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 |
||
| 15 | class Crawler implements LoggerAwareInterface |
||
| 16 | { |
||
| 17 | /** |
||
| 18 | * @var Client |
||
| 19 | */ |
||
| 20 | private $client; |
||
| 21 | |||
| 22 | /** |
||
| 23 | * @var int |
||
| 24 | */ |
||
| 25 | private $limit = 0; |
||
| 26 | |||
| 27 | /** |
||
| 28 | * @var bool |
||
| 29 | */ |
||
| 30 | private $stopOnError = false; |
||
| 31 | |||
| 32 | /** |
||
| 33 | * @var bool |
||
| 34 | */ |
||
| 35 | private $exceptionOnError = false; |
||
| 36 | |||
| 37 | /** |
||
| 38 | * @var UrlMatcherInterface[] |
||
| 39 | */ |
||
| 40 | private $whitelistUrlMatchers = []; |
||
| 41 | |||
| 42 | /** |
||
| 43 | * @var UrlMatcherInterface[] |
||
| 44 | */ |
||
| 45 | private $blacklistUrlMatchers = []; |
||
| 46 | |||
| 47 | /** |
||
| 48 | * @var UrlNormalizerInterface[] |
||
| 49 | */ |
||
| 50 | private $urlNormalizers = []; |
||
| 51 | |||
| 52 | /** |
||
| 53 | * @var Url |
||
| 54 | */ |
||
| 55 | private $baseUrl; |
||
| 56 | |||
| 57 | /** |
||
| 58 | * @var array |
||
| 59 | */ |
||
| 60 | private $urlsCrawled = []; |
||
| 61 | |||
| 62 | /** |
||
| 63 | * @var array |
||
| 64 | */ |
||
| 65 | private $urlsQueued = []; |
||
| 66 | |||
| 67 | /** |
||
| 68 | * @var array |
||
| 69 | */ |
||
| 70 | private $urlsRejected = []; |
||
| 71 | |||
| 72 | /** |
||
| 73 | * @var array |
||
| 74 | */ |
||
| 75 | private $urlsReturned = []; |
||
| 76 | |||
| 77 | /** |
||
| 78 | * @var LoggerInterface |
||
| 79 | */ |
||
| 80 | private $logger = null; |
||
| 81 | |||
| 82 | /** |
||
| 83 | * @param Client $client |
||
| 84 | */ |
||
| 85 | 15 | public function __construct(Client $client = null) |
|
| 95 | |||
| 96 | /** |
||
| 97 | * @param Client $client |
||
| 98 | */ |
||
| 99 | 15 | public function setClient(Client $client) |
|
| 103 | |||
| 104 | /** |
||
| 105 | * @return Client |
||
| 106 | */ |
||
| 107 | 2 | public function getClient() |
|
| 111 | |||
| 112 | /** |
||
| 113 | * @return int |
||
| 114 | */ |
||
| 115 | 2 | public function getLimit() |
|
| 119 | |||
| 120 | /** |
||
| 121 | * @param int $limit |
||
| 122 | * @return $this |
||
| 123 | */ |
||
| 124 | 2 | public function setLimit($limit) |
|
| 130 | |||
| 131 | /** |
||
| 132 | * @return boolean |
||
| 133 | */ |
||
| 134 | 5 | public function getStopOnError() |
|
| 138 | |||
| 139 | /** |
||
| 140 | * @param boolean $stopOnError |
||
| 141 | * @return $this |
||
| 142 | */ |
||
| 143 | 2 | public function setStopOnError($stopOnError) |
|
| 149 | |||
| 150 | /** |
||
| 151 | * @return boolean |
||
| 152 | */ |
||
| 153 | 2 | public function getExceptionOnError() |
|
| 157 | |||
| 158 | /** |
||
| 159 | * @param boolean $exceptionOnError |
||
| 160 | * @return $this |
||
| 161 | */ |
||
| 162 | 1 | public function setExceptionOnError($exceptionOnError) |
|
| 168 | |||
| 169 | /** |
||
| 170 | * @return array |
||
| 171 | */ |
||
| 172 | 9 | public function getUrlsCrawled() |
|
| 176 | |||
| 177 | /** |
||
| 178 | * @return array |
||
| 179 | */ |
||
| 180 | 2 | public function getUrlsQueued() |
|
| 184 | |||
| 185 | /** |
||
| 186 | * @return array |
||
| 187 | */ |
||
| 188 | 2 | public function getUrlsRejected() |
|
| 192 | |||
| 193 | /** |
||
| 194 | * @return array |
||
| 195 | */ |
||
| 196 | 4 | public function getUrlsReturned() |
|
| 200 | |||
| 201 | /** |
||
| 202 | * @param $urlMatchers |
||
| 203 | * @return $this |
||
| 204 | */ |
||
| 205 | 1 | public function setWhitelistUrlMatchers(array $urlMatchers) |
|
| 214 | |||
| 215 | /** |
||
| 216 | * @return Url\Matcher\UrlMatcherInterface[] |
||
| 217 | */ |
||
| 218 | 2 | public function getWhitelistUrlMatchers() |
|
| 222 | |||
| 223 | /** |
||
| 224 | * @param UrlMatcherInterface $urlMatcher |
||
| 225 | * @return $this |
||
| 226 | */ |
||
| 227 | 2 | public function addWhitelistUrlMatcher(UrlMatcherInterface $urlMatcher) |
|
| 233 | |||
| 234 | /** |
||
| 235 | * @return $this |
||
| 236 | */ |
||
| 237 | 1 | public function clearWhitelistUrlMatchers() |
|
| 243 | |||
| 244 | /** |
||
| 245 | * @param array $urlMatchers |
||
| 246 | * @return $this |
||
| 247 | */ |
||
| 248 | 1 | public function setBlacklistUrlMatchers(array $urlMatchers) |
|
| 257 | |||
| 258 | /** |
||
| 259 | * @return Url\Matcher\UrlMatcherInterface[] |
||
| 260 | */ |
||
| 261 | 2 | public function getBlacklistUrlMatchers() |
|
| 265 | |||
| 266 | /** |
||
| 267 | * @param UrlMatcherInterface $urlMatcher |
||
| 268 | * @return $this |
||
| 269 | */ |
||
| 270 | 2 | public function addBlacklistUrlMatcher(UrlMatcherInterface $urlMatcher) |
|
| 276 | |||
| 277 | /** |
||
| 278 | * @return $this |
||
| 279 | */ |
||
| 280 | 1 | public function clearBlacklistUrlMatchers() |
|
| 286 | |||
| 287 | /** |
||
| 288 | * @param array $normalizers |
||
| 289 | * @return $this |
||
| 290 | */ |
||
| 291 | 1 | public function setUrlNormalizers(array $normalizers) |
|
| 301 | |||
| 302 | /** |
||
| 303 | * @return UrlNormalizerInterface[] |
||
| 304 | */ |
||
| 305 | 1 | public function getUrlNormalizers() |
|
| 309 | |||
| 310 | /** |
||
| 311 | * @param UrlNormalizerInterface $normalizer |
||
| 312 | * @return $this |
||
| 313 | */ |
||
| 314 | 2 | public function addUrlNormalizer(UrlNormalizerInterface $normalizer) |
|
| 320 | |||
| 321 | /** |
||
| 322 | * @return $this |
||
| 323 | */ |
||
| 324 | 1 | public function clearUrlNormalizers() |
|
| 330 | |||
| 331 | /** |
||
| 332 | * @return LoggerInterface |
||
| 333 | */ |
||
| 334 | 13 | public function getLogger() |
|
| 342 | |||
| 343 | /** |
||
| 344 | * @param LoggerInterface $logger |
||
| 345 | * @return $this |
||
| 346 | */ |
||
| 347 | 1 | public function setLogger(LoggerInterface $logger) |
|
| 353 | |||
| 354 | /** |
||
| 355 | * @param Url $url |
||
| 356 | */ |
||
| 357 | 11 | protected function addUrlToQueue(Url $url) |
|
| 361 | |||
| 362 | /** |
||
| 363 | * @param $url |
||
| 364 | * @return Url |
||
| 365 | * @throws \Exception |
||
| 366 | */ |
||
| 367 | 10 | protected function createHttpUrlString($url) |
|
| 380 | |||
| 381 | /** |
||
| 382 | * @param Url $url |
||
| 383 | */ |
||
| 384 | 11 | protected function reset(Url $url) |
|
| 392 | |||
| 393 | /** |
||
| 394 | * @param string $url |
||
| 395 | * @return \Generator|Page[] |
||
| 396 | * @throws RequestException |
||
| 397 | */ |
||
| 398 | 10 | public function crawl($url) |
|
| 440 | |||
| 441 | /** |
||
| 442 | * @param Url $url |
||
| 443 | * @return Url |
||
| 444 | */ |
||
| 445 | 10 | protected function updateUrl(Url $url) |
|
| 454 | |||
| 455 | /** |
||
| 456 | * @param DomCrawler $crawler |
||
| 457 | */ |
||
| 458 | 9 | protected function updateQueue(DomCrawler $crawler) |
|
| 473 | |||
| 474 | /** |
||
| 475 | * @param Url $url |
||
| 476 | * @return Url |
||
| 477 | */ |
||
| 478 | 7 | protected function normalizeUrl(Url $url) |
|
| 486 | |||
| 487 | /** |
||
| 488 | * @param Url $url |
||
| 489 | * @return bool |
||
| 490 | */ |
||
| 491 | 9 | protected function shouldReturnUrl(Url $url) |
|
| 509 | |||
| 510 | /** |
||
| 511 | * @param Url $url |
||
| 512 | * @return bool |
||
| 513 | */ |
||
| 514 | 1 | protected function isUrlWhitelisted(Url $url) |
|
| 524 | |||
| 525 | /** |
||
| 526 | * @param Url $url |
||
| 527 | * @return bool |
||
| 528 | */ |
||
| 529 | 9 | protected function isUrlBlacklisted(Url $url) |
|
| 539 | |||
| 540 | /** |
||
| 541 | * @param Url $url |
||
| 542 | * @return bool |
||
| 543 | */ |
||
| 544 | 8 | protected function shouldCrawlUrl(Url $url) |
|
| 561 | |||
| 562 | /** |
||
| 563 | * @param Url $url |
||
| 564 | * @return bool |
||
| 565 | */ |
||
| 566 | 8 | protected function isUrlRejected(Url $url) |
|
| 570 | |||
| 571 | /** |
||
| 572 | * @param Url $url |
||
| 573 | * @return bool |
||
| 574 | */ |
||
| 575 | 8 | protected function isUrlCrawled(Url $url) |
|
| 579 | |||
| 580 | /** |
||
| 581 | * @param Url $url |
||
| 582 | * @return bool |
||
| 583 | */ |
||
| 584 | 8 | protected function isUrlQueued(Url $url) |
|
| 588 | |||
| 589 | /** |
||
| 590 | * @param Url $url |
||
| 591 | * @return bool |
||
| 592 | */ |
||
| 593 | 8 | protected function isUrlPartOfBaseUrl(Url $url) |
|
| 603 | |||
| 604 | /** |
||
| 605 | * @return bool |
||
| 606 | */ |
||
| 607 | 9 | protected function isLimitReached() |
|
| 611 | |||
| 612 | /** |
||
| 613 | * @param DomCrawler $crawler |
||
| 614 | * @return array |
||
| 615 | */ |
||
| 616 | 9 | protected function extractUrlsFromCrawler(DomCrawler $crawler) |
|
| 624 | |||
| 625 | /** |
||
| 626 | * @param string $url |
||
| 627 | * @return DomCrawler |
||
| 628 | */ |
||
| 629 | 10 | protected function requestPage($url) |
|
| 637 | } |
||
| 638 |
Unless you are absolutely sure that the expression can never be null because of other conditions, we strongly recommend to add an additional type check to your code: