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) |
|
| 48 | { |
||
| 49 | 1 | foreach ($this as $node) { |
|
| 50 | 1 | if ($node instanceof \DOMElement) { |
|
| 51 | /** @var \DOMElement $node */ |
||
| 52 | 1 | $classes = preg_split('/\s+/s', $node->getAttribute('class')); |
|
| 53 | 1 | $found = false; |
|
| 54 | 1 | $count = count($classes); |
|
| 55 | 1 | for ($i = 0; $i < $count; $i++) { |
|
| 56 | 1 | if ($classes[$i] == $name) { |
|
| 57 | $found = true; |
||
| 58 | } |
||
| 59 | } |
||
| 60 | 1 | if (!$found) { |
|
| 61 | 1 | $classes[] = $name; |
|
| 62 | 1 | $node->setAttribute('class', trim(join(' ', $classes))); |
|
| 63 | } |
||
| 64 | } |
||
| 65 | } |
||
| 66 | 1 | return $this; |
|
| 67 | } |
||
| 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) |
|
| 77 | { |
||
| 78 | 3 | $content = self::create($content); |
|
| 79 | 3 | $newnodes = array(); |
|
| 80 | 3 | foreach ($this as $i => $node) { |
|
| 81 | /** @var \DOMNode $node */ |
||
| 82 | 3 | $refnode = $node->nextSibling; |
|
| 83 | 3 | foreach ($content as $newnode) { |
|
| 84 | /** @var \DOMNode $newnode */ |
||
| 85 | 3 | $newnode = static::importNewnode($newnode, $node, $i); |
|
| 86 | 3 | if ($refnode === null) { |
|
| 87 | 3 | $node->parentNode->appendChild($newnode); |
|
| 88 | } else { |
||
| 89 | $node->parentNode->insertBefore($newnode, $refnode); |
||
| 90 | } |
||
| 91 | 3 | $newnodes[] = $newnode; |
|
| 92 | } |
||
| 93 | } |
||
| 94 | 3 | $content->clear(); |
|
| 95 | 3 | $content->add($newnodes); |
|
| 96 | 3 | return $this; |
|
| 97 | } |
||
| 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) |
|
| 107 | { |
||
| 108 | 2 | $content = self::create($content); |
|
| 109 | 2 | $newnodes = array(); |
|
| 110 | 2 | foreach ($this as $i => $node) { |
|
| 111 | /** @var \DOMNode $node */ |
||
| 112 | 2 | foreach ($content as $newnode) { |
|
| 113 | /** @var \DOMNode $newnode */ |
||
| 114 | 2 | $newnode = static::importNewnode($newnode, $node, $i); |
|
| 115 | // if ($newnode->ownerDocument !== $node->ownerDocument) { |
||
| 116 | // $newnode = $node->ownerDocument->importNode($newnode, true); |
||
| 117 | // } else { |
||
| 118 | // if ($i > 0) { |
||
| 119 | // $newnode = $newnode->cloneNode(true); |
||
| 120 | // } |
||
| 121 | // } |
||
| 122 | 2 | $node->appendChild($newnode); |
|
| 123 | 2 | $newnodes[] = $newnode; |
|
| 124 | } |
||
| 125 | } |
||
| 126 | 2 | $content->clear(); |
|
| 127 | 2 | $content->add($newnodes); |
|
| 128 | 2 | return $this; |
|
| 129 | } |
||
| 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) |
|
| 139 | { |
||
| 140 | 1 | $e = self::create($element); |
|
| 141 | 1 | $newnodes = array(); |
|
| 142 | 1 | foreach ($e as $i => $node) { |
|
| 143 | /** @var \DOMNode $node */ |
||
| 144 | 1 | foreach ($this as $newnode) { |
|
| 145 | /** @var \DOMNode $newnode */ |
||
| 146 | 1 | $newnode = static::importNewnode($newnode, $node, $i); |
|
| 147 | 1 | $node->appendChild($newnode); |
|
| 148 | 1 | $newnodes[] = $newnode; |
|
| 149 | } |
||
| 150 | } |
||
| 151 | 1 | return self::create($newnodes); |
|
| 152 | } |
||
| 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, $value) |
|
| 182 | { |
||
| 183 | 2 | foreach ($this as $node) { |
|
| 184 | 2 | if ($node instanceof \DOMElement) { |
|
| 185 | /** @var \DOMElement $node */ |
||
| 186 | 2 | $node->setAttribute($name, $value); |
|
| 187 | } |
||
| 188 | } |
||
| 189 | 2 | return $this; |
|
| 190 | } |
||
| 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) |
|
| 201 | { |
||
| 202 | 1 | if (!count($this)) { |
|
| 203 | throw new \InvalidArgumentException('The current node list is empty.'); |
||
| 204 | } |
||
| 205 | 1 | $node = $this->getNode(0); |
|
| 206 | 1 | return $node->hasAttribute($name) ? $node->getAttribute($name) : null; |
|
| 207 | } |
||
| 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) |
|
| 217 | { |
||
| 218 | 2 | $content = self::create($content); |
|
| 219 | 2 | $newnodes = array(); |
|
| 220 | 2 | foreach ($this as $i => $node) { |
|
| 221 | /** @var \DOMNode $node */ |
||
| 222 | 2 | foreach ($content as $newnode) { |
|
| 223 | /** @var \DOMNode $newnode */ |
||
| 224 | 2 | $newnode = static::importNewnode($newnode, $node, $i); |
|
| 225 | 2 | $node->parentNode->insertBefore($newnode, $node); |
|
| 226 | 2 | $newnodes[] = $newnode; |
|
| 227 | } |
||
| 228 | } |
||
| 229 | 2 | $content->clear(); |
|
| 230 | 2 | $content->add($newnodes); |
|
| 231 | 2 | return $this; |
|
| 232 | } |
||
| 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() |
|
| 248 | { |
||
| 249 | 1 | $newnodes = array(); |
|
| 250 | 1 | foreach ($this as $node) { |
|
| 251 | /** @var \DOMNode $node */ |
||
| 252 | 1 | $newnodes[] = $node->cloneNode(true); |
|
| 253 | } |
||
| 254 | 1 | $this->clear(); |
|
| 255 | 1 | $this->add($newnodes); |
|
| 256 | 1 | } |
|
| 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, $value) |
|
| 300 | { |
||
| 301 | 1 | foreach ($this as $node) { |
|
| 302 | 1 | if ($node instanceof \DOMElement) { |
|
| 303 | /** @var \DOMElement $node */ |
||
| 304 | 1 | $styles = Helpers::cssStringToArray($node->getAttribute('style')); |
|
| 305 | 1 | if ($value != '') { |
|
| 306 | 1 | $styles[$key] = $value; |
|
| 307 | } elseif (isset($styles[$key])) { |
||
| 308 | unset($styles[$key]); |
||
| 309 | } |
||
| 310 | 1 | $node->setAttribute('style', Helpers::cssArrayToString($styles)); |
|
| 311 | } |
||
| 312 | } |
||
| 313 | 1 | return $this; |
|
| 314 | } |
||
| 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() |
||
| 330 | |||
| 331 | /** |
||
| 332 | * Determine whether any of the matched elements are assigned the given class. |
||
| 333 | * |
||
| 334 | * @param string $name |
||
| 335 | * @return bool |
||
| 336 | * @api |
||
| 337 | */ |
||
| 338 | 1 | public function hasClass($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) |
|
| 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) |
|
| 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) |
|
| 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) |
|
| 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) |
||
| 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() |
|
| 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) |
|
| 569 | |||
| 570 | /** |
||
| 571 | * Remove a class from each element in the list |
||
| 572 | * |
||
| 573 | * @param string $name |
||
| 574 | * @return HtmlPageCrawler $this for chaining |
||
| 575 | * @api |
||
| 576 | */ |
||
| 577 | 1 | public function removeClass($name) |
|
| 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) |
|
| 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) |
|
| 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) |
|
| 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) |
|
| 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() |
|
| 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() |
|
| 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) |
|
| 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) |
|
| 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) |
|
| 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 | /* Output DocType if exists */ |
||
| 879 | 3 | $documentHtml = $this->getDOMDocument()->saveHTML(); |
|
| 880 | 3 | $html .= preg_match("/<!DOCTYPE.*?>/is", $documentHtml, $match) ? $match[0]."\n" : ''; |
|
| 881 | 3 | foreach ($this as $node) { |
|
| 882 | 3 | $html .= trim($this->getDOMDocument()->saveHTML($node)); |
|
| 883 | } |
||
| 884 | 3 | return $html; |
|
| 885 | } |
||
| 886 | |||
| 887 | public function __toString() |
||
| 888 | { |
||
| 889 | return $this->saveHTML(); |
||
| 890 | } |
||
| 891 | |||
| 892 | /** |
||
| 893 | * checks whether the first node contains a complete html document |
||
| 894 | * (as opposed to a document fragment) |
||
| 895 | * |
||
| 896 | * @return boolean |
||
| 897 | */ |
||
| 898 | 1 | public function isHtmlDocument() |
|
| 911 | |||
| 912 | /** |
||
| 913 | * get ownerDocument of the first element |
||
| 914 | * |
||
| 915 | * @return \DOMDocument|null |
||
| 916 | */ |
||
| 917 | 2 | public function getDOMDocument() |
|
| 918 | { |
||
| 919 | 2 | $node = $this->getNode(0); |
|
| 920 | 2 | $r = null; |
|
| 921 | 2 | if ($node instanceof \DOMElement |
|
| 922 | 2 | && $node->ownerDocument instanceof \DOMDocument |
|
| 923 | ) { |
||
| 924 | 2 | $r = $node->ownerDocument; |
|
| 925 | } |
||
| 926 | 2 | return $r; |
|
| 927 | } |
||
| 928 | |||
| 929 | /** |
||
| 930 | * Filters the list of nodes with a CSS selector. |
||
| 931 | * |
||
| 932 | * @param string $selector |
||
| 933 | * @return HtmlPageCrawler |
||
| 934 | */ |
||
| 935 | 6 | public function filter($selector) |
|
| 939 | |||
| 940 | /** |
||
| 941 | * Filters the list of nodes with an XPath expression. |
||
| 942 | * |
||
| 943 | * @param string $xpath An XPath expression |
||
| 944 | * |
||
| 945 | * @return HtmlPageCrawler A new instance of Crawler with the filtered list of nodes |
||
| 946 | * |
||
| 947 | * @api |
||
| 948 | */ |
||
| 949 | 1 | public function filterXPath($xpath) |
|
| 953 | |||
| 954 | /** |
||
| 955 | * Adds HTML/XML content to the HtmlPageCrawler object (but not to the DOM of an already attached node). |
||
| 956 | * |
||
| 957 | * Function overriden from Crawler because HTML fragments are always added as complete documents there |
||
| 958 | * |
||
| 959 | * |
||
| 960 | * @param string $content A string to parse as HTML/XML |
||
| 961 | * @param null|string $type The content type of the string |
||
| 962 | * |
||
| 963 | * @return null|void |
||
| 964 | */ |
||
| 965 | 12 | public function addContent($content, $type = null) |
|
| 966 | { |
||
| 967 | 12 | if (empty($type)) { |
|
| 968 | 12 | $type = 'text/html;charset=UTF-8'; |
|
| 969 | } |
||
| 970 | 12 | if (substr($type, 0, 9) == 'text/html' && !preg_match('/<html\b[^>]*>/i', $content)) { |
|
| 971 | // string contains no <html> Tag => no complete document but an HTML fragment! |
||
| 972 | 10 | $this->addHtmlFragment($content); |
|
| 973 | } else { |
||
| 974 | 2 | parent::addContent($content, $type); |
|
| 975 | } |
||
| 976 | 12 | } |
|
| 977 | |||
| 978 | 10 | public function addHtmlFragment($content, $charset = 'UTF-8') |
|
| 979 | { |
||
| 980 | 10 | $d = new \DOMDocument('1.0', $charset); |
|
| 981 | 10 | $root = $d->appendChild($d->createElement(self::FRAGMENT_ROOT_TAGNAME)); |
|
| 982 | 10 | $bodynode = Helpers::getBodyNodeFromHtmlFragment($content, $charset); |
|
| 983 | 10 | foreach ($bodynode->childNodes as $child) { |
|
| 984 | 10 | $inode = $root->appendChild($d->importNode($child, true)); |
|
| 985 | 10 | if ($inode) { |
|
| 986 | 10 | $this->addNode($inode); |
|
| 987 | } |
||
| 988 | } |
||
| 989 | 10 | } |
|
| 990 | |||
| 991 | /** |
||
| 992 | * returns the first node |
||
| 993 | * deprecated, use getNode(0) instead |
||
| 994 | * |
||
| 995 | * @return \DOMNode|null |
||
| 996 | * @deprecated |
||
| 997 | * @see Crawler::getNode |
||
| 998 | */ |
||
| 999 | 1 | public function getFirstNode() |
|
| 1003 | |||
| 1004 | /** |
||
| 1005 | * @param int $position |
||
| 1006 | * |
||
| 1007 | * overridden from Crawler because it is not public in Symfony 2.3 |
||
| 1008 | * TODO: throw away as soon as we don't need to support SF 2.3 any more |
||
| 1009 | * |
||
| 1010 | * @return \DOMElement|null |
||
| 1011 | */ |
||
| 1012 | 5 | public function getNode($position) |
|
| 1016 | |||
| 1017 | /** |
||
| 1018 | * Returns the node name of the first node of the list. |
||
| 1019 | * |
||
| 1020 | * in Crawler (parent), this function will be available starting with 2.6.0, |
||
| 1021 | * therefore this method be removed from here as soon as we don't need to keep compatibility |
||
| 1022 | * with Symfony < 2.6 |
||
| 1023 | * |
||
| 1024 | * TODO: throw away as soon as we don't need to support SF 2.3 any more |
||
| 1025 | * |
||
| 1026 | * @return string The node name |
||
| 1027 | * |
||
| 1028 | * @throws \InvalidArgumentException When current node is empty |
||
| 1029 | */ |
||
| 1030 | 1 | public function nodeName() |
|
| 1037 | |||
| 1038 | /** |
||
| 1039 | * Adds a node to the current list of nodes. |
||
| 1040 | * |
||
| 1041 | * This method uses the appropriate specialized add*() method based |
||
| 1042 | * on the type of the argument. |
||
| 1043 | * |
||
| 1044 | * Overwritten from parent to allow Crawler to be added |
||
| 1045 | * |
||
| 1046 | * @param null|\DOMNodeList|array|\DOMNode|Crawler $node A node |
||
| 1047 | * |
||
| 1048 | * @api |
||
| 1049 | */ |
||
| 1050 | 14 | public function add($node) |
|
| 1051 | { |
||
| 1052 | 14 | if ($node instanceof Crawler) { |
|
| 1053 | foreach ($node as $childnode) { |
||
| 1054 | $this->addNode($childnode); |
||
| 1055 | } |
||
| 1056 | } else { |
||
| 1057 | 14 | parent::add($node); |
|
| 1058 | } |
||
| 1059 | 14 | } |
|
| 1060 | |||
| 1061 | /** |
||
| 1062 | * @param \DOMNode $newnode |
||
| 1063 | * @param \DOMNode $referencenode |
||
| 1064 | * @param int $clone |
||
| 1065 | * @return \DOMNode |
||
| 1066 | */ |
||
| 1067 | 5 | protected static function importNewnode(\DOMNode $newnode, \DOMNode $referencenode, $clone = 0) { |
|
| 1068 | 5 | if ($newnode->ownerDocument !== $referencenode->ownerDocument) { |
|
| 1069 | 4 | $newnode = $referencenode->ownerDocument->importNode($newnode, true); |
|
| 1070 | } else { |
||
| 1071 | 2 | if ($clone > 0) { |
|
| 1072 | $newnode = $newnode->cloneNode(true); |
||
| 1073 | } |
||
| 1074 | } |
||
| 1075 | 5 | return $newnode; |
|
| 1076 | } |
||
| 1077 | |||
| 1078 | /** |
||
| 1079 | * Checks whether the first node in the set is disconnected (has no parent node) |
||
| 1080 | * |
||
| 1081 | * @return bool |
||
| 1082 | */ |
||
| 1083 | 1 | public function isDisconnected() |
|
| 1088 | |||
| 1089 | 1 | public function __get($name) |
|
| 1098 | } |
||
| 1099 |
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.