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 $this for chaining |
||
180 | */ |
||
181 | 3 | public function setAttribute($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 | 1 | public function makeEmpty() |
|
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() |
|
394 | |||
395 | /** |
||
396 | * Set the HTML contents of each element |
||
397 | * |
||
398 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content HTML code fragment |
||
399 | * @return HtmlPageCrawler $this for chaining |
||
400 | */ |
||
401 | 2 | public function setInnerHtml($content) |
|
415 | |||
416 | /** |
||
417 | * Insert every element in the set of matched elements after the target. |
||
418 | * |
||
419 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
420 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
421 | * @api |
||
422 | */ |
||
423 | 1 | public function insertAfter($element) |
|
443 | |||
444 | /** |
||
445 | * Insert every element in the set of matched elements before the target. |
||
446 | * |
||
447 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
448 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
449 | * @api |
||
450 | */ |
||
451 | 1 | public function insertBefore($element) |
|
466 | |||
467 | /** |
||
468 | * Insert content, specified by the parameter, to the beginning of each element in the set of matched elements. |
||
469 | * |
||
470 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content HTML code fragment |
||
471 | * @return HtmlPageCrawler $this for chaining |
||
472 | * @api |
||
473 | */ |
||
474 | 2 | public function prepend($content) |
|
496 | |||
497 | /** |
||
498 | * Insert every element in the set of matched elements to the beginning of the target. |
||
499 | * |
||
500 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
501 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements prepended to the target elements |
||
502 | * @api |
||
503 | */ |
||
504 | public function prependTo($element) |
||
524 | |||
525 | /** |
||
526 | * Remove the set of matched elements from the DOM. |
||
527 | * |
||
528 | * (as opposed to Crawler::clear() which detaches the nodes only from Crawler |
||
529 | * but leaves them in the DOM) |
||
530 | * |
||
531 | * @api |
||
532 | */ |
||
533 | 2 | public function remove() |
|
545 | |||
546 | /** |
||
547 | * Remove an attribute from each element in the set of matched elements. |
||
548 | * |
||
549 | * Alias for removeAttribute for compatibility with jQuery |
||
550 | * |
||
551 | * @param string $name |
||
552 | * @return HtmlPageCrawler |
||
553 | * @api |
||
554 | */ |
||
555 | 1 | public function removeAttr($name) |
|
559 | |||
560 | /** |
||
561 | * Remove an attribute from each element in the set of matched elements. |
||
562 | * |
||
563 | * @param string $name |
||
564 | * @return HtmlPageCrawler |
||
565 | */ |
||
566 | 1 | public function removeAttribute($name) |
|
578 | |||
579 | /** |
||
580 | * Remove a class from each element in the list |
||
581 | * |
||
582 | * @param string $name |
||
583 | * @return HtmlPageCrawler $this for chaining |
||
584 | * @api |
||
585 | */ |
||
586 | 2 | public function removeClass($name) |
|
603 | |||
604 | /** |
||
605 | * Replace each target element with the set of matched elements. |
||
606 | * |
||
607 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
608 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
609 | * @api |
||
610 | */ |
||
611 | 2 | public function replaceAll($element) |
|
632 | |||
633 | /** |
||
634 | * Replace each element in the set of matched elements with the provided new content and return the set of elements that was removed. |
||
635 | * |
||
636 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content |
||
637 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
638 | * @api |
||
639 | */ |
||
640 | 2 | public function replaceWith($content) |
|
663 | |||
664 | /** |
||
665 | * Get the combined text contents of each element in the set of matched elements, including their descendants, |
||
666 | * or set the text contents of the matched elements. |
||
667 | * |
||
668 | * ATTENTION: Contrary to the parent Crawler class, which returns the text from the first element only, |
||
669 | * this functions returns the combined text of all elements (as jQuery does). If this is not what you need you |
||
670 | * must call ->first() before calling ->text(), e.g. |
||
671 | * |
||
672 | * in Symfony\DOMCrawler\Crawler: $c->filter('p')->text() returns the text of the first paragraph only |
||
673 | * in HtmlPageCrawler you need to call: $c->filter('p')->first()->text() |
||
674 | * |
||
675 | * @param null|string $text |
||
676 | * @return string|HtmlPageCrawler |
||
677 | * @api |
||
678 | */ |
||
679 | 1 | public function text($text = null) |
|
696 | |||
697 | |||
698 | /** |
||
699 | * Add or remove one or more classes from each element in the set of matched elements, depending the class’s presence. |
||
700 | * |
||
701 | * @param string $classname One or more classnames separated by spaces |
||
702 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
703 | * @api |
||
704 | */ |
||
705 | 1 | public function toggleClass($classname) |
|
721 | |||
722 | /** |
||
723 | * Remove the parents of the set of matched elements from the DOM, leaving the matched elements in their place. |
||
724 | * |
||
725 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
726 | * @api |
||
727 | */ |
||
728 | 1 | public function unwrap() |
|
738 | |||
739 | /** |
||
740 | * Remove the matched elements, but promote the children to take their place. |
||
741 | * |
||
742 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
743 | * @api |
||
744 | */ |
||
745 | 1 | public function unwrapInner() |
|
746 | { |
||
747 | 1 | foreach($this as $i => $node) { |
|
748 | 1 | if (!$node->parentNode instanceof \DOMElement) { |
|
749 | throw new \InvalidArgumentException('DOMElement does not have a parent DOMElement node.'); |
||
750 | } |
||
751 | |||
752 | /** @var \DOMNode[] $children */ |
||
753 | 1 | $children = iterator_to_array($node->childNodes); |
|
754 | 1 | foreach ($children as $child) { |
|
755 | 1 | $node->parentNode->insertBefore($child, $node); |
|
756 | 1 | } |
|
757 | |||
758 | 1 | $node->parentNode->removeChild($node); |
|
759 | 1 | } |
|
760 | 1 | } |
|
761 | |||
762 | |||
763 | /** |
||
764 | * Wrap an HTML structure around each element in the set of matched elements |
||
765 | * |
||
766 | * The HTML structure must contain only one root node, e.g.: |
||
767 | * Works: <div><div></div></div> |
||
768 | * Does not work: <div></div><div></div> |
||
769 | * |
||
770 | * @param string|HtmlPageCrawler|\DOMNode $wrappingElement |
||
771 | * @return HtmlPageCrawler $this for chaining |
||
772 | * @api |
||
773 | */ |
||
774 | 1 | public function wrap($wrappingElement) |
|
811 | |||
812 | /** |
||
813 | * Wrap an HTML structure around all elements in the set of matched elements. |
||
814 | * |
||
815 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content |
||
816 | * @throws \LogicException |
||
817 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
818 | * @api |
||
819 | */ |
||
820 | 1 | public function wrapAll($content) |
|
858 | |||
859 | /** |
||
860 | * Wrap an HTML structure around the content of each element in the set of matched elements. |
||
861 | * |
||
862 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content |
||
863 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
864 | * @api |
||
865 | */ |
||
866 | 1 | public function wrapInner($content) |
|
874 | |||
875 | /** |
||
876 | * Get the HTML code fragment of all elements and their contents. |
||
877 | * |
||
878 | * If the first node contains a complete HTML document return only |
||
879 | * the full code of this document. |
||
880 | * |
||
881 | * @return string HTML code (fragment) |
||
882 | * @api |
||
883 | */ |
||
884 | 3 | public function saveHTML() |
|
898 | |||
899 | public function __toString() |
||
903 | |||
904 | /** |
||
905 | * checks whether the first node contains a complete html document |
||
906 | * (as opposed to a document fragment) |
||
907 | * |
||
908 | * @return boolean |
||
909 | */ |
||
910 | 3 | public function isHtmlDocument() |
|
923 | |||
924 | /** |
||
925 | * get ownerDocument of the first element |
||
926 | * |
||
927 | * @return \DOMDocument|null |
||
928 | */ |
||
929 | public function getDOMDocument() |
||
940 | |||
941 | /** |
||
942 | * Filters the list of nodes with a CSS selector. |
||
943 | * |
||
944 | * @param string $selector |
||
945 | * @return HtmlPageCrawler |
||
946 | */ |
||
947 | 6 | public function filter($selector) |
|
951 | |||
952 | /** |
||
953 | * Filters the list of nodes with an XPath expression. |
||
954 | * |
||
955 | * @param string $xpath An XPath expression |
||
956 | * |
||
957 | * @return HtmlPageCrawler A new instance of Crawler with the filtered list of nodes |
||
958 | * |
||
959 | * @api |
||
960 | */ |
||
961 | 1 | public function filterXPath($xpath) |
|
965 | |||
966 | /** |
||
967 | * Adds HTML/XML content to the HtmlPageCrawler object (but not to the DOM of an already attached node). |
||
968 | * |
||
969 | * Function overriden from Crawler because HTML fragments are always added as complete documents there |
||
970 | * |
||
971 | * |
||
972 | * @param string $content A string to parse as HTML/XML |
||
973 | * @param null|string $type The content type of the string |
||
974 | * |
||
975 | * @return null|void |
||
976 | */ |
||
977 | 12 | public function addContent($content, $type = null) |
|
989 | |||
990 | 10 | public function addHtmlFragment($content, $charset = 'UTF-8') |
|
1002 | |||
1003 | /** |
||
1004 | * returns the first node |
||
1005 | * deprecated, use getNode(0) instead |
||
1006 | * |
||
1007 | * @return \DOMNode|null |
||
1008 | * @deprecated |
||
1009 | * @see Crawler::getNode |
||
1010 | */ |
||
1011 | public function getFirstNode() |
||
1015 | |||
1016 | /** |
||
1017 | * @param int $position |
||
1018 | * |
||
1019 | * overridden from Crawler because it is not public in Symfony 2.3 |
||
1020 | * TODO: throw away as soon as we don't need to support SF 2.3 any more |
||
1021 | * |
||
1022 | * @return \DOMElement|null |
||
1023 | */ |
||
1024 | 5 | public function getNode($position) |
|
1028 | |||
1029 | /** |
||
1030 | * Returns the node name of the first node of the list. |
||
1031 | * |
||
1032 | * in Crawler (parent), this function will be available starting with 2.6.0, |
||
1033 | * therefore this method be removed from here as soon as we don't need to keep compatibility |
||
1034 | * with Symfony < 2.6 |
||
1035 | * |
||
1036 | * TODO: throw away as soon as we don't need to support SF 2.3 any more |
||
1037 | * |
||
1038 | * @return string The node name |
||
1039 | * |
||
1040 | * @throws \InvalidArgumentException When current node is empty |
||
1041 | */ |
||
1042 | 1 | public function nodeName() |
|
1049 | |||
1050 | /** |
||
1051 | * Adds a node to the current list of nodes. |
||
1052 | * |
||
1053 | * This method uses the appropriate specialized add*() method based |
||
1054 | * on the type of the argument. |
||
1055 | * |
||
1056 | * Overwritten from parent to allow Crawler to be added |
||
1057 | * |
||
1058 | * @param null|\DOMNodeList|array|\DOMNode|Crawler $node A node |
||
1059 | * |
||
1060 | * @api |
||
1061 | */ |
||
1062 | 14 | public function add($node) |
|
1072 | |||
1073 | /** |
||
1074 | * @param \DOMNode $newnode |
||
1075 | * @param \DOMNode $referencenode |
||
1076 | * @param int $clone |
||
1077 | * @return \DOMNode |
||
1078 | */ |
||
1079 | 5 | protected static function importNewnode(\DOMNode $newnode, \DOMNode $referencenode, $clone = 0) { |
|
1089 | |||
1090 | /** |
||
1091 | * Checks whether the first node in the set is disconnected (has no parent node) |
||
1092 | * |
||
1093 | * @return bool |
||
1094 | */ |
||
1095 | 1 | public function isDisconnected() |
|
1100 | |||
1101 | 1 | public function __get($name) { |
|
1109 | } |
||
1110 |
Really long classes often contain too much logic and violate the single responsibility principle.
We suggest to take a look at the “Code” section for options on how to refactor this code.