}
return [
'status' => 'clean',
'summary' => 'Not in any operator-published crawler range (Googlebot, Bingbot, Meta, Apple).',
'data' => [
'Checked against' => 'Googlebot, Bingbot, Meta crawler, Applebot published prefixes (offline snapshot 2026-10)',
'What it means' => 'Any user-agent claiming to be those crawlers from this IP is SPOOFED — treat as automated scraping or scanning traffic.',
'Note' => 'Operators add ranges over time; a miss is not absolute proof. Verify surprising traffic via the operator\'s documented reverse-DNS method.',
],
'severity' => 'info',
];
}
/**
* @return null|array{operator: string, network: string, kind: string, ptr_hint: string}
*/
private function lookup(string $ip): ?array
{
$long = ip2long($ip);
if ($long === false) {
return null;
}
foreach (self::RANGES as $prefix => [$operator, $kind, $ptrHint]) {
[$net, $bits] = explode('/', $prefix, 2);
$netLong = ip2long($net);
// RANGES prefixes are all /16-/24, so $bits is always a valid mask length.
if ($netLong === false || !ctype_digit($bits)) {
continue;
}
$mask = (-1 << (32 - (int) $bits)) & 0xFFFFFFFF;
if (($long & $mask) === ($netLong & $mask)) {
return [
'operator' => $operator,
'network' => $prefix,
'kind' => $kind,
'ptr_hint' => $ptrHint,
];
}
}
return null;
}
}