1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
|
<?php
namespace andreskrey\Readability\NodeClass;
use andreskrey\Readability\NodeUtility;
trait NodeClassTrait
{
/**
* Content score of the node. Used to determine the value of the content
*
* @var int
*/
public $contentScore = 0;
/**
* Flag for initialized status
*
* @var bool
*/
private $initialized = false;
/**
* @var array
*/
private $divToPElements = [
'a',
'blockquote',
'dl',
'div',
'img',
'ol',
'p',
'pre',
'table',
'ul',
'select',
];
/**
* initialized getter
*
* @return bool
*/
public function isInitialized()
{
return $this->initialized;
}
/**
* Initializer. Calculates the current score of the node and returns a full Readability object.
*
* @ TODO: I don't like the weightClasses param. How can we get the config here?
*
* @param $weightClasses bool Weight classes?
* @return static
*/
public function initializeNode($weightClasses)
{
if (!$this->isInitialized()) {
$contentScore = 0;
switch ($this->nodeName) {
case 'div':
$contentScore += 5;
break;
case 'pre':
case 'td':
case 'blockquote':
$contentScore += 3;
break;
case 'address':
case 'ol':
case 'ul':
case 'dl':
case 'dd':
case 'dt':
case 'li':
case 'form':
$contentScore -= 3;
break;
case 'h1':
case 'h2':
case 'h3':
case 'h4':
case 'h5':
case 'h6':
case 'th':
$contentScore -= 5;
break;
}
$this->contentScore = $contentScore + ($weightClasses ? $this->getClassWeight() : 0);
$this->initialized = true;
}
return $this;
}
/**
* Override for native getAttribute method. Some nodes have the getAttribute method, some don't, so we need
* to check first the existence of the attributes property.
*
* @param $attributeName string Attribute to retrieve
*
* @return string
*/
public function getAttribute($attributeName)
{
if (!is_null($this->attributes)) {
return parent::getAttribute($attributeName);
}
return '';
}
/**
* Get the ancestors of the current node.
*
* @param int|bool $maxLevel Max amount of ancestors to get. False for all of them
*
* @return array
*/
public function getNodeAncestors($maxLevel = 3)
{
$ancestors = [];
$level = 0;
$node = $this->parentNode;
while ($node) {
$ancestors[] = $node;
$level++;
if ($level === $maxLevel) {
break;
}
$node = $node->parentNode;
}
return $ancestors;
}
/**
* Returns all links from the current element.
*
* @return array
*/
public function getAllLinks()
{
return iterator_to_array($this->getElementsByTagName('a'));
}
/**
* Get the density of links as a percentage of the content
* This is the amount of text that is inside a link divided by the total text in the node.
*
* @return int
*/
public function getLinkDensity()
{
$linkLength = 0;
$textLength = mb_strlen($this->getTextContent(true));
if (!$textLength) {
return 0;
}
$links = $this->getAllLinks();
if ($links) {
/** @var DOMElement $link */
foreach ($links as $link) {
$linkLength += mb_strlen($link->getTextContent(true));
}
}
return $linkLength / $textLength;
}
/**
* Calculates the weight of the class/id of the current element.
*
* @return int
*/
public function getClassWeight()
{
$weight = 0;
// Look for a special classname
$class = $this->getAttribute('class');
if (trim($class)) {
if (preg_match(NodeUtility::$regexps['negative'], $class)) {
$weight -= 25;
}
if (preg_match(NodeUtility::$regexps['positive'], $class)) {
$weight += 25;
}
}
// Look for a special ID
$id = $this->getAttribute('id');
if (trim($id)) {
if (preg_match(NodeUtility::$regexps['negative'], $id)) {
$weight -= 25;
}
if (preg_match(NodeUtility::$regexps['positive'], $id)) {
$weight += 25;
}
}
return $weight;
}
/**
* Returns the full text of the node.
*
* @param bool $normalize Normalize white space?
*
* @return string
*/
public function getTextContent($normalize = false)
{
$nodeValue = $this->nodeValue;
if ($normalize) {
$nodeValue = trim(preg_replace('/\s{2,}/', ' ', $nodeValue));
}
return $nodeValue;
}
/**
* Creates a new node based on the text content of the original node.
*
* @param $originalNode DOMElement
* @param $tagName string
*
* @return DOMElement
*/
public function createNode($originalNode, $tagName)
{
$text = $originalNode->getTextContent();
$newNode = $originalNode->ownerDocument->createElement($tagName, $text);
return $newNode;
}
/**
* Check if a given node has one of its ancestor tag name matching the
* provided one.
*
* @param DOMElement $node
* @param string $tagName
* @param int $maxDepth
*
* @return bool
*/
public function hasAncestorTag($node, $tagName, $maxDepth = 3)
{
$depth = 0;
while ($node->parentNode) {
if ($maxDepth > 0 && $depth > $maxDepth) {
return false;
}
if ($node->parentNode->nodeName === $tagName) {
return true;
}
$node = $node->parentNode;
$depth++;
}
return false;
}
/**
* Checks if the current node has a single child and if that child is a P node.
* Useful to convert <div><p> nodes to a single <p> node and avoid confusing the scoring system since div with p
* tags are, in practice, paragraphs.
*
* @param DOMNode $node
*
* @return bool
*/
public function hasSinglePNode()
{
// There should be exactly 1 element child which is a P:
if (count($children = $this->getChildren(true)) !== 1 || $children[0]->nodeName !== 'p') {
return false;
}
// And there should be no text nodes with real content (param true on ->getChildren)
foreach ($children as $child) {
/** @var $child DOMNode */
if ($child->nodeType === XML_TEXT_NODE && !preg_match('/\S$/', $child->getTextContent())) {
return false;
}
}
return true;
}
/**
* @param $node DOMNode
* @return bool
*/
public function hasSingleChildBlockElement()
{
$result = false;
if ($this->hasChildNodes()) {
foreach ($this->getChildren() as $child) {
if (in_array($child->nodeName, $this->divToPElements)) {
$result = true;
} else {
// If any of the hasSingleChildBlockElement calls return true, return true then.
$result = ($result || $child->hasSingleChildBlockElement());
}
}
}
return $result;
}
/**
* Returns the children of the current node.
*
* @param bool $filterEmptyDOMText Filter empty DOMText nodes?
*
* @return array
*/
public function getChildren($filterEmptyDOMText = false)
{
$ret = iterator_to_array($this->childNodes);
if ($filterEmptyDOMText) {
// Array values is used to discard the key order. Needs to be 0 to whatever without skipping any number
$ret = array_values(array_filter($ret, function ($node) {
return $node->nodeName !== '#text' || mb_strlen(trim($node->nodeValue));
}));
}
return $ret;
}
/**
* Determines if a node has no content or it is just a bunch of dividing lines and/or whitespace.
*
* @return bool
*/
public function isElementWithoutContent()
{
return $this instanceof DOMElement &&
mb_strlen(preg_replace(NodeUtility::$regexps['onlyWhitespace'], '', $this->textContent)) === 0 &&
($this->childNodes->length === 0 ||
$this->childNodes->length === $this->getElementsByTagName('br')->length + $this->getElementsByTagName('hr')->length
/*
* Special PHP DOMDocument case: We also need to count how many DOMText we have inside the node.
* If there's an empty tag with an space inside and a BR (for example "<p> <br/></p>) counting only BRs and
* HRs will will say that the example has 2 nodes, instead of one. This happens because in DOMDocument,
* DOMTexts are also nodes (which doesn't happen in JS). So we need to also count how many DOMText we
* are dealing with (And at this point we know they are empty or are just whitespace, because of the
* mb_strlen in this chain of checks).
*/
+ count(array_filter(iterator_to_array($this->childNodes), function ($child) {
return $child instanceof DOMText;
}))
);
}
/**
* Return an array indicating how many rows and columns this table has.
*
* @return array
*/
public function _getRowAndColumnCount()
{
$rows = $columns = 0;
$trs = $this->getElementsByTagName('tr');
foreach ($trs as $tr) {
/** @var \DOMElement $tr */
$rowspan = $tr->getAttribute('rowspan');
$rows += ($rowspan || 1);
// Now look for column-related info
$columnsInThisRow = 0;
$cells = $tr->getElementsByTagName('td');
foreach ($cells as $cell) {
/** @var \DOMElement $cell */
$colspan = $cell->getAttribute('colspan');
$columnsInThisRow += ($colspan || 1);
}
$columns = max($columns, $columnsInThisRow);
}
return ['rows' => $rows, 'columns' => $columns];
}
}
|