1
|
|
|
<?php declare(strict_types=1); |
2
|
|
|
|
3
|
|
|
namespace MOrtola\BehatSEOContexts\Context; |
4
|
|
|
|
5
|
|
|
use Behat\Mink\Exception\UnsupportedDriverActionException; |
6
|
|
|
use Behat\Symfony2Extension\Driver\KernelDriver; |
7
|
|
|
use InvalidArgumentException; |
8
|
|
|
use vipnytt\RobotsTxtParser\UriClient; |
9
|
|
|
use Webmozart\Assert\Assert; |
10
|
|
|
|
11
|
|
|
class RobotsContext extends BaseContext |
12
|
|
|
{ |
13
|
|
|
/** |
14
|
|
|
* @var string |
15
|
|
|
*/ |
16
|
|
|
private $crawlerUserAgent = 'Googlebot'; |
17
|
|
|
|
18
|
|
|
/** |
19
|
|
|
* @Given I am a :crawlerUserAgent crawler |
20
|
|
|
*/ |
21
|
|
|
public function iAmACrawler(string $crawlerUserAgent): void |
22
|
|
|
{ |
23
|
|
|
$this->crawlerUserAgent = $crawlerUserAgent; |
24
|
|
|
} |
25
|
|
|
|
26
|
|
|
/** |
27
|
|
|
* @Then I should not be able to crawl :resource |
28
|
|
|
*/ |
29
|
|
|
public function iShouldNotBeAbleToCrawl(string $resource): void |
30
|
|
|
{ |
31
|
|
|
Assert::false( |
32
|
|
|
$this->getRobotsClient()->userAgent($this->crawlerUserAgent)->isAllowed($resource), |
33
|
|
|
sprintf( |
34
|
|
|
'Crawler with User-Agent %s is allowed to crawl %s', |
35
|
|
|
$this->crawlerUserAgent, |
36
|
|
|
$resource |
37
|
|
|
) |
38
|
|
|
); |
39
|
|
|
} |
40
|
|
|
|
41
|
|
|
private function getRobotsClient(): UriClient |
42
|
|
|
{ |
43
|
|
|
return new UriClient($this->webUrl); |
44
|
|
|
} |
45
|
|
|
|
46
|
|
|
/** |
47
|
|
|
* @throws UnsupportedDriverActionException |
48
|
|
|
* |
49
|
|
|
* @Then I should be able to get the sitemap URL |
50
|
|
|
*/ |
51
|
|
|
public function iShouldBeAbleToGetTheSitemapUrl(): void |
52
|
|
|
{ |
53
|
|
|
$this->doesNotSupportDriver(KernelDriver::class); |
54
|
|
|
|
55
|
|
|
$sitemaps = $this->getRobotsClient()->sitemap()->export(); |
56
|
|
|
|
57
|
|
|
Assert::false( |
58
|
|
|
empty($sitemaps), |
59
|
|
|
sprintf('Crawler with User-Agent %s can not find a sitemap url in robots file.', $this->crawlerUserAgent) |
60
|
|
|
); |
61
|
|
|
|
62
|
|
|
Assert::count( |
63
|
|
|
$sitemaps, |
64
|
|
|
1, |
65
|
|
|
sprintf( |
66
|
|
|
'Crawler with User-Agent %s has find more than 1 sitemap url in robots file.', |
67
|
|
|
$this->crawlerUserAgent |
68
|
|
|
) |
69
|
|
|
); |
70
|
|
|
|
71
|
|
|
try { |
72
|
|
|
$this->getSession()->visit($sitemaps[0]); |
73
|
|
|
} catch (\Throwable $e) { |
74
|
|
|
throw new InvalidArgumentException( |
75
|
|
|
sprintf( |
76
|
|
|
'Sitemap url %s is not valid. Exception: %s', |
77
|
|
|
$sitemaps[0], |
78
|
|
|
$e->getMessage() |
79
|
|
|
), |
80
|
|
|
0, |
81
|
|
|
$e |
82
|
|
|
); |
83
|
|
|
} |
84
|
|
|
|
85
|
|
|
Assert::eq( |
86
|
|
|
200, |
87
|
|
|
$this->getStatusCode(), |
88
|
|
|
sprintf('Sitemap url %s is not valid.', $sitemaps[0]) |
89
|
|
|
); |
90
|
|
|
} |
91
|
|
|
|
92
|
|
|
/** |
93
|
|
|
* @Then I should be able to crawl :resource |
94
|
|
|
*/ |
95
|
|
|
public function iShouldBeAbleToCrawl(string $resource): void |
96
|
|
|
{ |
97
|
|
|
Assert::true( |
98
|
|
|
$this->getRobotsClient()->userAgent($this->crawlerUserAgent)->isAllowed($resource), |
99
|
|
|
sprintf( |
100
|
|
|
'Crawler with User-Agent %s is not allowed to crawl %s', |
101
|
|
|
$this->crawlerUserAgent, |
102
|
|
|
$resource |
103
|
|
|
) |
104
|
|
|
); |
105
|
|
|
} |
106
|
|
|
} |
107
|
|
|
|