|
1
|
|
|
<?php |
|
2
|
|
|
namespace vipnytt\RobotsTxtParser; |
|
3
|
|
|
|
|
4
|
|
|
use vipnytt\RobotsTxtParser\Directives\DisAllow; |
|
5
|
|
|
use vipnytt\RobotsTxtParser\Exceptions\ParserException; |
|
6
|
|
|
|
|
7
|
|
|
class UserAgentClient implements RobotsTxtInterface |
|
8
|
|
|
{ |
|
9
|
|
|
protected $allow; |
|
10
|
|
|
protected $disallow; |
|
11
|
|
|
|
|
12
|
|
|
protected $userAgent; |
|
13
|
|
|
protected $origin; |
|
14
|
|
|
protected $statusCodeParser; |
|
15
|
|
|
|
|
16
|
|
|
public function __construct($rules, $userAgent, $origin, $statusCode) |
|
17
|
|
|
{ |
|
18
|
|
|
$this->statusCodeParser = new StatusCodeParser($statusCode, parse_url($origin, PHP_URL_SCHEME)); |
|
|
|
|
|
|
19
|
|
|
$this->userAgent = $userAgent; |
|
20
|
|
|
$this->origin = $origin; |
|
21
|
|
|
$this->validateRules($rules); |
|
22
|
|
|
} |
|
23
|
|
|
|
|
24
|
|
|
protected function validateRules($rules) |
|
25
|
|
|
{ |
|
26
|
|
|
foreach ([self::DIRECTIVE_DISALLOW, self::DIRECTIVE_ALLOW] as $directive) { |
|
27
|
|
|
if (!$rules[$directive] instanceof DisAllow) { |
|
28
|
|
|
throw new ParserException('Invalid rule object'); |
|
29
|
|
|
} |
|
30
|
|
|
$this->$directive = $rules[$directive]; |
|
31
|
|
|
} |
|
32
|
|
|
} |
|
33
|
|
|
|
|
34
|
|
|
/** |
|
35
|
|
|
* Check if URL is allowed to crawl |
|
36
|
|
|
* |
|
37
|
|
|
* @param string $url |
|
38
|
|
|
* @return bool |
|
39
|
|
|
*/ |
|
40
|
|
|
public function isAllowed($url) |
|
41
|
|
|
{ |
|
42
|
|
|
return $this->check(self::DIRECTIVE_ALLOW, $url); |
|
43
|
|
|
} |
|
44
|
|
|
|
|
45
|
|
|
/** |
|
46
|
|
|
* Check |
|
47
|
|
|
* |
|
48
|
|
|
* @param string $directive |
|
49
|
|
|
* @param string $url - URL to check |
|
50
|
|
|
* @return bool |
|
51
|
|
|
* @throws ParserException |
|
52
|
|
|
*/ |
|
53
|
|
|
protected function check($directive, $url) |
|
54
|
|
|
{ |
|
55
|
|
|
//TODO: Throw new exception Cannot check URL, belongs to a different robots.txt |
|
56
|
|
|
$this->statusCodeParser->replaceUnofficial(); |
|
57
|
|
|
if (($result = $this->statusCodeParser->check()) !== null) { |
|
58
|
|
|
return $directive === $result; |
|
59
|
|
|
} |
|
60
|
|
|
$result = self::DIRECTIVE_ALLOW; |
|
61
|
|
|
foreach ([self::DIRECTIVE_DISALLOW, self::DIRECTIVE_ALLOW] as $currentDirective) { |
|
62
|
|
|
if ($this->$currentDirective->check($url)) { |
|
63
|
|
|
$result = $currentDirective; |
|
64
|
|
|
} |
|
65
|
|
|
} |
|
66
|
|
|
return $directive === $result; |
|
67
|
|
|
} |
|
68
|
|
|
|
|
69
|
|
|
/** |
|
70
|
|
|
* Check if URL is disallowed to crawl |
|
71
|
|
|
* |
|
72
|
|
|
* @param string $url |
|
73
|
|
|
* @return bool |
|
74
|
|
|
*/ |
|
75
|
|
|
public function isDisallowed($url) |
|
76
|
|
|
{ |
|
77
|
|
|
return $this->check(self::DIRECTIVE_DISALLOW, $url); |
|
78
|
|
|
} |
|
79
|
|
|
|
|
80
|
|
|
/** |
|
81
|
|
|
* Get Crawl-delay |
|
82
|
|
|
* |
|
83
|
|
|
* @return array |
|
84
|
|
|
*/ |
|
85
|
|
|
public function getCrawlDelay() |
|
86
|
|
|
{ |
|
87
|
|
|
//TODO: Crawl-delay |
|
88
|
|
|
} |
|
89
|
|
|
|
|
90
|
|
|
/** |
|
91
|
|
|
* Get Cache-delay |
|
92
|
|
|
* |
|
93
|
|
|
* @return array |
|
94
|
|
|
*/ |
|
95
|
|
|
public function getCacheDelay() |
|
96
|
|
|
{ |
|
97
|
|
|
//TODO: Cache-delay |
|
98
|
|
|
} |
|
99
|
|
|
} |
|
100
|
|
|
|
VIPnytt /
RobotsTxtParser
Loading history...