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 $content |
||
28 | * @return HtmlPageCrawler |
||
29 | * @api |
||
30 | */ |
||
31 | 17 | public static function create($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 $element |
||
135 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
136 | * @api |
||
137 | */ |
||
138 | 2 | public function appendTo($element) |
|
155 | |||
156 | /** |
||
157 | * Returns the attribute value of the first node of the list, or sets an attribute on each element |
||
158 | * |
||
159 | * @see HtmlPageCrawler::getAttribute() |
||
160 | * @see HtmlPageCrawler::setAttribute |
||
161 | * |
||
162 | * @param string $name |
||
163 | * @param null|string $value |
||
164 | * @return null|string|HtmlPageCrawler |
||
165 | * @api |
||
166 | */ |
||
167 | 2 | public function attr($name, $value = null) |
|
175 | |||
176 | /** |
||
177 | * Sets an attribute on each element |
||
178 | * |
||
179 | * @param string $name |
||
180 | * @param string $value |
||
181 | * @return HtmlPageCrawler $this for chaining |
||
182 | */ |
||
183 | 3 | public function setAttribute($name, $value) |
|
193 | |||
194 | /** |
||
195 | * Returns the attribute value of the first node of the list. |
||
196 | * |
||
197 | * @param string $name The attribute name |
||
198 | * @return string|null The attribute value or null if the attribute does not exist |
||
199 | * @throws \InvalidArgumentException When current node is empty |
||
200 | * |
||
201 | */ |
||
202 | 2 | public function getAttribute($name) |
|
210 | |||
211 | /** |
||
212 | * Insert content, specified by the parameter, before each element in the set of matched elements. |
||
213 | * |
||
214 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content |
||
215 | * @return HtmlPageCrawler $this for chaining |
||
216 | * @api |
||
217 | */ |
||
218 | 2 | public function before($content) |
|
237 | |||
238 | /** |
||
239 | * Create a deep copy of the set of matched elements. |
||
240 | * |
||
241 | * Equivalent to clone() in jQuery (clone is not a valid PHP function name) |
||
242 | * |
||
243 | * @return HtmlPageCrawler |
||
244 | * @api |
||
245 | */ |
||
246 | 1 | public function makeClone() |
|
250 | |||
251 | 1 | public function __clone() |
|
261 | |||
262 | /** |
||
263 | * Get one CSS style property of the first element or set it for all elements in the list |
||
264 | * |
||
265 | * Function is here for compatibility with jQuery; it is the same as getStyle() and setStyle() |
||
266 | * |
||
267 | * @see HtmlPageCrawler::getStyle() |
||
268 | * @see HtmlPageCrawler::setStyle() |
||
269 | * |
||
270 | * @param string $key The name of the style property |
||
271 | * @param null|string $value The CSS value to set, or NULL to get the current value |
||
272 | * @return HtmlPageCrawler|string If no param is provided, returns the CSS styles of the first element |
||
273 | * @api |
||
274 | */ |
||
275 | 1 | public function css($key, $value = null) |
|
283 | |||
284 | /** |
||
285 | * get one CSS style property of the first element |
||
286 | * |
||
287 | * @param string $key name of the property |
||
288 | * @return string|null value of the property |
||
289 | */ |
||
290 | 1 | public function getStyle($key) |
|
295 | |||
296 | /** |
||
297 | * set one CSS style property for all elements in the list |
||
298 | * |
||
299 | * @param string $key name of the property |
||
300 | * @param string $value value of the property |
||
301 | * @return HtmlPageCrawler $this for chaining |
||
302 | */ |
||
303 | 1 | public function setStyle($key, $value) |
|
319 | |||
320 | /** |
||
321 | * Removes all child nodes and text from all nodes in set |
||
322 | * |
||
323 | * Equivalent to jQuery's empty() function which is not a valid function name in PHP |
||
324 | * @return HtmlPageCrawler $this |
||
325 | * @api |
||
326 | */ |
||
327 | 1 | public function makeEmpty() |
|
334 | |||
335 | /** |
||
336 | * Determine whether any of the matched elements are assigned the given class. |
||
337 | * |
||
338 | * @param string $name |
||
339 | * @return bool |
||
340 | * @api |
||
341 | */ |
||
342 | 2 | public function hasClass($name) |
|
354 | |||
355 | /** |
||
356 | * Set the HTML contents of each element |
||
357 | * |
||
358 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content HTML code fragment |
||
359 | * @return HtmlPageCrawler $this for chaining |
||
360 | */ |
||
361 | 3 | public function setInnerHtml($content) |
|
375 | |||
376 | /** |
||
377 | * Insert every element in the set of matched elements after the target. |
||
378 | * |
||
379 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
380 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
381 | * @api |
||
382 | */ |
||
383 | 2 | public function insertAfter($element) |
|
403 | |||
404 | /** |
||
405 | * Insert every element in the set of matched elements before the target. |
||
406 | * |
||
407 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
408 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
409 | * @api |
||
410 | */ |
||
411 | 2 | public function insertBefore($element) |
|
428 | |||
429 | /** |
||
430 | * Insert content, specified by the parameter, to the beginning of each element in the set of matched elements. |
||
431 | * |
||
432 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content HTML code fragment |
||
433 | * @return HtmlPageCrawler $this for chaining |
||
434 | * @api |
||
435 | */ |
||
436 | 2 | public function prepend($content) |
|
458 | |||
459 | /** |
||
460 | * Insert every element in the set of matched elements to the beginning of the target. |
||
461 | * |
||
462 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
463 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements prepended to the target elements |
||
464 | * @api |
||
465 | */ |
||
466 | 1 | public function prependTo($element) |
|
488 | |||
489 | /** |
||
490 | * Remove the set of matched elements from the DOM. |
||
491 | * |
||
492 | * (as opposed to Crawler::clear() which detaches the nodes only from Crawler |
||
493 | * but leaves them in the DOM) |
||
494 | * |
||
495 | * @api |
||
496 | */ |
||
497 | 2 | public function remove() |
|
509 | |||
510 | /** |
||
511 | * Remove an attribute from each element in the set of matched elements. |
||
512 | * |
||
513 | * Alias for removeAttribute for compatibility with jQuery |
||
514 | * |
||
515 | * @param string $name |
||
516 | * @return HtmlPageCrawler |
||
517 | * @api |
||
518 | */ |
||
519 | 1 | public function removeAttr($name) |
|
523 | |||
524 | /** |
||
525 | * Remove an attribute from each element in the set of matched elements. |
||
526 | * |
||
527 | * @param string $name |
||
528 | * @return HtmlPageCrawler |
||
529 | */ |
||
530 | 1 | public function removeAttribute($name) |
|
542 | |||
543 | /** |
||
544 | * Remove a class from each element in the list |
||
545 | * |
||
546 | * @param string $name |
||
547 | * @return HtmlPageCrawler $this for chaining |
||
548 | * @api |
||
549 | */ |
||
550 | 2 | public function removeClass($name) |
|
567 | |||
568 | /** |
||
569 | * Replace each target element with the set of matched elements. |
||
570 | * |
||
571 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
572 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
573 | * @api |
||
574 | */ |
||
575 | 2 | public function replaceAll($element) |
|
596 | |||
597 | /** |
||
598 | * Replace each element in the set of matched elements with the provided new content and return the set of elements that was removed. |
||
599 | * |
||
600 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content |
||
601 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
602 | * @api |
||
603 | */ |
||
604 | 2 | public function replaceWith($content) |
|
627 | |||
628 | /** |
||
629 | * Get the combined text contents of each element in the set of matched elements, including their descendants. |
||
630 | * This is what the jQuery text() function does, contrary to the Crawler::text() method that returns only |
||
631 | * the text of the first node. |
||
632 | * |
||
633 | * @return string |
||
634 | * @api |
||
635 | */ |
||
636 | 1 | public function getCombinedText() |
|
645 | |||
646 | /** |
||
647 | * Set the text contents of the matched elements. |
||
648 | * |
||
649 | * @param string $text |
||
650 | * @return HtmlPageCrawler |
||
651 | * @api |
||
652 | */ |
||
653 | 1 | public function setText($text) |
|
661 | |||
662 | /** |
||
663 | * Add or remove one or more classes from each element in the set of matched elements, depending the class’s presence. |
||
664 | * |
||
665 | * @param string $classname One or more classnames separated by spaces |
||
666 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
667 | * @api |
||
668 | */ |
||
669 | 1 | public function toggleClass($classname) |
|
685 | |||
686 | /** |
||
687 | * Remove the parents of the set of matched elements from the DOM, leaving the matched elements in their place. |
||
688 | * |
||
689 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
690 | * @api |
||
691 | */ |
||
692 | 1 | public function unwrap() |
|
702 | |||
703 | /** |
||
704 | * Remove the matched elements, but promote the children to take their place. |
||
705 | * |
||
706 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
707 | * @api |
||
708 | */ |
||
709 | 2 | public function unwrapInner() |
|
725 | |||
726 | |||
727 | /** |
||
728 | * Wrap an HTML structure around each element in the set of matched elements |
||
729 | * |
||
730 | * The HTML structure must contain only one root node, e.g.: |
||
731 | * Works: <div><div></div></div> |
||
732 | * Does not work: <div></div><div></div> |
||
733 | * |
||
734 | * @param string|HtmlPageCrawler|\DOMNode $wrappingElement |
||
735 | * @return HtmlPageCrawler $this for chaining |
||
736 | * @api |
||
737 | */ |
||
738 | 1 | public function wrap($wrappingElement) |
|
775 | |||
776 | /** |
||
777 | * Wrap an HTML structure around all elements in the set of matched elements. |
||
778 | * |
||
779 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content |
||
780 | * @throws \LogicException |
||
781 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
782 | * @api |
||
783 | */ |
||
784 | 1 | public function wrapAll($content) |
|
822 | |||
823 | /** |
||
824 | * Wrap an HTML structure around the content of each element in the set of matched elements. |
||
825 | * |
||
826 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content |
||
827 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
828 | * @api |
||
829 | */ |
||
830 | 1 | public function wrapInner($content) |
|
838 | |||
839 | /** |
||
840 | * Get the HTML code fragment of all elements and their contents. |
||
841 | * |
||
842 | * If the first node contains a complete HTML document return only |
||
843 | * the full code of this document. |
||
844 | * |
||
845 | * @return string HTML code (fragment) |
||
846 | * @api |
||
847 | */ |
||
848 | 8 | public function saveHTML() |
|
862 | |||
863 | 4 | public function __toString() |
|
867 | |||
868 | /** |
||
869 | * checks whether the first node contains a complete html document |
||
870 | * (as opposed to a document fragment) |
||
871 | * |
||
872 | * @return boolean |
||
873 | */ |
||
874 | 8 | public function isHtmlDocument() |
|
887 | |||
888 | /** |
||
889 | * get ownerDocument of the first element |
||
890 | * |
||
891 | * @return \DOMDocument|null |
||
892 | */ |
||
893 | 1 | public function getDOMDocument() |
|
904 | |||
905 | /** |
||
906 | * Filters the list of nodes with a CSS selector. |
||
907 | * |
||
908 | * @param string $selector |
||
909 | * @return HtmlPageCrawler |
||
910 | */ |
||
911 | 8 | public function filter($selector) |
|
915 | |||
916 | /** |
||
917 | * Filters the list of nodes with an XPath expression. |
||
918 | * |
||
919 | * @param string $xpath An XPath expression |
||
920 | * |
||
921 | * @return HtmlPageCrawler A new instance of Crawler with the filtered list of nodes |
||
922 | * |
||
923 | * @api |
||
924 | */ |
||
925 | 2 | public function filterXPath($xpath) |
|
929 | |||
930 | /** |
||
931 | * Adds HTML/XML content to the HtmlPageCrawler object (but not to the DOM of an already attached node). |
||
932 | * |
||
933 | * Function overriden from Crawler because HTML fragments are always added as complete documents there |
||
934 | * |
||
935 | * |
||
936 | * @param string $content A string to parse as HTML/XML |
||
937 | * @param null|string $type The content type of the string |
||
938 | * |
||
939 | * @return null|void |
||
940 | */ |
||
941 | 17 | public function addContent($content, $type = null) |
|
953 | |||
954 | 15 | public function addHtmlFragment($content, $charset = 'UTF-8') |
|
966 | |||
967 | /** |
||
968 | * returns the first node |
||
969 | * deprecated, use getNode(0) instead |
||
970 | * |
||
971 | * @return \DOMNode|null |
||
972 | * @deprecated |
||
973 | * @see Crawler::getNode |
||
974 | */ |
||
975 | 1 | public function getFirstNode() |
|
979 | |||
980 | /** |
||
981 | * @param int $position |
||
982 | * |
||
983 | * overridden from Crawler because it is not public in Symfony 2.3 |
||
984 | * TODO: throw away as soon as we don't need to support SF 2.3 any more |
||
985 | * |
||
986 | * @return \DOMElement|null |
||
987 | */ |
||
988 | 13 | public function getNode($position) |
|
992 | |||
993 | /** |
||
994 | * Returns the node name of the first node of the list. |
||
995 | * |
||
996 | * in Crawler (parent), this function will be available starting with 2.6.0, |
||
997 | * therefore this method be removed from here as soon as we don't need to keep compatibility |
||
998 | * with Symfony < 2.6 |
||
999 | * |
||
1000 | * TODO: throw away as soon as we don't need to support SF 2.3 any more |
||
1001 | * |
||
1002 | * @return string The node name |
||
1003 | * |
||
1004 | * @throws \InvalidArgumentException When current node is empty |
||
1005 | */ |
||
1006 | 1 | public function nodeName() |
|
1013 | |||
1014 | /** |
||
1015 | * Adds a node to the current list of nodes. |
||
1016 | * |
||
1017 | * This method uses the appropriate specialized add*() method based |
||
1018 | * on the type of the argument. |
||
1019 | * |
||
1020 | * Overwritten from parent to allow Crawler to be added |
||
1021 | * |
||
1022 | * @param null|\DOMNodeList|array|\DOMNode|Crawler $node A node |
||
1023 | * |
||
1024 | * @api |
||
1025 | */ |
||
1026 | 28 | public function add($node) |
|
1036 | |||
1037 | /** |
||
1038 | * @param \DOMNode $newnode |
||
1039 | * @param \DOMNode $referencenode |
||
1040 | * @param int $clone |
||
1041 | * @return \DOMNode |
||
1042 | */ |
||
1043 | 6 | protected static function importNewnode(\DOMNode $newnode, \DOMNode $referencenode, $clone = 0) { |
|
1053 | |||
1054 | /** |
||
1055 | * Checks whether the first node in the set is disconnected (has no parent node) |
||
1056 | * |
||
1057 | * @return bool |
||
1058 | */ |
||
1059 | 1 | public function isDisconnected() |
|
1064 | |||
1065 | 1 | public function __get($name) |
|
1074 | } |
||
1075 |
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.