Duplicate code is one of the most pungent code smells. A rule that is often used is to re-structure code once it is duplicated in three or more places.
Common duplication problems, and corresponding solutions are:
Complex classes like Crawler often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes. You can also have a look at the cohesion graph to spot any un-connected, or weakly-connected components.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
While breaking up the class, it is a good idea to analyze how other classes use Crawler, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 26 | class Crawler |
||
| 27 | { |
||
| 28 | /** @var \GuzzleHttp\Client */ |
||
| 29 | protected $client; |
||
| 30 | |||
| 31 | /** @var \Psr\Http\Message\UriInterface */ |
||
| 32 | protected $baseUrl; |
||
| 33 | |||
| 34 | /** @var array[\Spatie\Crawler\CrawlObserver] */ |
||
| 35 | protected $crawlObservers; |
||
| 36 | |||
| 37 | /** @var \Spatie\Crawler\CrawlProfile */ |
||
| 38 | protected $crawlProfile; |
||
| 39 | |||
| 40 | /** @var int */ |
||
| 41 | protected $concurrency; |
||
| 42 | |||
| 43 | /** @var \Spatie\Crawler\CrawlQueue\CrawlQueue */ |
||
| 44 | protected $crawlQueue; |
||
| 45 | |||
| 46 | /** @var int */ |
||
| 47 | protected $crawledUrlCount = 0; |
||
| 48 | |||
| 49 | /** @var int|null */ |
||
| 50 | protected $maximumCrawlCount = null; |
||
| 51 | |||
| 52 | /** @var int */ |
||
| 53 | protected $maximumResponseSize = 1024 * 1024 * 2; |
||
| 54 | |||
| 55 | /** @var int|null */ |
||
| 56 | protected $maximumDepth = null; |
||
| 57 | |||
| 58 | /** @var bool */ |
||
| 59 | protected $respectRobots = true; |
||
| 60 | |||
| 61 | /** @var \Tree\Node\Node */ |
||
| 62 | protected $depthTree; |
||
| 63 | |||
| 64 | /** @var bool */ |
||
| 65 | protected $executeJavaScript = false; |
||
| 66 | |||
| 67 | /** @var Browsershot */ |
||
| 68 | protected $browsershot = null; |
||
| 69 | |||
| 70 | /** @var \Spatie\Robots\RobotsTxt */ |
||
| 71 | protected $robotsTxt = null; |
||
| 72 | |||
| 73 | protected static $defaultClientOptions = [ |
||
| 74 | RequestOptions::COOKIES => true, |
||
| 75 | RequestOptions::CONNECT_TIMEOUT => 10, |
||
| 76 | RequestOptions::TIMEOUT => 10, |
||
| 77 | RequestOptions::ALLOW_REDIRECTS => false, |
||
| 78 | ]; |
||
| 79 | |||
| 80 | /** |
||
| 81 | * @param array $clientOptions |
||
| 82 | * |
||
| 83 | * @return static |
||
| 84 | */ |
||
| 85 | public static function create(array $clientOptions = []) |
||
| 95 | |||
| 96 | public function __construct(Client $client, int $concurrency = 10) |
||
| 106 | |||
| 107 | /** |
||
| 108 | * @param int $concurrency |
||
| 109 | * |
||
| 110 | * @return $this |
||
| 111 | */ |
||
| 112 | public function setConcurrency(int $concurrency) |
||
| 118 | |||
| 119 | /** |
||
| 120 | * Responses that are larger that then specified value will be ignored. |
||
| 121 | * |
||
| 122 | * @param int $maximumResponseSizeInBytes |
||
| 123 | * |
||
| 124 | * @return $this |
||
| 125 | */ |
||
| 126 | public function setMaximumResponseSize(int $maximumResponseSizeInBytes) |
||
| 132 | |||
| 133 | /** |
||
| 134 | * @param int $maximumCrawlCount |
||
| 135 | * |
||
| 136 | * @return $this |
||
| 137 | */ |
||
| 138 | public function setMaximumCrawlCount(int $maximumCrawlCount) |
||
| 144 | |||
| 145 | /** |
||
| 146 | * @param int $maximumDepth |
||
| 147 | * |
||
| 148 | * @return $this |
||
| 149 | */ |
||
| 150 | public function setMaximumDepth(int $maximumDepth) |
||
| 156 | |||
| 157 | /** |
||
| 158 | * @return $this |
||
| 159 | */ |
||
| 160 | public function ignoreRobots() |
||
| 166 | |||
| 167 | /** |
||
| 168 | * @return $this |
||
| 169 | */ |
||
| 170 | public function respectRobots() |
||
| 176 | |||
| 177 | /** |
||
| 178 | * @param CrawlQueue $crawlQueue |
||
| 179 | * |
||
| 180 | * @return $this |
||
| 181 | */ |
||
| 182 | public function setCrawlQueue(CrawlQueue $crawlQueue) |
||
| 188 | |||
| 189 | /** |
||
| 190 | * @return $this |
||
| 191 | */ |
||
| 192 | public function executeJavaScript() |
||
| 198 | |||
| 199 | /** |
||
| 200 | * @return $this |
||
| 201 | */ |
||
| 202 | public function doNotExecuteJavaScript() |
||
| 208 | |||
| 209 | /** |
||
| 210 | * @param \Spatie\Crawler\CrawlObserver|array[\Spatie\Crawler\CrawlObserver] $crawlObservers |
||
|
|
|||
| 211 | * |
||
| 212 | * @return $this |
||
| 213 | */ |
||
| 214 | public function setCrawlObserver($crawlObservers) |
||
| 222 | |||
| 223 | public function setCrawlObservers(array $crawlObservers) |
||
| 229 | |||
| 230 | public function addCrawlObserver(CrawlObserver $crawlObserver) |
||
| 236 | |||
| 237 | /** |
||
| 238 | * @param \Spatie\Crawler\CrawlProfile $crawlProfile |
||
| 239 | * |
||
| 240 | * @return $this |
||
| 241 | */ |
||
| 242 | public function setCrawlProfile(CrawlProfile $crawlProfile) |
||
| 248 | |||
| 249 | /** |
||
| 250 | * @param \Psr\Http\Message\UriInterface|string $baseUrl |
||
| 251 | */ |
||
| 252 | public function startCrawling($baseUrl) |
||
| 282 | |||
| 283 | protected function startCrawlingQueue() |
||
| 332 | |||
| 333 | public function endsWith($haystack, $needle) |
||
| 338 | |||
| 339 | protected function convertBodyToString(StreamInterface $bodyStream, $readMaximumBytes = 1024 * 1024 * 2): string |
||
| 347 | |||
| 348 | protected function createRobotsTxt(UriInterface $uri): RobotsTxt |
||
| 352 | |||
| 353 | /** |
||
| 354 | * @param ResponseInterface|null $response |
||
| 355 | * @param CrawlUrl $crawlUrl |
||
| 356 | */ |
||
| 357 | protected function handleCrawled(ResponseInterface $response, CrawlUrl $crawlUrl) |
||
| 367 | |||
| 368 | /** |
||
| 369 | * @param RequestException $exception |
||
| 370 | * @param CrawlUrl $crawlUrl |
||
| 371 | */ |
||
| 372 | protected function handleCrawlFailed(RequestException $exception, CrawlUrl $crawlUrl) |
||
| 382 | |||
| 383 | protected function getCrawlRequests(): Generator |
||
| 404 | |||
| 405 | protected function addAllLinksToCrawlQueue(string $html, UriInterface $foundOnUrl) |
||
| 442 | |||
| 443 | protected function shouldCrawl(Node $node): bool |
||
| 455 | |||
| 456 | /** |
||
| 457 | * @param string $html |
||
| 458 | * @param \Psr\Http\Message\UriInterface $foundOnUrl |
||
| 459 | * |
||
| 460 | * @return \Illuminate\Support\Collection|\Tightenco\Collect\Support\Collection|null |
||
| 461 | */ |
||
| 462 | protected function extractAllLinks(string $html, UriInterface $foundOnUrl) |
||
| 483 | |||
| 484 | protected function normalizeUrl(UriInterface $url): UriInterface |
||
| 488 | |||
| 489 | protected function hasCrawlableScheme(UriInterface $uri): bool |
||
| 493 | |||
| 494 | protected function addtoDepthTree(Node $node, UriInterface $url, UriInterface $parentUrl) |
||
| 516 | |||
| 517 | protected function getBodyAfterExecutingJavaScript(UriInterface $foundOnUrl): string |
||
| 525 | |||
| 526 | protected function getBrowsershot(): Browsershot |
||
| 536 | |||
| 537 | public function setBrowsershot(Browsershot $browsershot) |
||
| 543 | |||
| 544 | protected function addToCrawlQueue(CrawlUrl $crawlUrl) |
||
| 552 | |||
| 553 | protected function maximumCrawlCountReached(): bool |
||
| 561 | |||
| 562 | View Code Duplication | protected function mayIndex(RobotsHeaders $robotsHeaders, RobotsMeta $robotsMeta): bool |
|
| 578 | |||
| 579 | View Code Duplication | protected function mayFollow(RobotsHeaders $robotsHeaders, RobotsMeta $robotsMeta): bool |
|
| 595 | } |
||
| 596 |
This check marks PHPDoc comments that could not be parsed by our parser. To see which comment annotations we can parse, please refer to our documentation on supported doc-types.