|
1
|
|
|
<?php
|
|
2
|
|
|
|
|
3
|
|
|
declare(strict_types=1);
|
|
4
|
|
|
|
|
5
|
|
|
namespace PHPHtmlParser\Dom;
|
|
6
|
|
|
|
|
7
|
|
|
use PHPHtmlParser\Contracts\Dom\CleanerInterface;
|
|
8
|
|
|
use PHPHtmlParser\Exceptions\LogicalException;
|
|
9
|
|
|
use PHPHtmlParser\Options;
|
|
10
|
|
|
|
|
11
|
|
|
class Cleaner implements CleanerInterface
|
|
12
|
|
|
{
|
|
13
|
|
|
/**
|
|
14
|
|
|
* Cleans the html of any none-html information.
|
|
15
|
|
|
*
|
|
16
|
|
|
* @throws LogicalException
|
|
17
|
|
|
*/
|
|
18
|
285 |
|
public function clean(string $str, Options $options): string
|
|
19
|
|
|
{
|
|
20
|
285 |
|
if (!$options->isCleanupInput()) {
|
|
21
|
|
|
// skip entire cleanup step
|
|
22
|
12 |
|
return $str;
|
|
23
|
|
|
}
|
|
24
|
|
|
|
|
25
|
273 |
|
$is_gzip = 0 === \mb_strpos($str, "\x1f" . "\x8b" . "\x08", 0, 'US-ASCII');
|
|
26
|
273 |
|
if ($is_gzip) {
|
|
27
|
|
|
$str = \gzdecode($str);
|
|
28
|
|
|
if ($str === false) {
|
|
29
|
|
|
throw new LogicalException('gzdecode returned false. Error when trying to decode the string.');
|
|
30
|
|
|
}
|
|
31
|
|
|
}
|
|
32
|
|
|
|
|
33
|
|
|
// remove white space before closing tags
|
|
34
|
273 |
|
$str = \mb_eregi_replace("'\s+>", "'>", $str);
|
|
35
|
273 |
|
if ($str === false) {
|
|
36
|
|
|
throw new LogicalException('mb_eregi_replace returned false instead of a string. Error when attempting to clean single quotes.');
|
|
37
|
|
|
}
|
|
38
|
273 |
|
$str = \mb_eregi_replace('"\s+>', '">', $str);
|
|
39
|
273 |
|
if ($str === false) {
|
|
40
|
|
|
throw new LogicalException('mb_eregi_replace returned false instead of a string. Error when attempting to clean double quotes.');
|
|
41
|
|
|
}
|
|
42
|
|
|
|
|
43
|
|
|
// clean out the \n\r
|
|
44
|
273 |
|
$replace = ' ';
|
|
45
|
273 |
|
if ($options->isPreserveLineBreaks()) {
|
|
46
|
3 |
|
$replace = ' ';
|
|
47
|
|
|
}
|
|
48
|
273 |
|
$str = \str_replace(["\r\n", "\r", "\n"], $replace, $str);
|
|
49
|
273 |
|
if ($str === false) {
|
|
50
|
|
|
throw new LogicalException('str_replace returned false instead of a string. Error when attempting to clean input string.');
|
|
51
|
|
|
}
|
|
52
|
|
|
|
|
53
|
|
|
// strip the doctype
|
|
54
|
273 |
|
$str = \mb_eregi_replace('<!doctype(.*?)>', '', $str);
|
|
55
|
273 |
|
if ($str === false) {
|
|
56
|
|
|
throw new LogicalException('mb_eregi_replace returned false instead of a string. Error when attempting to strip the doctype.');
|
|
57
|
|
|
}
|
|
58
|
|
|
|
|
59
|
|
|
// strip out comments
|
|
60
|
273 |
|
$str = \mb_eregi_replace('<!--(.*?)-->', '', $str);
|
|
61
|
273 |
|
if ($str === false) {
|
|
62
|
|
|
throw new LogicalException('mb_eregi_replace returned false instead of a string. Error when attempting to strip comments.');
|
|
63
|
|
|
}
|
|
64
|
|
|
|
|
65
|
|
|
// strip out cdata
|
|
66
|
273 |
|
$str = \mb_eregi_replace("<!\[CDATA\[(.*?)\]\]>", '', $str);
|
|
67
|
273 |
|
if ($str === false) {
|
|
68
|
|
|
throw new LogicalException('mb_eregi_replace returned false instead of a string. Error when attempting to strip out cdata.');
|
|
69
|
|
|
}
|
|
70
|
|
|
|
|
71
|
|
|
// strip out <script> tags
|
|
72
|
273 |
|
if ($options->isRemoveScripts()) {
|
|
73
|
270 |
|
$str = \mb_eregi_replace("<\s*script[^>]*[^/]>(.*?)<\s*/\s*script\s*>", '', $str);
|
|
74
|
270 |
|
if ($str === false) {
|
|
75
|
|
|
throw new LogicalException('mb_eregi_replace returned false instead of a string. Error when attempting to remove scripts 1.');
|
|
76
|
|
|
}
|
|
77
|
270 |
|
$str = \mb_eregi_replace("<\s*script\s*>(.*?)<\s*/\s*script\s*>", '', $str);
|
|
78
|
270 |
|
if ($str === false) {
|
|
79
|
|
|
throw new LogicalException('mb_eregi_replace returned false instead of a string. Error when attempting to remove scripts 2.');
|
|
80
|
|
|
}
|
|
81
|
|
|
}
|
|
82
|
|
|
|
|
83
|
|
|
// strip out <style> tags
|
|
84
|
273 |
|
if ($options->isRemoveStyles()) {
|
|
85
|
270 |
|
$str = \mb_eregi_replace("<\s*style[^>]*[^/]>(.*?)<\s*/\s*style\s*>", '', $str);
|
|
86
|
270 |
|
if ($str === false) {
|
|
87
|
|
|
throw new LogicalException('mb_eregi_replace returned false instead of a string. Error when attempting to strip out style tags 1.');
|
|
88
|
|
|
}
|
|
89
|
270 |
|
$str = \mb_eregi_replace("<\s*style\s*>(.*?)<\s*/\s*style\s*>", '', $str);
|
|
90
|
270 |
|
if ($str === false) {
|
|
91
|
|
|
throw new LogicalException('mb_eregi_replace returned false instead of a string. Error when attempting to strip out style tags 2.');
|
|
92
|
|
|
}
|
|
93
|
|
|
}
|
|
94
|
|
|
|
|
95
|
|
|
// strip smarty scripts
|
|
96
|
273 |
|
if ($options->isRemoveSmartyScripts()) {
|
|
97
|
270 |
|
$str = \mb_eregi_replace("(\{\w)(.*?)(\})", '', $str);
|
|
98
|
270 |
|
if ($str === false) {
|
|
99
|
|
|
throw new LogicalException('mb_eregi_replace returned false instead of a string. Error when attempting to remove smarty scripts.');
|
|
100
|
|
|
}
|
|
101
|
|
|
}
|
|
102
|
|
|
|
|
103
|
273 |
|
return $str;
|
|
104
|
|
|
}
|
|
105
|
|
|
|
|
106
|
|
|
|
|
107
|
|
|
}
|
|
108
|
|
|
|
|
109
|
|
|
|
paquettg /
php-html-parser
