feat: custom link parser (#458)

* feat: allow custom url parsers Previously named LinkAdder * fix: removed incorrect type check * feat: added sitemap url parser * tests: added sitemap url parsing test * chore: added readme documentation for custom url parsers * Update README.md * tests: added more consistent tests with sitemapindex and sitemap childs * Fix styling * chore: added documentation for the built-in SitemapUrlParser --------- Co-authored-by: Freek Van der Herten <[email protected]> Co-authored-by: Velka-DEV <[email protected]>
spatie · Jan 2, 2024 · f4958b4 · f4958b4
1 parent 25c378a
commit f4958b4
Show file tree

Hide file tree

Showing 14 changed files with 777 additions and 272 deletions.
diff --git a/README.md b/README.md
@@ -153,6 +153,26 @@ This package comes with three `CrawlProfiles` out of the box:
 - `CrawlInternalUrls`: this profile will only crawl the internal urls on the pages of a host.
 - `CrawlSubdomains`: this profile will only crawl the internal urls and its subdomains on the pages of a host.
 
+### Custom link extraction
+
+You can customize how links are extracted from a page by passing a custom `UrlParser` to the crawler.
+
+```php
+Crawler::create()
+    ->setUrlParserClass(<class that implements \Spatie\Crawler\UrlParsers\UrlParser>::class)
+    ...
+```
+
+By default, the `LinkUrlParser` is used. This parser will extract all links from the `href` attribute of `a` tags.
+
+There is also a built-in `SitemapUrlParser` that will extract & crawl all links from a sitemap. It does support sitemap index files.
+
+```php
+Crawler::create()
+    ->setUrlParserClass(SitemapUrlParser::class)
+    ...
+```
+
 ### Ignoring robots.txt and robots meta
 
 By default, the crawler will respect robots data. It is possible to disable these checks like so:

diff --git a/src/CrawlObservers/CrawlObserver.php b/src/CrawlObservers/CrawlObserver.php
@@ -21,8 +21,8 @@ public function willCrawl(UriInterface $url, ?string $linkText): void
     public function crawled(
         UriInterface $url,
         ResponseInterface $response,
-        UriInterface $foundOnUrl = null,
-        string $linkText = null,
+        ?UriInterface $foundOnUrl = null,
+        ?string $linkText = null,
     ): void {
     }
 
@@ -32,8 +32,8 @@ public function crawled(
     public function crawlFailed(
         UriInterface $url,
         RequestException $requestException,
-        UriInterface $foundOnUrl = null,
-        string $linkText = null,
+        ?UriInterface $foundOnUrl = null,
+        ?string $linkText = null,
     ): void {
     }
 

diff --git a/src/CrawlUrl.php b/src/CrawlUrl.php
@@ -16,9 +16,9 @@ class CrawlUrl
 
     public static function create(
         UriInterface $url,
-        UriInterface $foundOnUrl = null,
+        ?UriInterface $foundOnUrl = null,
         $id = null,
-        string $linkText = null,
+        ?string $linkText = null,
     ): static {
         $static = new static($url, $foundOnUrl, linkText: $linkText);
 

diff --git a/src/Crawler.php b/src/Crawler.php
@@ -19,6 +19,7 @@
 use Spatie\Crawler\Exceptions\InvalidCrawlRequestHandler;
 use Spatie\Crawler\Handlers\CrawlRequestFailed;
 use Spatie\Crawler\Handlers\CrawlRequestFulfilled;
+use Spatie\Crawler\UrlParsers\LinkUrlParser;
 use Spatie\Robots\RobotsTxt;
 use Tree\Node\Node;
 
@@ -62,6 +63,8 @@ class Crawler
 
     protected string $crawlRequestFailedClass;
 
+    protected string $urlParserClass;
+
     protected int $delayBetweenRequests = 0;
 
     protected array $allowedMimeTypes = [];
@@ -102,6 +105,8 @@ public function __construct(
         $this->crawlRequestFulfilledClass = CrawlRequestFulfilled::class;
 
         $this->crawlRequestFailedClass = CrawlRequestFailed::class;
+
+        $this->urlParserClass = LinkUrlParser::class;
     }
 
     public function getDefaultScheme(): string
@@ -345,6 +350,18 @@ public function setCrawlFailedHandlerClass(string $crawlRequestFailedClass): sel
         return $this;
     }
 
+    public function setUrlParserClass(string $urlParserClass): self
+    {
+        $this->urlParserClass = $urlParserClass;
+
+        return $this;
+    }
+
+    public function getUrlParserClass(): string
+    {
+        return $this->urlParserClass;
+    }
+
     public function setBrowsershot(Browsershot $browsershot)
     {
         $this->browsershot = $browsershot;
@@ -430,7 +447,7 @@ public function startCrawling(UriInterface|string $baseUrl)
         }
     }
 
-    public function addToDepthTree(UriInterface $url, UriInterface $parentUrl, Node $node = null): ?Node
+    public function addToDepthTree(UriInterface $url, UriInterface $parentUrl, ?Node $node = null): ?Node
     {
         if (is_null($this->maximumDepth)) {
             return new Node((string) $url);

diff --git a/src/Handlers/CrawlRequestFulfilled.php b/src/Handlers/CrawlRequestFulfilled.php
@@ -13,16 +13,17 @@
 use Spatie\Crawler\CrawlerRobots;
 use Spatie\Crawler\CrawlProfiles\CrawlSubdomains;
 use Spatie\Crawler\CrawlUrl;
-use Spatie\Crawler\LinkAdder;
 use Spatie\Crawler\ResponseWithCachedBody;
+use Spatie\Crawler\UrlParsers\UrlParser;
 
 class CrawlRequestFulfilled
 {
-    protected LinkAdder $linkAdder;
+    protected UrlParser $urlParser;
 
     public function __construct(protected Crawler $crawler)
     {
-        $this->linkAdder = new LinkAdder($this->crawler);
+        $urlParserClass = $this->crawler->getUrlParserClass();
+        $this->urlParser = new $urlParserClass($this->crawler);
     }
 
     public function __invoke(ResponseInterface $response, $index)
@@ -62,7 +63,7 @@ public function __invoke(ResponseInterface $response, $index)
 
         $baseUrl = $this->getBaseUrl($response, $crawlUrl);
 
-        $this->linkAdder->addFromHtml($body, $baseUrl);
+        $this->urlParser->addFromHtml($body, $baseUrl);
 
         usleep($this->crawler->getDelayBetweenRequests());
     }

diff --git a/src/ResponseWithCachedBody.php b/src/ResponseWithCachedBody.php
@@ -20,7 +20,7 @@ public static function fromGuzzlePsr7Response(ResponseInterface $response): stat
         );
     }
 
-    public function setCachedBody(string $body = null): void
+    public function setCachedBody(?string $body = null): void
     {
         $this->cachedBody = $body;
     }

diff --git a/src/LinkAdder.php → src/UrlParsers/LinkUrlParser.php b/src/LinkAdder.php → src/UrlParsers/LinkUrlParser.php
@@ -1,15 +1,18 @@
 <?php
 
-namespace Spatie\Crawler;
+namespace Spatie\Crawler\UrlParsers;
 
 use Illuminate\Support\Collection;
 use InvalidArgumentException;
 use Psr\Http\Message\UriInterface;
+use Spatie\Crawler\Crawler;
+use Spatie\Crawler\CrawlUrl;
+use Spatie\Crawler\Url;
 use Symfony\Component\DomCrawler\Crawler as DomCrawler;
 use Symfony\Component\DomCrawler\Link;
 use Tree\Node\Node;
 
-class LinkAdder
+class LinkUrlParser implements UrlParser
 {
     protected Crawler $crawler;
 
@@ -66,7 +69,7 @@ protected function extractLinksFromHtml(string $html, UriInterface $foundOnUrl):
 
                     return new Url($link->getUri(), $linkText);
                 } catch (InvalidArgumentException $exception) {
-                    return;
+                    return null;
                 }
             })
             ->filter();

diff --git a/src/UrlParsers/SitemapUrlParser.php b/src/UrlParsers/SitemapUrlParser.php
@@ -0,0 +1,89 @@
+<?php
+
+namespace Spatie\Crawler\UrlParsers;
+
+use Illuminate\Support\Collection;
+use InvalidArgumentException;
+use Psr\Http\Message\UriInterface;
+use Spatie\Crawler\Crawler;
+use Spatie\Crawler\CrawlUrl;
+use Spatie\Crawler\Url;
+use Symfony\Component\DomCrawler\Crawler as DomCrawler;
+use Tree\Node\Node;
+
+class SitemapUrlParser implements UrlParser
+{
+    protected Crawler $crawler;
+
+    public function __construct(Crawler $crawler)
+    {
+        $this->crawler = $crawler;
+    }
+
+    public function addFromHtml(string $html, UriInterface $foundOnUrl): void
+    {
+        $allLinks = $this->extractLinksFromHtml($html, $foundOnUrl);
+
+        collect($allLinks)
+            ->filter(fn (Url $url) => $this->hasCrawlableScheme($url))
+            ->map(fn (Url $url) => $this->normalizeUrl($url))
+            ->filter(function (Url $url) use ($foundOnUrl) {
+                if (! $node = $this->crawler->addToDepthTree($url, $foundOnUrl)) {
+                    return false;
+                }
+
+                return $this->shouldCrawl($node);
+            })
+            ->filter(fn (Url $url) => ! str_contains($url->getPath(), '/tel:'))
+            ->each(function (Url $url) use ($foundOnUrl) {
+                $crawlUrl = CrawlUrl::create($url, $foundOnUrl, linkText: $url->linkText());
+
+                $this->crawler->addToCrawlQueue($crawlUrl);
+            });
+    }
+
+    protected function extractLinksFromHtml(string $html, UriInterface $foundOnUrl): ?Collection
+    {
+        $domCrawler = new DomCrawler($html, $foundOnUrl);
+
+        return collect($domCrawler->filterXPath('//loc')
+            ->each(function (DomCrawler $node) {
+                try {
+                    $linkText = $node->text();
+
+                    if ($linkText) {
+                        $linkText = substr($linkText, 0, 4000);
+                    }
+
+                    return new Url($linkText, $linkText);
+                } catch (InvalidArgumentException $exception) {
+                    return null;
+                }
+            }));
+    }
+
+    protected function hasCrawlableScheme(UriInterface $uri): bool
+    {
+        return in_array($uri->getScheme(), ['http', 'https']);
+    }
+
+    protected function normalizeUrl(UriInterface $url): UriInterface
+    {
+        return $url->withFragment('');
+    }
+
+    protected function shouldCrawl(Node $node): bool
+    {
+        if ($this->crawler->mustRespectRobots() && ! $this->crawler->getRobotsTxt()->allows($node->getValue(), $this->crawler->getUserAgent())) {
+            return false;
+        }
+
+        $maximumDepth = $this->crawler->getMaximumDepth();
+
+        if (is_null($maximumDepth)) {
+            return true;
+        }
+
+        return $node->getDepth() <= $maximumDepth;
+    }
+}
diff --git a/src/UrlParsers/UrlParser.php b/src/UrlParsers/UrlParser.php
@@ -0,0 +1,13 @@
+<?php
+
+namespace Spatie\Crawler\UrlParsers;
+
+use Psr\Http\Message\UriInterface;
+use Spatie\Crawler\Crawler;
+
+interface UrlParser
+{
+    public function __construct(Crawler $crawler);
+
+    public function addFromHtml(string $html, UriInterface $foundOnUrl): void;
+}
diff --git a/tests/CrawlObserverCollectionTest.php b/tests/CrawlObserverCollectionTest.php
@@ -20,17 +20,17 @@
         public function crawled(
             UriInterface $url,
             ResponseInterface $response,
-            UriInterface $foundOnUrl = null,
-            string $linkText = null,
+            ?UriInterface $foundOnUrl = null,
+            ?string $linkText = null,
         ): void {
             $this->crawled = true;
         }
 
         public function crawlFailed(
             UriInterface $url,
             RequestException $requestException,
-            UriInterface $foundOnUrl = null,
-            string $linkText = null,
+            ?UriInterface $foundOnUrl = null,
+            ?string $linkText = null,
         ): void {
             $this->failed = true;
         }

diff --git a/tests/SitemapUrlParserTest.php b/tests/SitemapUrlParserTest.php
@@ -0,0 +1,46 @@
+<?php
+
+use Spatie\Crawler\Test\TestClasses\Log;
+use Spatie\Crawler\UrlParsers\SitemapUrlParser;
+
+beforeEach(function () {
+    skipIfTestServerIsNotRunning();
+
+    Log::reset();
+});
+
+it('should extract child sitemaps from sitemap index', function () {
+    createCrawler()
+        ->setUrlParserClass(SitemapUrlParser::class)
+        ->startCrawling('http://localhost:8080/sitemap_index.xml');
+
+    expect(['url' => 'http://localhost:8080/sitemap1.xml', 'foundOn' => 'http://localhost:8080/sitemap_index.xml'])
+        ->toBeCrawledOnce();
+
+    expect(['url' => 'http://localhost:8080/sitemap2.xml', 'foundOn' => 'http://localhost:8080/sitemap_index.xml'])
+        ->toBeCrawledOnce();
+});
+
+it('should extract urls from sitemaps trough sitemap index', function () {
+    createCrawler()
+        ->setUrlParserClass(SitemapUrlParser::class)
+        ->startCrawling('http://localhost:8080/sitemap_index.xml');
+
+    expect(['url' => 'http://localhost:8080/', 'foundOn' => 'http://localhost:8080/sitemap1.xml'])
+        ->toBeCrawledOnce();
+
+    expect(['url' => 'http://localhost:8080/link1', 'foundOn' => 'http://localhost:8080/sitemap1.xml'])
+        ->toBeCrawledOnce();
+
+    expect(['url' => 'http://localhost:8080/link1-next', 'foundOn' => 'http://localhost:8080/sitemap2.xml'])
+        ->toBeCrawledOnce();
+
+    expect(['url' => 'http://localhost:8080/link1-prev', 'foundOn' => 'http://localhost:8080/sitemap2.xml'])
+        ->toBeCrawledOnce();
+
+    expect(['url' => 'http://localhost:8080/link2', 'foundOn' => 'http://localhost:8080/sitemap2.xml'])
+        ->toBeCrawledOnce();
+
+    expect(['url' => 'http://localhost:8080/link3', 'foundOn' => 'http://localhost:8080/sitemap2.xml'])
+        ->toBeCrawledOnce();
+});
diff --git a/tests/TestClasses/CrawlLogger.php b/tests/TestClasses/CrawlLogger.php
@@ -34,22 +34,22 @@ public function willCrawl(UriInterface $url, ?string $linkText): void
     public function crawled(
         UriInterface $url,
         ResponseInterface $response,
-        UriInterface $foundOnUrl = null,
-        string $linkText = null,
+        ?UriInterface $foundOnUrl = null,
+        ?string $linkText = null,
     ): void {
         $this->logCrawl($url, $foundOnUrl, $linkText);
     }
 
     public function crawlFailed(
         UriInterface $url,
         RequestException $requestException,
-        UriInterface $foundOnUrl = null,
-        string $linkText = null,
+        ?UriInterface $foundOnUrl = null,
+        ?string $linkText = null,
     ): void {
         $this->logCrawl($url, $foundOnUrl, $linkText);
     }
 
-    protected function logCrawl(UriInterface $url, ?UriInterface $foundOnUrl, string $linkText = null)
+    protected function logCrawl(UriInterface $url, ?UriInterface $foundOnUrl, ?string $linkText = null)
     {
         $logText = "{$this->observerId}hasBeenCrawled: {$url}";
-Original file line number
+Diff line change
@@ Expand Up @@
             );
         }
-        public function setCachedBody(string $body = null): void
+        public function setCachedBody(?string $body = null): void
         {
             $this->cachedBody = $body;
         }
@@ Expand Down @@