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 |
||
| 14 | class Crawler implements LoggerAwareInterface |
||
| 15 | { |
||
| 16 | /** |
||
| 17 | * @var Client |
||
| 18 | */ |
||
| 19 | private $client; |
||
| 20 | |||
| 21 | /** |
||
| 22 | * @var int |
||
| 23 | */ |
||
| 24 | private $limit = 0; |
||
| 25 | |||
| 26 | /** |
||
| 27 | * @var bool |
||
| 28 | */ |
||
| 29 | private $stopOnError = false; |
||
| 30 | |||
| 31 | /** |
||
| 32 | * @var bool |
||
| 33 | */ |
||
| 34 | private $exceptionOnError = false; |
||
| 35 | |||
| 36 | /** |
||
| 37 | * @var UrlMatcherInterface[] |
||
| 38 | */ |
||
| 39 | private $whitelistUrlMatchers = []; |
||
| 40 | |||
| 41 | /** |
||
| 42 | * @var UrlMatcherInterface[] |
||
| 43 | */ |
||
| 44 | private $blacklistUrlMatchers = []; |
||
| 45 | |||
| 46 | /** |
||
| 47 | * @var UrlNormalizerInterface[] |
||
| 48 | */ |
||
| 49 | private $urlNormalizers = []; |
||
| 50 | |||
| 51 | /** |
||
| 52 | * @var Url |
||
| 53 | */ |
||
| 54 | private $baseUrl; |
||
| 55 | |||
| 56 | /** |
||
| 57 | * @var array |
||
| 58 | */ |
||
| 59 | private $urlsCrawled = []; |
||
| 60 | |||
| 61 | /** |
||
| 62 | * @var array |
||
| 63 | */ |
||
| 64 | private $urlsQueued = []; |
||
| 65 | |||
| 66 | /** |
||
| 67 | * @var array |
||
| 68 | */ |
||
| 69 | private $urlsRejected = []; |
||
| 70 | |||
| 71 | /** |
||
| 72 | * @var array |
||
| 73 | */ |
||
| 74 | private $urlsReturned = []; |
||
| 75 | |||
| 76 | /** |
||
| 77 | * @var LoggerInterface |
||
| 78 | */ |
||
| 79 | private $logger = null; |
||
| 80 | |||
| 81 | /** |
||
| 82 | * @param Client $client |
||
| 83 | * @param array $options |
||
| 84 | */ |
||
| 85 | 14 | public function __construct(Client $client = null, array $options = []) |
|
| 96 | |||
| 97 | /** |
||
| 98 | * @param Client $client |
||
| 99 | */ |
||
| 100 | 14 | public function setClient(Client $client) |
|
| 104 | |||
| 105 | /** |
||
| 106 | * @return Client |
||
| 107 | */ |
||
| 108 | 2 | public function getClient() |
|
| 112 | |||
| 113 | /** |
||
| 114 | * @param array $options |
||
| 115 | */ |
||
| 116 | 14 | public function setOptions(array $options) |
|
| 140 | |||
| 141 | /** |
||
| 142 | * @return int |
||
| 143 | */ |
||
| 144 | 3 | public function getLimit() |
|
| 148 | |||
| 149 | /** |
||
| 150 | * @param int $limit |
||
| 151 | * @return $this |
||
| 152 | */ |
||
| 153 | 3 | public function setLimit($limit) |
|
| 159 | |||
| 160 | /** |
||
| 161 | * @return boolean |
||
| 162 | */ |
||
| 163 | 6 | public function getStopOnError() |
|
| 167 | |||
| 168 | /** |
||
| 169 | * @param boolean $stopOnError |
||
| 170 | * @return $this |
||
| 171 | */ |
||
| 172 | 3 | public function setStopOnError($stopOnError) |
|
| 178 | |||
| 179 | /** |
||
| 180 | * @return boolean |
||
| 181 | */ |
||
| 182 | 3 | public function getExceptionOnError() |
|
| 186 | |||
| 187 | /** |
||
| 188 | * @param boolean $exceptionOnError |
||
| 189 | * @return $this |
||
| 190 | */ |
||
| 191 | 2 | public function setExceptionOnError($exceptionOnError) |
|
| 197 | |||
| 198 | /** |
||
| 199 | * @return array |
||
| 200 | */ |
||
| 201 | 9 | public function getUrlsCrawled() |
|
| 205 | |||
| 206 | /** |
||
| 207 | * @return array |
||
| 208 | */ |
||
| 209 | 2 | public function getUrlsQueued() |
|
| 213 | |||
| 214 | /** |
||
| 215 | * @return array |
||
| 216 | */ |
||
| 217 | 2 | public function getUrlsRejected() |
|
| 221 | |||
| 222 | /** |
||
| 223 | * @return array |
||
| 224 | */ |
||
| 225 | 4 | public function getUrlsReturned() |
|
| 229 | |||
| 230 | /** |
||
| 231 | * @param $urlMatchers |
||
| 232 | * @return $this |
||
| 233 | */ |
||
| 234 | 2 | public function setWhitelistUrlMatchers(array $urlMatchers) |
|
| 243 | |||
| 244 | /** |
||
| 245 | * @return Url\Matcher\UrlMatcherInterface[] |
||
| 246 | */ |
||
| 247 | 3 | public function getWhitelistUrlMatchers() |
|
| 251 | |||
| 252 | /** |
||
| 253 | * @param UrlMatcherInterface $urlMatcher |
||
| 254 | * @return $this |
||
| 255 | */ |
||
| 256 | 3 | public function addWhitelistUrlMatcher(UrlMatcherInterface $urlMatcher) |
|
| 262 | |||
| 263 | /** |
||
| 264 | * @return $this |
||
| 265 | */ |
||
| 266 | 2 | public function clearWhitelistUrlMatchers() |
|
| 272 | |||
| 273 | /** |
||
| 274 | * @param array $urlMatchers |
||
| 275 | * @return $this |
||
| 276 | */ |
||
| 277 | 2 | public function setBlacklistUrlMatchers(array $urlMatchers) |
|
| 286 | |||
| 287 | /** |
||
| 288 | * @return Url\Matcher\UrlMatcherInterface[] |
||
| 289 | */ |
||
| 290 | 3 | public function getBlacklistUrlMatchers() |
|
| 294 | |||
| 295 | /** |
||
| 296 | * @param UrlMatcherInterface $urlMatcher |
||
| 297 | * @return $this |
||
| 298 | */ |
||
| 299 | 3 | public function addBlacklistUrlMatcher(UrlMatcherInterface $urlMatcher) |
|
| 305 | |||
| 306 | /** |
||
| 307 | * @return $this |
||
| 308 | */ |
||
| 309 | 2 | public function clearBlacklistUrlMatchers() |
|
| 315 | |||
| 316 | /** |
||
| 317 | * @param array $normalizers |
||
| 318 | * @return $this |
||
| 319 | */ |
||
| 320 | 2 | public function setUrlNormalizers(array $normalizers) |
|
| 330 | |||
| 331 | /** |
||
| 332 | * @return UrlNormalizerInterface[] |
||
| 333 | */ |
||
| 334 | 2 | public function getUrlNormalizers() |
|
| 338 | |||
| 339 | /** |
||
| 340 | * @param UrlNormalizerInterface $normalizer |
||
| 341 | * @return $this |
||
| 342 | */ |
||
| 343 | 3 | public function addUrlNormalizer(UrlNormalizerInterface $normalizer) |
|
| 349 | |||
| 350 | /** |
||
| 351 | * @return $this |
||
| 352 | */ |
||
| 353 | 2 | public function clearUrlNormalizers() |
|
| 359 | |||
| 360 | /** |
||
| 361 | * @return LoggerInterface |
||
| 362 | */ |
||
| 363 | 12 | public function getLogger() |
|
| 371 | |||
| 372 | /** |
||
| 373 | * @param LoggerInterface $logger |
||
| 374 | * @return $this |
||
| 375 | */ |
||
| 376 | 2 | public function setLogger(LoggerInterface $logger) |
|
| 382 | |||
| 383 | /** |
||
| 384 | * @param Url $url |
||
| 385 | */ |
||
| 386 | 9 | protected function addUrlToQueue(Url $url) |
|
| 390 | |||
| 391 | /** |
||
| 392 | * @param string $url |
||
| 393 | * @return Url |
||
| 394 | */ |
||
| 395 | 9 | protected function createHttpUrlString($url) |
|
| 399 | |||
| 400 | /** |
||
| 401 | * @param Url $url |
||
| 402 | */ |
||
| 403 | 9 | protected function reset(Url $url) |
|
| 411 | |||
| 412 | /** |
||
| 413 | * @param string $url |
||
| 414 | * @return \Generator |
||
| 415 | * @throws RequestException |
||
| 416 | */ |
||
| 417 | 9 | public function crawl($url) |
|
| 458 | |||
| 459 | /** |
||
| 460 | * @param DomCrawler $crawler |
||
| 461 | */ |
||
| 462 | 9 | protected function updateQueue(DomCrawler $crawler) |
|
| 480 | |||
| 481 | /** |
||
| 482 | * @param Url $url |
||
| 483 | * @return Url |
||
| 484 | */ |
||
| 485 | 8 | protected function normalizeUrl(Url $url) |
|
| 493 | |||
| 494 | /** |
||
| 495 | * @param Url $url |
||
| 496 | * @return bool |
||
| 497 | */ |
||
| 498 | 9 | protected function shouldReturnUrl(Url $url) |
|
| 516 | |||
| 517 | /** |
||
| 518 | * @param Url $url |
||
| 519 | * @return bool |
||
| 520 | */ |
||
| 521 | 1 | protected function isUrlWhitelisted(Url $url) |
|
| 531 | |||
| 532 | /** |
||
| 533 | * @param Url $url |
||
| 534 | * @return bool |
||
| 535 | */ |
||
| 536 | 9 | protected function isUrlBlacklisted(Url $url) |
|
| 546 | |||
| 547 | /** |
||
| 548 | * @param Url $url |
||
| 549 | * @return bool |
||
| 550 | */ |
||
| 551 | 8 | protected function shouldCrawlUrl(Url $url) |
|
| 565 | |||
| 566 | /** |
||
| 567 | * @param Url $url |
||
| 568 | * @return bool |
||
| 569 | */ |
||
| 570 | 8 | protected function isUrlRejected(Url $url) |
|
| 574 | |||
| 575 | /** |
||
| 576 | * @param Url $url |
||
| 577 | * @return bool |
||
| 578 | */ |
||
| 579 | 8 | protected function isUrlCrawled(Url $url) |
|
| 583 | |||
| 584 | /** |
||
| 585 | * @param Url $url |
||
| 586 | * @return bool |
||
| 587 | */ |
||
| 588 | 8 | protected function isUrlQueued(Url $url) |
|
| 592 | |||
| 593 | /** |
||
| 594 | * @param Url $url |
||
| 595 | * @return bool |
||
| 596 | */ |
||
| 597 | 8 | protected function isUrlPartOfBaseUrl(Url $url) |
|
| 607 | |||
| 608 | /** |
||
| 609 | * @return bool |
||
| 610 | */ |
||
| 611 | 9 | protected function isLimitReached() |
|
| 615 | |||
| 616 | /** |
||
| 617 | * @param DomCrawler $crawler |
||
| 618 | * @return array |
||
| 619 | */ |
||
| 620 | 9 | protected function extractUrlsFromCrawler(DomCrawler $crawler) |
|
| 628 | |||
| 629 | /** |
||
| 630 | * @param string $url |
||
| 631 | * @return DomCrawler |
||
| 632 | */ |
||
| 633 | 9 | protected function requestPage($url) |
|
| 641 | } |
||
| 642 |