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 $content |
||
28 | * @return HtmlPageCrawler |
||
29 | * @api |
||
30 | */ |
||
31 | 18 | public static function create($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 | 1 | $found = true; |
|
58 | 1 | } |
|
59 | 1 | } |
|
60 | 1 | if (!$found) { |
|
61 | 1 | $classes[] = $name; |
|
62 | 1 | $node->setAttribute('class', trim(join(' ', $classes))); |
|
63 | 1 | } |
|
64 | 1 | } |
|
65 | 1 | } |
|
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 | 3 | } else { |
|
89 | 1 | $node->parentNode->insertBefore($newnode, $refnode); |
|
90 | } |
||
91 | 3 | $newnodes[] = $newnode; |
|
92 | 3 | } |
|
93 | 3 | } |
|
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 | 2 | } |
|
125 | 2 | } |
|
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 $element |
||
135 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
136 | * @api |
||
137 | */ |
||
138 | 2 | public function appendTo($element) |
|
139 | { |
||
140 | 2 | $e = self::create($element); |
|
141 | 2 | $newnodes = array(); |
|
142 | 2 | foreach ($e as $i => $node) { |
|
143 | /** @var \DOMNode $node */ |
||
144 | 2 | foreach ($this as $newnode) { |
|
145 | /** @var \DOMNode $newnode */ |
||
146 | 2 | if ($node !== $newnode) { |
|
147 | 2 | $newnode = static::importNewnode($newnode, $node, $i); |
|
148 | 2 | $node->appendChild($newnode); |
|
149 | 2 | } |
|
150 | 2 | $newnodes[] = $newnode; |
|
151 | 2 | } |
|
152 | 2 | } |
|
153 | 2 | return self::create($newnodes); |
|
154 | } |
||
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, $value) |
|
184 | { |
||
185 | 3 | foreach ($this as $node) { |
|
186 | 3 | if ($node instanceof \DOMElement) { |
|
187 | /** @var \DOMElement $node */ |
||
188 | 3 | $node->setAttribute($name, $value); |
|
189 | 3 | } |
|
190 | 3 | } |
|
191 | 3 | return $this; |
|
192 | } |
||
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) |
|
219 | { |
||
220 | 2 | $content = self::create($content); |
|
221 | 2 | $newnodes = array(); |
|
222 | 2 | foreach ($this as $i => $node) { |
|
223 | /** @var \DOMNode $node */ |
||
224 | 2 | foreach ($content as $newnode) { |
|
225 | /** @var \DOMNode $newnode */ |
||
226 | 2 | if ($node !== $newnode) { |
|
227 | 2 | $newnode = static::importNewnode($newnode, $node, $i); |
|
228 | 2 | $node->parentNode->insertBefore($newnode, $node); |
|
229 | 2 | $newnodes[] = $newnode; |
|
230 | 2 | } |
|
231 | 2 | } |
|
232 | 2 | } |
|
233 | 2 | $content->clear(); |
|
234 | 2 | $content->add($newnodes); |
|
235 | 2 | return $this; |
|
236 | } |
||
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() |
|
252 | { |
||
253 | 1 | $newnodes = array(); |
|
254 | 1 | foreach ($this as $node) { |
|
255 | /** @var \DOMNode $node */ |
||
256 | 1 | $newnodes[] = $node->cloneNode(true); |
|
257 | 1 | } |
|
258 | 1 | $this->clear(); |
|
259 | 1 | $this->add($newnodes); |
|
260 | 1 | } |
|
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, $value) |
|
304 | { |
||
305 | 1 | foreach ($this as $node) { |
|
306 | 1 | if ($node instanceof \DOMElement) { |
|
307 | /** @var \DOMElement $node */ |
||
308 | 1 | $styles = Helpers::cssStringToArray($node->getAttribute('style')); |
|
309 | 1 | if ($value != '') { |
|
310 | 1 | $styles[$key] = $value; |
|
311 | 1 | } elseif (isset($styles[$key])) { |
|
312 | 1 | unset($styles[$key]); |
|
313 | 1 | } |
|
314 | 1 | $node->setAttribute('style', Helpers::cssArrayToString($styles)); |
|
315 | 1 | } |
|
316 | 1 | } |
|
317 | 1 | return $this; |
|
318 | } |
||
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 $this |
||
325 | * @api |
||
326 | */ |
||
327 | 1 | public function makeEmpty() |
|
328 | { |
||
329 | 1 | foreach ($this as $node) { |
|
330 | 1 | $node->nodeValue = ''; |
|
331 | 1 | } |
|
332 | 1 | return $this; |
|
333 | } |
||
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) |
|
343 | { |
||
344 | 2 | foreach ($this as $node) { |
|
345 | 2 | if ($node instanceof \DOMElement && $class = $node->getAttribute('class')) { |
|
346 | 2 | $classes = preg_split('/\s+/s', $class); |
|
347 | 2 | if (in_array($name, $classes)) { |
|
348 | 2 | return true; |
|
349 | } |
||
350 | 1 | } |
|
351 | 2 | } |
|
352 | 2 | return false; |
|
353 | } |
||
354 | |||
355 | /** |
||
356 | * Get the HTML contents of the first element in the set of matched elements |
||
357 | * or set the HTML contents of every matched element. |
||
358 | * |
||
359 | * Function is here for compatibility with jQuery: When called with a parameter, it is |
||
360 | * equivalent to setInnerHtml(), without parameter it is the same as getInnerHtml() |
||
361 | * |
||
362 | * @see HtmlPageCrawler::setInnerHtml() |
||
363 | * @see HtmlPageCrawler::getInnerHtml() |
||
364 | * |
||
365 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList|null $html The HTML content to set, or NULL to get the current content |
||
366 | * |
||
367 | * @return HtmlPageCrawler|string If no param is provided, returns the HTML content of the first element |
||
368 | * @api |
||
369 | */ |
||
370 | 1 | public function html($html = null) |
|
379 | |||
380 | /** |
||
381 | * Get the innerHTML contents of the first element |
||
382 | * |
||
383 | * @return string HTML code fragment |
||
384 | */ |
||
385 | 4 | public function getInnerHtml() |
|
398 | |||
399 | /** |
||
400 | * Set the HTML contents of each element |
||
401 | * |
||
402 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content HTML code fragment |
||
403 | * @return HtmlPageCrawler $this for chaining |
||
404 | */ |
||
405 | 3 | public function setInnerHtml($content) |
|
406 | { |
||
407 | 3 | $content = self::create($content); |
|
408 | 3 | foreach ($this as $node) { |
|
409 | 3 | $node->nodeValue = ''; |
|
410 | 3 | foreach ($content as $newnode) { |
|
411 | /** @var \DOMNode $node */ |
||
412 | /** @var \DOMNode $newnode */ |
||
413 | 3 | $newnode = static::importNewnode($newnode, $node); |
|
414 | 3 | $node->appendChild($newnode); |
|
415 | 3 | } |
|
416 | 3 | } |
|
417 | 3 | return $this; |
|
418 | } |
||
419 | |||
420 | /** |
||
421 | * Insert every element in the set of matched elements after the target. |
||
422 | * |
||
423 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
424 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
425 | * @api |
||
426 | */ |
||
427 | 2 | public function insertAfter($element) |
|
428 | { |
||
429 | 2 | $e = self::create($element); |
|
430 | 2 | $newnodes = array(); |
|
431 | 2 | foreach ($e as $i => $node) { |
|
432 | /** @var \DOMNode $node */ |
||
433 | 2 | $refnode = $node->nextSibling; |
|
434 | 2 | foreach ($this as $newnode) { |
|
435 | /** @var \DOMNode $newnode */ |
||
436 | 2 | $newnode = static::importNewnode($newnode, $node, $i); |
|
437 | 2 | if ($refnode === null) { |
|
438 | 2 | $node->parentNode->appendChild($newnode); |
|
439 | 2 | } else { |
|
440 | 1 | $node->parentNode->insertBefore($newnode, $refnode); |
|
441 | } |
||
442 | 2 | $newnodes[] = $newnode; |
|
443 | 2 | } |
|
444 | 2 | } |
|
445 | 2 | return self::create($newnodes); |
|
446 | } |
||
447 | |||
448 | /** |
||
449 | * Insert every element in the set of matched elements before the target. |
||
450 | * |
||
451 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
452 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
453 | * @api |
||
454 | */ |
||
455 | 2 | public function insertBefore($element) |
|
456 | { |
||
457 | 2 | $e = self::create($element); |
|
458 | 2 | $newnodes = array(); |
|
459 | 2 | foreach ($e as $i => $node) { |
|
460 | /** @var \DOMNode $node */ |
||
461 | 2 | foreach ($this as $newnode) { |
|
462 | /** @var \DOMNode $newnode */ |
||
463 | 2 | $newnode = static::importNewnode($newnode, $node, $i); |
|
464 | 2 | if ($newnode !== $node) { |
|
465 | 2 | $node->parentNode->insertBefore($newnode, $node); |
|
466 | 2 | } |
|
467 | 2 | $newnodes[] = $newnode; |
|
468 | 2 | } |
|
469 | 2 | } |
|
470 | 2 | return self::create($newnodes); |
|
471 | } |
||
472 | |||
473 | /** |
||
474 | * Insert content, specified by the parameter, to the beginning of each element in the set of matched elements. |
||
475 | * |
||
476 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content HTML code fragment |
||
477 | * @return HtmlPageCrawler $this for chaining |
||
478 | * @api |
||
479 | */ |
||
480 | 2 | public function prepend($content) |
|
481 | { |
||
482 | 2 | $content = self::create($content); |
|
483 | 2 | $newnodes = array(); |
|
484 | 2 | foreach ($this as $i => $node) { |
|
485 | 2 | $refnode = $node->firstChild; |
|
486 | /** @var \DOMNode $node */ |
||
487 | 2 | foreach ($content as $newnode) { |
|
488 | /** @var \DOMNode $newnode */ |
||
489 | 2 | $newnode = static::importNewnode($newnode, $node, $i); |
|
490 | 2 | if ($refnode === null) { |
|
491 | 1 | $node->appendChild($newnode); |
|
492 | 2 | } else if ($refnode !== $newnode) { |
|
493 | 2 | $node->insertBefore($newnode, $refnode); |
|
494 | 2 | } |
|
495 | 2 | $newnodes[] = $newnode; |
|
496 | 2 | } |
|
497 | 2 | } |
|
498 | 2 | $content->clear(); |
|
499 | 2 | $content->add($newnodes); |
|
500 | 2 | return $this; |
|
501 | } |
||
502 | |||
503 | /** |
||
504 | * Insert every element in the set of matched elements to the beginning of the target. |
||
505 | * |
||
506 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
507 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements prepended to the target elements |
||
508 | * @api |
||
509 | */ |
||
510 | 1 | public function prependTo($element) |
|
511 | { |
||
512 | 1 | $e = self::create($element); |
|
513 | 1 | $newnodes = array(); |
|
514 | 1 | foreach ($e as $i => $node) { |
|
515 | 1 | $refnode = $node->firstChild; |
|
516 | /** @var \DOMNode $node */ |
||
517 | 1 | foreach ($this as $newnode) { |
|
518 | /** @var \DOMNode $newnode */ |
||
519 | 1 | $newnode = static::importNewnode($newnode, $node, $i); |
|
520 | 1 | if ($newnode !== $node) { |
|
521 | 1 | if ($refnode === null) { |
|
522 | 1 | $node->appendChild($newnode); |
|
523 | 1 | } else { |
|
524 | 1 | $node->insertBefore($newnode, $refnode); |
|
525 | } |
||
526 | 1 | } |
|
527 | 1 | $newnodes[] = $newnode; |
|
528 | 1 | } |
|
529 | 1 | } |
|
530 | 1 | return self::create($newnodes); |
|
531 | } |
||
532 | |||
533 | /** |
||
534 | * Remove the set of matched elements from the DOM. |
||
535 | * |
||
536 | * (as opposed to Crawler::clear() which detaches the nodes only from Crawler |
||
537 | * but leaves them in the DOM) |
||
538 | * |
||
539 | * @api |
||
540 | */ |
||
541 | 2 | public function remove() |
|
542 | { |
||
543 | 2 | foreach ($this as $node) { |
|
544 | /** |
||
545 | * @var \DOMNode $node |
||
546 | */ |
||
547 | 2 | if ($node->parentNode instanceof \DOMElement) { |
|
548 | 2 | $node->parentNode->removeChild($node); |
|
549 | 2 | } |
|
550 | 2 | } |
|
551 | 2 | $this->clear(); |
|
552 | 2 | } |
|
553 | |||
554 | /** |
||
555 | * Remove an attribute from each element in the set of matched elements. |
||
556 | * |
||
557 | * Alias for removeAttribute for compatibility with jQuery |
||
558 | * |
||
559 | * @param string $name |
||
560 | * @return HtmlPageCrawler |
||
561 | * @api |
||
562 | */ |
||
563 | 1 | public function removeAttr($name) |
|
567 | |||
568 | /** |
||
569 | * Remove an attribute from each element in the set of matched elements. |
||
570 | * |
||
571 | * @param string $name |
||
572 | * @return HtmlPageCrawler |
||
573 | */ |
||
574 | 1 | public function removeAttribute($name) |
|
575 | { |
||
576 | 1 | foreach ($this as $node) { |
|
577 | 1 | if ($node instanceof \DOMElement) { |
|
578 | /** @var \DOMElement $node */ |
||
579 | 1 | if ($node->hasAttribute($name)) { |
|
580 | 1 | $node->removeAttribute($name); |
|
581 | 1 | } |
|
582 | 1 | } |
|
583 | 1 | } |
|
584 | 1 | return $this; |
|
585 | } |
||
586 | |||
587 | /** |
||
588 | * Remove a class from each element in the list |
||
589 | * |
||
590 | * @param string $name |
||
591 | * @return HtmlPageCrawler $this for chaining |
||
592 | * @api |
||
593 | */ |
||
594 | 2 | public function removeClass($name) |
|
595 | { |
||
596 | 2 | foreach ($this as $node) { |
|
597 | 2 | if ($node instanceof \DOMElement) { |
|
598 | /** @var \DOMElement $node */ |
||
599 | 2 | $classes = preg_split('/\s+/s', $node->getAttribute('class')); |
|
600 | 2 | $count = count($classes); |
|
601 | 2 | for ($i = 0; $i < $count; $i++) { |
|
602 | 2 | if ($classes[$i] == $name) { |
|
603 | 2 | unset($classes[$i]); |
|
604 | 2 | } |
|
605 | 2 | } |
|
606 | 2 | $node->setAttribute('class', trim(join(' ', $classes))); |
|
607 | 2 | } |
|
608 | 2 | } |
|
609 | 2 | return $this; |
|
610 | } |
||
611 | |||
612 | /** |
||
613 | * Replace each target element with the set of matched elements. |
||
614 | * |
||
615 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
616 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
617 | * @api |
||
618 | */ |
||
619 | 2 | public function replaceAll($element) |
|
620 | { |
||
621 | 2 | $e = self::create($element); |
|
622 | 2 | $newnodes = array(); |
|
623 | 2 | foreach ($e as $i => $node) { |
|
624 | /** @var \DOMNode $node */ |
||
625 | 2 | $parent = $node->parentNode; |
|
626 | 2 | $refnode = $node->nextSibling; |
|
627 | 2 | foreach ($this as $j => $newnode) { |
|
628 | /** @var \DOMNode $newnode */ |
||
629 | 2 | $newnode = static::importNewnode($newnode, $node, $i); |
|
630 | 2 | if ($j == 0) { |
|
631 | 2 | $parent->replaceChild($newnode, $node); |
|
632 | 2 | } else { |
|
633 | 1 | $parent->insertBefore($newnode, $refnode); |
|
634 | } |
||
635 | 2 | $newnodes[] = $newnode; |
|
636 | 2 | } |
|
637 | 2 | } |
|
638 | 2 | return self::create($newnodes); |
|
639 | } |
||
640 | |||
641 | /** |
||
642 | * Replace each element in the set of matched elements with the provided new content and return the set of elements that was removed. |
||
643 | * |
||
644 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content |
||
645 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
646 | * @api |
||
647 | */ |
||
648 | 2 | public function replaceWith($content) |
|
649 | { |
||
650 | 2 | $content = self::create($content); |
|
651 | 2 | $newnodes = array(); |
|
652 | 2 | foreach ($this as $i => $node) { |
|
653 | /** @var \DOMNode $node */ |
||
654 | 2 | $parent = $node->parentNode; |
|
655 | 2 | $refnode = $node->nextSibling; |
|
656 | 2 | foreach ($content as $j => $newnode) { |
|
657 | /** @var \DOMNode $newnode */ |
||
658 | 2 | $newnode = static::importNewnode($newnode, $node, $i); |
|
659 | 2 | if ($j == 0) { |
|
660 | 2 | $parent->replaceChild($newnode, $node); |
|
661 | 2 | } else { |
|
662 | 1 | $parent->insertBefore($newnode, $refnode); |
|
663 | } |
||
664 | 2 | $newnodes[] = $newnode; |
|
665 | 2 | } |
|
666 | 2 | } |
|
667 | 2 | $content->clear(); |
|
668 | 2 | $content->add($newnodes); |
|
669 | 2 | return $this; |
|
670 | } |
||
671 | |||
672 | /** |
||
673 | * Get the combined text contents of each element in the set of matched elements, including their descendants, |
||
674 | * or set the text contents of the matched elements. |
||
675 | * |
||
676 | * ATTENTION: Contrary to the parent Crawler class, which returns the text from the first element only, |
||
677 | * this functions returns the combined text of all elements (as jQuery does). If this is not what you need you |
||
678 | * must call ->first() before calling ->text(), e.g. |
||
679 | * |
||
680 | * in Symfony\DOMCrawler\Crawler: $c->filter('p')->text() returns the text of the first paragraph only |
||
681 | * in HtmlPageCrawler you need to call: $c->filter('p')->first()->text() |
||
682 | * |
||
683 | * @param null|string $text |
||
684 | * @return string|HtmlPageCrawler |
||
685 | * @api |
||
686 | */ |
||
687 | 1 | public function text($text = null) |
|
688 | { |
||
689 | 1 | if ($text === null) { |
|
690 | 1 | $text = ''; |
|
691 | 1 | foreach ($this as $node) { |
|
692 | /** @var \DOMNode $node */ |
||
693 | 1 | $text .= $node->nodeValue; |
|
694 | 1 | } |
|
695 | 1 | return $text; |
|
696 | } else { |
||
697 | 1 | foreach ($this as $node) { |
|
698 | /** @var \DOMNode $node */ |
||
699 | 1 | $node->nodeValue = $text; |
|
700 | 1 | } |
|
701 | 1 | return $this; |
|
702 | } |
||
703 | } |
||
704 | |||
705 | |||
706 | /** |
||
707 | * Add or remove one or more classes from each element in the set of matched elements, depending the class’s presence. |
||
708 | * |
||
709 | * @param string $classname One or more classnames separated by spaces |
||
710 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
711 | * @api |
||
712 | */ |
||
713 | 1 | public function toggleClass($classname) |
|
714 | { |
||
715 | 1 | $classes = explode(' ', $classname); |
|
716 | 1 | foreach ($this as $i => $node) { |
|
717 | 1 | $c = self::create($node); |
|
718 | /** @var \DOMNode $node */ |
||
719 | 1 | foreach ($classes as $class) { |
|
720 | 1 | if ($c->hasClass($class)) { |
|
721 | 1 | $c->removeClass($class); |
|
722 | 1 | } else { |
|
723 | 1 | $c->addClass($class); |
|
724 | } |
||
725 | 1 | } |
|
726 | 1 | } |
|
727 | 1 | return $this; |
|
728 | } |
||
729 | |||
730 | /** |
||
731 | * Remove the parents of the set of matched elements from the DOM, leaving the matched elements in their place. |
||
732 | * |
||
733 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
734 | * @api |
||
735 | */ |
||
736 | 1 | public function unwrap() |
|
737 | { |
||
738 | 1 | $parents = array(); |
|
739 | 1 | foreach($this as $i => $node) { |
|
740 | 1 | $parents[] = $node->parentNode; |
|
741 | 1 | } |
|
742 | |||
743 | 1 | self::create($parents)->unwrapInner(); |
|
744 | 1 | return $this; |
|
745 | } |
||
746 | |||
747 | /** |
||
748 | * Remove the matched elements, but promote the children to take their place. |
||
749 | * |
||
750 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
751 | * @api |
||
752 | */ |
||
753 | 2 | public function unwrapInner() |
|
754 | { |
||
755 | 2 | foreach($this as $i => $node) { |
|
756 | 2 | if (!$node->parentNode instanceof \DOMElement) { |
|
757 | 1 | throw new \InvalidArgumentException('DOMElement does not have a parent DOMElement node.'); |
|
758 | } |
||
759 | |||
760 | /** @var \DOMNode[] $children */ |
||
761 | 2 | $children = iterator_to_array($node->childNodes); |
|
762 | 2 | foreach ($children as $child) { |
|
763 | 1 | $node->parentNode->insertBefore($child, $node); |
|
764 | 2 | } |
|
765 | |||
766 | 2 | $node->parentNode->removeChild($node); |
|
767 | 2 | } |
|
768 | 2 | } |
|
769 | |||
770 | |||
771 | /** |
||
772 | * Wrap an HTML structure around each element in the set of matched elements |
||
773 | * |
||
774 | * The HTML structure must contain only one root node, e.g.: |
||
775 | * Works: <div><div></div></div> |
||
776 | * Does not work: <div></div><div></div> |
||
777 | * |
||
778 | * @param string|HtmlPageCrawler|\DOMNode $wrappingElement |
||
779 | * @return HtmlPageCrawler $this for chaining |
||
780 | * @api |
||
781 | */ |
||
782 | 1 | public function wrap($wrappingElement) |
|
783 | { |
||
784 | 1 | $content = self::create($wrappingElement); |
|
785 | 1 | $newnodes = array(); |
|
786 | 1 | foreach ($this as $i => $node) { |
|
787 | /** @var \DOMNode $node */ |
||
788 | 1 | $newnode = $content->getNode(0); |
|
789 | /** @var \DOMNode $newnode */ |
||
790 | // $newnode = static::importNewnode($newnode, $node, $i); |
||
791 | 1 | if ($newnode->ownerDocument !== $node->ownerDocument) { |
|
792 | 1 | $newnode = $node->ownerDocument->importNode($newnode, true); |
|
793 | 1 | } else { |
|
794 | if ($i > 0) { |
||
795 | $newnode = $newnode->cloneNode(true); |
||
796 | } |
||
797 | } |
||
798 | 1 | $oldnode = $node->parentNode->replaceChild($newnode, $node); |
|
799 | 1 | while ($newnode->hasChildNodes()) { |
|
800 | 1 | $elementFound = false; |
|
801 | 1 | foreach ($newnode->childNodes as $child) { |
|
802 | 1 | if ($child instanceof \DOMElement) { |
|
803 | 1 | $newnode = $child; |
|
804 | 1 | $elementFound = true; |
|
805 | 1 | break; |
|
806 | } |
||
807 | 1 | } |
|
808 | 1 | if (!$elementFound) { |
|
809 | 1 | break; |
|
810 | } |
||
811 | 1 | } |
|
812 | 1 | $newnode->appendChild($oldnode); |
|
813 | 1 | $newnodes[] = $newnode; |
|
814 | 1 | } |
|
815 | 1 | $content->clear(); |
|
816 | 1 | $content->add($newnodes); |
|
817 | 1 | return $this; |
|
818 | } |
||
819 | |||
820 | /** |
||
821 | * Wrap an HTML structure around all elements in the set of matched elements. |
||
822 | * |
||
823 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content |
||
824 | * @throws \LogicException |
||
825 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
826 | * @api |
||
827 | */ |
||
828 | 1 | public function wrapAll($content) |
|
829 | { |
||
830 | 1 | $content = self::create($content); |
|
831 | 1 | $parent = $this->getNode(0)->parentNode; |
|
832 | 1 | foreach ($this as $i => $node) { |
|
833 | /** @var \DOMNode $node */ |
||
834 | 1 | if ($node->parentNode !== $parent) { |
|
835 | throw new \LogicException('Nodes to be wrapped with wrapAll() must all have the same parent'); |
||
836 | } |
||
837 | 1 | } |
|
838 | |||
839 | 1 | $newnode = $content->getNode(0); |
|
840 | /** @var \DOMNode $newnode */ |
||
841 | 1 | $newnode = static::importNewnode($newnode, $parent); |
|
842 | |||
843 | 1 | $newnode = $parent->insertBefore($newnode,$this->getNode(0)); |
|
844 | 1 | $content->clear(); |
|
845 | 1 | $content->add($newnode); |
|
846 | |||
847 | 1 | while ($newnode->hasChildNodes()) { |
|
848 | 1 | $elementFound = false; |
|
849 | 1 | foreach ($newnode->childNodes as $child) { |
|
850 | 1 | if ($child instanceof \DOMElement) { |
|
851 | 1 | $newnode = $child; |
|
852 | 1 | $elementFound = true; |
|
853 | 1 | break; |
|
854 | } |
||
855 | 1 | } |
|
856 | 1 | if (!$elementFound) { |
|
857 | break; |
||
858 | } |
||
859 | 1 | } |
|
860 | 1 | foreach ($this as $i => $node) { |
|
861 | /** @var \DOMNode $node */ |
||
862 | 1 | $newnode->appendChild($node); |
|
863 | 1 | } |
|
864 | 1 | return $this; |
|
865 | } |
||
866 | |||
867 | /** |
||
868 | * Wrap an HTML structure around the content of each element in the set of matched elements. |
||
869 | * |
||
870 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content |
||
871 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
872 | * @api |
||
873 | */ |
||
874 | 1 | public function wrapInner($content) |
|
875 | { |
||
876 | 1 | foreach ($this as $i => $node) { |
|
877 | /** @var \DOMNode $node */ |
||
878 | 1 | self::create($node->childNodes)->wrapAll($content); |
|
879 | 1 | } |
|
880 | 1 | return $this; |
|
881 | } |
||
882 | |||
883 | /** |
||
884 | * Get the HTML code fragment of all elements and their contents. |
||
885 | * |
||
886 | * If the first node contains a complete HTML document return only |
||
887 | * the full code of this document. |
||
888 | * |
||
889 | * @return string HTML code (fragment) |
||
890 | * @api |
||
891 | */ |
||
892 | 8 | public function saveHTML() |
|
893 | { |
||
894 | 8 | if ($this->isHtmlDocument()) { |
|
895 | 1 | return $this->getDOMDocument()->saveHTML(); |
|
896 | } else { |
||
897 | 8 | $doc = new \DOMDocument('1.0', 'UTF-8'); |
|
898 | 8 | $root = $doc->appendChild($doc->createElement('_root')); |
|
899 | 8 | foreach ($this as $node) { |
|
900 | 8 | $root->appendChild($doc->importNode($node, true)); |
|
901 | 8 | } |
|
902 | 8 | $html = trim($doc->saveHTML()); |
|
903 | 8 | return preg_replace('@^<'.self::FRAGMENT_ROOT_TAGNAME.'[^>]*>|</'.self::FRAGMENT_ROOT_TAGNAME.'>$@', '', $html); |
|
904 | } |
||
905 | } |
||
906 | |||
907 | 4 | public function __toString() |
|
911 | |||
912 | /** |
||
913 | * checks whether the first node contains a complete html document |
||
914 | * (as opposed to a document fragment) |
||
915 | * |
||
916 | * @return boolean |
||
917 | */ |
||
918 | 8 | public function isHtmlDocument() |
|
931 | |||
932 | /** |
||
933 | * get ownerDocument of the first element |
||
934 | * |
||
935 | * @return \DOMDocument|null |
||
936 | */ |
||
937 | 1 | public function getDOMDocument() |
|
938 | { |
||
939 | 1 | $node = $this->getNode(0); |
|
940 | 1 | $r = null; |
|
941 | if ($node instanceof \DOMElement |
||
942 | 1 | && $node->ownerDocument instanceof \DOMDocument |
|
943 | 1 | ) { |
|
944 | 1 | $r = $node->ownerDocument; |
|
945 | 1 | } |
|
946 | 1 | return $r; |
|
947 | } |
||
948 | |||
949 | /** |
||
950 | * Filters the list of nodes with a CSS selector. |
||
951 | * |
||
952 | * @param string $selector |
||
953 | * @return HtmlPageCrawler |
||
954 | */ |
||
955 | 8 | public function filter($selector) |
|
959 | |||
960 | /** |
||
961 | * Filters the list of nodes with an XPath expression. |
||
962 | * |
||
963 | * @param string $xpath An XPath expression |
||
964 | * |
||
965 | * @return HtmlPageCrawler A new instance of Crawler with the filtered list of nodes |
||
966 | * |
||
967 | * @api |
||
968 | */ |
||
969 | 2 | public function filterXPath($xpath) |
|
973 | |||
974 | /** |
||
975 | * Adds HTML/XML content to the HtmlPageCrawler object (but not to the DOM of an already attached node). |
||
976 | * |
||
977 | * Function overriden from Crawler because HTML fragments are always added as complete documents there |
||
978 | * |
||
979 | * |
||
980 | * @param string $content A string to parse as HTML/XML |
||
981 | * @param null|string $type The content type of the string |
||
982 | * |
||
983 | * @return null|void |
||
984 | */ |
||
985 | 17 | public function addContent($content, $type = null) |
|
986 | { |
||
987 | 17 | if (empty($type)) { |
|
988 | 17 | $type = 'text/html;charset=UTF-8'; |
|
989 | 17 | } |
|
990 | 17 | if (substr($type, 0, 9) == 'text/html' && !preg_match('/<html\b[^>]*>/i', $content)) { |
|
991 | // string contains no <html> Tag => no complete document but an HTML fragment! |
||
992 | 16 | $this->addHtmlFragment($content); |
|
993 | 16 | } else { |
|
994 | 2 | parent::addContent($content, $type); |
|
995 | } |
||
996 | 17 | } |
|
997 | |||
998 | 15 | public function addHtmlFragment($content, $charset = 'UTF-8') |
|
999 | { |
||
1000 | 15 | $d = new \DOMDocument('1.0', $charset); |
|
1001 | 15 | $root = $d->appendChild($d->createElement(self::FRAGMENT_ROOT_TAGNAME)); |
|
1002 | 15 | $bodynode = Helpers::getBodyNodeFromHtmlFragment($content, $charset); |
|
1003 | 15 | foreach ($bodynode->childNodes as $child) { |
|
1004 | 15 | $inode = $root->appendChild($d->importNode($child, true)); |
|
1005 | 15 | if ($inode) { |
|
1006 | 15 | $this->addNode($inode); |
|
1007 | 15 | } |
|
1008 | 15 | } |
|
1009 | 15 | } |
|
1010 | |||
1011 | /** |
||
1012 | * returns the first node |
||
1013 | * deprecated, use getNode(0) instead |
||
1014 | * |
||
1015 | * @return \DOMNode|null |
||
1016 | * @deprecated |
||
1017 | * @see Crawler::getNode |
||
1018 | */ |
||
1019 | public function getFirstNode() |
||
1020 | { |
||
1021 | return $this->getNode(0); |
||
1022 | } |
||
1023 | |||
1024 | /** |
||
1025 | * @param int $position |
||
1026 | * |
||
1027 | * overridden from Crawler because it is not public in Symfony 2.3 |
||
1028 | * TODO: throw away as soon as we don't need to support SF 2.3 any more |
||
1029 | * |
||
1030 | * @return \DOMElement|null |
||
1031 | */ |
||
1032 | 14 | public function getNode($position) |
|
1036 | |||
1037 | /** |
||
1038 | * Returns the node name of the first node of the list. |
||
1039 | * |
||
1040 | * in Crawler (parent), this function will be available starting with 2.6.0, |
||
1041 | * therefore this method be removed from here as soon as we don't need to keep compatibility |
||
1042 | * with Symfony < 2.6 |
||
1043 | * |
||
1044 | * TODO: throw away as soon as we don't need to support SF 2.3 any more |
||
1045 | * |
||
1046 | * @return string The node name |
||
1047 | * |
||
1048 | * @throws \InvalidArgumentException When current node is empty |
||
1049 | */ |
||
1050 | 1 | public function nodeName() |
|
1057 | |||
1058 | /** |
||
1059 | * Adds a node to the current list of nodes. |
||
1060 | * |
||
1061 | * This method uses the appropriate specialized add*() method based |
||
1062 | * on the type of the argument. |
||
1063 | * |
||
1064 | * Overwritten from parent to allow Crawler to be added |
||
1065 | * |
||
1066 | * @param null|\DOMNodeList|array|\DOMNode|Crawler $node A node |
||
1067 | * |
||
1068 | * @api |
||
1069 | */ |
||
1070 | 29 | public function add($node) |
|
1071 | { |
||
1072 | 29 | if ($node instanceof Crawler) { |
|
1073 | 1 | foreach ($node as $childnode) { |
|
1074 | 1 | $this->addNode($childnode); |
|
1075 | 1 | } |
|
1076 | 1 | } else { |
|
1077 | 29 | parent::add($node); |
|
1078 | } |
||
1079 | 29 | } |
|
1080 | |||
1081 | /** |
||
1082 | * @param \DOMNode $newnode |
||
1083 | * @param \DOMNode $referencenode |
||
1084 | * @param int $clone |
||
1085 | * @return \DOMNode |
||
1086 | */ |
||
1087 | 6 | protected static function importNewnode(\DOMNode $newnode, \DOMNode $referencenode, $clone = 0) { |
|
1088 | 6 | if ($newnode->ownerDocument !== $referencenode->ownerDocument) { |
|
1089 | 5 | $newnode = $referencenode->ownerDocument->importNode($newnode, true); |
|
1090 | 5 | } else { |
|
1091 | 2 | if ($clone > 0) { |
|
1092 | $newnode = $newnode->cloneNode(true); |
||
1093 | } |
||
1094 | } |
||
1095 | 6 | return $newnode; |
|
1096 | } |
||
1097 | |||
1098 | /** |
||
1099 | * Checks whether the first node in the set is disconnected (has no parent node) |
||
1100 | * |
||
1101 | * @return bool |
||
1102 | */ |
||
1103 | 1 | public function isDisconnected() |
|
1108 | |||
1109 | 1 | public function __get($name) |
|
1118 | } |
||
1119 |
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.