BadBotBlocker::__construct() - Code Metrics - Inspection of "Merge changes from 2.2" - fisharebest/webtrees - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — 2.1 ( cc4763...230ed5 )

by Greg

created 2025-03-09 17:44 UTC

BadBotBlocker::__construct() A

↳ Parent: BadBotBlocker

Complexity

Conditions	1
Paths	1

Size

Total Lines	3
Code Lines	1

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	1
eloc	1
c	0
b	0
f	0
nc	1
nop	1
dl	0
loc	3
rs	10

<?php

/**
 * webtrees: online genealogy
 * Copyright (C) 2025 webtrees development team
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation, either version 3 of the License, or
 * (at your option) any later version.
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
 * GNU General Public License for more details.
 * You should have received a copy of the GNU General Public License
 * along with this program. If not, see <https://www.gnu.org/licenses/>.
 */

declare(strict_types=1);

namespace Fisharebest\Webtrees\Http\Middleware;

use Fig\Http\Message\StatusCodeInterface;
use Fisharebest\Webtrees\Registry;
use Fisharebest\Webtrees\Services\NetworkService;
use Fisharebest\Webtrees\Validator;
use IPLib\Address\AddressInterface;
use IPLib\Factory;
use IPLib\Range\RangeInterface;
use Psr\Http\Message\ResponseInterface;
use Psr\Http\Message\ServerRequestInterface;
use Psr\Http\Server\MiddlewareInterface;
use Psr\Http\Server\RequestHandlerInterface;

use function array_filter;
use function array_map;
use function assert;
use function gethostbyaddr;
use function gethostbyname;
use function preg_match_all;
use function random_int;
use function response;
use function str_contains;
use function str_ends_with;

/**
 * Middleware to block bad robots before they waste our valuable CPU cycles.
 */
class BadBotBlocker implements MiddlewareInterface
{
    // Cache whois requests.  Try to avoid all caches expiring at the same time.
    private const WHOIS_TTL_MIN = 28 * 86400;
    private const WHOIS_TTL_MAX = 35 * 86400;

    /**
     * @see https://github.com/ai-robots-txt/ai.robots.txt for a list of AI crawlers.
     * We can't load this repository as a dependency as it's not a package.
     * Instead, the list from version 1.26 is copied here.
     */
    public const AI_ROBOTS = [
         'AI2Bot',
         'Ai2Bot-Dolma',
         'Amazonbot',
         'anthropic-ai',
         'Applebot',
         'Applebot-Extended',
         'Brightbot 1.0',
         'Bytespider',
         'CCBot',
         'ChatGPT-User',
         'Claude-Web',
         'ClaudeBot',
         'cohere-ai',
         'cohere-training-data-crawler',
         'Crawlspace',
         'Diffbot',
         'DuckAssistBot',
         'FacebookBot',
         'FriendlyCrawler',
         'Google-Extended',
         'GoogleOther',
         'GoogleOther-Image',
         'GoogleOther-Video',
         'GPTBot',
         'iaskspider/2.0',
         'ICC-Crawler',
         'ImagesiftBot',
         'img2dataset',
         'ISSCyberRiskCrawler',
         'Kangaroo Bot',
         'Meta-ExternalAgent',
         'Meta-ExternalFetcher',
         'OAI-SearchBot',
         'omgili',
         'omgilibot',
         'PanguBot',
         'PerplexityBot',
         'PetalBot',
         'Scrapy',
         'SemrushBot-OCOB',
         'SemrushBot-SWA',
         'Sidetrade indexer bot',
         'Timpibot',
         'VelenPublicWebCrawler',
         'Webzio-Extended',
         'YouBot',
    ];

    // Other bad robots - SEO optimisers, advertisers, etc.  This list is shared with robots.txt.
    public const BAD_ROBOTS = [
        'admantx',
        'Adsbot',
        'AhrefsBot',
        'AntBot', // Aggressive crawler
        'AspiegelBot',
        'Awario', // Brand management
        'Barkrowler', // Crawler for babbar.tech
        'BLEXBot',
        'CensysInspect', // Vulnerability scanner
        'DataForSeoBot', // https://dataforseo.com/dataforseo-bot
        'DotBot',
        'Expanse', // Another pointless crawler
        'fidget-spinner-bot', // Agressive crawler
        'Foregenix', // Vulnerability scanner
        'Go-http-client', // Crawler library used by many bots
        'Grapeshot',
        'Honolulu-bot', // Aggressive crawer, no info available
        'ia_archiver',
        'internet-measurement', // Driftnet
        'IonCrawl',
        'Java', // Crawler library used by many bots
        'linabot', // Aggressive crawer, no info available
        'Linguee',
        'MegaIndex.ru',
        'MJ12bot',
        'netEstate NE',
        'panscient',
        'phxbot', // Badly written crawler
        'proximic',
        'python-requests', // Crawler library used by many bots
        'SeekportBot', // Pretends to be a search engine - but isn't
        'SemrushBot',
        'serpstatbot',
        'SEOkicks',
        'SiteKiosk',
        'test-bot', // Agressive crawler
        'TinyTestBot',
        'Turnitin',
        'wp_is_mobile', // Nothing to do with wordpress
        'XoviBot',
        'YisouSpider',
        'ZoominfoBot',
    ];

    /**
     * Some search engines use reverse/forward DNS to verify the IP address.
     *
     * @see https://support.google.com/webmasters/answer/80553?hl=en
     * @see https://www.bing.com/webmaster/help/which-crawlers-does-bing-use-8c184ec0
     * @see https://www.bing.com/webmaster/help/how-to-verify-bingbot-3905dc26
     * @see https://yandex.com/support/webmaster/robot-workings/check-yandex-robots.html
     * @see https://www.mojeek.com/bot.html
     */
    private const ROBOT_REV_FWD_DNS = [
        'BingPreview'      => ['.search.msn.com'],
        'Google'           => ['.google.com', '.googlebot.com'],
        'Mail.RU_Bot'      => ['.mail.ru'],
        'MicrosoftPreview' => ['.search.msn.com'],
        'MojeekBot'        => ['.mojeek.com'],
        'Qwantify'         => ['.qwant.com'],
        'Sogou'            => ['.crawl.sogou.com'],
        'Yahoo'            => ['.crawl.yahoo.net'],
        'Yandex'           => ['.yandex.ru', '.yandex.net', '.yandex.com'],
        'bingbot'          => ['.search.msn.com'],
        'msnbot'           => ['.search.msn.com'],
    ];

    /**
     * Some search engines only use reverse DNS to verify the IP address.
     *
     * @see https://help.baidu.com/question?prod_id=99&class=0&id=3001
     * @see https://napoveda.seznam.cz/en/full-text-search/seznambot-crawler
     * @see https://www.ionos.de/terms-gtc/faq-crawler
     */
    private const ROBOT_REV_ONLY_DNS = [
        'Baiduspider' => ['.baidu.com', '.baidu.jp'],
        'FreshBot'    => ['.seznam.cz'],
        'Neevabot'    => ['.neeva.com'],
        'SeznamBot'   => ['.seznam.cz'],
    ];

    /**
     * Some search engines operate from designated IP addresses.
     *
     * @see https://help.duckduckgo.com/duckduckgo-help-pages/results/duckduckbot
     */
    private const ROBOT_IPS = [
        'DuckDuckBot' => [
            '23.21.227.69',
            '50.16.241.113',
            '50.16.241.114',
            '50.16.241.117',
            '50.16.247.234',
            '52.204.97.54',
            '52.5.190.19',
            '54.197.234.188',
            '54.208.100.253',
            '54.208.102.37',
            '107.21.1.8',
        ],
    ];

    /**
     * Some search engines operate from within a designated autonomous system.
     *
     * @see https://developers.facebook.com/docs/sharing/webmasters/crawler
     * @see https://www.facebook.com/peering/
     */
    private const ROBOT_ASNS = [
        'facebook' => ['AS32934'],
        'twitter'  => ['AS13414'],
    ];

    private NetworkService $network_service;

    public function __construct(NetworkService $network_service)
    {
        $this->network_service = $network_service;
    }

    public function process(ServerRequestInterface $request, RequestHandlerInterface $handler): ResponseInterface
    {
        $ua      = Validator::serverParams($request)->string('HTTP_USER_AGENT', '');
        $ip      = Validator::attributes($request)->string('client-ip');
        $address = Factory::parseAddressString($ip);
        assert($address instanceof AddressInterface);

        foreach ([self::AI_ROBOTS, self::BAD_ROBOTS] as $robots) {
            foreach ($robots as $robot) {
                if (str_contains($ua, $robot)) {
                    return $this->response();
                }
            }
        }

        foreach (self::ROBOT_REV_FWD_DNS as $robot => $valid_domains) {
            if (str_contains($ua, $robot) && !$this->checkRobotDNS($ip, $valid_domains, false)) {
                return $this->response();
            }
        }

        foreach (self::ROBOT_REV_ONLY_DNS as $robot => $valid_domains) {
            if (str_contains($ua, $robot) && !$this->checkRobotDNS($ip, $valid_domains, true)) {
                return $this->response();
            }
        }

        foreach (self::ROBOT_IPS as $robot => $valid_ip_ranges) {
            if (str_contains($ua, $robot)) {
                foreach ($valid_ip_ranges as $ip_range) {
                    $range = Factory::parseRangeString($ip_range);

                    if ($range instanceof RangeInterface && $range->contains($address)) {
                        continue 2;
                    }
                }

                return $this->response();
            }
        }

        foreach (self::ROBOT_ASNS as $robot => $asns) {
            foreach ($asns as $asn) {
                if (str_contains($ua, $robot)) {
                    foreach ($this->fetchIpRangesForAsn($asn) as $range) {
                        if ($range->contains($address)) {
                            continue 2;
                        }
                    }

                    return $this->response();
                }
            }
        }

        // Allow sites to block access from entire networks.
        $block_asn = Validator::attributes($request)->string('block_asn', '');
        preg_match_all('/(AS\d+)/', $block_asn, $matches);

        foreach ($matches[1] as $asn) {
            foreach ($this->fetchIpRangesForAsn($asn) as $range) {
                if ($range->contains($address)) {
                    return $this->response();
                }
            }
        }

        return $handler->handle($request);
    }

    /**
     * Check that an IP address belongs to a robot operator using a forward/reverse DNS lookup.
     *
     * @param list<string> $valid_domains
filter:
    dependency_paths: ["lib/*"]
     */
    private function checkRobotDNS(string $ip, array $valid_domains, bool $reverse_only): bool
    {
        $host = gethostbyaddr($ip);

        if ($host === false) {
            return false;
        }

        foreach ($valid_domains as $domain) {
            if (str_ends_with($host, $domain)) {
                return $reverse_only || $ip === gethostbyname($host);
            }
        }

        return false;
    }

    /**
     * @return array<RangeInterface>
     */
    private function fetchIpRangesForAsn(string $asn): array
    {
        return Registry::cache()->file()->remember('whois-asn-' . $asn, function () use ($asn): array {
            $ranges = $this->network_service->findIpRangesForAsn($asn);
            $mapper = static fn (string $range): ?RangeInterface => Factory::parseRangeString($range);
            $ranges = array_map($mapper, $ranges);

            return array_filter($ranges);
        }, random_int(self::WHOIS_TTL_MIN, self::WHOIS_TTL_MAX));
    }

    private function response(): ResponseInterface
    {
        return response('Not acceptable', StatusCodeInterface::STATUS_NOT_ACCEPTABLE);
    }
}


1			<?php
2
3			/**
4			* webtrees: online genealogy
5			* Copyright (C) 2025 webtrees development team
6			* This program is free software: you can redistribute it and/or modify
7			* it under the terms of the GNU General Public License as published by
8			* the Free Software Foundation, either version 3 of the License, or
9			* (at your option) any later version.
10			* This program is distributed in the hope that it will be useful,
11			* but WITHOUT ANY WARRANTY; without even the implied warranty of
12			* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13			* GNU General Public License for more details.
14			* You should have received a copy of the GNU General Public License
15			* along with this program. If not, see <https://www.gnu.org/licenses/>.
16			*/
17
18			declare(strict_types=1);
19
20			namespace Fisharebest\Webtrees\Http\Middleware;
21
22			use Fig\Http\Message\StatusCodeInterface;
23			use Fisharebest\Webtrees\Registry;
24			use Fisharebest\Webtrees\Services\NetworkService;
25			use Fisharebest\Webtrees\Validator;
26			use IPLib\Address\AddressInterface;
27			use IPLib\Factory;
28			use IPLib\Range\RangeInterface;
29			use Psr\Http\Message\ResponseInterface;
30			use Psr\Http\Message\ServerRequestInterface;
31			use Psr\Http\Server\MiddlewareInterface;
32			use Psr\Http\Server\RequestHandlerInterface;
33
34			use function array_filter;
35			use function array_map;
36			use function assert;
37			use function gethostbyaddr;
38			use function gethostbyname;
39			use function preg_match_all;
40			use function random_int;
41			use function response;
42			use function str_contains;
43			use function str_ends_with;
44
45			/**
46			* Middleware to block bad robots before they waste our valuable CPU cycles.
47			*/
48			class BadBotBlocker implements MiddlewareInterface
49			{
50			// Cache whois requests. Try to avoid all caches expiring at the same time.
51			private const WHOIS_TTL_MIN = 28 * 86400;
52			private const WHOIS_TTL_MAX = 35 * 86400;
53
54			/**
55			* @see https://github.com/ai-robots-txt/ai.robots.txt for a list of AI crawlers.
56			* We can't load this repository as a dependency as it's not a package.
57			* Instead, the list from version 1.26 is copied here.
58			*/
59			public const AI_ROBOTS = [
60			'AI2Bot',
61			'Ai2Bot-Dolma',
62			'Amazonbot',
63			'anthropic-ai',
64			'Applebot',
65			'Applebot-Extended',
66			'Brightbot 1.0',
67			'Bytespider',
68			'CCBot',
69			'ChatGPT-User',
70			'Claude-Web',
71			'ClaudeBot',
72			'cohere-ai',
73			'cohere-training-data-crawler',
74			'Crawlspace',
75			'Diffbot',
76			'DuckAssistBot',
77			'FacebookBot',
78			'FriendlyCrawler',
79			'Google-Extended',
80			'GoogleOther',
81			'GoogleOther-Image',
82			'GoogleOther-Video',
83			'GPTBot',
84			'iaskspider/2.0',
85			'ICC-Crawler',
86			'ImagesiftBot',
87			'img2dataset',
88			'ISSCyberRiskCrawler',
89			'Kangaroo Bot',
90			'Meta-ExternalAgent',
91			'Meta-ExternalFetcher',
92			'OAI-SearchBot',
93			'omgili',
94			'omgilibot',
95			'PanguBot',
96			'PerplexityBot',
97			'PetalBot',
98			'Scrapy',
99			'SemrushBot-OCOB',
100			'SemrushBot-SWA',
101			'Sidetrade indexer bot',
102			'Timpibot',
103			'VelenPublicWebCrawler',
104			'Webzio-Extended',
105			'YouBot',
106			];
107
108			// Other bad robots - SEO optimisers, advertisers, etc. This list is shared with robots.txt.
109			public const BAD_ROBOTS = [
110			'admantx',
111			'Adsbot',
112			'AhrefsBot',
113			'AntBot', // Aggressive crawler
114			'AspiegelBot',
115			'Awario', // Brand management
116			'Barkrowler', // Crawler for babbar.tech
117			'BLEXBot',
118			'CensysInspect', // Vulnerability scanner
119			'DataForSeoBot', // https://dataforseo.com/dataforseo-bot
120			'DotBot',
121			'Expanse', // Another pointless crawler
122			'fidget-spinner-bot', // Agressive crawler
123			'Foregenix', // Vulnerability scanner
124			'Go-http-client', // Crawler library used by many bots
125			'Grapeshot',
126			'Honolulu-bot', // Aggressive crawer, no info available
127			'ia_archiver',
128			'internet-measurement', // Driftnet
129			'IonCrawl',
130			'Java', // Crawler library used by many bots
131			'linabot', // Aggressive crawer, no info available
132			'Linguee',
133			'MegaIndex.ru',
134			'MJ12bot',
135			'netEstate NE',
136			'panscient',
137			'phxbot', // Badly written crawler
138			'proximic',
139			'python-requests', // Crawler library used by many bots
140			'SeekportBot', // Pretends to be a search engine - but isn't
141			'SemrushBot',
142			'serpstatbot',
143			'SEOkicks',
144			'SiteKiosk',
145			'test-bot', // Agressive crawler
146			'TinyTestBot',
147			'Turnitin',
148			'wp_is_mobile', // Nothing to do with wordpress
149			'XoviBot',
150			'YisouSpider',
151			'ZoominfoBot',
152			];
153
154			/**
155			* Some search engines use reverse/forward DNS to verify the IP address.
156			*
157			* @see https://support.google.com/webmasters/answer/80553?hl=en
158			* @see https://www.bing.com/webmaster/help/which-crawlers-does-bing-use-8c184ec0
159			* @see https://www.bing.com/webmaster/help/how-to-verify-bingbot-3905dc26
160			* @see https://yandex.com/support/webmaster/robot-workings/check-yandex-robots.html
161			* @see https://www.mojeek.com/bot.html
162			*/
163			private const ROBOT_REV_FWD_DNS = [
164			'BingPreview' => ['.search.msn.com'],
165			'Google' => ['.google.com', '.googlebot.com'],
166			'Mail.RU_Bot' => ['.mail.ru'],
167			'MicrosoftPreview' => ['.search.msn.com'],
168			'MojeekBot' => ['.mojeek.com'],
169			'Qwantify' => ['.qwant.com'],
170			'Sogou' => ['.crawl.sogou.com'],
171			'Yahoo' => ['.crawl.yahoo.net'],
172			'Yandex' => ['.yandex.ru', '.yandex.net', '.yandex.com'],
173			'bingbot' => ['.search.msn.com'],
174			'msnbot' => ['.search.msn.com'],
175			];
176
177			/**
178			* Some search engines only use reverse DNS to verify the IP address.
179			*
180			* @see https://help.baidu.com/question?prod_id=99&class=0&id=3001
181			* @see https://napoveda.seznam.cz/en/full-text-search/seznambot-crawler
182			* @see https://www.ionos.de/terms-gtc/faq-crawler
183			*/
184			private const ROBOT_REV_ONLY_DNS = [
185			'Baiduspider' => ['.baidu.com', '.baidu.jp'],
186			'FreshBot' => ['.seznam.cz'],
187			'Neevabot' => ['.neeva.com'],
188			'SeznamBot' => ['.seznam.cz'],
189			];
190
191			/**
192			* Some search engines operate from designated IP addresses.
193			*
194			* @see https://help.duckduckgo.com/duckduckgo-help-pages/results/duckduckbot
195			*/
196			private const ROBOT_IPS = [
197			'DuckDuckBot' => [
198			'23.21.227.69',
199			'50.16.241.113',
200			'50.16.241.114',
201			'50.16.241.117',
202			'50.16.247.234',
203			'52.204.97.54',
204			'52.5.190.19',
205			'54.197.234.188',
206			'54.208.100.253',
207			'54.208.102.37',
208			'107.21.1.8',
209			],
210			];
211
212			/**
213			* Some search engines operate from within a designated autonomous system.
214			*
215			* @see https://developers.facebook.com/docs/sharing/webmasters/crawler
216			* @see https://www.facebook.com/peering/
217			*/
218			private const ROBOT_ASNS = [
219			'facebook' => ['AS32934'],
220			'twitter' => ['AS13414'],
221			];
222
223			private NetworkService $network_service;
224
225			public function __construct(NetworkService $network_service)
226			{
227			$this->network_service = $network_service;
228			}
229
230			public function process(ServerRequestInterface $request, RequestHandlerInterface $handler): ResponseInterface
231			{
232			$ua = Validator::serverParams($request)->string('HTTP_USER_AGENT', '');
233			$ip = Validator::attributes($request)->string('client-ip');
234			$address = Factory::parseAddressString($ip);
235			assert($address instanceof AddressInterface);
236
237			foreach ([self::AI_ROBOTS, self::BAD_ROBOTS] as $robots) {
238			foreach ($robots as $robot) {
239			if (str_contains($ua, $robot)) {
240			return $this->response();
241			}
242			}
243			}
244
245			foreach (self::ROBOT_REV_FWD_DNS as $robot => $valid_domains) {
246			if (str_contains($ua, $robot) && !$this->checkRobotDNS($ip, $valid_domains, false)) {
247			return $this->response();
248			}
249			}
250
251			foreach (self::ROBOT_REV_ONLY_DNS as $robot => $valid_domains) {
252			if (str_contains($ua, $robot) && !$this->checkRobotDNS($ip, $valid_domains, true)) {
253			return $this->response();
254			}
255			}
256
257			foreach (self::ROBOT_IPS as $robot => $valid_ip_ranges) {
258			if (str_contains($ua, $robot)) {
259			foreach ($valid_ip_ranges as $ip_range) {
260			$range = Factory::parseRangeString($ip_range);
261
262			if ($range instanceof RangeInterface && $range->contains($address)) {
263			continue 2;
264			}
265			}
266
267			return $this->response();
268			}
269			}
270
271			foreach (self::ROBOT_ASNS as $robot => $asns) {
272			foreach ($asns as $asn) {
273			if (str_contains($ua, $robot)) {
274			foreach ($this->fetchIpRangesForAsn($asn) as $range) {
275			if ($range->contains($address)) {
276			continue 2;
277			}
278			}
279
280			return $this->response();
281			}
282			}
283			}
284
285			// Allow sites to block access from entire networks.
286			$block_asn = Validator::attributes($request)->string('block_asn', '');
287			preg_match_all('/(AS\d+)/', $block_asn, $matches);
288
289			foreach ($matches[1] as $asn) {
290			foreach ($this->fetchIpRangesForAsn($asn) as $range) {
291			if ($range->contains($address)) {
292			return $this->response();
293			}
294			}
295			}
296
297			return $handler->handle($request);
298			}
299
300			/**
301			* Check that an IP address belongs to a robot operator using a forward/reverse DNS lookup.
302			*
303			* @param list<string> $valid_domains
			0 ignored issues – show Bug introduced 2025-03-09 17:51 UTC by Report Bug Copy Issue Report The type `Fisharebest\Webtrees\Http\Middleware\list` was not found. Maybe you did not declare it correctly or list all dependencies? The issue could also be caused by a filter entry in the build configuration. If the path has been excluded in your configuration, e.g. `excluded_paths: ["lib/"]`, you can move it to the dependency path list as follows: filter: dependency_paths: ["lib/"] For further information see https://scrutinizer-ci.com/docs/tools/php/php-scrutinizer/#list-dependency-paths Loading history...
304			*/
305			private function checkRobotDNS(string $ip, array $valid_domains, bool $reverse_only): bool
306			{
307			$host = gethostbyaddr($ip);
308
309			if ($host === false) {
310			return false;
311			}
312
313			foreach ($valid_domains as $domain) {
314			if (str_ends_with($host, $domain)) {
315			return $reverse_only \|\| $ip === gethostbyname($host);
316			}
317			}
318
319			return false;
320			}
321
322			/**
323			* @return array<RangeInterface>
324			*/
325			private function fetchIpRangesForAsn(string $asn): array
326			{
327			return Registry::cache()->file()->remember('whois-asn-' . $asn, function () use ($asn): array {
328			$ranges = $this->network_service->findIpRangesForAsn($asn);
329			$mapper = static fn (string $range): ?RangeInterface => Factory::parseRangeString($range);
330			$ranges = array_map($mapper, $ranges);
331
332			return array_filter($ranges);
333			}, random_int(self::WHOIS_TTL_MIN, self::WHOIS_TTL_MAX));
334			}
335
336			private function response(): ResponseInterface
337			{
338			return response('Not acceptable', StatusCodeInterface::STATUS_NOT_ACCEPTABLE);
339			}
340			}
341

fisharebest / webtrees

Push — 2.1 ( cc4763...230ed5 )

BadBotBlocker::__construct() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like