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() |
|
| 395 | |||
| 396 | /** |
||
| 397 | * Set the HTML contents of each element |
||
| 398 | * |
||
| 399 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content HTML code fragment |
||
| 400 | * @return HtmlPageCrawler $this for chaining |
||
| 401 | */ |
||
| 402 | 2 | public function setInnerHtml($content) |
|
| 416 | |||
| 417 | /** |
||
| 418 | * Insert every element in the set of matched elements after the target. |
||
| 419 | * |
||
| 420 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
| 421 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
| 422 | * @api |
||
| 423 | */ |
||
| 424 | 1 | public function insertAfter($element) |
|
| 444 | |||
| 445 | /** |
||
| 446 | * Insert every element in the set of matched elements before the target. |
||
| 447 | * |
||
| 448 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
| 449 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
| 450 | * @api |
||
| 451 | */ |
||
| 452 | 1 | public function insertBefore($element) |
|
| 467 | |||
| 468 | /** |
||
| 469 | * Insert content, specified by the parameter, to the beginning of each element in the set of matched elements. |
||
| 470 | * |
||
| 471 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content HTML code fragment |
||
| 472 | * @return HtmlPageCrawler $this for chaining |
||
| 473 | * @api |
||
| 474 | */ |
||
| 475 | 2 | public function prepend($content) |
|
| 497 | |||
| 498 | /** |
||
| 499 | * Insert every element in the set of matched elements to the beginning of the target. |
||
| 500 | * |
||
| 501 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
| 502 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements prepended to the target elements |
||
| 503 | * @api |
||
| 504 | */ |
||
| 505 | public function prependTo($element) |
||
| 525 | |||
| 526 | /** |
||
| 527 | * Remove the set of matched elements from the DOM. |
||
| 528 | * |
||
| 529 | * (as opposed to Crawler::clear() which detaches the nodes only from Crawler |
||
| 530 | * but leaves them in the DOM) |
||
| 531 | * |
||
| 532 | * @api |
||
| 533 | */ |
||
| 534 | 2 | public function remove() |
|
| 546 | |||
| 547 | /** |
||
| 548 | * Remove an attribute from each element in the set of matched elements. |
||
| 549 | * |
||
| 550 | * Alias for removeAttribute for compatibility with jQuery |
||
| 551 | * |
||
| 552 | * @param string $name |
||
| 553 | * @return HtmlPageCrawler |
||
| 554 | * @api |
||
| 555 | */ |
||
| 556 | 1 | public function removeAttr($name) |
|
| 560 | |||
| 561 | /** |
||
| 562 | * Remove an attribute from each element in the set of matched elements. |
||
| 563 | * |
||
| 564 | * @param string $name |
||
| 565 | * @return HtmlPageCrawler |
||
| 566 | */ |
||
| 567 | 1 | public function removeAttribute($name) |
|
| 579 | |||
| 580 | /** |
||
| 581 | * Remove a class from each element in the list |
||
| 582 | * |
||
| 583 | * @param string $name |
||
| 584 | * @return HtmlPageCrawler $this for chaining |
||
| 585 | * @api |
||
| 586 | */ |
||
| 587 | 2 | public function removeClass($name) |
|
| 604 | |||
| 605 | /** |
||
| 606 | * Replace each target element with the set of matched elements. |
||
| 607 | * |
||
| 608 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
| 609 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
| 610 | * @api |
||
| 611 | */ |
||
| 612 | 2 | public function replaceAll($element) |
|
| 633 | |||
| 634 | /** |
||
| 635 | * Replace each element in the set of matched elements with the provided new content and return the set of elements that was removed. |
||
| 636 | * |
||
| 637 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content |
||
| 638 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
| 639 | * @api |
||
| 640 | */ |
||
| 641 | 2 | public function replaceWith($content) |
|
| 664 | |||
| 665 | /** |
||
| 666 | * Get the combined text contents of each element in the set of matched elements, including their descendants, |
||
| 667 | * or set the text contents of the matched elements. |
||
| 668 | * |
||
| 669 | * ATTENTION: Contrary to the parent Crawler class, which returns the text from the first element only, |
||
| 670 | * this functions returns the combined text of all elements (as jQuery does). If this is not what you need you |
||
| 671 | * must call ->first() before calling ->text(), e.g. |
||
| 672 | * |
||
| 673 | * in Symfony\DOMCrawler\Crawler: $c->filter('p')->text() returns the text of the first paragraph only |
||
| 674 | * in HtmlPageCrawler you need to call: $c->filter('p')->first()->text() |
||
| 675 | * |
||
| 676 | * @param null|string $text |
||
| 677 | * @return string|HtmlPageCrawler |
||
| 678 | * @api |
||
| 679 | */ |
||
| 680 | 1 | public function text($text = null) |
|
| 697 | |||
| 698 | |||
| 699 | /** |
||
| 700 | * Add or remove one or more classes from each element in the set of matched elements, depending the class’s presence. |
||
| 701 | * |
||
| 702 | * @param string $classname One or more classnames separated by spaces |
||
| 703 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
| 704 | * @api |
||
| 705 | */ |
||
| 706 | 1 | public function toggleClass($classname) |
|
| 722 | |||
| 723 | /** |
||
| 724 | * Remove the parents of the set of matched elements from the DOM, leaving the matched elements in their place. |
||
| 725 | * |
||
| 726 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
| 727 | * @api |
||
| 728 | */ |
||
| 729 | 1 | public function unwrap() |
|
| 739 | |||
| 740 | /** |
||
| 741 | * Remove the matched elements, but promote the children to take their place. |
||
| 742 | * |
||
| 743 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
| 744 | * @api |
||
| 745 | */ |
||
| 746 | 1 | public function unwrapInner() |
|
| 762 | |||
| 763 | |||
| 764 | /** |
||
| 765 | * Wrap an HTML structure around each element in the set of matched elements |
||
| 766 | * |
||
| 767 | * The HTML structure must contain only one root node, e.g.: |
||
| 768 | * Works: <div><div></div></div> |
||
| 769 | * Does not work: <div></div><div></div> |
||
| 770 | * |
||
| 771 | * @param string|HtmlPageCrawler|\DOMNode $wrappingElement |
||
| 772 | * @return HtmlPageCrawler $this for chaining |
||
| 773 | * @api |
||
| 774 | */ |
||
| 775 | 1 | public function wrap($wrappingElement) |
|
| 812 | |||
| 813 | /** |
||
| 814 | * Wrap an HTML structure around all elements in the set of matched elements. |
||
| 815 | * |
||
| 816 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content |
||
| 817 | * @throws \LogicException |
||
| 818 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
| 819 | * @api |
||
| 820 | */ |
||
| 821 | 1 | public function wrapAll($content) |
|
| 859 | |||
| 860 | /** |
||
| 861 | * Wrap an HTML structure around the content of each element in the set of matched elements. |
||
| 862 | * |
||
| 863 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content |
||
| 864 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
| 865 | * @api |
||
| 866 | */ |
||
| 867 | 1 | public function wrapInner($content) |
|
| 875 | |||
| 876 | /** |
||
| 877 | * Get the HTML code fragment of all elements and their contents. |
||
| 878 | * |
||
| 879 | * If the first node contains a complete HTML document return only |
||
| 880 | * the full code of this document. |
||
| 881 | * |
||
| 882 | * @return string HTML code (fragment) |
||
| 883 | * @api |
||
| 884 | */ |
||
| 885 | 3 | public function saveHTML() |
|
| 886 | { |
||
| 887 | /* don't see any reason we should handle the complete HTML document seperately. */ |
||
| 888 | // if ($this->isHtmlDocument()) { |
||
| 889 | // return $this->getDOMDocument()->saveHTML(); |
||
| 890 | // } else { |
||
| 891 | 3 | $doc = new \DOMDocument('1.0', 'UTF-8'); |
|
| 892 | 3 | $doc->loadHTML('<meta http-equiv="Content-Type" content="text/html;charset=utf-8">'); |
|
| 893 | 3 | $root = $doc->appendChild($doc->createElement(self::FRAGMENT_ROOT_TAGNAME)); |
|
| 894 | 3 | foreach ($this as $node) { |
|
| 895 | 3 | $root->appendChild($doc->importNode($node, true)); |
|
| 896 | 3 | } |
|
| 897 | 3 | $html = trim($doc->saveHTML()); |
|
| 898 | 3 | return preg_replace('@^.*<'.self::FRAGMENT_ROOT_TAGNAME.'[^>]*>|</'.self::FRAGMENT_ROOT_TAGNAME.'>$@s', '', $html); |
|
| 899 | // } |
||
| 900 | } |
||
| 901 | |||
| 902 | public function __toString() |
||
| 906 | |||
| 907 | /** |
||
| 908 | * checks whether the first node contains a complete html document |
||
| 909 | * (as opposed to a document fragment) |
||
| 910 | * |
||
| 911 | * @return boolean |
||
| 912 | */ |
||
| 913 | 1 | public function isHtmlDocument() |
|
| 926 | |||
| 927 | /** |
||
| 928 | * get ownerDocument of the first element |
||
| 929 | * |
||
| 930 | * @return \DOMDocument|null |
||
| 931 | */ |
||
| 932 | public function getDOMDocument() |
||
| 943 | |||
| 944 | /** |
||
| 945 | * Filters the list of nodes with a CSS selector. |
||
| 946 | * |
||
| 947 | * @param string $selector |
||
| 948 | * @return HtmlPageCrawler |
||
| 949 | */ |
||
| 950 | 6 | public function filter($selector) |
|
| 954 | |||
| 955 | /** |
||
| 956 | * Filters the list of nodes with an XPath expression. |
||
| 957 | * |
||
| 958 | * @param string $xpath An XPath expression |
||
| 959 | * |
||
| 960 | * @return HtmlPageCrawler A new instance of Crawler with the filtered list of nodes |
||
| 961 | * |
||
| 962 | * @api |
||
| 963 | */ |
||
| 964 | 1 | public function filterXPath($xpath) |
|
| 968 | |||
| 969 | /** |
||
| 970 | * Adds HTML/XML content to the HtmlPageCrawler object (but not to the DOM of an already attached node). |
||
| 971 | * |
||
| 972 | * Function overriden from Crawler because HTML fragments are always added as complete documents there |
||
| 973 | * |
||
| 974 | * |
||
| 975 | * @param string $content A string to parse as HTML/XML |
||
| 976 | * @param null|string $type The content type of the string |
||
| 977 | * |
||
| 978 | * @return null|void |
||
| 979 | */ |
||
| 980 | 12 | public function addContent($content, $type = null) |
|
| 992 | |||
| 993 | 10 | public function addHtmlFragment($content, $charset = 'UTF-8') |
|
| 1005 | |||
| 1006 | /** |
||
| 1007 | * returns the first node |
||
| 1008 | * deprecated, use getNode(0) instead |
||
| 1009 | * |
||
| 1010 | * @return \DOMNode|null |
||
| 1011 | * @deprecated |
||
| 1012 | * @see Crawler::getNode |
||
| 1013 | */ |
||
| 1014 | public function getFirstNode() |
||
| 1018 | |||
| 1019 | /** |
||
| 1020 | * @param int $position |
||
| 1021 | * |
||
| 1022 | * overridden from Crawler because it is not public in Symfony 2.3 |
||
| 1023 | * TODO: throw away as soon as we don't need to support SF 2.3 any more |
||
| 1024 | * |
||
| 1025 | * @return \DOMElement|null |
||
| 1026 | */ |
||
| 1027 | 3 | public function getNode($position) |
|
| 1031 | |||
| 1032 | /** |
||
| 1033 | * Returns the node name of the first node of the list. |
||
| 1034 | * |
||
| 1035 | * in Crawler (parent), this function will be available starting with 2.6.0, |
||
| 1036 | * therefore this method be removed from here as soon as we don't need to keep compatibility |
||
| 1037 | * with Symfony < 2.6 |
||
| 1038 | * |
||
| 1039 | * TODO: throw away as soon as we don't need to support SF 2.3 any more |
||
| 1040 | * |
||
| 1041 | * @return string The node name |
||
| 1042 | * |
||
| 1043 | * @throws \InvalidArgumentException When current node is empty |
||
| 1044 | */ |
||
| 1045 | 1 | public function nodeName() |
|
| 1052 | |||
| 1053 | /** |
||
| 1054 | * Adds a node to the current list of nodes. |
||
| 1055 | * |
||
| 1056 | * This method uses the appropriate specialized add*() method based |
||
| 1057 | * on the type of the argument. |
||
| 1058 | * |
||
| 1059 | * Overwritten from parent to allow Crawler to be added |
||
| 1060 | * |
||
| 1061 | * @param null|\DOMNodeList|array|\DOMNode|Crawler $node A node |
||
| 1062 | * |
||
| 1063 | * @api |
||
| 1064 | */ |
||
| 1065 | 14 | public function add($node) |
|
| 1075 | |||
| 1076 | /** |
||
| 1077 | * @param \DOMNode $newnode |
||
| 1078 | * @param \DOMNode $referencenode |
||
| 1079 | * @param int $clone |
||
| 1080 | * @return \DOMNode |
||
| 1081 | */ |
||
| 1082 | 5 | protected static function importNewnode(\DOMNode $newnode, \DOMNode $referencenode, $clone = 0) { |
|
| 1092 | |||
| 1093 | /** |
||
| 1094 | * Checks whether the first node in the set is disconnected (has no parent node) |
||
| 1095 | * |
||
| 1096 | * @return bool |
||
| 1097 | */ |
||
| 1098 | 1 | public function isDisconnected() |
|
| 1103 | |||
| 1104 | 1 | public function __get($name) |
|
| 1113 | } |
||
| 1114 |
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.