|
1
|
|
|
<?php |
|
2
|
|
|
namespace vipnytt\RobotsTxtParser; |
|
3
|
|
|
|
|
4
|
|
|
use vipnytt\RobotsTxtParser\Directives\CleanParam; |
|
5
|
|
|
use vipnytt\RobotsTxtParser\Directives\Host; |
|
6
|
|
|
use vipnytt\RobotsTxtParser\Directives\Sitemap; |
|
7
|
|
|
use vipnytt\RobotsTxtParser\Directives\UserAgent; |
|
8
|
|
|
|
|
9
|
|
|
class Parser implements RobotsTxtInterface |
|
10
|
|
|
{ |
|
11
|
|
|
use ObjectTools; |
|
12
|
|
|
|
|
13
|
|
|
const TOP_LEVEL_DIRECTIVES = [ |
|
14
|
|
|
self::DIRECTIVE_CLEAN_PARAM, |
|
15
|
|
|
self::DIRECTIVE_HOST, |
|
16
|
|
|
self::DIRECTIVE_SITEMAP, |
|
17
|
|
|
self::DIRECTIVE_USER_AGENT, |
|
18
|
|
|
]; |
|
19
|
|
|
|
|
20
|
|
|
protected $raw; |
|
21
|
|
|
|
|
22
|
|
|
protected $previousDirective; |
|
23
|
|
|
protected $userAgentValues; |
|
24
|
|
|
|
|
25
|
|
|
protected $cleanParam; |
|
26
|
|
|
protected $host; |
|
27
|
|
|
protected $sitemap; |
|
28
|
|
|
protected $userAgent; |
|
29
|
|
|
|
|
30
|
|
|
/** |
|
31
|
|
|
* Constructor |
|
32
|
|
|
* |
|
33
|
|
|
* @param string $content - file content |
|
34
|
|
|
* @param string $encoding - character encoding |
|
35
|
|
|
* @param integer|null $byteLimit - maximum of bytes to parse |
|
36
|
|
|
* @throws Exceptions\ParserException |
|
37
|
|
|
*/ |
|
38
|
|
|
public function __construct($content, $encoding = self::ENCODING, $byteLimit = self::BYTE_LIMIT) |
|
39
|
|
|
{ |
|
40
|
|
|
if (!mb_internal_encoding($encoding)) { |
|
41
|
|
|
throw new Exceptions\ParserException('Unable to set internal character encoding to `' . $encoding . '`'); |
|
42
|
|
|
} |
|
43
|
|
|
|
|
44
|
|
|
$this->cleanParam = new CleanParam(); |
|
45
|
|
|
$this->host = new Host(); |
|
46
|
|
|
$this->sitemap = new Sitemap(); |
|
47
|
|
|
$this->userAgent = new UserAgent(); |
|
48
|
|
|
|
|
49
|
|
|
$this->raw = is_int($byteLimit) ? mb_strcut($content, 0, $byteLimit, $encoding) : $content; |
|
50
|
|
|
$this->parseTxt(); |
|
51
|
|
|
} |
|
52
|
|
|
|
|
53
|
|
|
/** |
|
54
|
|
|
* Parse robots.txt |
|
55
|
|
|
* |
|
56
|
|
|
* @return void |
|
57
|
|
|
*/ |
|
58
|
|
|
private function parseTxt() |
|
59
|
|
|
{ |
|
60
|
|
|
$lines = array_filter(array_map('trim', mb_split('\r\n|\n|\r', $this->raw))); |
|
61
|
|
|
// Parse each line individually |
|
62
|
|
|
foreach ($lines as $line) { |
|
63
|
|
|
// Limit rule length |
|
64
|
|
|
$line = mb_substr($line, 0, self::MAX_LENGTH_RULE); |
|
65
|
|
|
// Remove comments |
|
66
|
|
|
$line = mb_split('#', $line, 2)[0]; |
|
67
|
|
|
// Parse line |
|
68
|
|
|
$this->add($line); |
|
69
|
|
|
} |
|
70
|
|
|
} |
|
71
|
|
|
|
|
72
|
|
|
public function add($line) |
|
73
|
|
|
{ |
|
74
|
|
|
$previousDirective = $this->previousDirective; |
|
75
|
|
|
$pair = $this->generateRulePair($line, self::TOP_LEVEL_DIRECTIVES); |
|
76
|
|
|
if ($pair['directive'] === self::DIRECTIVE_USER_AGENT) { |
|
77
|
|
|
if ($previousDirective !== self::DIRECTIVE_USER_AGENT) { |
|
78
|
|
|
$this->userAgentValues = []; |
|
79
|
|
|
} |
|
80
|
|
|
$this->userAgentValues[] = $pair['value']; |
|
81
|
|
|
} |
|
82
|
|
|
$this->previousDirective = $pair['directive']; |
|
83
|
|
|
switch ($pair['directive']) { |
|
84
|
|
|
case self::DIRECTIVE_CLEAN_PARAM: |
|
85
|
|
|
return $this->cleanParam->add($pair['value']); |
|
86
|
|
|
case self::DIRECTIVE_HOST: |
|
87
|
|
|
return $this->host->add($pair['value']); |
|
88
|
|
|
case self::DIRECTIVE_SITEMAP: |
|
89
|
|
|
return $this->sitemap->add($pair['value']); |
|
90
|
|
|
case self::DIRECTIVE_USER_AGENT: |
|
91
|
|
|
return $this->userAgent->set($this->userAgentValues); |
|
92
|
|
|
} |
|
93
|
|
|
return $this->userAgent->add($line); |
|
94
|
|
|
} |
|
95
|
|
|
|
|
96
|
|
|
public function export() |
|
97
|
|
|
{ |
|
98
|
|
|
return $this->cleanParam->export() |
|
99
|
|
|
+ $this->host->export() |
|
100
|
|
|
+ $this->sitemap->export() |
|
101
|
|
|
+ $this->userAgent->export(); |
|
102
|
|
|
} |
|
103
|
|
|
|
|
104
|
|
|
/** |
|
105
|
|
|
* Check if URL is allowed to crawl |
|
106
|
|
|
* |
|
107
|
|
|
* @param string $url - url to check |
|
108
|
|
|
* @return bool |
|
109
|
|
|
*/ |
|
110
|
|
|
public function isAllowed($url) |
|
111
|
|
|
{ |
|
112
|
|
|
return $this->userAgent->check($url, self::DIRECTIVE_ALLOW); |
|
113
|
|
|
} |
|
114
|
|
|
|
|
115
|
|
|
/** |
|
116
|
|
|
* Check if URL is disallowed to crawl |
|
117
|
|
|
* |
|
118
|
|
|
* @param string $url - url to check |
|
119
|
|
|
* @return bool |
|
120
|
|
|
*/ |
|
121
|
|
|
public function isDisallowed($url) |
|
122
|
|
|
{ |
|
123
|
|
|
return $this->userAgent->check($url, self::DIRECTIVE_DISALLOW); |
|
124
|
|
|
} |
|
125
|
|
|
|
|
126
|
|
|
/** |
|
127
|
|
|
* Get sitemaps |
|
128
|
|
|
* |
|
129
|
|
|
* @return array |
|
130
|
|
|
*/ |
|
131
|
|
|
public function getSitemaps() |
|
132
|
|
|
{ |
|
133
|
|
|
return $this->sitemap->export(); |
|
134
|
|
|
} |
|
135
|
|
|
|
|
136
|
|
|
/** |
|
137
|
|
|
* Get host |
|
138
|
|
|
* |
|
139
|
|
|
* @return string|null |
|
140
|
|
|
*/ |
|
141
|
|
|
public function getHost() |
|
142
|
|
|
{ |
|
143
|
|
|
return $this->host->export(); |
|
144
|
|
|
} |
|
145
|
|
|
|
|
146
|
|
|
/** |
|
147
|
|
|
* Get Clean-param |
|
148
|
|
|
* |
|
149
|
|
|
* @return array |
|
150
|
|
|
*/ |
|
151
|
|
|
public function getCleanParam() |
|
152
|
|
|
{ |
|
153
|
|
|
return $this->cleanParam->export(); |
|
154
|
|
|
} |
|
155
|
|
|
} |
|
156
|
|
|
|
VIPnytt /
RobotsTxtParser
