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) |
|
32 | { |
||
33 | 18 | if ($content instanceof HtmlPageCrawler) { |
|
34 | 3 | return $content; |
|
35 | } else { |
||
36 | 18 | return new HtmlPageCrawler($content); |
|
37 | } |
||
38 | } |
||
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 $element |
||
135 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
136 | * @api |
||
137 | */ |
||
138 | 1 | public function appendTo($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[] = $newnode; |
|
149 | 1 | } |
|
150 | 1 | } |
|
151 | 1 | return self::create($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 $value |
||
162 | * @return null|string|HtmlPageCrawler |
||
163 | * @api |
||
164 | */ |
||
165 | 2 | public function attr($name, $value = null) |
|
173 | |||
174 | /** |
||
175 | * Sets an attribute on each element |
||
176 | * |
||
177 | * @param string $name |
||
178 | * @param string $value |
||
179 | * @return HtmlPageCrawler $this for chaining |
||
180 | */ |
||
181 | 3 | public function setAttribute($name, $value) |
|
182 | { |
||
183 | 3 | foreach ($this as $node) { |
|
184 | 3 | if ($node instanceof \DOMElement) { |
|
185 | /** @var \DOMElement $node */ |
||
186 | 3 | $node->setAttribute($name, $value); |
|
187 | 3 | } |
|
188 | 3 | } |
|
189 | 3 | return $this; |
|
190 | } |
||
191 | |||
192 | /** |
||
193 | * Returns the attribute value of the first node of the list. |
||
194 | * |
||
195 | * @param string $name The attribute name |
||
196 | * @return string|null The attribute value or null if the attribute does not exist |
||
197 | * @throws \InvalidArgumentException When current node is empty |
||
198 | * |
||
199 | */ |
||
200 | 2 | public function getAttribute($name) |
|
201 | { |
||
202 | 2 | if (!count($this)) { |
|
203 | 1 | 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 | 2 | } |
|
228 | 2 | } |
|
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 | 1 | } |
|
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) |
|
272 | { |
||
273 | 1 | if (null === $value) { |
|
274 | 1 | return $this->getStyle($key); |
|
275 | } else { |
||
276 | 1 | return $this->setStyle($key, $value); |
|
277 | } |
||
278 | } |
||
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) |
|
287 | { |
||
288 | 1 | $styles = Helpers::cssStringToArray($this->getAttribute('style')); |
|
289 | 1 | return (isset($styles[$key]) ? $styles[$key] : null); |
|
290 | } |
||
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] = $value; |
|
307 | 1 | } elseif (isset($styles[$key])) { |
|
308 | 1 | unset($styles[$key]); |
|
309 | 1 | } |
|
310 | 1 | $node->setAttribute('style', Helpers::cssArrayToString($styles)); |
|
311 | 1 | } |
|
312 | 1 | } |
|
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 $this |
||
321 | * @api |
||
322 | */ |
||
323 | 1 | public function makeEmpty() |
|
324 | { |
||
325 | 1 | foreach ($this as $node) { |
|
326 | 1 | $node->nodeValue = ''; |
|
327 | 1 | } |
|
328 | 1 | 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) |
|
339 | { |
||
340 | 2 | foreach ($this as $node) { |
|
341 | 2 | if ($node instanceof \DOMElement && $class = $node->getAttribute('class')) { |
|
342 | 2 | $classes = preg_split('/\s+/s', $class); |
|
343 | 2 | if (in_array($name, $classes)) { |
|
344 | 2 | return true; |
|
345 | } |
||
346 | 1 | } |
|
347 | 2 | } |
|
348 | 2 | return false; |
|
349 | } |
||
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 $html The HTML content to set, or NULL to get the current content |
||
362 | * |
||
363 | * @return HtmlPageCrawler|string If no param is provided, returns the HTML content of the first element |
||
364 | * @api |
||
365 | */ |
||
366 | 1 | public function html($html = null) |
|
367 | { |
||
368 | 1 | if (null === $html) { |
|
369 | 1 | return $this->getInnerHtml(); |
|
370 | } else { |
||
371 | 1 | $this->setInnerHtml($html); |
|
372 | 1 | return $this; |
|
373 | } |
||
374 | } |
||
375 | |||
376 | /** |
||
377 | * Get the innerHTML contents of the first element |
||
378 | * |
||
379 | * @return string HTML code fragment |
||
380 | */ |
||
381 | 4 | public function getInnerHtml() |
|
382 | { |
||
383 | 4 | $node = $this->getNode(0); |
|
384 | 4 | if ($node instanceof \DOMNode) { |
|
385 | 3 | $doc = new \DOMDocument('1.0', 'UTF-8'); |
|
386 | 3 | $doc->appendChild($doc->importNode($node, true)); |
|
387 | 3 | $html = trim($doc->saveHTML()); |
|
388 | 3 | $tag = $node->nodeName; |
|
389 | 3 | return preg_replace('@^<' . $tag . '[^>]*>|</' . $tag . '>$@', '', $html); |
|
390 | } else { |
||
391 | 1 | return ''; |
|
392 | } |
||
393 | } |
||
394 | |||
395 | /** |
||
396 | * Set the HTML contents of each element |
||
397 | * |
||
398 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content HTML code fragment |
||
399 | * @return HtmlPageCrawler $this for chaining |
||
400 | */ |
||
401 | 3 | public function setInnerHtml($content) |
|
402 | { |
||
403 | 3 | $content = self::create($content); |
|
404 | 3 | foreach ($this as $node) { |
|
405 | 3 | $node->nodeValue = ''; |
|
406 | 3 | foreach ($content as $newnode) { |
|
407 | /** @var \DOMNode $node */ |
||
408 | /** @var \DOMNode $newnode */ |
||
409 | 3 | $newnode = static::importNewnode($newnode, $node); |
|
410 | 3 | $node->appendChild($newnode); |
|
411 | 3 | } |
|
412 | 3 | } |
|
413 | 3 | return $this; |
|
414 | } |
||
415 | |||
416 | /** |
||
417 | * Insert every element in the set of matched elements after the target. |
||
418 | * |
||
419 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
420 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
421 | * @api |
||
422 | */ |
||
423 | 1 | public function insertAfter($element) |
|
424 | { |
||
425 | 1 | $e = self::create($element); |
|
426 | 1 | $newnodes = array(); |
|
427 | 1 | foreach ($e as $i => $node) { |
|
428 | /** @var \DOMNode $node */ |
||
429 | 1 | $refnode = $node->nextSibling; |
|
430 | 1 | foreach ($this as $newnode) { |
|
431 | /** @var \DOMNode $newnode */ |
||
432 | 1 | $newnode = static::importNewnode($newnode, $node, $i); |
|
433 | 1 | if ($refnode === null) { |
|
434 | 1 | $node->parentNode->appendChild($newnode); |
|
435 | 1 | } else { |
|
436 | 1 | $node->parentNode->insertBefore($newnode, $refnode); |
|
437 | } |
||
438 | 1 | $newnodes[] = $newnode; |
|
439 | 1 | } |
|
440 | 1 | } |
|
441 | 1 | return self::create($newnodes); |
|
442 | } |
||
443 | |||
444 | /** |
||
445 | * Insert every element in the set of matched elements before the target. |
||
446 | * |
||
447 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
448 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
449 | * @api |
||
450 | */ |
||
451 | 1 | public function insertBefore($element) |
|
452 | { |
||
453 | 1 | $e = self::create($element); |
|
454 | 1 | $newnodes = array(); |
|
455 | 1 | foreach ($e as $i => $node) { |
|
456 | /** @var \DOMNode $node */ |
||
457 | 1 | foreach ($this as $newnode) { |
|
458 | /** @var \DOMNode $newnode */ |
||
459 | 1 | $newnode = static::importNewnode($newnode, $node, $i); |
|
460 | 1 | $node->parentNode->insertBefore($newnode, $node); |
|
461 | 1 | $newnodes[] = $newnode; |
|
462 | 1 | } |
|
463 | 1 | } |
|
464 | 1 | return self::create($newnodes); |
|
465 | } |
||
466 | |||
467 | /** |
||
468 | * Insert content, specified by the parameter, to the beginning of each element in the set of matched elements. |
||
469 | * |
||
470 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content HTML code fragment |
||
471 | * @return HtmlPageCrawler $this for chaining |
||
472 | * @api |
||
473 | */ |
||
474 | 2 | public function prepend($content) |
|
475 | { |
||
476 | 2 | $content = self::create($content); |
|
477 | 2 | $newnodes = array(); |
|
478 | 2 | foreach ($this as $i => $node) { |
|
479 | 2 | $refnode = $node->firstChild; |
|
480 | /** @var \DOMNode $node */ |
||
481 | 2 | foreach ($content as $newnode) { |
|
482 | /** @var \DOMNode $newnode */ |
||
483 | 2 | $newnode = static::importNewnode($newnode, $node, $i); |
|
484 | 2 | if ($refnode === null) { |
|
485 | 1 | $node->appendChild($newnode); |
|
486 | 1 | } else { |
|
487 | 2 | $node->insertBefore($newnode, $refnode); |
|
488 | } |
||
489 | 2 | $newnodes[] = $newnode; |
|
490 | 2 | } |
|
491 | 2 | } |
|
492 | 2 | $content->clear(); |
|
493 | 2 | $content->add($newnodes); |
|
494 | 2 | return $this; |
|
495 | } |
||
496 | |||
497 | /** |
||
498 | * Insert every element in the set of matched elements to the beginning of the target. |
||
499 | * |
||
500 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
501 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements prepended to the target elements |
||
502 | * @api |
||
503 | */ |
||
504 | 1 | public function prependTo($element) |
|
505 | { |
||
506 | 1 | $e = self::create($element); |
|
507 | 1 | $newnodes = array(); |
|
508 | 1 | foreach ($e as $i => $node) { |
|
509 | 1 | $refnode = $node->firstChild; |
|
510 | /** @var \DOMNode $node */ |
||
511 | 1 | foreach ($this as $newnode) { |
|
512 | /** @var \DOMNode $newnode */ |
||
513 | 1 | $newnode = static::importNewnode($newnode, $node, $i); |
|
514 | 1 | if ($refnode === null) { |
|
515 | 1 | $node->appendChild($newnode); |
|
516 | 1 | } else { |
|
517 | 1 | $node->insertBefore($newnode, $refnode); |
|
518 | } |
||
519 | 1 | $newnodes[] = $newnode; |
|
520 | 1 | } |
|
521 | 1 | } |
|
522 | 1 | return self::create($newnodes); |
|
523 | } |
||
524 | |||
525 | /** |
||
526 | * Remove the set of matched elements from the DOM. |
||
527 | * |
||
528 | * (as opposed to Crawler::clear() which detaches the nodes only from Crawler |
||
529 | * but leaves them in the DOM) |
||
530 | * |
||
531 | * @api |
||
532 | */ |
||
533 | 2 | public function remove() |
|
534 | { |
||
535 | 2 | foreach ($this as $node) { |
|
536 | /** |
||
537 | * @var \DOMNode $node |
||
538 | */ |
||
539 | 2 | if ($node->parentNode instanceof \DOMElement) { |
|
540 | 2 | $node->parentNode->removeChild($node); |
|
541 | 2 | } |
|
542 | 2 | } |
|
543 | 2 | $this->clear(); |
|
544 | 2 | } |
|
545 | |||
546 | /** |
||
547 | * Remove an attribute from each element in the set of matched elements. |
||
548 | * |
||
549 | * Alias for removeAttribute for compatibility with jQuery |
||
550 | * |
||
551 | * @param string $name |
||
552 | * @return HtmlPageCrawler |
||
553 | * @api |
||
554 | */ |
||
555 | 1 | public function removeAttr($name) |
|
559 | |||
560 | /** |
||
561 | * Remove an attribute from each element in the set of matched elements. |
||
562 | * |
||
563 | * @param string $name |
||
564 | * @return HtmlPageCrawler |
||
565 | */ |
||
566 | 1 | public function removeAttribute($name) |
|
567 | { |
||
568 | 1 | foreach ($this as $node) { |
|
569 | 1 | if ($node instanceof \DOMElement) { |
|
570 | /** @var \DOMElement $node */ |
||
571 | 1 | if ($node->hasAttribute($name)) { |
|
572 | 1 | $node->removeAttribute($name); |
|
573 | 1 | } |
|
574 | 1 | } |
|
575 | 1 | } |
|
576 | 1 | return $this; |
|
577 | } |
||
578 | |||
579 | /** |
||
580 | * Remove a class from each element in the list |
||
581 | * |
||
582 | * @param string $name |
||
583 | * @return HtmlPageCrawler $this for chaining |
||
584 | * @api |
||
585 | */ |
||
586 | 2 | public function removeClass($name) |
|
587 | { |
||
588 | 2 | foreach ($this as $node) { |
|
589 | 2 | if ($node instanceof \DOMElement) { |
|
590 | /** @var \DOMElement $node */ |
||
591 | 2 | $classes = preg_split('/\s+/s', $node->getAttribute('class')); |
|
592 | 2 | $count = count($classes); |
|
593 | 2 | for ($i = 0; $i < $count; $i++) { |
|
594 | 2 | if ($classes[$i] == $name) { |
|
595 | 2 | unset($classes[$i]); |
|
596 | 2 | } |
|
597 | 2 | } |
|
598 | 2 | $node->setAttribute('class', trim(join(' ', $classes))); |
|
599 | 2 | } |
|
600 | 2 | } |
|
601 | 2 | return $this; |
|
602 | } |
||
603 | |||
604 | /** |
||
605 | * Replace each target element with the set of matched elements. |
||
606 | * |
||
607 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $element |
||
608 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler A new Crawler object containing all elements appended to the target elements |
||
609 | * @api |
||
610 | */ |
||
611 | 2 | public function replaceAll($element) |
|
612 | { |
||
613 | 2 | $e = self::create($element); |
|
614 | 2 | $newnodes = array(); |
|
615 | 2 | foreach ($e as $i => $node) { |
|
616 | /** @var \DOMNode $node */ |
||
617 | 2 | $parent = $node->parentNode; |
|
618 | 2 | $refnode = $node->nextSibling; |
|
619 | 2 | foreach ($this as $j => $newnode) { |
|
620 | /** @var \DOMNode $newnode */ |
||
621 | 2 | $newnode = static::importNewnode($newnode, $node, $i); |
|
622 | 2 | if ($j == 0) { |
|
623 | 2 | $parent->replaceChild($newnode, $node); |
|
624 | 2 | } else { |
|
625 | 1 | $parent->insertBefore($newnode, $refnode); |
|
626 | } |
||
627 | 2 | $newnodes[] = $newnode; |
|
628 | 2 | } |
|
629 | 2 | } |
|
630 | 2 | return self::create($newnodes); |
|
631 | } |
||
632 | |||
633 | /** |
||
634 | * Replace each element in the set of matched elements with the provided new content and return the set of elements that was removed. |
||
635 | * |
||
636 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content |
||
637 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
638 | * @api |
||
639 | */ |
||
640 | 2 | public function replaceWith($content) |
|
641 | { |
||
642 | 2 | $content = self::create($content); |
|
643 | 2 | $newnodes = array(); |
|
644 | 2 | foreach ($this as $i => $node) { |
|
645 | /** @var \DOMNode $node */ |
||
646 | 2 | $parent = $node->parentNode; |
|
647 | 2 | $refnode = $node->nextSibling; |
|
648 | 2 | foreach ($content as $j => $newnode) { |
|
649 | /** @var \DOMNode $newnode */ |
||
650 | 2 | $newnode = static::importNewnode($newnode, $node, $i); |
|
651 | 2 | if ($j == 0) { |
|
652 | 2 | $parent->replaceChild($newnode, $node); |
|
653 | 2 | } else { |
|
654 | 1 | $parent->insertBefore($newnode, $refnode); |
|
655 | } |
||
656 | 2 | $newnodes[] = $newnode; |
|
657 | 2 | } |
|
658 | 2 | } |
|
659 | 2 | $content->clear(); |
|
660 | 2 | $content->add($newnodes); |
|
661 | 2 | return $this; |
|
662 | } |
||
663 | |||
664 | /** |
||
665 | * Get the combined text contents of each element in the set of matched elements, including their descendants, |
||
666 | * or set the text contents of the matched elements. |
||
667 | * |
||
668 | * ATTENTION: Contrary to the parent Crawler class, which returns the text from the first element only, |
||
669 | * this functions returns the combined text of all elements (as jQuery does). If this is not what you need you |
||
670 | * must call ->first() before calling ->text(), e.g. |
||
671 | * |
||
672 | * in Symfony\DOMCrawler\Crawler: $c->filter('p')->text() returns the text of the first paragraph only |
||
673 | * in HtmlPageCrawler you need to call: $c->filter('p')->first()->text() |
||
674 | * |
||
675 | * @param null|string $text |
||
676 | * @return string|HtmlPageCrawler |
||
677 | * @api |
||
678 | */ |
||
679 | 1 | public function text($text = null) |
|
696 | |||
697 | |||
698 | /** |
||
699 | * Add or remove one or more classes from each element in the set of matched elements, depending the class’s presence. |
||
700 | * |
||
701 | * @param string $classname One or more classnames separated by spaces |
||
702 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
703 | * @api |
||
704 | */ |
||
705 | 1 | public function toggleClass($classname) |
|
706 | { |
||
707 | 1 | $classes = explode(' ', $classname); |
|
708 | 1 | foreach ($this as $i => $node) { |
|
709 | 1 | $c = self::create($node); |
|
710 | /** @var \DOMNode $node */ |
||
711 | 1 | foreach ($classes as $class) { |
|
712 | 1 | if ($c->hasClass($class)) { |
|
713 | 1 | $c->removeClass($class); |
|
714 | 1 | } else { |
|
715 | 1 | $c->addClass($class); |
|
716 | } |
||
717 | 1 | } |
|
718 | 1 | } |
|
719 | 1 | return $this; |
|
720 | } |
||
721 | |||
722 | /** |
||
723 | * Remove the parents of the set of matched elements from the DOM, leaving the matched elements in their place. |
||
724 | * |
||
725 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
726 | * @api |
||
727 | */ |
||
728 | 1 | public function unwrap() |
|
729 | { |
||
730 | 1 | $parents = array(); |
|
731 | 1 | foreach($this as $i => $node) { |
|
732 | 1 | $parents[] = $node->parentNode; |
|
733 | 1 | } |
|
734 | |||
735 | 1 | self::create($parents)->unwrapInner(); |
|
736 | 1 | return $this; |
|
737 | } |
||
738 | |||
739 | /** |
||
740 | * Remove the matched elements, but promote the children to take their place. |
||
741 | * |
||
742 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
743 | * @api |
||
744 | */ |
||
745 | 2 | public function unwrapInner() |
|
746 | { |
||
747 | 2 | foreach($this as $i => $node) { |
|
748 | 2 | if (!$node->parentNode instanceof \DOMElement) { |
|
749 | 1 | throw new \InvalidArgumentException('DOMElement does not have a parent DOMElement node.'); |
|
750 | } |
||
751 | |||
752 | /** @var \DOMNode[] $children */ |
||
753 | 2 | $children = iterator_to_array($node->childNodes); |
|
754 | 2 | foreach ($children as $child) { |
|
755 | 1 | $node->parentNode->insertBefore($child, $node); |
|
756 | 2 | } |
|
757 | |||
758 | 2 | $node->parentNode->removeChild($node); |
|
759 | 2 | } |
|
760 | 2 | } |
|
761 | |||
762 | |||
763 | /** |
||
764 | * Wrap an HTML structure around each element in the set of matched elements |
||
765 | * |
||
766 | * The HTML structure must contain only one root node, e.g.: |
||
767 | * Works: <div><div></div></div> |
||
768 | * Does not work: <div></div><div></div> |
||
769 | * |
||
770 | * @param string|HtmlPageCrawler|\DOMNode $wrappingElement |
||
771 | * @return HtmlPageCrawler $this for chaining |
||
772 | * @api |
||
773 | */ |
||
774 | 1 | public function wrap($wrappingElement) |
|
775 | { |
||
776 | 1 | $content = self::create($wrappingElement); |
|
777 | 1 | $newnodes = array(); |
|
778 | 1 | foreach ($this as $i => $node) { |
|
779 | /** @var \DOMNode $node */ |
||
780 | 1 | $newnode = $content->getNode(0); |
|
781 | /** @var \DOMNode $newnode */ |
||
782 | // $newnode = static::importNewnode($newnode, $node, $i); |
||
783 | 1 | if ($newnode->ownerDocument !== $node->ownerDocument) { |
|
784 | 1 | $newnode = $node->ownerDocument->importNode($newnode, true); |
|
785 | 1 | } else { |
|
786 | if ($i > 0) { |
||
787 | $newnode = $newnode->cloneNode(true); |
||
788 | } |
||
789 | } |
||
790 | 1 | $oldnode = $node->parentNode->replaceChild($newnode, $node); |
|
791 | 1 | while ($newnode->hasChildNodes()) { |
|
792 | 1 | $elementFound = false; |
|
793 | 1 | foreach ($newnode->childNodes as $child) { |
|
794 | 1 | if ($child instanceof \DOMElement) { |
|
795 | 1 | $newnode = $child; |
|
796 | 1 | $elementFound = true; |
|
797 | 1 | break; |
|
798 | } |
||
799 | 1 | } |
|
800 | 1 | if (!$elementFound) { |
|
801 | 1 | break; |
|
802 | } |
||
803 | 1 | } |
|
804 | 1 | $newnode->appendChild($oldnode); |
|
805 | 1 | $newnodes[] = $newnode; |
|
806 | 1 | } |
|
807 | 1 | $content->clear(); |
|
808 | 1 | $content->add($newnodes); |
|
809 | 1 | return $this; |
|
810 | } |
||
811 | |||
812 | /** |
||
813 | * Wrap an HTML structure around all elements in the set of matched elements. |
||
814 | * |
||
815 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content |
||
816 | * @throws \LogicException |
||
817 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
818 | * @api |
||
819 | */ |
||
820 | 1 | public function wrapAll($content) |
|
821 | { |
||
822 | 1 | $content = self::create($content); |
|
823 | 1 | $parent = $this->getNode(0)->parentNode; |
|
824 | 1 | foreach ($this as $i => $node) { |
|
825 | /** @var \DOMNode $node */ |
||
826 | 1 | if ($node->parentNode !== $parent) { |
|
827 | throw new \LogicException('Nodes to be wrapped with wrapAll() must all have the same parent'); |
||
828 | } |
||
829 | 1 | } |
|
830 | |||
831 | 1 | $newnode = $content->getNode(0); |
|
832 | /** @var \DOMNode $newnode */ |
||
833 | 1 | $newnode = static::importNewnode($newnode, $parent); |
|
834 | |||
835 | 1 | $newnode = $parent->insertBefore($newnode,$this->getNode(0)); |
|
836 | 1 | $content->clear(); |
|
837 | 1 | $content->add($newnode); |
|
838 | |||
839 | 1 | while ($newnode->hasChildNodes()) { |
|
840 | 1 | $elementFound = false; |
|
841 | 1 | foreach ($newnode->childNodes as $child) { |
|
842 | 1 | if ($child instanceof \DOMElement) { |
|
843 | 1 | $newnode = $child; |
|
844 | 1 | $elementFound = true; |
|
845 | 1 | break; |
|
846 | } |
||
847 | 1 | } |
|
848 | 1 | if (!$elementFound) { |
|
849 | break; |
||
850 | } |
||
851 | 1 | } |
|
852 | 1 | foreach ($this as $i => $node) { |
|
853 | /** @var \DOMNode $node */ |
||
854 | 1 | $newnode->appendChild($node); |
|
855 | 1 | } |
|
856 | 1 | return $this; |
|
857 | } |
||
858 | |||
859 | /** |
||
860 | * Wrap an HTML structure around the content of each element in the set of matched elements. |
||
861 | * |
||
862 | * @param string|HtmlPageCrawler|\DOMNode|\DOMNodeList $content |
||
863 | * @return \Wa72\HtmlPageDom\HtmlPageCrawler $this for chaining |
||
864 | * @api |
||
865 | */ |
||
866 | 1 | public function wrapInner($content) |
|
867 | { |
||
868 | 1 | foreach ($this as $i => $node) { |
|
869 | /** @var \DOMNode $node */ |
||
870 | 1 | self::create($node->childNodes)->wrapAll($content); |
|
871 | 1 | } |
|
872 | 1 | return $this; |
|
873 | } |
||
874 | |||
875 | /** |
||
876 | * Get the HTML code fragment of all elements and their contents. |
||
877 | * |
||
878 | * If the first node contains a complete HTML document return only |
||
879 | * the full code of this document. |
||
880 | * |
||
881 | * @return string HTML code (fragment) |
||
882 | * @api |
||
883 | */ |
||
884 | 8 | public function saveHTML() |
|
885 | { |
||
886 | 8 | if ($this->isHtmlDocument()) { |
|
887 | 1 | return $this->getDOMDocument()->saveHTML(); |
|
888 | } else { |
||
889 | 8 | $doc = new \DOMDocument('1.0', 'UTF-8'); |
|
890 | 8 | $root = $doc->appendChild($doc->createElement('_root')); |
|
891 | 8 | foreach ($this as $node) { |
|
892 | 8 | $root->appendChild($doc->importNode($node, true)); |
|
893 | 8 | } |
|
894 | 8 | $html = trim($doc->saveHTML()); |
|
895 | 8 | return preg_replace('@^<'.self::FRAGMENT_ROOT_TAGNAME.'[^>]*>|</'.self::FRAGMENT_ROOT_TAGNAME.'>$@', '', $html); |
|
896 | } |
||
897 | } |
||
898 | |||
899 | 4 | public function __toString() |
|
900 | { |
||
901 | 4 | return $this->saveHTML(); |
|
902 | } |
||
903 | |||
904 | /** |
||
905 | * checks whether the first node contains a complete html document |
||
906 | * (as opposed to a document fragment) |
||
907 | * |
||
908 | * @return boolean |
||
909 | */ |
||
910 | 8 | public function isHtmlDocument() |
|
911 | { |
||
912 | 8 | $node = $this->getNode(0); |
|
913 | if ($node instanceof \DOMElement |
||
914 | 8 | && $node->ownerDocument instanceof \DOMDocument |
|
915 | 8 | && $node->ownerDocument->documentElement === $node |
|
916 | 8 | && $node->nodeName == 'html' |
|
917 | 8 | ) { |
|
918 | 1 | return true; |
|
919 | } else { |
||
920 | 8 | return false; |
|
921 | } |
||
922 | } |
||
923 | |||
924 | /** |
||
925 | * get ownerDocument of the first element |
||
926 | * |
||
927 | * @return \DOMDocument|null |
||
928 | */ |
||
929 | 1 | public function getDOMDocument() |
|
930 | { |
||
931 | 1 | $node = $this->getNode(0); |
|
932 | 1 | $r = null; |
|
933 | if ($node instanceof \DOMElement |
||
934 | 1 | && $node->ownerDocument instanceof \DOMDocument |
|
935 | 1 | ) { |
|
936 | 1 | $r = $node->ownerDocument; |
|
937 | 1 | } |
|
938 | 1 | return $r; |
|
939 | } |
||
940 | |||
941 | /** |
||
942 | * Filters the list of nodes with a CSS selector. |
||
943 | * |
||
944 | * @param string $selector |
||
945 | * @return HtmlPageCrawler |
||
946 | */ |
||
947 | 8 | public function filter($selector) |
|
948 | { |
||
949 | 8 | return parent::filter($selector); |
|
950 | } |
||
951 | |||
952 | /** |
||
953 | * Filters the list of nodes with an XPath expression. |
||
954 | * |
||
955 | * @param string $xpath An XPath expression |
||
956 | * |
||
957 | * @return HtmlPageCrawler A new instance of Crawler with the filtered list of nodes |
||
958 | * |
||
959 | * @api |
||
960 | */ |
||
961 | 2 | public function filterXPath($xpath) |
|
962 | { |
||
963 | 2 | return parent::filterXPath($xpath); |
|
964 | } |
||
965 | |||
966 | /** |
||
967 | * Adds HTML/XML content to the HtmlPageCrawler object (but not to the DOM of an already attached node). |
||
968 | * |
||
969 | * Function overriden from Crawler because HTML fragments are always added as complete documents there |
||
970 | * |
||
971 | * |
||
972 | * @param string $content A string to parse as HTML/XML |
||
973 | * @param null|string $type The content type of the string |
||
974 | * |
||
975 | * @return null|void |
||
976 | */ |
||
977 | 17 | public function addContent($content, $type = null) |
|
978 | { |
||
979 | 17 | if (empty($type)) { |
|
980 | 17 | $type = 'text/html;charset=UTF-8'; |
|
981 | 17 | } |
|
982 | 17 | if (substr($type, 0, 9) == 'text/html' && !preg_match('/<html\b[^>]*>/i', $content)) { |
|
983 | // string contains no <html> Tag => no complete document but an HTML fragment! |
||
984 | 16 | $this->addHtmlFragment($content); |
|
985 | 16 | } else { |
|
986 | 2 | parent::addContent($content, $type); |
|
987 | } |
||
988 | 17 | } |
|
989 | |||
990 | 15 | public function addHtmlFragment($content, $charset = 'UTF-8') |
|
991 | { |
||
992 | 15 | $d = new \DOMDocument('1.0', $charset); |
|
993 | 15 | $root = $d->appendChild($d->createElement(self::FRAGMENT_ROOT_TAGNAME)); |
|
994 | 15 | $bodynode = Helpers::getBodyNodeFromHtmlFragment($content, $charset); |
|
995 | 15 | foreach ($bodynode->childNodes as $child) { |
|
996 | 15 | $inode = $root->appendChild($d->importNode($child, true)); |
|
997 | 15 | if ($inode) { |
|
998 | 15 | $this->addNode($inode); |
|
999 | 15 | } |
|
1000 | 15 | } |
|
1001 | 15 | } |
|
1002 | |||
1003 | /** |
||
1004 | * returns the first node |
||
1005 | * deprecated, use getNode(0) instead |
||
1006 | * |
||
1007 | * @return \DOMNode|null |
||
1008 | * @deprecated |
||
1009 | * @see Crawler::getNode |
||
1010 | */ |
||
1011 | 1 | public function getFirstNode() |
|
1012 | { |
||
1013 | 1 | return $this->getNode(0); |
|
1014 | } |
||
1015 | |||
1016 | /** |
||
1017 | * @param int $position |
||
1018 | * |
||
1019 | * overridden from Crawler because it is not public in Symfony 2.3 |
||
1020 | * TODO: throw away as soon as we don't need to support SF 2.3 any more |
||
1021 | * |
||
1022 | * @return \DOMElement|null |
||
1023 | */ |
||
1024 | 14 | public function getNode($position) |
|
1028 | |||
1029 | /** |
||
1030 | * Returns the node name of the first node of the list. |
||
1031 | * |
||
1032 | * in Crawler (parent), this function will be available starting with 2.6.0, |
||
1033 | * therefore this method be removed from here as soon as we don't need to keep compatibility |
||
1034 | * with Symfony < 2.6 |
||
1035 | * |
||
1036 | * TODO: throw away as soon as we don't need to support SF 2.3 any more |
||
1037 | * |
||
1038 | * @return string The node name |
||
1039 | * |
||
1040 | * @throws \InvalidArgumentException When current node is empty |
||
1041 | */ |
||
1042 | 1 | public function nodeName() |
|
1043 | { |
||
1044 | 1 | if (!count($this)) { |
|
1045 | throw new \InvalidArgumentException('The current node list is empty.'); |
||
1046 | } |
||
1047 | 1 | return $this->getNode(0)->nodeName; |
|
1048 | } |
||
1049 | |||
1050 | /** |
||
1051 | * Adds a node to the current list of nodes. |
||
1052 | * |
||
1053 | * This method uses the appropriate specialized add*() method based |
||
1054 | * on the type of the argument. |
||
1055 | * |
||
1056 | * Overwritten from parent to allow Crawler to be added |
||
1057 | * |
||
1058 | * @param null|\DOMNodeList|array|\DOMNode|Crawler $node A node |
||
1059 | * |
||
1060 | * @api |
||
1061 | */ |
||
1062 | 29 | public function add($node) |
|
1063 | { |
||
1064 | 29 | if ($node instanceof Crawler) { |
|
1065 | 1 | foreach ($node as $childnode) { |
|
1066 | 1 | $this->addNode($childnode); |
|
1067 | 1 | } |
|
1068 | 1 | } else { |
|
1069 | 29 | parent::add($node); |
|
1070 | } |
||
1071 | 29 | } |
|
1072 | |||
1073 | /** |
||
1074 | * @param \DOMNode $newnode |
||
1075 | * @param \DOMNode $referencenode |
||
1076 | * @param int $clone |
||
1077 | * @return \DOMNode |
||
1078 | */ |
||
1079 | 6 | protected static function importNewnode(\DOMNode $newnode, \DOMNode $referencenode, $clone = 0) { |
|
1089 | |||
1090 | /** |
||
1091 | * Checks whether the first node in the set is disconnected (has no parent node) |
||
1092 | * |
||
1093 | * @return bool |
||
1094 | */ |
||
1095 | 1 | public function isDisconnected() |
|
1100 | |||
1101 | 1 | public function __get($name) |
|
1102 | { |
||
1103 | switch ($name) { |
||
1104 | 1 | case 'count': |
|
1105 | 1 | case 'length': |
|
1106 | 1 | return count($this); |
|
1107 | } |
||
1108 | 1 | throw new \Exception('No such property ' . $name); |
|
1109 | } |
||
1110 | } |
||
1111 |
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.