wasinger /
htmlpagedom
Complex classes like HtmlPageCrawler 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 HtmlPageCrawler, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 15 | class HtmlPageCrawler extends Crawler |
||
| 16 | { |
||
| 17 | /** |
||
| 18 | * the (internal) root element name used when importing html fragments |
||
| 19 | * */ |
||
| 20 | const FRAGMENT_ROOT_TAGNAME = '_root'; |
||
| 21 | |||
| 22 | /** |
||
| 23 | * Get an HtmlPageCrawler object from a HTML string, DOMNode, DOMNodeList or HtmlPageCrawler |
||
| 24 | * |
||
| 25 | * This is the equivalent to jQuery's $() function when used for wrapping DOMNodes or creating DOMElements from HTML code. |
||
| 26 | * |
||
| 27 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList|array $content |
||
| 28 | * @return HtmlPageCrawler |
||
| 29 | * @api |
||
| 30 | */ |
||
| 31 | 11 | public static function create($content) |
|
| 39 | |||
| 40 | /** |
||
| 41 | * Adds the specified class(es) to each element in the set of matched elements. |
||
| 42 | * |
||
| 43 | * @param string $name One or more space-separated classes to be added to the class attribute of each matched element. |
||
| 44 | * @return HtmlPageCrawler $this for chaining |
||
| 45 | * @api |
||
| 46 | */ |
||
| 47 | 1 | public function addClass($name) |
|
| 68 | |||
| 69 | /** |
||
| 70 | * Insert content, specified by the parameter, after each element in the set of matched elements. |
||
| 71 | * |
||
| 72 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content |
||
| 73 | * @return HtmlPageCrawler $this for chaining |
||
| 74 | * @api |
||
| 75 | */ |
||
| 76 | 3 | public function after($content) |
|
| 98 | |||
| 99 | /** |
||
| 100 | * Insert HTML content as child nodes of each element after existing children |
||
| 101 | * |
||
| 102 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content HTML code fragment or DOMNode to append |
||
| 103 | * @return HtmlPageCrawler $this for chaining |
||
| 104 | * @api |
||
| 105 | */ |
||
| 106 | 2 | public function append($content) |
|
| 130 | |||
| 131 | /** |
||
| 132 | * Insert every element in the set of matched elements to the end of the target. |
||
| 133 | * |
||
| 134 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
| 135 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
| 136 | * @api |
||
| 137 | */ |
||
| 138 | 1 | public function appendTo($element) |
|
| 153 | |||
| 154 | /** |
||
| 155 | * Returns the attribute value of the first node of the list, or sets an attribute on each element |
||
| 156 | * |
||
| 157 | * @see HtmlPageCrawler::getAttribute() |
||
| 158 | * @see HtmlPageCrawler::setAttribute |
||
| 159 | * |
||
| 160 | * @param string $name |
||
| 161 | * @param null|string $value |
||
| 162 | * @return null|string|HtmlPageCrawler |
||
| 163 | * @api |
||
| 164 | */ |
||
| 165 | 1 | public function attr($name, $value = null) |
|
| 173 | |||
| 174 | /** |
||
| 175 | * Sets an attribute on each element |
||
| 176 | * |
||
| 177 | * @param string $name |
||
| 178 | * @param string $value |
||
| 179 | * @return HtmlPageCrawler $this for chaining |
||
| 180 | */ |
||
| 181 | 2 | public function setAttribute($name, $value) |
|
| 191 | |||
| 192 | /** |
||
| 193 | * Returns the attribute value of the first node of the list. |
||
| 194 | * |
||
| 195 | * @param string $name The attribute name |
||
| 196 | * @return string|null The attribute value or null if the attribute does not exist |
||
| 197 | * @throws \InvalidArgumentException When current node is empty |
||
| 198 | * |
||
| 199 | */ |
||
| 200 | 1 | public function getAttribute($name) |
|
| 208 | |||
| 209 | /** |
||
| 210 | * Insert content, specified by the parameter, before each element in the set of matched elements. |
||
| 211 | * |
||
| 212 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content |
||
| 213 | * @return HtmlPageCrawler $this for chaining |
||
| 214 | * @api |
||
| 215 | */ |
||
| 216 | 2 | public function before($content) |
|
| 233 | |||
| 234 | /** |
||
| 235 | * Create a deep copy of the set of matched elements. |
||
| 236 | * |
||
| 237 | * Equivalent to clone() in jQuery (clone is not a valid PHP function name) |
||
| 238 | * |
||
| 239 | * @return HtmlPageCrawler |
||
| 240 | * @api |
||
| 241 | */ |
||
| 242 | 1 | public function makeClone() |
|
| 246 | |||
| 247 | 1 | public function __clone() |
|
| 257 | |||
| 258 | /** |
||
| 259 | * Get one CSS style property of the first element or set it for all elements in the list |
||
| 260 | * |
||
| 261 | * Function is here for compatibility with jQuery; it is the same as getStyle() and setStyle() |
||
| 262 | * |
||
| 263 | * @see HtmlPageCrawler::getStyle() |
||
| 264 | * @see HtmlPageCrawler::setStyle() |
||
| 265 | * |
||
| 266 | * @param string $key The name of the style property |
||
| 267 | * @param null|string $value The CSS value to set, or NULL to get the current value |
||
| 268 | * @return HtmlPageCrawler|string If no param is provided, returns the CSS styles of the first element |
||
| 269 | * @api |
||
| 270 | */ |
||
| 271 | 1 | public function css($key, $value = null) |
|
| 279 | |||
| 280 | /** |
||
| 281 | * get one CSS style property of the first element |
||
| 282 | * |
||
| 283 | * @param string $key name of the property |
||
| 284 | * @return string|null value of the property |
||
| 285 | */ |
||
| 286 | 1 | public function getStyle($key) |
|
| 291 | |||
| 292 | /** |
||
| 293 | * set one CSS style property for all elements in the list |
||
| 294 | * |
||
| 295 | * @param string $key name of the property |
||
| 296 | * @param string $value value of the property |
||
| 297 | * @return HtmlPageCrawler $this for chaining |
||
| 298 | */ |
||
| 299 | 1 | public function setStyle($key, $value) |
|
| 315 | |||
| 316 | /** |
||
| 317 | * Removes all child nodes and text from all nodes in set |
||
| 318 | * |
||
| 319 | * Equivalent to jQuery's empty() function which is not a valid function name in PHP |
||
| 320 | * @return HtmlPageCrawler $this |
||
| 321 | * @api |
||
| 322 | */ |
||
| 323 | public function makeEmpty() |
||
| 324 | { |
||
| 325 | foreach ($this as $node) { |
||
| 326 | $node->nodeValue = ''; |
||
| 327 | } |
||
| 328 | return $this; |
||
| 329 | } |
||
| 330 | |||
| 331 | /** |
||
| 332 | * Determine whether any of the matched elements are assigned the given class. |
||
| 333 | * |
||
| 334 | * @param string $name |
||
| 335 | * @return bool |
||
| 336 | * @api |
||
| 337 | */ |
||
| 338 | 2 | public function hasClass($name) |
|
| 350 | |||
| 351 | /** |
||
| 352 | * Get the HTML contents of the first element in the set of matched elements |
||
| 353 | * or set the HTML contents of every matched element. |
||
| 354 | * |
||
| 355 | * Function is here for compatibility with jQuery: When called with a parameter, it is |
||
| 356 | * equivalent to setInnerHtml(), without parameter it is the same as getInnerHtml() |
||
| 357 | * |
||
| 358 | * @see HtmlPageCrawler::setInnerHtml() |
||
| 359 | * @see HtmlPageCrawler::getInnerHtml() |
||
| 360 | * |
||
| 361 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList|null $html The HTML content to set, or NULL to get the current content |
||
| 362 | * |
||
| 363 | * @return HtmlPageCrawler|string If no param is provided, returns the HTML content of the first element |
||
| 364 | * @api |
||
| 365 | */ |
||
| 366 | public function html($html = null) |
||
| 375 | |||
| 376 | /** |
||
| 377 | * Get the innerHTML contents of the first element |
||
| 378 | * |
||
| 379 | * @return string HTML code fragment |
||
| 380 | */ |
||
| 381 | 2 | public function getInnerHtml() |
|
| 385 | |||
| 386 | /** |
||
| 387 | * Set the HTML contents of each element |
||
| 388 | * |
||
| 389 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content HTML code fragment |
||
| 390 | * @return HtmlPageCrawler $this for chaining |
||
| 391 | */ |
||
| 392 | 1 | public function setInnerHtml($content) |
|
| 393 | { |
||
| 394 | 1 | $content = self::create($content); |
|
| 395 | 1 | foreach ($this as $node) { |
|
| 396 | 1 | $node->nodeValue = ''; |
|
| 397 | 1 | foreach ($content as $newnode) { |
|
| 398 | /** @var \DOMNode $node */ |
||
| 399 | /** @var \DOMNode $newnode */ |
||
| 400 | 1 | $newnode = static::importNewnode($newnode, $node); |
|
| 401 | 1 | $node->appendChild($newnode); |
|
| 402 | 1 | } |
|
| 403 | 1 | } |
|
| 404 | 1 | return $this; |
|
| 405 | } |
||
| 406 | |||
| 407 | /** |
||
| 408 | * Insert every element in the set of matched elements after the target. |
||
| 409 | * |
||
| 410 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
| 411 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
| 412 | * @api |
||
| 413 | */ |
||
| 414 | 1 | public function insertAfter($element) |
|
| 415 | { |
||
| 416 | 1 | $e = self::create($element); |
|
| 417 | 1 | $newnodes = array(); |
|
| 418 | 1 | foreach ($e as $i => $node) { |
|
| 419 | /** @var \DOMNode $node */ |
||
| 420 | 1 | $refnode = $node->nextSibling; |
|
| 421 | 1 | foreach ($this as $newnode) { |
|
| 422 | /** @var \DOMNode $newnode */ |
||
| 423 | 1 | $newnode = static::importNewnode($newnode, $node, $i); |
|
| 424 | 1 | if ($refnode === null) { |
|
| 425 | 1 | $node->parentNode->appendChild($newnode); |
|
| 426 | 1 | } else { |
|
| 427 | 1 | $node->parentNode->insertBefore($newnode, $refnode); |
|
| 428 | } |
||
| 429 | 1 | $newnodes[] = $newnode; |
|
| 430 | 1 | } |
|
| 431 | 1 | } |
|
| 432 | 1 | return self::create($newnodes); |
|
| 433 | } |
||
| 434 | |||
| 435 | /** |
||
| 436 | * Insert every element in the set of matched elements before the target. |
||
| 437 | * |
||
| 438 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
| 439 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
| 440 | * @api |
||
| 441 | */ |
||
| 442 | 1 | public function insertBefore($element) |
|
| 443 | { |
||
| 444 | 1 | $e = self::create($element); |
|
| 445 | 1 | $newnodes = array(); |
|
| 446 | 1 | foreach ($e as $i => $node) { |
|
| 447 | /** @var \DOMNode $node */ |
||
| 448 | 1 | foreach ($this as $newnode) { |
|
| 449 | /** @var \DOMNode $newnode */ |
||
| 450 | 1 | $newnode = static::importNewnode($newnode, $node, $i); |
|
| 451 | 1 | $node->parentNode->insertBefore($newnode, $node); |
|
| 452 | 1 | $newnodes[] = $newnode; |
|
| 453 | 1 | } |
|
| 454 | 1 | } |
|
| 455 | 1 | return self::create($newnodes); |
|
| 456 | } |
||
| 457 | |||
| 458 | /** |
||
| 459 | * Insert content, specified by the parameter, to the beginning of each element in the set of matched elements. |
||
| 460 | * |
||
| 461 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content HTML code fragment |
||
| 462 | * @return HtmlPageCrawler $this for chaining |
||
| 463 | * @api |
||
| 464 | */ |
||
| 465 | 1 | public function prepend($content) |
|
| 466 | { |
||
| 467 | 1 | $content = self::create($content); |
|
| 468 | 1 | $newnodes = array(); |
|
| 469 | 1 | foreach ($this as $i => $node) { |
|
| 470 | 1 | $refnode = $node->firstChild; |
|
| 471 | /** @var \DOMNode $node */ |
||
| 472 | 1 | foreach ($content as $newnode) { |
|
| 473 | /** @var \DOMNode $newnode */ |
||
| 474 | 1 | $newnode = static::importNewnode($newnode, $node, $i); |
|
| 475 | 1 | if ($refnode === null) { |
|
| 476 | $node->appendChild($newnode); |
||
| 477 | } else { |
||
| 478 | 1 | $node->insertBefore($newnode, $refnode); |
|
| 479 | } |
||
| 480 | 1 | $newnodes[] = $newnode; |
|
| 481 | 1 | } |
|
| 482 | 1 | } |
|
| 483 | 1 | $content->clear(); |
|
| 484 | 1 | $content->add($newnodes); |
|
| 485 | 1 | return $this; |
|
| 486 | } |
||
| 487 | |||
| 488 | /** |
||
| 489 | * Insert every element in the set of matched elements to the beginning of the target. |
||
| 490 | * |
||
| 491 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
| 492 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements prepended to the target elements |
||
| 493 | * @api |
||
| 494 | */ |
||
| 495 | public function prependTo($element) |
||
| 496 | { |
||
| 497 | $e = self::create($element); |
||
| 498 | $newnodes = array(); |
||
| 499 | foreach ($e as $i => $node) { |
||
| 500 | $refnode = $node->firstChild; |
||
| 501 | /** @var \DOMNode $node */ |
||
| 502 | foreach ($this as $newnode) { |
||
| 503 | /** @var \DOMNode $newnode */ |
||
| 504 | $newnode = static::importNewnode($newnode, $node, $i); |
||
| 505 | if ($refnode === null) { |
||
| 506 | $node->appendChild($newnode); |
||
| 507 | } else { |
||
| 508 | $node->insertBefore($newnode, $refnode); |
||
| 509 | } |
||
| 510 | $newnodes[] = $newnode; |
||
| 511 | } |
||
| 512 | } |
||
| 513 | return self::create($newnodes); |
||
| 514 | } |
||
| 515 | |||
| 516 | /** |
||
| 517 | * Remove the set of matched elements from the DOM. |
||
| 518 | * |
||
| 519 | * (as opposed to Crawler::clear() which detaches the nodes only from Crawler |
||
| 520 | * but leaves them in the DOM) |
||
| 521 | * |
||
| 522 | * @api |
||
| 523 | */ |
||
| 524 | 2 | public function remove() |
|
| 525 | { |
||
| 526 | 2 | foreach ($this as $node) { |
|
| 527 | /** |
||
| 528 | * @var \DOMNode $node |
||
| 529 | */ |
||
| 530 | 2 | if ($node->parentNode instanceof \DOMElement) { |
|
| 531 | 2 | $node->parentNode->removeChild($node); |
|
| 532 | 2 | } |
|
| 533 | 2 | } |
|
| 534 | 2 | $this->clear(); |
|
| 535 | 2 | } |
|
| 536 | |||
| 537 | /** |
||
| 538 | * Remove an attribute from each element in the set of matched elements. |
||
| 539 | * |
||
| 540 | * Alias for removeAttribute for compatibility with jQuery |
||
| 541 | * |
||
| 542 | * @param string $name |
||
| 543 | * @return HtmlPageCrawler |
||
| 544 | * @api |
||
| 545 | */ |
||
| 546 | 1 | public function removeAttr($name) |
|
| 550 | |||
| 551 | /** |
||
| 552 | * Remove an attribute from each element in the set of matched elements. |
||
| 553 | * |
||
| 554 | * @param string $name |
||
| 555 | * @return HtmlPageCrawler |
||
| 556 | */ |
||
| 557 | 1 | public function removeAttribute($name) |
|
| 558 | { |
||
| 559 | 1 | foreach ($this as $node) { |
|
| 560 | 1 | if ($node instanceof \DOMElement) { |
|
| 561 | /** @var \DOMElement $node */ |
||
| 562 | 1 | if ($node->hasAttribute($name)) { |
|
| 563 | 1 | $node->removeAttribute($name); |
|
| 564 | 1 | } |
|
| 565 | 1 | } |
|
| 566 | 1 | } |
|
| 567 | 1 | return $this; |
|
| 568 | } |
||
| 569 | |||
| 570 | /** |
||
| 571 | * Remove a class from each element in the list |
||
| 572 | * |
||
| 573 | * @param string $name |
||
| 574 | * @return HtmlPageCrawler $this for chaining |
||
| 575 | * @api |
||
| 576 | */ |
||
| 577 | 2 | public function removeClass($name) |
|
| 578 | { |
||
| 579 | 2 | foreach ($this as $node) { |
|
| 580 | 2 | if ($node instanceof \DOMElement) { |
|
| 581 | /** @var \DOMElement $node */ |
||
| 582 | 2 | $classes = preg_split('/\s+/s', $node->getAttribute('class')); |
|
| 583 | 2 | $count = count($classes); |
|
| 584 | 2 | for ($i = 0; $i < $count; $i++) { |
|
| 585 | 2 | if ($classes[$i] == $name) { |
|
| 586 | 2 | unset($classes[$i]); |
|
| 587 | 2 | } |
|
| 588 | 2 | } |
|
| 589 | 2 | $node->setAttribute('class', trim(join(' ', $classes))); |
|
| 590 | 2 | } |
|
| 591 | 2 | } |
|
| 592 | 2 | return $this; |
|
| 593 | } |
||
| 594 | |||
| 595 | /** |
||
| 596 | * Replace each target element with the set of matched elements. |
||
| 597 | * |
||
| 598 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
| 599 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
| 600 | * @api |
||
| 601 | */ |
||
| 602 | 2 | public function replaceAll($element) |
|
| 603 | { |
||
| 604 | 2 | $e = self::create($element); |
|
| 605 | 2 | $newnodes = array(); |
|
| 606 | 2 | foreach ($e as $i => $node) { |
|
| 607 | /** @var \DOMNode $node */ |
||
| 608 | 2 | $parent = $node->parentNode; |
|
| 609 | 2 | $refnode = $node->nextSibling; |
|
| 610 | 2 | foreach ($this as $j => $newnode) { |
|
| 611 | /** @var \DOMNode $newnode */ |
||
| 612 | 2 | $newnode = static::importNewnode($newnode, $node, $i); |
|
| 613 | 2 | if ($j == 0) { |
|
| 614 | 2 | $parent->replaceChild($newnode, $node); |
|
| 615 | 2 | } else { |
|
| 616 | 1 | $parent->insertBefore($newnode, $refnode); |
|
| 617 | } |
||
| 618 | 2 | $newnodes[] = $newnode; |
|
| 619 | 2 | } |
|
| 620 | 2 | } |
|
| 621 | 2 | return self::create($newnodes); |
|
| 622 | } |
||
| 623 | |||
| 624 | /** |
||
| 625 | * Replace each element in the set of matched elements with the provided new content and return the set of elements that was removed. |
||
| 626 | * |
||
| 627 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content |
||
| 628 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
| 629 | * @api |
||
| 630 | */ |
||
| 631 | 2 | public function replaceWith($content) |
|
| 632 | { |
||
| 633 | 2 | $content = self::create($content); |
|
| 634 | 2 | $newnodes = array(); |
|
| 635 | 2 | foreach ($this as $i => $node) { |
|
| 636 | /** @var \DOMNode $node */ |
||
| 637 | 2 | $parent = $node->parentNode; |
|
| 638 | 2 | $refnode = $node->nextSibling; |
|
| 639 | 2 | foreach ($content as $j => $newnode) { |
|
| 640 | /** @var \DOMNode $newnode */ |
||
| 641 | 2 | $newnode = static::importNewnode($newnode, $node, $i); |
|
| 642 | 2 | if ($j == 0) { |
|
| 643 | 2 | $parent->replaceChild($newnode, $node); |
|
| 644 | 2 | } else { |
|
| 645 | 1 | $parent->insertBefore($newnode, $refnode); |
|
| 646 | } |
||
| 647 | 2 | $newnodes[] = $newnode; |
|
| 648 | 2 | } |
|
| 649 | 2 | } |
|
| 650 | 2 | $content->clear(); |
|
| 651 | 2 | $content->add($newnodes); |
|
| 652 | 2 | return $this; |
|
| 653 | } |
||
| 654 | |||
| 655 | /** |
||
| 656 | * Get the combined text contents of each element in the set of matched elements, including their descendants, |
||
| 657 | * or set the text contents of the matched elements. |
||
| 658 | * |
||
| 659 | * ATTENTION: Contrary to the parent Crawler class, which returns the text from the first element only, |
||
| 660 | * this functions returns the combined text of all elements (as jQuery does). If this is not what you need you |
||
| 661 | * must call ->first() before calling ->text(), e.g. |
||
| 662 | * |
||
| 663 | * in Symfony\DOMCrawler\Crawler: $c->filter('p')->text() returns the text of the first paragraph only |
||
| 664 | * in HtmlPageCrawler you need to call: $c->filter('p')->first()->text() |
||
| 665 | * |
||
| 666 | * @param null|string $text |
||
| 667 | * @return string|HtmlPageCrawler |
||
| 668 | * @api |
||
| 669 | */ |
||
| 670 | 1 | public function text($text = null) |
|
| 671 | { |
||
| 672 | 1 | if ($text === null) { |
|
| 673 | 1 | $text = ''; |
|
| 674 | 1 | foreach ($this as $node) { |
|
| 675 | /** @var \DOMNode $node */ |
||
| 676 | 1 | $text .= $node->nodeValue; |
|
| 677 | 1 | } |
|
| 678 | 1 | return $text; |
|
| 679 | } else { |
||
| 680 | 1 | foreach ($this as $node) { |
|
| 681 | /** @var \DOMNode $node */ |
||
| 682 | 1 | $node->nodeValue = $text; |
|
| 683 | 1 | } |
|
| 684 | 1 | return $this; |
|
| 685 | } |
||
| 686 | } |
||
| 687 | |||
| 688 | |||
| 689 | /** |
||
| 690 | * Add or remove one or more classes from each element in the set of matched elements, depending the class’s presence. |
||
| 691 | * |
||
| 692 | * @param string $classname One or more classnames separated by spaces |
||
| 693 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
| 694 | * @api |
||
| 695 | */ |
||
| 696 | 1 | public function toggleClass($classname) |
|
| 697 | { |
||
| 698 | 1 | $classes = explode(' ', $classname); |
|
| 699 | 1 | foreach ($this as $i => $node) { |
|
| 700 | 1 | $c = self::create($node); |
|
| 701 | /** @var \DOMNode $node */ |
||
| 702 | 1 | foreach ($classes as $class) { |
|
| 703 | 1 | if ($c->hasClass($class)) { |
|
| 704 | 1 | $c->removeClass($class); |
|
| 705 | 1 | } else { |
|
| 706 | 1 | $c->addClass($class); |
|
| 707 | } |
||
| 708 | 1 | } |
|
| 709 | 1 | } |
|
| 710 | 1 | return $this; |
|
| 711 | } |
||
| 712 | |||
| 713 | /** |
||
| 714 | * Remove the parents of the set of matched elements from the DOM, leaving the matched elements in their place. |
||
| 715 | * |
||
| 716 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
| 717 | * @api |
||
| 718 | */ |
||
| 719 | 1 | public function unwrap() |
|
| 720 | { |
||
| 721 | 1 | $parents = array(); |
|
| 722 | 1 | foreach($this as $i => $node) { |
|
| 723 | 1 | $parents[] = $node->parentNode; |
|
| 724 | 1 | } |
|
| 725 | |||
| 726 | 1 | self::create($parents)->unwrapInner(); |
|
| 727 | 1 | return $this; |
|
| 728 | } |
||
| 729 | |||
| 730 | /** |
||
| 731 | * Remove the matched elements, but promote the children to take their place. |
||
| 732 | * |
||
| 733 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
| 734 | * @api |
||
| 735 | */ |
||
| 736 | 1 | public function unwrapInner() |
|
| 737 | { |
||
| 738 | 1 | foreach($this as $i => $node) { |
|
| 739 | 1 | if (!$node->parentNode instanceof \DOMElement) { |
|
| 740 | throw new \InvalidArgumentException('DOMElement does not have a parent DOMElement node.'); |
||
| 741 | } |
||
| 742 | |||
| 743 | /** @var \DOMNode[] $children */ |
||
| 744 | 1 | $children = iterator_to_array($node->childNodes); |
|
| 745 | 1 | foreach ($children as $child) { |
|
| 746 | 1 | $node->parentNode->insertBefore($child, $node); |
|
| 747 | 1 | } |
|
| 748 | |||
| 749 | 1 | $node->parentNode->removeChild($node); |
|
| 750 | 1 | } |
|
| 751 | 1 | } |
|
| 752 | |||
| 753 | |||
| 754 | /** |
||
| 755 | * Wrap an HTML structure around each element in the set of matched elements |
||
| 756 | * |
||
| 757 | * The HTML structure must contain only one root node, e.g.: |
||
| 758 | * Works: <div><div></div></div> |
||
| 759 | * Does not work: <div></div><div></div> |
||
| 760 | * |
||
| 761 | * @param string|HtmlPageCrawler|\DOMNode $wrappingElement |
||
| 762 | * @return HtmlPageCrawler $this for chaining |
||
| 763 | * @api |
||
| 764 | */ |
||
| 765 | 1 | public function wrap($wrappingElement) |
|
| 766 | { |
||
| 767 | 1 | $content = self::create($wrappingElement); |
|
| 768 | 1 | $newnodes = array(); |
|
| 769 | 1 | foreach ($this as $i => $node) { |
|
| 770 | /** @var \DOMNode $node */ |
||
| 771 | 1 | $newnode = $content->getNode(0); |
|
| 772 | /** @var \DOMNode $newnode */ |
||
| 773 | // $newnode = static::importNewnode($newnode, $node, $i); |
||
| 774 | 1 | if ($newnode->ownerDocument !== $node->ownerDocument) { |
|
| 775 | 1 | $newnode = $node->ownerDocument->importNode($newnode, true); |
|
| 776 | 1 | } else { |
|
| 777 | if ($i > 0) { |
||
| 778 | $newnode = $newnode->cloneNode(true); |
||
| 779 | } |
||
| 780 | } |
||
| 781 | 1 | $oldnode = $node->parentNode->replaceChild($newnode, $node); |
|
| 782 | 1 | while ($newnode->hasChildNodes()) { |
|
| 783 | 1 | $elementFound = false; |
|
| 784 | 1 | foreach ($newnode->childNodes as $child) { |
|
| 785 | 1 | if ($child instanceof \DOMElement) { |
|
| 786 | 1 | $newnode = $child; |
|
| 787 | 1 | $elementFound = true; |
|
| 788 | 1 | break; |
|
| 789 | } |
||
| 790 | 1 | } |
|
| 791 | 1 | if (!$elementFound) { |
|
| 792 | break; |
||
| 793 | } |
||
| 794 | 1 | } |
|
| 795 | 1 | $newnode->appendChild($oldnode); |
|
| 796 | 1 | $newnodes[] = $newnode; |
|
| 797 | 1 | } |
|
| 798 | 1 | $content->clear(); |
|
| 799 | 1 | $content->add($newnodes); |
|
| 800 | 1 | return $this; |
|
| 801 | } |
||
| 802 | |||
| 803 | /** |
||
| 804 | * Wrap an HTML structure around all elements in the set of matched elements. |
||
| 805 | * |
||
| 806 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content |
||
| 807 | * @throws \LogicException |
||
| 808 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
| 809 | * @api |
||
| 810 | */ |
||
| 811 | 1 | public function wrapAll($content) |
|
| 812 | { |
||
| 813 | 1 | $content = self::create($content); |
|
| 814 | 1 | $parent = $this->getNode(0)->parentNode; |
|
| 815 | 1 | foreach ($this as $i => $node) { |
|
| 816 | /** @var \DOMNode $node */ |
||
| 817 | 1 | if ($node->parentNode !== $parent) { |
|
| 818 | throw new \LogicException('Nodes to be wrapped with wrapAll() must all have the same parent'); |
||
| 819 | } |
||
| 820 | 1 | } |
|
| 821 | |||
| 822 | 1 | $newnode = $content->getNode(0); |
|
| 823 | /** @var \DOMNode $newnode */ |
||
| 824 | 1 | $newnode = static::importNewnode($newnode, $parent); |
|
| 825 | |||
| 826 | 1 | $newnode = $parent->insertBefore($newnode,$this->getNode(0)); |
|
| 827 | 1 | $content->clear(); |
|
| 828 | 1 | $content->add($newnode); |
|
| 829 | |||
| 830 | 1 | while ($newnode->hasChildNodes()) { |
|
| 831 | $elementFound = false; |
||
| 832 | foreach ($newnode->childNodes as $child) { |
||
| 833 | if ($child instanceof \DOMElement) { |
||
| 834 | $newnode = $child; |
||
| 835 | $elementFound = true; |
||
| 836 | break; |
||
| 837 | } |
||
| 838 | } |
||
| 839 | if (!$elementFound) { |
||
| 840 | break; |
||
| 841 | } |
||
| 842 | } |
||
| 843 | 1 | foreach ($this as $i => $node) { |
|
| 844 | /** @var \DOMNode $node */ |
||
| 845 | 1 | $newnode->appendChild($node); |
|
| 846 | 1 | } |
|
| 847 | 1 | return $this; |
|
| 848 | } |
||
| 849 | |||
| 850 | /** |
||
| 851 | * Wrap an HTML structure around the content of each element in the set of matched elements. |
||
| 852 | * |
||
| 853 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content |
||
| 854 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
| 855 | * @api |
||
| 856 | */ |
||
| 857 | 1 | public function wrapInner($content) |
|
| 858 | { |
||
| 859 | 1 | foreach ($this as $i => $node) { |
|
| 860 | /** @var \DOMNode $node */ |
||
| 861 | 1 | self::create($node->childNodes)->wrapAll($content); |
|
| 862 | 1 | } |
|
| 863 | 1 | return $this; |
|
| 864 | } |
||
| 865 | |||
| 866 | /** |
||
| 867 | * Get the HTML code fragment of all elements and their contents. |
||
| 868 | * |
||
| 869 | * If the first node contains a complete HTML document return only |
||
| 870 | * the full code of this document. |
||
| 871 | * |
||
| 872 | * @return string HTML code (fragment) |
||
| 873 | * @api |
||
| 874 | */ |
||
| 875 | 3 | public function saveHTML() |
|
| 876 | { |
||
| 877 | 3 | $html = ''; |
|
| 878 | 3 | foreach ($this as $node) { |
|
| 879 | 3 | $html .= $node->ownerDocument->saveHTML($node); |
|
| 880 | 3 | } |
|
| 881 | 3 | return $html; |
|
| 882 | } |
||
| 883 | |||
| 884 | public function __toString() |
||
| 885 | { |
||
| 886 | return $this->saveHTML(); |
||
| 887 | } |
||
| 888 | |||
| 889 | /** |
||
| 890 | * checks whether the first node contains a complete html document |
||
| 891 | * (as opposed to a document fragment) |
||
| 892 | * |
||
| 893 | * @return boolean |
||
| 894 | */ |
||
| 895 | 1 | public function isHtmlDocument() |
|
| 908 | |||
| 909 | /** |
||
| 910 | * get ownerDocument of the first element |
||
| 911 | * |
||
| 912 | * @return \DOMDocument|null |
||
| 913 | */ |
||
| 914 | public function getDOMDocument() |
||
| 915 | { |
||
| 916 | $node = $this->getNode(0); |
||
| 917 | $r = null; |
||
| 918 | if ($node instanceof \DOMElement |
||
| 919 | && $node->ownerDocument instanceof \DOMDocument |
||
| 920 | ) { |
||
| 921 | $r = $node->ownerDocument; |
||
| 922 | } |
||
| 923 | return $r; |
||
| 924 | } |
||
| 925 | |||
| 926 | /** |
||
| 927 | * Filters the list of nodes with a CSS selector. |
||
| 928 | * |
||
| 929 | * @param string $selector |
||
| 930 | * @return HtmlPageCrawler |
||
| 931 | */ |
||
| 932 | 6 | public function filter($selector) |
|
| 936 | |||
| 937 | /** |
||
| 938 | * Filters the list of nodes with an XPath expression. |
||
| 939 | * |
||
| 940 | * @param string $xpath An XPath expression |
||
| 941 | * |
||
| 942 | * @return HtmlPageCrawler A new instance of Crawler with the filtered list of nodes |
||
| 943 | * |
||
| 944 | * @api |
||
| 945 | */ |
||
| 946 | 1 | public function filterXPath($xpath) |
|
| 950 | |||
| 951 | /** |
||
| 952 | * Adds HTML/XML content to the HtmlPageCrawler object (but not to the DOM of an already attached node). |
||
| 953 | * |
||
| 954 | * Function overriden from Crawler because HTML fragments are always added as complete documents there |
||
| 955 | * |
||
| 956 | * |
||
| 957 | * @param string $content A string to parse as HTML/XML |
||
| 958 | * @param null|string $type The content type of the string |
||
| 959 | * |
||
| 960 | * @return null|void |
||
| 961 | */ |
||
| 962 | 12 | public function addContent($content, $type = null) |
|
| 963 | { |
||
| 964 | 12 | if (empty($type)) { |
|
| 965 | 12 | $type = 'text/html;charset=UTF-8'; |
|
| 966 | 12 | } |
|
| 967 | 12 | if (substr($type, 0, 9) == 'text/html' && !preg_match('/<html\b[^>]*>/i', $content)) { |
|
| 968 | // string contains no <html> Tag => no complete document but an HTML fragment! |
||
| 969 | 10 | $this->addHtmlFragment($content); |
|
| 970 | 10 | } else { |
|
| 971 | 2 | parent::addContent($content, $type); |
|
| 972 | } |
||
| 973 | 12 | } |
|
| 974 | |||
| 975 | 10 | public function addHtmlFragment($content, $charset = 'UTF-8') |
|
| 976 | { |
||
| 977 | 10 | $d = new \DOMDocument('1.0', $charset); |
|
| 978 | 10 | $root = $d->appendChild($d->createElement(self::FRAGMENT_ROOT_TAGNAME)); |
|
| 979 | 10 | $bodynode = Helpers::getBodyNodeFromHtmlFragment($content, $charset); |
|
| 980 | 10 | foreach ($bodynode->childNodes as $child) { |
|
| 981 | 10 | $inode = $root->appendChild($d->importNode($child, true)); |
|
| 982 | 10 | if ($inode) { |
|
| 983 | 10 | $this->addNode($inode); |
|
| 984 | 10 | } |
|
| 985 | 10 | } |
|
| 986 | 10 | } |
|
| 987 | |||
| 988 | /** |
||
| 989 | * returns the first node |
||
| 990 | * deprecated, use getNode(0) instead |
||
| 991 | * |
||
| 992 | * @return \DOMNode|null |
||
| 993 | * @deprecated |
||
| 994 | * @see Crawler::getNode |
||
| 995 | */ |
||
| 996 | public function getFirstNode() |
||
| 997 | { |
||
| 998 | return $this->getNode(0); |
||
| 999 | } |
||
| 1000 | |||
| 1001 | /** |
||
| 1002 | * @param int $position |
||
| 1003 | * |
||
| 1004 | * overridden from Crawler because it is not public in Symfony 2.3 |
||
| 1005 | * TODO: throw away as soon as we don't need to support SF 2.3 any more |
||
| 1006 | * |
||
| 1007 | * @return \DOMElement|null |
||
| 1008 | */ |
||
| 1009 | 3 | public function getNode($position) |
|
| 1013 | |||
| 1014 | /** |
||
| 1015 | * Returns the node name of the first node of the list. |
||
| 1016 | * |
||
| 1017 | * in Crawler (parent), this function will be available starting with 2.6.0, |
||
| 1018 | * therefore this method be removed from here as soon as we don't need to keep compatibility |
||
| 1019 | * with Symfony < 2.6 |
||
| 1020 | * |
||
| 1021 | * TODO: throw away as soon as we don't need to support SF 2.3 any more |
||
| 1022 | * |
||
| 1023 | * @return string The node name |
||
| 1024 | * |
||
| 1025 | * @throws \InvalidArgumentException When current node is empty |
||
| 1026 | */ |
||
| 1027 | 1 | public function nodeName() |
|
| 1034 | |||
| 1035 | /** |
||
| 1036 | * Adds a node to the current list of nodes. |
||
| 1037 | * |
||
| 1038 | * This method uses the appropriate specialized add*() method based |
||
| 1039 | * on the type of the argument. |
||
| 1040 | * |
||
| 1041 | * Overwritten from parent to allow Crawler to be added |
||
| 1042 | * |
||
| 1043 | * @param null|\DOMNodeList|array|\DOMNode|Crawler $node A node |
||
| 1044 | * |
||
| 1045 | * @api |
||
| 1046 | */ |
||
| 1047 | 14 | public function add($node) |
|
| 1048 | { |
||
| 1049 | 14 | if ($node instanceof Crawler) { |
|
| 1050 | foreach ($node as $childnode) { |
||
| 1051 | $this->addNode($childnode); |
||
| 1052 | } |
||
| 1053 | } else { |
||
| 1054 | 14 | parent::add($node); |
|
| 1055 | } |
||
| 1056 | 14 | } |
|
| 1057 | |||
| 1058 | /** |
||
| 1059 | * @param \DOMNode $newnode |
||
| 1060 | * @param \DOMNode $referencenode |
||
| 1061 | * @param int $clone |
||
| 1062 | * @return \DOMNode |
||
| 1063 | */ |
||
| 1064 | 5 | protected static function importNewnode(\DOMNode $newnode, \DOMNode $referencenode, $clone = 0) { |
|
| 1065 | 5 | if ($newnode->ownerDocument !== $referencenode->ownerDocument) { |
|
| 1066 | 4 | $newnode = $referencenode->ownerDocument->importNode($newnode, true); |
|
| 1067 | 4 | } else { |
|
| 1068 | 2 | if ($clone > 0) { |
|
| 1069 | $newnode = $newnode->cloneNode(true); |
||
| 1070 | } |
||
| 1071 | } |
||
| 1072 | 5 | return $newnode; |
|
| 1073 | } |
||
| 1074 | |||
| 1075 | /** |
||
| 1076 | * Checks whether the first node in the set is disconnected (has no parent node) |
||
| 1077 | * |
||
| 1078 | * @return bool |
||
| 1079 | */ |
||
| 1080 | 1 | public function isDisconnected() |
|
| 1085 | |||
| 1086 | 1 | public function __get($name) |
|
| 1095 | } |
||
| 1096 |
Loading history...
The number of this metric differs depending on the chosen design (inheritance vs. composition). For inheritance, the number should generally be a bit lower.
A high number indicates a reusable class. It might also make the class harder to change without breaking other classes though.