1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
declare(strict_types=1); |
4
|
|
|
|
5
|
|
|
namespace voku\helper; |
6
|
|
|
|
7
|
|
|
/** |
8
|
|
|
* @noinspection PhpHierarchyChecksInspection |
9
|
|
|
* |
10
|
|
|
* {@inheritdoc} |
11
|
|
|
* |
12
|
|
|
* @implements \IteratorAggregate<int, \DOMNode> |
13
|
|
|
*/ |
14
|
|
|
class SimpleHtmlDom extends AbstractSimpleHtmlDom implements \IteratorAggregate, SimpleHtmlDomInterface |
15
|
|
|
{ |
16
|
|
|
/** |
17
|
|
|
* @param \DOMElement|\DOMNode $node |
18
|
|
|
*/ |
19
|
164 |
|
public function __construct(\DOMNode $node) |
20
|
|
|
{ |
21
|
164 |
|
$this->node = $node; |
22
|
164 |
|
} |
23
|
|
|
|
24
|
|
|
/** |
25
|
|
|
* @param string $name |
26
|
|
|
* @param array $arguments |
27
|
|
|
* |
28
|
|
|
* @throws \BadMethodCallException |
29
|
|
|
* |
30
|
|
|
* @return SimpleHtmlDomInterface|string|null |
31
|
|
|
*/ |
32
|
11 |
|
public function __call($name, $arguments) |
33
|
|
|
{ |
34
|
11 |
|
$name = \strtolower($name); |
35
|
|
|
|
36
|
11 |
|
if (isset(self::$functionAliases[$name])) { |
37
|
11 |
|
return \call_user_func_array([$this, self::$functionAliases[$name]], $arguments); |
38
|
|
|
} |
39
|
|
|
|
40
|
|
|
throw new \BadMethodCallException('Method does not exist'); |
41
|
|
|
} |
42
|
|
|
|
43
|
|
|
/** |
44
|
|
|
* Find list of nodes with a CSS selector. |
45
|
|
|
* |
46
|
|
|
* @param string $selector |
47
|
|
|
* @param int|null $idx |
48
|
|
|
* |
49
|
|
|
* @return SimpleHtmlDomInterface|SimpleHtmlDomInterface[]|SimpleHtmlDomNodeInterface<SimpleHtmlDomInterface> |
|
|
|
|
50
|
|
|
*/ |
51
|
27 |
|
public function find(string $selector, $idx = null) |
52
|
|
|
{ |
53
|
27 |
|
return $this->getHtmlDomParser()->find($selector, $idx); |
54
|
|
|
} |
55
|
|
|
|
56
|
|
|
/** |
57
|
|
|
* Returns an array of attributes. |
58
|
|
|
* |
59
|
|
|
* @return string[]|null |
60
|
|
|
*/ |
61
|
3 |
View Code Duplication |
public function getAllAttributes() |
|
|
|
|
62
|
|
|
{ |
63
|
|
|
if ( |
64
|
3 |
|
$this->node |
65
|
|
|
&& |
66
|
3 |
|
$this->node->hasAttributes() |
67
|
|
|
) { |
68
|
3 |
|
$attributes = []; |
69
|
3 |
|
foreach ($this->node->attributes ?? [] as $attr) { |
70
|
3 |
|
$attributes[$attr->name] = HtmlDomParser::putReplacedBackToPreserveHtmlEntities($attr->value); |
71
|
|
|
} |
72
|
|
|
|
73
|
3 |
|
return $attributes; |
|
|
|
|
74
|
|
|
} |
75
|
|
|
|
76
|
1 |
|
return null; |
77
|
|
|
} |
78
|
|
|
|
79
|
|
|
/** |
80
|
|
|
* @return bool |
81
|
|
|
*/ |
82
|
|
|
public function hasAttributes(): bool |
83
|
|
|
{ |
84
|
|
|
return $this->node && $this->node->hasAttributes(); |
85
|
|
|
} |
86
|
|
|
|
87
|
|
|
/** |
88
|
|
|
* Return attribute value. |
89
|
|
|
* |
90
|
|
|
* @param string $name |
91
|
|
|
* |
92
|
|
|
* @return string |
93
|
|
|
*/ |
94
|
26 |
|
public function getAttribute(string $name): string |
95
|
|
|
{ |
96
|
26 |
|
if ($this->node instanceof \DOMElement) { |
97
|
26 |
|
return HtmlDomParser::putReplacedBackToPreserveHtmlEntities( |
98
|
26 |
|
$this->node->getAttribute($name) |
99
|
|
|
); |
100
|
|
|
} |
101
|
|
|
|
102
|
|
|
return ''; |
103
|
|
|
} |
104
|
|
|
|
105
|
|
|
/** |
106
|
|
|
* Determine if an attribute exists on the element. |
107
|
|
|
* |
108
|
|
|
* @param string $name |
109
|
|
|
* |
110
|
|
|
* @return bool |
111
|
|
|
*/ |
112
|
2 |
|
public function hasAttribute(string $name): bool |
113
|
|
|
{ |
114
|
2 |
|
if (!$this->node instanceof \DOMElement) { |
115
|
|
|
return false; |
116
|
|
|
} |
117
|
|
|
|
118
|
2 |
|
return $this->node->hasAttribute($name); |
119
|
|
|
} |
120
|
|
|
|
121
|
|
|
/** |
122
|
|
|
* Get dom node's outer html. |
123
|
|
|
* |
124
|
|
|
* @param bool $multiDecodeNewHtmlEntity |
125
|
|
|
* |
126
|
|
|
* @return string |
127
|
|
|
*/ |
128
|
36 |
|
public function html(bool $multiDecodeNewHtmlEntity = false): string |
129
|
|
|
{ |
130
|
36 |
|
return $this->getHtmlDomParser()->html($multiDecodeNewHtmlEntity); |
131
|
|
|
} |
132
|
|
|
|
133
|
|
|
/** |
134
|
|
|
* Get dom node's inner html. |
135
|
|
|
* |
136
|
|
|
* @param bool $multiDecodeNewHtmlEntity |
137
|
|
|
* |
138
|
|
|
* @return string |
139
|
|
|
*/ |
140
|
24 |
|
public function innerHtml(bool $multiDecodeNewHtmlEntity = false): string |
141
|
|
|
{ |
142
|
24 |
|
return $this->getHtmlDomParser()->innerHtml($multiDecodeNewHtmlEntity); |
143
|
|
|
} |
144
|
|
|
|
145
|
|
|
/** |
146
|
|
|
* Remove attribute. |
147
|
|
|
* |
148
|
|
|
* @param string $name <p>The name of the html-attribute.</p> |
149
|
|
|
* |
150
|
|
|
* @return SimpleHtmlDomInterface |
151
|
|
|
*/ |
152
|
2 |
|
public function removeAttribute(string $name): SimpleHtmlDomInterface |
153
|
|
|
{ |
154
|
2 |
|
if (\method_exists($this->node, 'removeAttribute')) { |
155
|
2 |
|
$this->node->removeAttribute($name); |
|
|
|
|
156
|
|
|
} |
157
|
|
|
|
158
|
2 |
|
return $this; |
|
|
|
|
159
|
|
|
} |
160
|
|
|
|
161
|
|
|
/** |
162
|
|
|
* Replace child node. |
163
|
|
|
* |
164
|
|
|
* @param string $string |
165
|
|
|
* |
166
|
|
|
* @return SimpleHtmlDomInterface |
167
|
|
|
*/ |
168
|
9 |
View Code Duplication |
protected function replaceChildWithString(string $string): SimpleHtmlDomInterface |
|
|
|
|
169
|
|
|
{ |
170
|
9 |
|
if (!empty($string)) { |
171
|
8 |
|
$newDocument = new HtmlDomParser($string); |
172
|
|
|
|
173
|
8 |
|
$tmpDomString = $this->normalizeStringForComparision($newDocument); |
174
|
8 |
|
$tmpStr = $this->normalizeStringForComparision($string); |
175
|
8 |
|
if ($tmpDomString !== $tmpStr) { |
176
|
|
|
throw new \RuntimeException( |
177
|
|
|
'Not valid HTML fragment!' . "\n" . |
178
|
|
|
$tmpDomString . "\n" . |
179
|
|
|
$tmpStr |
180
|
|
|
); |
181
|
|
|
} |
182
|
|
|
} |
183
|
|
|
|
184
|
|
|
/** @var \DOMNode[] $remove_nodes */ |
185
|
9 |
|
$remove_nodes = []; |
186
|
9 |
|
if ($this->node->childNodes->length > 0) { |
187
|
|
|
// INFO: We need to fetch the nodes first, before we can delete them, because of missing references in the dom, |
188
|
|
|
// if we delete the elements on the fly. |
189
|
9 |
|
foreach ($this->node->childNodes as $node) { |
190
|
9 |
|
$remove_nodes[] = $node; |
191
|
|
|
} |
192
|
|
|
} |
193
|
9 |
|
foreach ($remove_nodes as $remove_node) { |
194
|
9 |
|
$this->node->removeChild($remove_node); |
195
|
|
|
} |
196
|
|
|
|
197
|
9 |
|
if (!empty($newDocument)) { |
198
|
8 |
|
$newDocument = $this->cleanHtmlWrapper($newDocument); |
199
|
8 |
|
$ownerDocument = $this->node->ownerDocument; |
200
|
|
|
if ( |
201
|
8 |
|
$ownerDocument |
202
|
|
|
&& |
203
|
8 |
|
$newDocument->getDocument()->documentElement |
204
|
|
|
) { |
205
|
8 |
|
$newNode = $ownerDocument->importNode($newDocument->getDocument()->documentElement, true); |
206
|
8 |
|
$this->node->appendChild($newNode); |
207
|
|
|
} |
208
|
|
|
} |
209
|
|
|
|
210
|
9 |
|
return $this; |
211
|
|
|
} |
212
|
|
|
|
213
|
|
|
/** |
214
|
|
|
* Replace this node. |
215
|
|
|
* |
216
|
|
|
* @param string $string |
217
|
|
|
* |
218
|
|
|
* @return SimpleHtmlDomInterface |
219
|
|
|
*/ |
220
|
8 |
|
protected function replaceNodeWithString(string $string): SimpleHtmlDomInterface |
221
|
|
|
{ |
222
|
8 |
|
if (empty($string)) { |
223
|
4 |
|
if ($this->node->parentNode) { |
224
|
4 |
|
$this->node->parentNode->removeChild($this->node); |
225
|
|
|
} |
226
|
4 |
|
$this->node = new \DOMText(); |
227
|
|
|
|
228
|
4 |
|
return $this; |
229
|
|
|
} |
230
|
|
|
|
231
|
6 |
|
$newDocument = new HtmlDomParser($string); |
232
|
|
|
|
233
|
6 |
|
$tmpDomOuterTextString = $this->normalizeStringForComparision($newDocument); |
234
|
6 |
|
$tmpStr = $this->normalizeStringForComparision($string); |
235
|
6 |
View Code Duplication |
if ($tmpDomOuterTextString !== $tmpStr) { |
|
|
|
|
236
|
|
|
throw new \RuntimeException( |
237
|
|
|
'Not valid HTML fragment!' . "\n" |
238
|
|
|
. $tmpDomOuterTextString . "\n" . |
239
|
|
|
$tmpStr |
240
|
|
|
); |
241
|
|
|
} |
242
|
|
|
|
243
|
6 |
|
$newDocument = $this->cleanHtmlWrapper($newDocument, true); |
244
|
6 |
|
$ownerDocument = $this->node->ownerDocument; |
245
|
|
|
if ( |
246
|
6 |
|
$ownerDocument === null |
247
|
|
|
|| |
248
|
6 |
|
$newDocument->getDocument()->documentElement === null |
249
|
|
|
) { |
250
|
|
|
return $this; |
251
|
|
|
} |
252
|
|
|
|
253
|
6 |
|
$newNode = $ownerDocument->importNode($newDocument->getDocument()->documentElement, true); |
254
|
|
|
|
255
|
6 |
|
$this->node->parentNode->replaceChild($newNode, $this->node); |
256
|
6 |
|
$this->node = $newNode; |
257
|
|
|
|
258
|
|
|
// Remove head element, preserving child nodes. (again) |
259
|
|
View Code Duplication |
if ( |
|
|
|
|
260
|
6 |
|
$this->node->parentNode instanceof \DOMElement |
261
|
|
|
&& |
262
|
6 |
|
$newDocument->getIsDOMDocumentCreatedWithoutHeadWrapper() |
263
|
|
|
) { |
264
|
3 |
|
$html = $this->node->parentNode->getElementsByTagName('head')[0]; |
265
|
|
|
|
266
|
|
|
if ( |
267
|
3 |
|
$html !== null |
268
|
|
|
&& |
269
|
3 |
|
$this->node->parentNode->ownerDocument |
270
|
|
|
) { |
271
|
1 |
|
$fragment = $this->node->parentNode->ownerDocument->createDocumentFragment(); |
272
|
|
|
/** @var \DOMNode $html */ |
273
|
1 |
|
while ($html->childNodes->length > 0) { |
274
|
1 |
|
$tmpNode = $html->childNodes->item(0); |
275
|
1 |
|
if ($tmpNode !== null) { |
276
|
|
|
/** @noinspection UnusedFunctionResultInspection */ |
277
|
1 |
|
$fragment->appendChild($tmpNode); |
278
|
|
|
} |
279
|
|
|
} |
280
|
1 |
|
$html->parentNode->replaceChild($fragment, $html); |
281
|
|
|
} |
282
|
|
|
} |
283
|
|
|
|
284
|
6 |
|
return $this; |
285
|
|
|
} |
286
|
|
|
|
287
|
|
|
/** |
288
|
|
|
* Replace this node with text |
289
|
|
|
* |
290
|
|
|
* @param string $string |
291
|
|
|
* |
292
|
|
|
* @return SimpleHtmlDomInterface |
293
|
|
|
*/ |
294
|
1 |
View Code Duplication |
protected function replaceTextWithString($string): SimpleHtmlDomInterface |
|
|
|
|
295
|
|
|
{ |
296
|
1 |
|
if (empty($string)) { |
297
|
1 |
|
if ($this->node->parentNode) { |
298
|
1 |
|
$this->node->parentNode->removeChild($this->node); |
299
|
|
|
} |
300
|
1 |
|
$this->node = new \DOMText(); |
301
|
|
|
|
302
|
1 |
|
return $this; |
303
|
|
|
} |
304
|
|
|
|
305
|
1 |
|
$ownerDocument = $this->node->ownerDocument; |
306
|
1 |
|
if ($ownerDocument) { |
307
|
1 |
|
$newElement = $ownerDocument->createTextNode($string); |
308
|
1 |
|
$newNode = $ownerDocument->importNode($newElement, true); |
309
|
1 |
|
$this->node->parentNode->replaceChild($newNode, $this->node); |
310
|
1 |
|
$this->node = $newNode; |
311
|
|
|
} |
312
|
|
|
|
313
|
1 |
|
return $this; |
314
|
|
|
} |
315
|
|
|
|
316
|
|
|
/** |
317
|
|
|
* Set attribute value. |
318
|
|
|
* |
319
|
|
|
* @param string $name <p>The name of the html-attribute.</p> |
320
|
|
|
* @param string|null $value <p>Set to NULL or empty string, to remove the attribute.</p> |
321
|
|
|
* @param bool $strictEmptyValueCheck <p> |
322
|
|
|
* $value must be NULL, to remove the attribute, |
323
|
|
|
* so that you can set an empty string as attribute-value e.g. autofocus="" |
324
|
|
|
* </p> |
325
|
|
|
* |
326
|
|
|
* @return SimpleHtmlDomInterface |
327
|
|
|
*/ |
328
|
16 |
View Code Duplication |
public function setAttribute(string $name, $value = null, bool $strictEmptyValueCheck = false): SimpleHtmlDomInterface |
|
|
|
|
329
|
|
|
{ |
330
|
|
|
if ( |
331
|
16 |
|
($strictEmptyValueCheck && $value === null) |
332
|
|
|
|| |
333
|
16 |
|
(!$strictEmptyValueCheck && empty($value)) |
334
|
|
|
) { |
335
|
|
|
/** @noinspection UnusedFunctionResultInspection */ |
336
|
2 |
|
$this->removeAttribute($name); |
337
|
16 |
|
} elseif (\method_exists($this->node, 'setAttribute')) { |
338
|
|
|
/** @noinspection UnusedFunctionResultInspection */ |
339
|
16 |
|
$this->node->setAttribute($name, HtmlDomParser::replaceToPreserveHtmlEntities((string) $value)); |
|
|
|
|
340
|
|
|
} |
341
|
|
|
|
342
|
16 |
|
return $this; |
|
|
|
|
343
|
|
|
} |
344
|
|
|
|
345
|
|
|
/** |
346
|
|
|
* Get dom node's plain text. |
347
|
|
|
* |
348
|
|
|
* @return string |
349
|
|
|
*/ |
350
|
32 |
|
public function text(): string |
351
|
|
|
{ |
352
|
32 |
|
return $this->getHtmlDomParser()->fixHtmlOutput($this->node->textContent); |
353
|
|
|
} |
354
|
|
|
|
355
|
|
|
/** |
356
|
|
|
* Change the name of a tag in a "DOMNode". |
357
|
|
|
* |
358
|
|
|
* @param \DOMNode $node |
359
|
|
|
* @param string $name |
360
|
|
|
* |
361
|
|
|
* @return \DOMElement|false |
362
|
|
|
* <p>DOMElement a new instance of class DOMElement or false |
363
|
|
|
* if an error occured.</p> |
364
|
|
|
*/ |
365
|
11 |
View Code Duplication |
protected function changeElementName(\DOMNode $node, string $name) |
|
|
|
|
366
|
|
|
{ |
367
|
11 |
|
$ownerDocument = $node->ownerDocument; |
368
|
11 |
|
if (!$ownerDocument) { |
369
|
|
|
return false; |
370
|
|
|
} |
371
|
|
|
|
372
|
11 |
|
$newNode = $ownerDocument->createElement($name); |
373
|
|
|
|
374
|
11 |
|
foreach ($node->childNodes as $child) { |
375
|
11 |
|
$child = $ownerDocument->importNode($child, true); |
376
|
11 |
|
$newNode->appendChild($child); |
377
|
|
|
} |
378
|
|
|
|
379
|
11 |
|
foreach ($node->attributes ?? [] as $attrName => $attrNode) { |
380
|
|
|
/** @noinspection UnusedFunctionResultInspection */ |
381
|
|
|
$newNode->setAttribute($attrName, $attrNode); |
382
|
|
|
} |
383
|
|
|
|
384
|
11 |
|
if ($newNode->ownerDocument) { |
385
|
|
|
/** @noinspection UnusedFunctionResultInspection */ |
386
|
11 |
|
$newNode->ownerDocument->replaceChild($newNode, $node); |
387
|
|
|
} |
388
|
|
|
|
389
|
11 |
|
return $newNode; |
390
|
|
|
} |
391
|
|
|
|
392
|
|
|
/** |
393
|
|
|
* Returns children of node. |
394
|
|
|
* |
395
|
|
|
* @param int $idx |
396
|
|
|
* |
397
|
|
|
* @return SimpleHtmlDomInterface|SimpleHtmlDomInterface[]|SimpleHtmlDomNodeInterface|null |
398
|
|
|
*/ |
399
|
2 |
View Code Duplication |
public function childNodes(int $idx = -1) |
|
|
|
|
400
|
|
|
{ |
401
|
2 |
|
$nodeList = $this->getIterator(); |
402
|
|
|
|
403
|
2 |
|
if ($idx === -1) { |
404
|
2 |
|
return $nodeList; |
405
|
|
|
} |
406
|
|
|
|
407
|
2 |
|
return $nodeList[$idx] ?? null; |
408
|
|
|
} |
409
|
|
|
|
410
|
|
|
/** |
411
|
|
|
* Find nodes with a CSS selector. |
412
|
|
|
* |
413
|
|
|
* @param string $selector |
414
|
|
|
* |
415
|
|
|
* @return SimpleHtmlDomInterface[]|SimpleHtmlDomNodeInterface<SimpleHtmlDomInterface> |
|
|
|
|
416
|
|
|
*/ |
417
|
1 |
|
public function findMulti(string $selector): SimpleHtmlDomNodeInterface |
418
|
|
|
{ |
419
|
1 |
|
return $this->getHtmlDomParser()->findMulti($selector); |
420
|
|
|
} |
421
|
|
|
|
422
|
|
|
/** |
423
|
|
|
* Find nodes with a CSS selector or false, if no element is found. |
424
|
|
|
* |
425
|
|
|
* @param string $selector |
426
|
|
|
* |
427
|
|
|
* @return false|SimpleHtmlDomInterface[]|SimpleHtmlDomNodeInterface<SimpleHtmlDomInterface> |
|
|
|
|
428
|
|
|
*/ |
429
|
1 |
|
public function findMultiOrFalse(string $selector) |
430
|
|
|
{ |
431
|
1 |
|
return $this->getHtmlDomParser()->findMultiOrFalse($selector); |
432
|
|
|
} |
433
|
|
|
|
434
|
|
|
/** |
435
|
|
|
* Find one node with a CSS selector. |
436
|
|
|
* |
437
|
|
|
* @param string $selector |
438
|
|
|
* |
439
|
|
|
* @return SimpleHtmlDomInterface |
440
|
|
|
*/ |
441
|
3 |
|
public function findOne(string $selector): SimpleHtmlDomInterface |
442
|
|
|
{ |
443
|
3 |
|
return $this->getHtmlDomParser()->findOne($selector); |
444
|
|
|
} |
445
|
|
|
|
446
|
|
|
/** |
447
|
|
|
* Find one node with a CSS selector or false, if no element is found. |
448
|
|
|
* |
449
|
|
|
* @param string $selector |
450
|
|
|
* |
451
|
|
|
* @return false|SimpleHtmlDomInterface |
452
|
|
|
*/ |
453
|
1 |
|
public function findOneOrFalse(string $selector) |
454
|
|
|
{ |
455
|
1 |
|
return $this->getHtmlDomParser()->findOneOrFalse($selector); |
456
|
|
|
} |
457
|
|
|
|
458
|
|
|
/** |
459
|
|
|
* Returns the first child of node. |
460
|
|
|
* |
461
|
|
|
* @return SimpleHtmlDomInterface|null |
462
|
|
|
*/ |
463
|
4 |
View Code Duplication |
public function firstChild() |
|
|
|
|
464
|
|
|
{ |
465
|
|
|
/** @var \DOMNode|null $node */ |
466
|
4 |
|
$node = $this->node->firstChild; |
467
|
|
|
|
468
|
4 |
|
if ($node === null) { |
469
|
1 |
|
return null; |
470
|
|
|
} |
471
|
|
|
|
472
|
4 |
|
return new static($node); |
473
|
|
|
} |
474
|
|
|
|
475
|
|
|
/** |
476
|
|
|
* Return elements by ".class". |
477
|
|
|
* |
478
|
|
|
* @param string $class |
479
|
|
|
* |
480
|
|
|
* @return SimpleHtmlDomInterface[]|SimpleHtmlDomNodeInterface<SimpleHtmlDomInterface> |
|
|
|
|
481
|
|
|
*/ |
482
|
|
|
public function getElementByClass(string $class): SimpleHtmlDomNodeInterface |
483
|
|
|
{ |
484
|
|
|
return $this->findMulti(".${class}"); |
485
|
|
|
} |
486
|
|
|
|
487
|
|
|
/** |
488
|
|
|
* Return element by #id. |
489
|
|
|
* |
490
|
|
|
* @param string $id |
491
|
|
|
* |
492
|
|
|
* @return SimpleHtmlDomInterface |
493
|
|
|
*/ |
494
|
1 |
|
public function getElementById(string $id): SimpleHtmlDomInterface |
495
|
|
|
{ |
496
|
1 |
|
return $this->findOne("#${id}"); |
497
|
|
|
} |
498
|
|
|
|
499
|
|
|
/** |
500
|
|
|
* Return element by tag name. |
501
|
|
|
* |
502
|
|
|
* @param string $name |
503
|
|
|
* |
504
|
|
|
* @return SimpleHtmlDomInterface |
505
|
|
|
*/ |
506
|
1 |
View Code Duplication |
public function getElementByTagName(string $name): SimpleHtmlDomInterface |
|
|
|
|
507
|
|
|
{ |
508
|
1 |
|
if ($this->node instanceof \DOMElement) { |
509
|
1 |
|
$node = $this->node->getElementsByTagName($name)->item(0); |
510
|
|
|
} else { |
511
|
|
|
$node = null; |
512
|
|
|
} |
513
|
|
|
|
514
|
1 |
|
if ($node === null) { |
515
|
|
|
return new SimpleHtmlDomBlank(); |
516
|
|
|
} |
517
|
|
|
|
518
|
1 |
|
return new static($node); |
519
|
|
|
} |
520
|
|
|
|
521
|
|
|
/** |
522
|
|
|
* Returns elements by "#id". |
523
|
|
|
* |
524
|
|
|
* @param string $id |
525
|
|
|
* @param int|null $idx |
526
|
|
|
* |
527
|
|
|
* @return SimpleHtmlDomInterface|SimpleHtmlDomInterface[]|SimpleHtmlDomNodeInterface<SimpleHtmlDomInterface> |
|
|
|
|
528
|
|
|
*/ |
529
|
|
|
public function getElementsById(string $id, $idx = null) |
530
|
|
|
{ |
531
|
|
|
return $this->find("#${id}", $idx); |
532
|
|
|
} |
533
|
|
|
|
534
|
|
|
/** |
535
|
|
|
* Returns elements by tag name. |
536
|
|
|
* |
537
|
|
|
* @param string $name |
538
|
|
|
* @param int|null $idx |
539
|
|
|
* |
540
|
|
|
* @return SimpleHtmlDomInterface|SimpleHtmlDomInterface[]|SimpleHtmlDomNodeInterface<SimpleHtmlDomInterface> |
|
|
|
|
541
|
|
|
*/ |
542
|
1 |
View Code Duplication |
public function getElementsByTagName(string $name, $idx = null) |
|
|
|
|
543
|
|
|
{ |
544
|
1 |
|
if ($this->node instanceof \DOMElement) { |
545
|
1 |
|
$nodesList = $this->node->getElementsByTagName($name); |
546
|
|
|
} else { |
547
|
|
|
$nodesList = []; |
548
|
|
|
} |
549
|
|
|
|
550
|
1 |
|
$elements = new SimpleHtmlDomNode(); |
551
|
|
|
|
552
|
1 |
|
foreach ($nodesList as $node) { |
553
|
1 |
|
$elements[] = new static($node); |
554
|
|
|
} |
555
|
|
|
|
556
|
|
|
// return all elements |
557
|
1 |
|
if ($idx === null) { |
558
|
1 |
|
if (\count($elements) === 0) { |
559
|
|
|
return new SimpleHtmlDomNodeBlank(); |
560
|
|
|
} |
561
|
|
|
|
562
|
1 |
|
return $elements; |
563
|
|
|
} |
564
|
|
|
|
565
|
|
|
// handle negative values |
566
|
|
|
if ($idx < 0) { |
567
|
|
|
$idx = \count($elements) + $idx; |
568
|
|
|
} |
569
|
|
|
|
570
|
|
|
// return one element |
571
|
|
|
return $elements[$idx] ?? new SimpleHtmlDomBlank(); |
572
|
|
|
} |
573
|
|
|
|
574
|
|
|
/** |
575
|
|
|
* Create a new "HtmlDomParser"-object from the current context. |
576
|
|
|
* |
577
|
|
|
* @return HtmlDomParser |
578
|
|
|
*/ |
579
|
105 |
|
public function getHtmlDomParser(): HtmlDomParser |
580
|
|
|
{ |
581
|
105 |
|
return new HtmlDomParser($this); |
582
|
|
|
} |
583
|
|
|
|
584
|
|
|
/** |
585
|
|
|
* @return \DOMNode |
586
|
|
|
*/ |
587
|
106 |
|
public function getNode(): \DOMNode |
588
|
|
|
{ |
589
|
106 |
|
return $this->node; |
590
|
|
|
} |
591
|
|
|
|
592
|
|
|
/** |
593
|
|
|
* Nodes can get partially destroyed in which they're still an |
594
|
|
|
* actual DOM node (such as \DOMElement) but almost their entire |
595
|
|
|
* body is gone, including the `nodeType` attribute. |
596
|
|
|
* |
597
|
|
|
* @return bool true if node has been destroyed |
598
|
|
|
*/ |
599
|
|
|
public function isRemoved(): bool |
600
|
|
|
{ |
601
|
|
|
return !isset($this->node->nodeType); |
602
|
|
|
} |
603
|
|
|
|
604
|
|
|
/** |
605
|
|
|
* Returns the last child of node. |
606
|
|
|
* |
607
|
|
|
* @return SimpleHtmlDomInterface|null |
608
|
|
|
*/ |
609
|
4 |
View Code Duplication |
public function lastChild() |
|
|
|
|
610
|
|
|
{ |
611
|
|
|
/** @var \DOMNode|null $node */ |
612
|
4 |
|
$node = $this->node->lastChild; |
613
|
|
|
|
614
|
4 |
|
if ($node === null) { |
615
|
1 |
|
return null; |
616
|
|
|
} |
617
|
|
|
|
618
|
4 |
|
return new static($node); |
619
|
|
|
} |
620
|
|
|
|
621
|
|
|
/** |
622
|
|
|
* Returns the next sibling of node. |
623
|
|
|
* |
624
|
|
|
* @return SimpleHtmlDomInterface|null |
625
|
|
|
*/ |
626
|
1 |
View Code Duplication |
public function nextSibling() |
|
|
|
|
627
|
|
|
{ |
628
|
|
|
/** @var \DOMNode|null $node */ |
629
|
1 |
|
$node = $this->node->nextSibling; |
630
|
|
|
|
631
|
1 |
|
if ($node === null) { |
632
|
1 |
|
return null; |
633
|
|
|
} |
634
|
|
|
|
635
|
1 |
|
return new static($node); |
636
|
|
|
} |
637
|
|
|
|
638
|
|
|
/** |
639
|
|
|
* Returns the next sibling of node. |
640
|
|
|
* |
641
|
|
|
* @return SimpleHtmlDomInterface|null |
642
|
|
|
*/ |
643
|
1 |
View Code Duplication |
public function nextNonWhitespaceSibling() |
|
|
|
|
644
|
|
|
{ |
645
|
|
|
/** @var \DOMNode|null $node */ |
646
|
1 |
|
$node = $this->node->nextSibling; |
647
|
|
|
|
648
|
1 |
|
while ($node && !\trim($node->textContent)) { |
649
|
|
|
/** @var \DOMNode|null $node */ |
650
|
1 |
|
$node = $node->nextSibling; |
651
|
|
|
} |
652
|
|
|
|
653
|
1 |
|
if ($node === null) { |
654
|
|
|
return null; |
655
|
|
|
} |
656
|
|
|
|
657
|
1 |
|
return new static($node); |
658
|
|
|
} |
659
|
|
|
|
660
|
|
|
/** |
661
|
|
|
* Returns the parent of node. |
662
|
|
|
* |
663
|
|
|
* @return SimpleHtmlDomInterface |
664
|
|
|
*/ |
665
|
2 |
|
public function parentNode(): SimpleHtmlDomInterface |
666
|
|
|
{ |
667
|
2 |
|
return new static($this->node->parentNode); |
|
|
|
|
668
|
|
|
} |
669
|
|
|
|
670
|
|
|
/** |
671
|
|
|
* Returns the previous sibling of node. |
672
|
|
|
* |
673
|
|
|
* @return SimpleHtmlDomInterface|null |
674
|
|
|
*/ |
675
|
1 |
View Code Duplication |
public function previousSibling() |
|
|
|
|
676
|
|
|
{ |
677
|
|
|
/** @var \DOMNode|null $node */ |
678
|
1 |
|
$node = $this->node->previousSibling; |
679
|
|
|
|
680
|
1 |
|
if ($node === null) { |
681
|
1 |
|
return null; |
682
|
|
|
} |
683
|
|
|
|
684
|
1 |
|
return new static($node); |
685
|
|
|
} |
686
|
|
|
|
687
|
|
|
|
688
|
|
|
/** |
689
|
|
|
* Returns the previous sibling of node. |
690
|
|
|
* |
691
|
|
|
* @return SimpleHtmlDomInterface|null |
692
|
|
|
*/ |
693
|
|
View Code Duplication |
public function previousNonWhitespaceSibling() |
|
|
|
|
694
|
|
|
{ |
695
|
1 |
|
/** @var \DOMNode|null $node */ |
696
|
|
|
$node = $this->node->previousSibling; |
697
|
1 |
|
|
698
|
|
|
while ($node && !\trim($node->textContent)) { |
699
|
1 |
|
/** @var \DOMNode|null $node */ |
700
|
|
|
$node = $node->previousSibling; |
701
|
|
|
} |
702
|
1 |
|
|
703
|
|
|
if ($node === null) { |
704
|
1 |
|
return null; |
705
|
|
|
} |
706
|
1 |
|
|
707
|
|
|
return new static($node); |
708
|
|
|
} |
709
|
1 |
|
|
710
|
|
|
/** |
711
|
|
|
* @param string|string[]|null $value <p> |
712
|
|
|
* null === get the current input value |
713
|
1 |
|
* text === set a new input value |
714
|
|
|
* </p> |
715
|
1 |
|
* |
716
|
|
|
* @return string|string[]|null |
717
|
1 |
|
*/ |
718
|
|
View Code Duplication |
public function val($value = null) |
|
|
|
|
719
|
|
|
{ |
720
|
1 |
|
if ($value === null) { |
721
|
|
|
if ( |
722
|
|
|
$this->tag === 'input' |
|
|
|
|
723
|
|
|
&& |
724
|
|
|
( |
725
|
|
|
$this->getAttribute('type') === 'hidden' |
726
|
|
|
|| |
727
|
|
|
$this->getAttribute('type') === 'text' |
728
|
|
|
|| |
729
|
|
|
!$this->hasAttribute('type') |
730
|
|
|
) |
731
|
|
|
) { |
732
|
|
|
return $this->getAttribute('value'); |
733
|
|
|
} |
734
|
|
|
|
735
|
|
|
if ( |
736
|
|
|
$this->hasAttribute('checked') |
737
|
|
|
&& |
738
|
1 |
|
\in_array($this->getAttribute('type'), ['checkbox', 'radio'], true) |
739
|
1 |
|
) { |
740
|
|
|
return $this->getAttribute('value'); |
741
|
|
|
} |
742
|
|
|
|
743
|
1 |
|
if ($this->node->nodeName === 'select') { |
744
|
1 |
|
$valuesFromDom = []; |
745
|
|
|
$options = $this->getElementsByTagName('option'); |
746
|
1 |
|
if ($options instanceof SimpleHtmlDomNode) { |
747
|
|
|
foreach ($options as $option) { |
748
|
|
|
if ($this->hasAttribute('checked')) { |
749
|
1 |
|
$valuesFromDom[] = (string) $option->getAttribute('value'); |
750
|
|
|
} |
751
|
1 |
|
} |
752
|
|
|
} |
753
|
|
|
|
754
|
|
|
if (\count($valuesFromDom) === 0) { |
755
|
|
|
return null; |
756
|
|
|
} |
757
|
|
|
|
758
|
|
|
return $valuesFromDom; |
|
|
|
|
759
|
|
|
} |
760
|
|
|
|
761
|
1 |
|
if ($this->node->nodeName === 'textarea') { |
762
|
|
|
return $this->node->nodeValue; |
763
|
|
|
} |
764
|
1 |
|
} else { |
765
|
1 |
|
/** @noinspection NestedPositiveIfStatementsInspection */ |
766
|
1 |
|
if (\in_array($this->getAttribute('type'), ['checkbox', 'radio'], true)) { |
767
|
|
|
if ($value === $this->getAttribute('value')) { |
768
|
|
|
/** @noinspection UnusedFunctionResultInspection */ |
769
|
|
|
$this->setAttribute('checked', 'checked'); |
770
|
1 |
|
} else { |
771
|
|
|
/** @noinspection UnusedFunctionResultInspection */ |
772
|
|
|
$this->removeAttribute('checked'); |
773
|
|
|
} |
774
|
|
|
} elseif ($this->node instanceof \DOMElement && $this->node->nodeName === 'select') { |
775
|
|
|
foreach ($this->node->getElementsByTagName('option') as $option) { |
776
|
|
|
/** @var \DOMElement $option */ |
777
|
|
|
if ($value === $option->getAttribute('value')) { |
778
|
|
|
/** @noinspection UnusedFunctionResultInspection */ |
779
|
14 |
|
$option->setAttribute('selected', 'selected'); |
780
|
|
|
} else { |
781
|
|
|
$option->removeAttribute('selected'); |
782
|
|
|
} |
783
|
|
|
} |
784
|
14 |
|
} elseif ($this->node->nodeName === 'input' && \is_string($value)) { |
785
|
|
|
// Set value for input elements |
786
|
14 |
|
/** @noinspection UnusedFunctionResultInspection */ |
787
|
|
|
$this->setAttribute('value', $value); |
788
|
|
|
} elseif ($this->node->nodeName === 'textarea' && \is_string($value)) { |
789
|
|
|
$this->node->nodeValue = $value; |
790
|
14 |
|
} |
791
|
|
|
} |
792
|
|
|
|
793
|
|
|
return null; |
794
|
|
|
} |
795
|
|
|
|
796
|
14 |
|
/** |
797
|
14 |
|
* @param HtmlDomParser $newDocument |
798
|
|
|
* @param bool $removeExtraHeadTag |
799
|
11 |
|
* |
800
|
|
|
* @return HtmlDomParser |
801
|
|
|
*/ |
802
|
14 |
|
protected function cleanHtmlWrapper( |
803
|
|
|
HtmlDomParser $newDocument, |
804
|
13 |
|
$removeExtraHeadTag = false |
805
|
13 |
|
): HtmlDomParser { |
806
|
8 |
|
if ( |
807
|
|
|
$newDocument->getIsDOMDocumentCreatedWithoutHtml() |
808
|
8 |
|
|| |
809
|
8 |
|
$newDocument->getIsDOMDocumentCreatedWithoutHtmlWrapper() |
810
|
8 |
|
) { |
811
|
|
|
|
812
|
8 |
|
// Remove doc-type node. |
813
|
|
|
if ($newDocument->getDocument()->doctype !== null) { |
814
|
|
|
$newDocument->getDocument()->doctype->parentNode->removeChild($newDocument->getDocument()->doctype); |
815
|
|
|
} |
816
|
8 |
|
|
817
|
8 |
|
// Replace html element, preserving child nodes -> but keep the html wrapper, otherwise we got other problems ... |
818
|
|
|
// so we replace it with "<simpleHtmlDomHtml>" and delete this at the ending. |
819
|
|
|
$item = $newDocument->getDocument()->getElementsByTagName('html')->item(0); |
820
|
|
|
if ($item !== null) { |
821
|
|
|
/** @noinspection UnusedFunctionResultInspection */ |
822
|
|
|
$this->changeElementName($item, 'simpleHtmlDomHtml'); |
823
|
14 |
|
} |
824
|
14 |
|
|
825
|
9 |
|
if ($newDocument->getIsDOMDocumentCreatedWithoutPTagWrapper()) { |
826
|
|
|
// Remove <p>-element, preserving child nodes. |
827
|
9 |
|
$pElement = $newDocument->getDocument()->getElementsByTagName('p')->item(0); |
828
|
9 |
View Code Duplication |
if ($pElement instanceof \DOMElement) { |
|
|
|
|
829
|
9 |
|
$fragment = $newDocument->getDocument()->createDocumentFragment(); |
830
|
|
|
|
831
|
9 |
|
while ($pElement->childNodes->length > 0) { |
832
|
|
|
$tmpNode = $pElement->childNodes->item(0); |
833
|
|
|
if ($tmpNode !== null) { |
834
|
|
|
/** @noinspection UnusedFunctionResultInspection */ |
835
|
9 |
|
$fragment->appendChild($tmpNode); |
836
|
9 |
|
} |
837
|
|
|
} |
838
|
|
|
|
839
|
|
|
if ($pElement->parentNode !== null) { |
840
|
|
|
$pElement->parentNode->replaceChild($fragment, $pElement); |
841
|
|
|
} |
842
|
|
|
} |
843
|
14 |
|
} |
844
|
|
|
|
845
|
14 |
|
// Remove <body>-element, preserving child nodes. |
846
|
|
|
$body = $newDocument->getDocument()->getElementsByTagName('body')->item(0); |
847
|
14 |
View Code Duplication |
if ($body instanceof \DOMElement) { |
|
|
|
|
848
|
|
|
$fragment = $newDocument->getDocument()->createDocumentFragment(); |
849
|
3 |
|
|
850
|
|
|
while ($body->childNodes->length > 0) { |
851
|
|
|
$tmpNode = $body->childNodes->item(0); |
852
|
3 |
|
if ($tmpNode !== null) { |
853
|
|
|
/** @noinspection UnusedFunctionResultInspection */ |
854
|
3 |
|
$fragment->appendChild($tmpNode); |
855
|
|
|
} |
856
|
|
|
} |
857
|
|
|
|
858
|
|
|
if ($body->parentNode !== null) { |
859
|
|
|
$body->parentNode->replaceChild($fragment, $body); |
860
|
|
|
} |
861
|
|
|
} |
862
|
|
|
} |
863
|
|
|
|
864
|
|
|
// Remove head element, preserving child nodes. |
865
|
|
View Code Duplication |
if ( |
|
|
|
|
866
|
|
|
$removeExtraHeadTag |
867
|
|
|
&& |
868
|
|
|
$this->node->parentNode instanceof \DOMElement |
869
|
|
|
&& |
870
|
|
|
$newDocument->getIsDOMDocumentCreatedWithoutHeadWrapper() |
871
|
14 |
|
) { |
872
|
|
|
$html = $this->node->parentNode->getElementsByTagName('head')[0] ?? null; |
873
|
|
|
|
874
|
|
|
if ( |
875
|
|
|
$html !== null |
876
|
|
|
&& |
877
|
|
|
$this->node->parentNode->ownerDocument |
878
|
|
|
) { |
879
|
|
|
$fragment = $this->node->parentNode->ownerDocument->createDocumentFragment(); |
880
|
|
|
|
881
|
|
|
/** @var \DOMNode $html */ |
882
|
|
|
while ($html->childNodes->length > 0) { |
883
|
|
|
$tmpNode = $html->childNodes->item(0); |
884
|
|
|
if ($tmpNode !== null) { |
885
|
3 |
|
/** @noinspection UnusedFunctionResultInspection */ |
886
|
|
|
$fragment->appendChild($tmpNode); |
887
|
3 |
|
} |
888
|
3 |
|
} |
889
|
3 |
|
|
890
|
3 |
|
$html->parentNode->replaceChild($fragment, $html); |
891
|
|
|
} |
892
|
|
|
} |
893
|
|
|
|
894
|
3 |
|
return $newDocument; |
895
|
|
|
} |
896
|
|
|
|
897
|
|
|
/** |
898
|
|
|
* Retrieve an external iterator. |
899
|
|
|
* |
900
|
|
|
* @see http://php.net/manual/en/iteratoraggregate.getiterator.php |
901
|
|
|
* |
902
|
|
|
* @return SimpleHtmlDomNode |
903
|
|
|
* <p> |
904
|
|
|
* An instance of an object implementing <b>Iterator</b> or |
905
|
|
|
* <b>Traversable</b> |
906
|
|
|
* </p> |
907
|
|
|
*/ |
908
|
|
View Code Duplication |
public function getIterator(): SimpleHtmlDomNodeInterface |
|
|
|
|
909
|
|
|
{ |
910
|
|
|
$elements = new SimpleHtmlDomNode(); |
911
|
|
|
if ($this->node->hasChildNodes()) { |
912
|
|
|
foreach ($this->node->childNodes as $node) { |
913
|
|
|
$elements[] = new static($node); |
914
|
|
|
} |
915
|
|
|
} |
916
|
14 |
|
|
917
|
|
|
return $elements; |
918
|
14 |
|
} |
919
|
14 |
|
|
920
|
|
|
/** |
921
|
14 |
|
* Get dom node's inner html. |
922
|
|
|
* |
923
|
14 |
|
* @param bool $multiDecodeNewHtmlEntity |
924
|
|
|
* |
925
|
|
|
* @return string |
926
|
14 |
|
*/ |
927
|
|
|
public function innerXml(bool $multiDecodeNewHtmlEntity = false): string |
928
|
|
|
{ |
929
|
|
|
return $this->getHtmlDomParser()->innerXml($multiDecodeNewHtmlEntity); |
930
|
14 |
|
} |
931
|
14 |
|
|
932
|
14 |
|
/** |
933
|
14 |
|
* Normalize the given input for comparision. |
934
|
|
|
* |
935
|
14 |
|
* @param HtmlDomParser|string $input |
936
|
|
|
* |
937
|
|
|
* @return string |
938
|
|
|
*/ |
939
|
|
|
private function normalizeStringForComparision($input): string |
940
|
|
|
{ |
941
|
14 |
|
if ($input instanceof HtmlDomParser) { |
942
|
|
|
$string = $input->outerText(); |
943
|
|
|
|
944
|
|
|
if ($input->getIsDOMDocumentCreatedWithoutHeadWrapper()) { |
945
|
|
|
/** @noinspection HtmlRequiredTitleElement */ |
946
|
14 |
|
$string = \str_replace(['<head>', '</head>'], '', $string); |
947
|
|
|
} |
948
|
|
|
} else { |
949
|
|
|
$string = (string) $input; |
950
|
|
|
} |
951
|
|
|
|
952
|
|
|
return |
953
|
|
|
\urlencode( |
954
|
|
|
\urldecode( |
955
|
|
|
\trim( |
956
|
|
|
\str_replace( |
957
|
|
|
[ |
958
|
|
|
' ', |
959
|
|
|
"\n", |
960
|
|
|
"\r", |
961
|
|
|
'/>', |
962
|
|
|
], |
963
|
|
|
[ |
964
|
|
|
'', |
965
|
|
|
'', |
966
|
|
|
'', |
967
|
|
|
'>', |
968
|
|
|
], |
969
|
|
|
\strtolower($string) |
970
|
|
|
) |
971
|
|
|
) |
972
|
|
|
) |
973
|
|
|
); |
974
|
|
|
} |
975
|
|
|
} |
976
|
|
|
|
This check marks PHPDoc comments that could not be parsed by our parser. To see which comment annotations we can parse, please refer to our documentation on supported doc-types.