1
|
|
|
<?php |
2
|
|
|
namespace PHPHtmlParser\Dom; |
3
|
|
|
|
4
|
|
|
use PHPHtmlParser\Selector; |
5
|
|
|
use PHPHtmlParser\Exceptions\CircularException; |
6
|
|
|
use PHPHtmlParser\Exceptions\ParentNotFoundException; |
7
|
|
|
use stringEncode\Encode; |
8
|
|
|
|
9
|
|
|
/** |
10
|
|
|
* Dom node object. |
11
|
|
|
* |
12
|
|
|
* @property string outerhtml |
13
|
|
|
* @property string innerhtml |
14
|
|
|
* @property string text |
15
|
|
|
* @property \PHPHtmlParser\Dom\Tag tag |
16
|
|
|
* @property InnerNode parent |
17
|
|
|
*/ |
18
|
|
|
abstract class AbstractNode |
19
|
|
|
{ |
20
|
|
|
|
21
|
|
|
/** |
22
|
|
|
* Contains the tag name/type |
23
|
|
|
* |
24
|
|
|
* @var \PHPHtmlParser\Dom\Tag |
25
|
|
|
*/ |
26
|
|
|
protected $tag; |
27
|
|
|
|
28
|
|
|
/** |
29
|
|
|
* Contains a list of attributes on this tag. |
30
|
|
|
* |
31
|
|
|
* @var array |
32
|
|
|
*/ |
33
|
|
|
protected $attr = []; |
34
|
|
|
|
35
|
|
|
/** |
36
|
|
|
* Contains the parent Node. |
37
|
|
|
* |
38
|
|
|
* @var InnerNode |
39
|
|
|
*/ |
40
|
|
|
protected $parent = null; |
41
|
|
|
|
42
|
|
|
/** |
43
|
|
|
* The unique id of the class. Given by PHP. |
44
|
|
|
* |
45
|
|
|
* @var string |
46
|
|
|
*/ |
47
|
|
|
protected $id; |
48
|
|
|
|
49
|
|
|
/** |
50
|
|
|
* The encoding class used to encode strings. |
51
|
|
|
* |
52
|
|
|
* @var mixed |
53
|
|
|
*/ |
54
|
|
|
protected $encode; |
55
|
|
|
|
56
|
|
|
/** |
57
|
|
|
* Creates a unique spl hash for this node. |
58
|
|
|
*/ |
59
|
|
|
public function __construct() |
60
|
|
|
{ |
61
|
|
|
$this->id = spl_object_hash($this); |
62
|
|
|
} |
63
|
|
|
|
64
|
|
|
/** |
65
|
|
|
* Magic get method for attributes and certain methods. |
66
|
|
|
* |
67
|
|
|
* @param string $key |
68
|
|
|
* @return mixed |
69
|
|
|
*/ |
70
|
|
|
public function __get($key) |
71
|
|
|
{ |
72
|
|
|
// check attribute first |
73
|
|
|
if ( ! is_null($this->getAttribute($key))) { |
74
|
|
|
return $this->getAttribute($key); |
75
|
|
|
} |
76
|
|
|
switch (strtolower($key)) { |
77
|
|
|
case 'outerhtml': |
78
|
|
|
return $this->outerHtml(); |
79
|
|
|
case 'innerhtml': |
80
|
|
|
return $this->innerHtml(); |
81
|
|
|
case 'text': |
82
|
|
|
return $this->text(); |
83
|
|
|
case 'tag': |
84
|
|
|
return $this->getTag(); |
85
|
|
|
case 'parent': $this->getParent(); |
|
|
|
|
86
|
|
|
} |
87
|
|
|
|
88
|
|
|
return null; |
89
|
|
|
} |
90
|
|
|
|
91
|
|
|
/** |
92
|
|
|
* Attempts to clear out any object references. |
93
|
|
|
*/ |
94
|
|
|
public function __destruct() |
95
|
|
|
{ |
96
|
|
|
$this->tag = null; |
97
|
|
|
$this->attr = []; |
98
|
|
|
$this->parent = null; |
99
|
|
|
$this->children = []; |
|
|
|
|
100
|
|
|
} |
101
|
|
|
|
102
|
|
|
/** |
103
|
|
|
* Simply calls the outer text method. |
104
|
|
|
* |
105
|
|
|
* @return string |
106
|
|
|
*/ |
107
|
|
|
public function __toString() |
108
|
|
|
{ |
109
|
|
|
return $this->outerHtml(); |
110
|
|
|
} |
111
|
|
|
|
112
|
|
|
/** |
113
|
|
|
* Returns the id of this object. |
114
|
|
|
*/ |
115
|
|
|
public function id() |
116
|
|
|
{ |
117
|
|
|
return $this->id; |
118
|
|
|
} |
119
|
|
|
|
120
|
|
|
/** |
121
|
|
|
* Returns the parent of node. |
122
|
|
|
* |
123
|
|
|
* @return AbstractNode |
124
|
|
|
*/ |
125
|
|
|
public function getParent() |
126
|
|
|
{ |
127
|
|
|
return $this->parent; |
128
|
|
|
} |
129
|
|
|
|
130
|
|
|
/** |
131
|
|
|
* Sets the parent node. |
132
|
|
|
* |
133
|
|
|
* @param InnerNode $parent |
134
|
|
|
* @return $this |
135
|
|
|
* @throws CircularException |
136
|
|
|
*/ |
137
|
|
|
public function setParent(InnerNode $parent) |
138
|
|
|
{ |
139
|
|
|
// remove from old parent |
140
|
|
|
if ( ! is_null($this->parent)) { |
141
|
|
|
if ($this->parent->id() == $parent->id()) { |
142
|
|
|
// already the parent |
143
|
|
|
return $this; |
144
|
|
|
} |
145
|
|
|
|
146
|
|
|
$this->parent->removeChild($this->id); |
147
|
|
|
} |
148
|
|
|
|
149
|
|
|
$this->parent = $parent; |
150
|
|
|
|
151
|
|
|
// assign child to parent |
152
|
|
|
$this->parent->addChild($this); |
153
|
|
|
|
154
|
|
|
//clear any cache |
155
|
|
|
$this->clear(); |
156
|
|
|
|
157
|
|
|
return $this; |
158
|
|
|
} |
159
|
|
|
|
160
|
|
|
/** |
161
|
|
|
* Removes this node and all its children from the |
162
|
|
|
* DOM tree. |
163
|
|
|
* |
164
|
|
|
* @return void |
165
|
|
|
*/ |
166
|
|
|
public function delete() |
167
|
|
|
{ |
168
|
|
|
if ( ! is_null($this->parent)) { |
169
|
|
|
$this->parent->removeChild($this->id); |
170
|
|
|
} |
171
|
|
|
|
172
|
|
|
$this->parent = null; |
173
|
|
|
} |
174
|
|
|
|
175
|
|
|
/** |
176
|
|
|
* Sets the encoding class to this node. |
177
|
|
|
* |
178
|
|
|
* @param Encode $encode |
179
|
|
|
* @return void |
180
|
|
|
*/ |
181
|
|
|
public function propagateEncoding(Encode $encode) |
182
|
|
|
{ |
183
|
|
|
$this->encode = $encode; |
184
|
|
|
$this->tag->setEncoding($encode); |
185
|
|
|
} |
186
|
|
|
|
187
|
|
|
/** |
188
|
|
|
* Checks if the given node id is an ancestor of |
189
|
|
|
* the current node. |
190
|
|
|
* |
191
|
|
|
* @param int $id |
192
|
|
|
* @return bool |
193
|
|
|
*/ |
194
|
|
|
public function isAncestor($id) |
195
|
|
|
{ |
196
|
|
|
if ( ! is_null($this->getAncestor($id))) { |
197
|
|
|
return true; |
198
|
|
|
} |
199
|
|
|
|
200
|
|
|
return false; |
201
|
|
|
} |
202
|
|
|
|
203
|
|
|
/** |
204
|
|
|
* Attempts to get an ancestor node by the given id. |
205
|
|
|
* |
206
|
|
|
* @param int $id |
207
|
|
|
* @return null|AbstractNode |
208
|
|
|
*/ |
209
|
|
|
public function getAncestor($id) |
210
|
|
|
{ |
211
|
|
|
if ( ! is_null($this->parent)) { |
212
|
|
|
if ($this->parent->id() == $id) { |
213
|
|
|
return $this->parent; |
214
|
|
|
} |
215
|
|
|
|
216
|
|
|
return $this->parent->getAncestor($id); |
217
|
|
|
} |
218
|
|
|
|
219
|
|
|
return null; |
220
|
|
|
} |
221
|
|
|
|
222
|
|
|
/** |
223
|
|
|
* Attempts to get the next sibling. |
224
|
|
|
* |
225
|
|
|
* @return AbstractNode |
226
|
|
|
* @throws ParentNotFoundException |
227
|
|
|
*/ |
228
|
|
|
public function nextSibling() |
229
|
|
|
{ |
230
|
|
|
if (is_null($this->parent)) { |
231
|
|
|
throw new ParentNotFoundException('Parent is not set for this node.'); |
232
|
|
|
} |
233
|
|
|
|
234
|
|
|
return $this->parent->nextChild($this->id); |
235
|
|
|
} |
236
|
|
|
|
237
|
|
|
/** |
238
|
|
|
* Attempts to get the previous sibling |
239
|
|
|
* |
240
|
|
|
* @return AbstractNode |
241
|
|
|
* @throws ParentNotFoundException |
242
|
|
|
*/ |
243
|
|
|
public function previousSibling() |
244
|
|
|
{ |
245
|
|
|
if (is_null($this->parent)) { |
246
|
|
|
throw new ParentNotFoundException('Parent is not set for this node.'); |
247
|
|
|
} |
248
|
|
|
|
249
|
|
|
return $this->parent->previousChild($this->id); |
250
|
|
|
} |
251
|
|
|
|
252
|
|
|
/** |
253
|
|
|
* Gets the tag object of this node. |
254
|
|
|
* |
255
|
|
|
* @return Tag |
256
|
|
|
*/ |
257
|
|
|
public function getTag() |
258
|
|
|
{ |
259
|
|
|
return $this->tag; |
260
|
|
|
} |
261
|
|
|
|
262
|
|
|
/** |
263
|
|
|
* A wrapper method that simply calls the getAttribute method |
264
|
|
|
* on the tag of this node. |
265
|
|
|
* |
266
|
|
|
* @return array |
267
|
|
|
*/ |
268
|
|
|
public function getAttributes() |
269
|
|
|
{ |
270
|
|
|
$attributes = $this->tag->getAttributes(); |
271
|
|
|
foreach ($attributes as $name => $info) { |
272
|
|
|
$attributes[$name] = $info['value']; |
273
|
|
|
} |
274
|
|
|
|
275
|
|
|
return $attributes; |
276
|
|
|
} |
277
|
|
|
|
278
|
|
|
/** |
279
|
|
|
* A wrapper method that simply calls the getAttribute method |
280
|
|
|
* on the tag of this node. |
281
|
|
|
* |
282
|
|
|
* @param string $key |
283
|
|
|
* @return mixed |
284
|
|
|
*/ |
285
|
|
|
public function getAttribute($key) |
286
|
|
|
{ |
287
|
|
|
$attribute = $this->tag->getAttribute($key); |
288
|
|
|
if ( ! is_null($attribute)) { |
289
|
|
|
$attribute = $attribute['value']; |
290
|
|
|
} |
291
|
|
|
|
292
|
|
|
return $attribute; |
293
|
|
|
} |
294
|
|
|
|
295
|
|
|
/** |
296
|
|
|
* A wrapper method that simply calls the setAttribute method |
297
|
|
|
* on the tag of this node. |
298
|
|
|
* |
299
|
|
|
* @param string $key |
300
|
|
|
* @param string $value |
301
|
|
|
* @return $this |
302
|
|
|
*/ |
303
|
|
|
public function setAttribute($key, $value) |
304
|
|
|
{ |
305
|
|
|
$this->tag->setAttribute($key, $value); |
306
|
|
|
|
307
|
|
|
return $this; |
308
|
|
|
} |
309
|
|
|
|
310
|
|
|
/** |
311
|
|
|
* A wrapper method that simply calls the removeAttribute method |
312
|
|
|
* on the tag of this node. |
313
|
|
|
* |
314
|
|
|
* @param string $key |
315
|
|
|
* @return void |
316
|
|
|
*/ |
317
|
|
|
public function removeAttribute($key) |
318
|
|
|
{ |
319
|
|
|
$this->tag->removeAttribute($key); |
320
|
|
|
} |
321
|
|
|
|
322
|
|
|
/** |
323
|
|
|
* A wrapper method that simply calls the removeAllAttributes |
324
|
|
|
* method on the tag of this node. |
325
|
|
|
* |
326
|
|
|
* @return void |
327
|
|
|
*/ |
328
|
|
|
public function removeAllAttributes() |
329
|
|
|
{ |
330
|
|
|
$this->tag->removeAllAttributes(); |
331
|
|
|
} |
332
|
|
|
|
333
|
|
|
/** |
334
|
|
|
* Function to locate a specific ancestor tag in the path to the root. |
335
|
|
|
* |
336
|
|
|
* @param string $tag |
337
|
|
|
* @return AbstractNode |
338
|
|
|
* @throws ParentNotFoundException |
339
|
|
|
*/ |
340
|
|
|
public function ancestorByTag($tag) |
341
|
|
|
{ |
342
|
|
|
// Start by including ourselves in the comparison. |
343
|
|
|
$node = $this; |
344
|
|
|
|
345
|
|
|
while ( ! is_null($node)) { |
346
|
|
|
if ($node->tag->name() == $tag) { |
347
|
|
|
return $node; |
348
|
|
|
} |
349
|
|
|
|
350
|
|
|
$node = $node->getParent(); |
351
|
|
|
} |
352
|
|
|
|
353
|
|
|
throw new ParentNotFoundException('Could not find an ancestor with "'.$tag.'" tag'); |
354
|
|
|
} |
355
|
|
|
|
356
|
|
|
/** |
357
|
|
|
* Find elements by css selector |
358
|
|
|
* |
359
|
|
|
* @param string $selector |
360
|
|
|
* @param int $nth |
361
|
|
|
* @return array|AbstractNode |
362
|
|
|
*/ |
363
|
|
|
public function find($selector, $nth = null) |
364
|
|
|
{ |
365
|
|
|
$selector = new Selector($selector); |
366
|
|
|
$nodes = $selector->find($this); |
367
|
|
|
|
368
|
|
|
if ( ! is_null($nth)) { |
369
|
|
|
// return nth-element or array |
370
|
|
|
if (isset($nodes[$nth])) { |
371
|
|
|
return $nodes[$nth]; |
372
|
|
|
} |
373
|
|
|
|
374
|
|
|
return null; |
375
|
|
|
} |
376
|
|
|
|
377
|
|
|
return $nodes; |
|
|
|
|
378
|
|
|
} |
379
|
|
|
|
380
|
|
|
/** |
381
|
|
|
* Function to try a few tricks to determine the displayed size of an img on the page. |
382
|
|
|
* NOTE: This will ONLY work on an IMG tag. Returns FALSE on all other tag types. |
383
|
|
|
* |
384
|
|
|
* Future enhancement: |
385
|
|
|
* Look in the tag to see if there is a class or id specified that has a height or width attribute to it. |
386
|
|
|
* |
387
|
|
|
* Far future enhancement |
388
|
|
|
* Look at all the parent tags of this image to see if they specify a class or id that has an img selector that specifies a height or width |
389
|
|
|
* Note that in this case, the class or id will have the img sub-selector for it to apply to the image. |
390
|
|
|
* |
391
|
|
|
* ridiculously far future development |
392
|
|
|
* If the class or id is specified in a SEPARATE css file that's not on the page, go get it and do what we were just doing for the ones on the page. |
393
|
|
|
* |
394
|
|
|
* @author John Schlick |
395
|
|
|
* @return array an array containing the 'height' and 'width' of the image on the page or -1 if we can't figure it out. |
396
|
|
|
*/ |
397
|
|
|
public function get_display_size() |
398
|
|
|
{ |
399
|
|
|
$width = -1; |
400
|
|
|
$height = -1; |
401
|
|
|
|
402
|
|
|
if ($this->tag->name() != 'img') { |
403
|
|
|
return false; |
404
|
|
|
} |
405
|
|
|
|
406
|
|
|
// See if there is a height or width attribute in the tag itself. |
407
|
|
|
if ( ! is_null($this->tag->getAttribute('width'))) { |
408
|
|
|
$width = $this->tag->getAttribute('width'); |
409
|
|
|
} |
410
|
|
|
|
411
|
|
|
if ( ! is_null($this->tag->getAttribute('height'))) { |
412
|
|
|
$height = $this->tag->getAttribute('height'); |
413
|
|
|
} |
414
|
|
|
|
415
|
|
|
// Now look for an inline style. |
416
|
|
|
if ( ! is_null($this->tag->getAttribute('style'))) { |
417
|
|
|
// Thanks to user 'gnarf' from stackoverflow for this regular expression. |
418
|
|
|
$attributes = []; |
419
|
|
|
preg_match_all("/([\w-]+)\s*:\s*([^;]+)\s*;?/", $this->tag->getAttribute('style'), $matches, |
420
|
|
|
PREG_SET_ORDER); |
421
|
|
|
foreach ($matches as $match) { |
|
|
|
|
422
|
|
|
$attributes[$match[1]] = $match[2]; |
423
|
|
|
} |
424
|
|
|
|
425
|
|
|
$width = $this->getLength($attributes, $width, 'width'); |
426
|
|
|
$height = $this->getLength($attributes, $width, 'height'); |
427
|
|
|
} |
428
|
|
|
|
429
|
|
|
$result = [ |
430
|
|
|
'height' => $height, |
431
|
|
|
'width' => $width, |
432
|
|
|
]; |
433
|
|
|
|
434
|
|
|
return $result; |
435
|
|
|
} |
436
|
|
|
|
437
|
|
|
/** |
438
|
|
|
* If there is a length in the style attributes use it. |
439
|
|
|
* |
440
|
|
|
* @param array $attributes |
441
|
|
|
* @param int $length |
442
|
|
|
* @param string $key |
443
|
|
|
* @return int |
444
|
|
|
*/ |
445
|
|
|
protected function getLength(array $attributes, $length, $key) |
446
|
|
|
{ |
447
|
|
|
if (isset($attributes[$key]) && $length == -1) { |
448
|
|
|
// check that the last two characters are px (pixels) |
449
|
|
|
if (strtolower(substr($attributes[$key], -2)) == 'px') { |
450
|
|
|
$proposed_length = substr($attributes[$key], 0, -2); |
451
|
|
|
// Now make sure that it's an integer and not something stupid. |
452
|
|
|
if (filter_var($proposed_length, FILTER_VALIDATE_INT)) { |
453
|
|
|
$length = $proposed_length; |
454
|
|
|
} |
455
|
|
|
} |
456
|
|
|
} |
457
|
|
|
|
458
|
|
|
return $length; |
459
|
|
|
} |
460
|
|
|
|
461
|
|
|
/** |
462
|
|
|
* Gets the inner html of this node. |
463
|
|
|
* |
464
|
|
|
* @return string |
465
|
|
|
*/ |
466
|
|
|
abstract public function innerHtml(); |
467
|
|
|
|
468
|
|
|
/** |
469
|
|
|
* Gets the html of this node, including it's own |
470
|
|
|
* tag. |
471
|
|
|
* |
472
|
|
|
* @return string |
473
|
|
|
*/ |
474
|
|
|
abstract public function outerHtml(); |
475
|
|
|
|
476
|
|
|
/** |
477
|
|
|
* Gets the text of this node (if there is any text). |
478
|
|
|
* |
479
|
|
|
* @return string |
480
|
|
|
*/ |
481
|
|
|
abstract public function text(); |
482
|
|
|
|
483
|
|
|
/** |
484
|
|
|
* Call this when something in the node tree has changed. Like a child has been added |
485
|
|
|
* or a parent has been changed. |
486
|
|
|
* |
487
|
|
|
* @return void |
488
|
|
|
*/ |
489
|
|
|
abstract protected function clear(); |
490
|
|
|
} |
491
|
|
|
|
PHP Analyzer performs a side-effects analysis of your code. A side-effect is basically anything that might be visible after the scope of the method is left.
Let’s take a look at an example:
If we look at the
getEmail()
method, we can see that it has no side-effect. Whether you call this method or not, no future calls to other methods are affected by this. As such code as the following is useless:On the hand, if we look at the
setEmail()
, this method _has_ side-effects. In the following case, we could not remove the method call: