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 | */ |
||
| 84 | 13 | public function __construct(Client $client = null) |
|
| 94 | |||
| 95 | /** |
||
| 96 | * @param Client $client |
||
| 97 | */ |
||
| 98 | 13 | public function setClient(Client $client) |
|
| 102 | |||
| 103 | /** |
||
| 104 | * @return Client |
||
| 105 | */ |
||
| 106 | 2 | public function getClient() |
|
| 110 | |||
| 111 | /** |
||
| 112 | * @return int |
||
| 113 | */ |
||
| 114 | 2 | public function getLimit() |
|
| 118 | |||
| 119 | /** |
||
| 120 | * @param int $limit |
||
| 121 | * @return $this |
||
| 122 | */ |
||
| 123 | 2 | public function setLimit($limit) |
|
| 129 | |||
| 130 | /** |
||
| 131 | * @return boolean |
||
| 132 | */ |
||
| 133 | 5 | public function getStopOnError() |
|
| 137 | |||
| 138 | /** |
||
| 139 | * @param boolean $stopOnError |
||
| 140 | * @return $this |
||
| 141 | */ |
||
| 142 | 2 | public function setStopOnError($stopOnError) |
|
| 148 | |||
| 149 | /** |
||
| 150 | * @return boolean |
||
| 151 | */ |
||
| 152 | 2 | public function getExceptionOnError() |
|
| 156 | |||
| 157 | /** |
||
| 158 | * @param boolean $exceptionOnError |
||
| 159 | * @return $this |
||
| 160 | */ |
||
| 161 | 1 | public function setExceptionOnError($exceptionOnError) |
|
| 167 | |||
| 168 | /** |
||
| 169 | * @return array |
||
| 170 | */ |
||
| 171 | 9 | public function getUrlsCrawled() |
|
| 175 | |||
| 176 | /** |
||
| 177 | * @return array |
||
| 178 | */ |
||
| 179 | 2 | public function getUrlsQueued() |
|
| 183 | |||
| 184 | /** |
||
| 185 | * @return array |
||
| 186 | */ |
||
| 187 | 2 | public function getUrlsRejected() |
|
| 191 | |||
| 192 | /** |
||
| 193 | * @return array |
||
| 194 | */ |
||
| 195 | 4 | public function getUrlsReturned() |
|
| 199 | |||
| 200 | /** |
||
| 201 | * @param $urlMatchers |
||
| 202 | * @return $this |
||
| 203 | */ |
||
| 204 | 1 | public function setWhitelistUrlMatchers(array $urlMatchers) |
|
| 213 | |||
| 214 | /** |
||
| 215 | * @return Url\Matcher\UrlMatcherInterface[] |
||
| 216 | */ |
||
| 217 | 2 | public function getWhitelistUrlMatchers() |
|
| 221 | |||
| 222 | /** |
||
| 223 | * @param UrlMatcherInterface $urlMatcher |
||
| 224 | * @return $this |
||
| 225 | */ |
||
| 226 | 2 | public function addWhitelistUrlMatcher(UrlMatcherInterface $urlMatcher) |
|
| 232 | |||
| 233 | /** |
||
| 234 | * @return $this |
||
| 235 | */ |
||
| 236 | 1 | public function clearWhitelistUrlMatchers() |
|
| 242 | |||
| 243 | /** |
||
| 244 | * @param array $urlMatchers |
||
| 245 | * @return $this |
||
| 246 | */ |
||
| 247 | 1 | public function setBlacklistUrlMatchers(array $urlMatchers) |
|
| 256 | |||
| 257 | /** |
||
| 258 | * @return Url\Matcher\UrlMatcherInterface[] |
||
| 259 | */ |
||
| 260 | 2 | public function getBlacklistUrlMatchers() |
|
| 264 | |||
| 265 | /** |
||
| 266 | * @param UrlMatcherInterface $urlMatcher |
||
| 267 | * @return $this |
||
| 268 | */ |
||
| 269 | 2 | public function addBlacklistUrlMatcher(UrlMatcherInterface $urlMatcher) |
|
| 275 | |||
| 276 | /** |
||
| 277 | * @return $this |
||
| 278 | */ |
||
| 279 | 1 | public function clearBlacklistUrlMatchers() |
|
| 285 | |||
| 286 | /** |
||
| 287 | * @param array $normalizers |
||
| 288 | * @return $this |
||
| 289 | */ |
||
| 290 | 1 | public function setUrlNormalizers(array $normalizers) |
|
| 300 | |||
| 301 | /** |
||
| 302 | * @return UrlNormalizerInterface[] |
||
| 303 | */ |
||
| 304 | 1 | public function getUrlNormalizers() |
|
| 308 | |||
| 309 | /** |
||
| 310 | * @param UrlNormalizerInterface $normalizer |
||
| 311 | * @return $this |
||
| 312 | */ |
||
| 313 | 2 | public function addUrlNormalizer(UrlNormalizerInterface $normalizer) |
|
| 319 | |||
| 320 | /** |
||
| 321 | * @return $this |
||
| 322 | */ |
||
| 323 | 1 | public function clearUrlNormalizers() |
|
| 329 | |||
| 330 | /** |
||
| 331 | * @return LoggerInterface |
||
| 332 | */ |
||
| 333 | 11 | public function getLogger() |
|
| 341 | |||
| 342 | /** |
||
| 343 | * @param LoggerInterface $logger |
||
| 344 | * @return $this |
||
| 345 | */ |
||
| 346 | 1 | public function setLogger(LoggerInterface $logger) |
|
| 352 | |||
| 353 | /** |
||
| 354 | * @param Url $url |
||
| 355 | */ |
||
| 356 | 9 | protected function addUrlToQueue(Url $url) |
|
| 360 | |||
| 361 | /** |
||
| 362 | * @param string $url |
||
| 363 | * @return Url |
||
| 364 | */ |
||
| 365 | 9 | protected function createHttpUrlString($url) |
|
| 369 | |||
| 370 | /** |
||
| 371 | * @param Url $url |
||
| 372 | */ |
||
| 373 | 9 | protected function reset(Url $url) |
|
| 381 | |||
| 382 | /** |
||
| 383 | * @param string $url |
||
| 384 | * @return \Generator |
||
| 385 | * @throws RequestException |
||
| 386 | */ |
||
| 387 | 9 | public function crawl($url) |
|
| 428 | |||
| 429 | /** |
||
| 430 | * @param DomCrawler $crawler |
||
| 431 | */ |
||
| 432 | 9 | protected function updateQueue(DomCrawler $crawler) |
|
| 450 | |||
| 451 | /** |
||
| 452 | * @param Url $url |
||
| 453 | * @return Url |
||
| 454 | */ |
||
| 455 | 8 | protected function normalizeUrl(Url $url) |
|
| 463 | |||
| 464 | /** |
||
| 465 | * @param Url $url |
||
| 466 | * @return bool |
||
| 467 | */ |
||
| 468 | 9 | protected function shouldReturnUrl(Url $url) |
|
| 486 | |||
| 487 | /** |
||
| 488 | * @param Url $url |
||
| 489 | * @return bool |
||
| 490 | */ |
||
| 491 | 1 | protected function isUrlWhitelisted(Url $url) |
|
| 501 | |||
| 502 | /** |
||
| 503 | * @param Url $url |
||
| 504 | * @return bool |
||
| 505 | */ |
||
| 506 | 9 | protected function isUrlBlacklisted(Url $url) |
|
| 516 | |||
| 517 | /** |
||
| 518 | * @param Url $url |
||
| 519 | * @return bool |
||
| 520 | */ |
||
| 521 | 8 | protected function shouldCrawlUrl(Url $url) |
|
| 535 | |||
| 536 | /** |
||
| 537 | * @param Url $url |
||
| 538 | * @return bool |
||
| 539 | */ |
||
| 540 | 8 | protected function isUrlRejected(Url $url) |
|
| 544 | |||
| 545 | /** |
||
| 546 | * @param Url $url |
||
| 547 | * @return bool |
||
| 548 | */ |
||
| 549 | 8 | protected function isUrlCrawled(Url $url) |
|
| 553 | |||
| 554 | /** |
||
| 555 | * @param Url $url |
||
| 556 | * @return bool |
||
| 557 | */ |
||
| 558 | 8 | protected function isUrlQueued(Url $url) |
|
| 562 | |||
| 563 | /** |
||
| 564 | * @param Url $url |
||
| 565 | * @return bool |
||
| 566 | */ |
||
| 567 | 8 | protected function isUrlPartOfBaseUrl(Url $url) |
|
| 577 | |||
| 578 | /** |
||
| 579 | * @return bool |
||
| 580 | */ |
||
| 581 | 9 | protected function isLimitReached() |
|
| 585 | |||
| 586 | /** |
||
| 587 | * @param DomCrawler $crawler |
||
| 588 | * @return array |
||
| 589 | */ |
||
| 590 | 9 | protected function extractUrlsFromCrawler(DomCrawler $crawler) |
|
| 598 | |||
| 599 | /** |
||
| 600 | * @param string $url |
||
| 601 | * @return DomCrawler |
||
| 602 | */ |
||
| 603 | 9 | protected function requestPage($url) |
|
| 611 | } |
||
| 612 |