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 |
||
| 13 | class Crawler implements LoggerAwareInterface |
||
| 14 | { |
||
| 15 | /** |
||
| 16 | * @var Client |
||
| 17 | */ |
||
| 18 | private $client; |
||
| 19 | |||
| 20 | /** |
||
| 21 | * @var int |
||
| 22 | */ |
||
| 23 | private $limit = 0; |
||
| 24 | |||
| 25 | /** |
||
| 26 | * @var bool |
||
| 27 | */ |
||
| 28 | private $stopOnError = false; |
||
| 29 | |||
| 30 | /** |
||
| 31 | * @var UrlMatcherInterface[] |
||
| 32 | */ |
||
| 33 | private $whitelistUrlMatchers = []; |
||
| 34 | |||
| 35 | /** |
||
| 36 | * @var UrlMatcherInterface[] |
||
| 37 | */ |
||
| 38 | private $blacklistUrlMatchers = []; |
||
| 39 | |||
| 40 | /** |
||
| 41 | * @var UrlNormalizerInterface[] |
||
| 42 | */ |
||
| 43 | private $urlNormalizers = []; |
||
| 44 | |||
| 45 | /** |
||
| 46 | * @var Url |
||
| 47 | */ |
||
| 48 | private $baseUrl; |
||
| 49 | |||
| 50 | /** |
||
| 51 | * @var array |
||
| 52 | */ |
||
| 53 | private $urlsCrawled = []; |
||
| 54 | |||
| 55 | /** |
||
| 56 | * @var array |
||
| 57 | */ |
||
| 58 | private $urlsQueued = []; |
||
| 59 | |||
| 60 | /** |
||
| 61 | * @var array |
||
| 62 | */ |
||
| 63 | private $urlsRejected = []; |
||
| 64 | |||
| 65 | /** |
||
| 66 | * @var array |
||
| 67 | */ |
||
| 68 | private $urlsReturned = []; |
||
| 69 | |||
| 70 | /** |
||
| 71 | * @var LoggerInterface |
||
| 72 | */ |
||
| 73 | private $logger = null; |
||
| 74 | |||
| 75 | /** |
||
| 76 | * @param Client $client |
||
| 77 | * @param array $options |
||
| 78 | */ |
||
| 79 | 13 | public function __construct(Client $client = null, array $options = []) |
|
| 90 | |||
| 91 | /** |
||
| 92 | * @param Client $client |
||
| 93 | */ |
||
| 94 | 13 | public function setClient(Client $client) |
|
| 98 | |||
| 99 | /** |
||
| 100 | * @return Client |
||
| 101 | */ |
||
| 102 | 2 | public function getClient() |
|
| 106 | |||
| 107 | /** |
||
| 108 | * @param array $options |
||
| 109 | */ |
||
| 110 | 13 | public function setOptions(array $options) |
|
| 131 | |||
| 132 | /** |
||
| 133 | * @return int |
||
| 134 | */ |
||
| 135 | 3 | public function getLimit() |
|
| 139 | |||
| 140 | /** |
||
| 141 | * @param int $limit |
||
| 142 | * @return $this |
||
| 143 | */ |
||
| 144 | 3 | public function setLimit($limit) |
|
| 150 | |||
| 151 | /** |
||
| 152 | * @return boolean |
||
| 153 | */ |
||
| 154 | 5 | public function getStopOnError() |
|
| 158 | |||
| 159 | /** |
||
| 160 | * @param boolean $stopOnError |
||
| 161 | * @return Crawler |
||
| 162 | */ |
||
| 163 | 3 | public function setStopOnError($stopOnError) |
|
| 169 | |||
| 170 | /** |
||
| 171 | * @return array |
||
| 172 | */ |
||
| 173 | 9 | public function getUrlsCrawled() |
|
| 177 | |||
| 178 | /** |
||
| 179 | * @return array |
||
| 180 | */ |
||
| 181 | 2 | public function getUrlsQueued() |
|
| 185 | |||
| 186 | /** |
||
| 187 | * @return array |
||
| 188 | */ |
||
| 189 | 2 | public function getUrlsRejected() |
|
| 193 | |||
| 194 | /** |
||
| 195 | * @return array |
||
| 196 | */ |
||
| 197 | 4 | public function getUrlsReturned() |
|
| 201 | |||
| 202 | /** |
||
| 203 | * @param $urlMatchers |
||
| 204 | * @return $this |
||
| 205 | */ |
||
| 206 | 2 | public function setWhitelistUrlMatchers(array $urlMatchers) |
|
| 215 | |||
| 216 | /** |
||
| 217 | * @return Url\Matcher\UrlMatcherInterface[] |
||
| 218 | */ |
||
| 219 | 3 | public function getWhitelistUrlMatchers() |
|
| 223 | |||
| 224 | /** |
||
| 225 | * @param UrlMatcherInterface $urlMatcher |
||
| 226 | * @return $this |
||
| 227 | */ |
||
| 228 | 3 | public function addWhitelistUrlMatcher(UrlMatcherInterface $urlMatcher) |
|
| 234 | |||
| 235 | /** |
||
| 236 | * @return $this |
||
| 237 | */ |
||
| 238 | 2 | public function clearWhitelistUrlMatchers() |
|
| 244 | |||
| 245 | /** |
||
| 246 | * @param array $urlMatchers |
||
| 247 | * @return $this |
||
| 248 | */ |
||
| 249 | 2 | public function setBlacklistUrlMatchers(array $urlMatchers) |
|
| 258 | |||
| 259 | /** |
||
| 260 | * @return Url\Matcher\UrlMatcherInterface[] |
||
| 261 | */ |
||
| 262 | 3 | public function getBlacklistUrlMatchers() |
|
| 266 | |||
| 267 | /** |
||
| 268 | * @param UrlMatcherInterface $urlMatcher |
||
| 269 | * @return $this |
||
| 270 | */ |
||
| 271 | 3 | public function addBlacklistUrlMatcher(UrlMatcherInterface $urlMatcher) |
|
| 277 | |||
| 278 | /** |
||
| 279 | * @return $this |
||
| 280 | */ |
||
| 281 | 2 | public function clearBlacklistUrlMatchers() |
|
| 287 | |||
| 288 | /** |
||
| 289 | * @param array $normalizers |
||
| 290 | * @return $this |
||
| 291 | */ |
||
| 292 | 1 | public function setUrlNormalizers(array $normalizers) |
|
| 302 | |||
| 303 | /** |
||
| 304 | * @return UrlNormalizerInterface[] |
||
| 305 | */ |
||
| 306 | 1 | public function getUrlNormalizers() |
|
| 310 | |||
| 311 | /** |
||
| 312 | * @param UrlNormalizerInterface $normalizer |
||
| 313 | * @return $this |
||
| 314 | */ |
||
| 315 | 2 | public function addUrlNormalizer(UrlNormalizerInterface $normalizer) |
|
| 321 | |||
| 322 | /** |
||
| 323 | * @return $this |
||
| 324 | */ |
||
| 325 | 1 | public function clearUrlNormalizers() |
|
| 331 | |||
| 332 | /** |
||
| 333 | * @return LoggerInterface |
||
| 334 | */ |
||
| 335 | 11 | public function getLogger() |
|
| 343 | |||
| 344 | /** |
||
| 345 | * @param LoggerInterface $logger |
||
| 346 | * @return $this |
||
| 347 | */ |
||
| 348 | 2 | public function setLogger(LoggerInterface $logger) |
|
| 354 | |||
| 355 | /** |
||
| 356 | * @param Url $url |
||
| 357 | */ |
||
| 358 | 8 | protected function addUrlToQueue(Url $url) |
|
| 362 | |||
| 363 | /** |
||
| 364 | * @param string $url |
||
| 365 | * @return Url |
||
| 366 | */ |
||
| 367 | 8 | protected function createHttpUrlString($url) |
|
| 371 | |||
| 372 | /** |
||
| 373 | * @param Url $url |
||
| 374 | */ |
||
| 375 | 8 | protected function reset(Url $url) |
|
| 383 | |||
| 384 | /** |
||
| 385 | * @param string $url |
||
| 386 | * @return \Generator |
||
| 387 | */ |
||
| 388 | 8 | public function crawl($url) |
|
| 389 | { |
||
| 390 | 8 | $url = $this->createHttpUrlString($url); |
|
| 391 | 8 | $this->reset($url); |
|
| 392 | |||
| 393 | 8 | while (count($this->urlsQueued) > 0) { |
|
| 394 | |||
| 395 | 8 | $url = array_shift($this->urlsQueued); |
|
| 396 | |||
| 397 | try { |
||
| 398 | 8 | $crawler = $this->requestPage((string)$url); |
|
| 399 | 8 | } catch (\Exception $e) { |
|
| 400 | 2 | $this->getLogger()->error(sprintf('Error requesting page %s: %s', $url, $e->getMessage())); |
|
| 401 | |||
| 402 | 2 | if ($this->getStopOnError()) { |
|
| 403 | 1 | return; |
|
| 404 | } |
||
| 405 | |||
| 406 | 1 | continue; |
|
| 407 | } |
||
| 408 | |||
| 409 | 8 | $this->urlsCrawled[] = (string)$url; |
|
| 410 | 8 | $this->updateQueue($crawler); |
|
| 411 | |||
| 412 | 8 | if ($this->shouldReturnUrl($url)) { |
|
| 413 | 8 | $this->getLogger()->debug(sprintf('Return url "%s"', $url)); |
|
| 414 | |||
| 415 | 8 | $this->urlsReturned[] = (string)$url; |
|
| 416 | |||
| 417 | 8 | yield new Page($url, $crawler); |
|
| 418 | 8 | } |
|
| 419 | |||
| 420 | 8 | if ($this->isLimitReached()) { |
|
| 421 | 1 | $this->getLogger()->info(sprintf('Crawl limit of %d was reach', $this->limit)); |
|
| 422 | |||
| 423 | 1 | return; |
|
| 424 | } |
||
| 425 | 8 | } |
|
| 426 | 6 | } |
|
| 427 | |||
| 428 | /** |
||
| 429 | * @param DomCrawler $crawler |
||
| 430 | */ |
||
| 431 | 8 | protected function updateQueue(DomCrawler $crawler) |
|
| 449 | |||
| 450 | /** |
||
| 451 | * @param Url $url |
||
| 452 | * @return Url |
||
| 453 | */ |
||
| 454 | 7 | protected function normalizeUrl(Url $url) |
|
| 462 | |||
| 463 | /** |
||
| 464 | * @param Url $url |
||
| 465 | * @return bool |
||
| 466 | */ |
||
| 467 | 8 | protected function shouldReturnUrl(Url $url) |
|
| 485 | |||
| 486 | /** |
||
| 487 | * @param Url $url |
||
| 488 | * @return bool |
||
| 489 | */ |
||
| 490 | 1 | protected function isUrlWhitelisted(Url $url) |
|
| 500 | |||
| 501 | /** |
||
| 502 | * @param Url $url |
||
| 503 | * @return bool |
||
| 504 | */ |
||
| 505 | 8 | protected function isUrlBlacklisted(Url $url) |
|
| 515 | |||
| 516 | /** |
||
| 517 | * @param Url $url |
||
| 518 | * @return bool |
||
| 519 | */ |
||
| 520 | 7 | protected function shouldCrawlUrl(Url $url) |
|
| 521 | { |
||
| 522 | 7 | $urlString = (string)$url; |
|
| 523 | 7 | if (in_array($urlString, $this->urlsRejected)) { |
|
| 524 | 5 | return false; |
|
| 525 | } |
||
| 526 | 7 | if (in_array($urlString, $this->urlsCrawled)) { |
|
| 527 | 5 | return false; |
|
| 528 | } |
||
| 529 | 7 | if (isset($this->urlsQueued[$urlString])) { |
|
| 530 | 1 | return false; |
|
| 531 | } |
||
| 532 | |||
| 533 | 7 | if (!$this->isUrlPartOfBaseUrl($url)) { |
|
| 534 | 6 | $this->urlsRejected[] = (string)$url; |
|
| 535 | |||
| 536 | 6 | return false; |
|
| 537 | } |
||
| 538 | |||
| 539 | 7 | return true; |
|
| 540 | } |
||
| 541 | |||
| 542 | /** |
||
| 543 | * @param Url $url |
||
| 544 | * @return bool |
||
| 545 | */ |
||
| 546 | 7 | protected function isUrlPartOfBaseUrl(Url $url) |
|
| 556 | |||
| 557 | /** |
||
| 558 | * @return bool |
||
| 559 | */ |
||
| 560 | 8 | private function isLimitReached() |
|
| 564 | |||
| 565 | /** |
||
| 566 | * @param DomCrawler $crawler |
||
| 567 | * @return array |
||
| 568 | */ |
||
| 569 | 8 | protected function extractUrlsFromCrawler(DomCrawler $crawler) |
|
| 577 | |||
| 578 | /** |
||
| 579 | * @param $url |
||
| 580 | * @return DomCrawler |
||
| 581 | */ |
||
| 582 | 8 | protected function requestPage($url) |
|
| 590 | } |
||
| 591 |