|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
namespace TreeHouse\IoBundle\Scrape\Crawler\Client; |
|
4
|
|
|
|
|
5
|
|
|
use GuzzleHttp\ClientInterface as GuzzleClientInterface; |
|
6
|
|
|
use GuzzleHttp\Exception\RequestException; |
|
7
|
|
|
use GuzzleHttp\RequestOptions; |
|
8
|
|
|
use GuzzleHttp\TransferStats; |
|
9
|
|
|
use Psr\Http\Message\ResponseInterface; |
|
10
|
|
|
use Psr\Log\LoggerAwareInterface; |
|
11
|
|
|
use Psr\Log\LoggerAwareTrait; |
|
12
|
|
|
use TreeHouse\IoBundle\Scrape\Exception\CrawlException; |
|
13
|
|
|
|
|
14
|
|
|
class GuzzleClient implements ClientInterface, LoggerAwareInterface |
|
15
|
|
|
{ |
|
16
|
|
|
use LoggerAwareTrait; |
|
17
|
|
|
|
|
18
|
|
|
/** |
|
19
|
|
|
* @var GuzzleClientInterface |
|
20
|
|
|
*/ |
|
21
|
|
|
protected $guzzle; |
|
22
|
|
|
|
|
23
|
|
|
/** |
|
24
|
|
|
* @var string[] |
|
25
|
|
|
*/ |
|
26
|
|
|
protected $effectiveUrls = []; |
|
27
|
|
|
|
|
28
|
|
|
/** |
|
29
|
|
|
* @param GuzzleClientInterface $guzzle |
|
30
|
|
|
*/ |
|
31
|
2 |
|
public function __construct(GuzzleClientInterface $guzzle) |
|
32
|
|
|
{ |
|
33
|
2 |
|
$this->guzzle = $guzzle; |
|
34
|
2 |
|
} |
|
35
|
|
|
|
|
36
|
|
|
/** |
|
37
|
|
|
* @inheritdoc |
|
38
|
|
|
*/ |
|
39
|
2 |
|
public function fetch($uri, $userAgent = null) |
|
40
|
|
|
{ |
|
41
|
2 |
|
$this->setEffectiveUri($uri, $uri); |
|
42
|
|
|
|
|
43
|
|
|
try { |
|
44
|
2 |
|
$response = $this->guzzle->request('GET', $uri, $this->getRequestOptions($userAgent)); |
|
45
|
|
|
|
|
46
|
2 |
|
return $this->transformResponse($uri, $response); |
|
47
|
|
|
} catch (RequestException $e) { |
|
48
|
|
|
$this->logger->error( |
|
49
|
|
|
sprintf('Error crawling: %s', $e->getMessage()), |
|
50
|
|
|
['url' => (string) $e->getRequest()->getUri()] |
|
51
|
|
|
); |
|
52
|
|
|
|
|
53
|
|
|
if ($response = $e->getResponse()) { |
|
54
|
|
|
return $this->transformResponse($uri, $response); |
|
55
|
|
|
} |
|
56
|
|
|
|
|
57
|
|
|
throw new CrawlException($uri, sprintf('Error crawling url: %s', $e->getMessage()), $e->getCode(), $e); |
|
58
|
|
|
} |
|
59
|
|
|
} |
|
60
|
|
|
|
|
61
|
|
|
/** |
|
62
|
|
|
* @param string $uri |
|
63
|
|
|
* @param string $effectiveUri |
|
64
|
|
|
*/ |
|
65
|
2 |
|
public function setEffectiveUri($uri, $effectiveUri) |
|
66
|
|
|
{ |
|
67
|
2 |
|
$this->effectiveUrls[$uri] = $effectiveUri; |
|
68
|
2 |
|
} |
|
69
|
|
|
|
|
70
|
|
|
/** |
|
71
|
|
|
* @param string $userAgent |
|
72
|
|
|
* |
|
73
|
|
|
* @return array |
|
74
|
|
|
*/ |
|
75
|
|
|
protected function getRequestOptions($userAgent = null) |
|
76
|
|
|
{ |
|
77
|
|
|
$options = [ |
|
78
|
2 |
|
RequestOptions::ON_STATS => function (TransferStats $stats) { |
|
79
|
|
|
$this->setEffectiveUri($stats->getRequest(), $stats->getEffectiveUri()); |
|
|
|
|
|
|
80
|
2 |
|
}, |
|
81
|
|
|
]; |
|
82
|
|
|
|
|
83
|
2 |
|
if ($userAgent) { |
|
|
|
|
|
|
84
|
2 |
|
$options[RequestOptions::HEADERS]['User-Agent'] = $userAgent; |
|
85
|
|
|
} |
|
86
|
|
|
|
|
87
|
2 |
|
return $options; |
|
88
|
|
|
} |
|
89
|
|
|
|
|
90
|
|
|
/** |
|
91
|
|
|
* @param string $uri |
|
92
|
|
|
* @param ResponseInterface $response |
|
93
|
|
|
* |
|
94
|
|
|
* @return array |
|
95
|
|
|
*/ |
|
96
|
2 |
|
protected function transformResponse($uri, ResponseInterface $response) |
|
97
|
|
|
{ |
|
98
|
|
|
return [ |
|
99
|
2 |
|
isset($this->effectiveUrls[$uri]) ? $this->effectiveUrls[$uri] : $uri, |
|
100
|
2 |
|
$response, |
|
101
|
|
|
]; |
|
102
|
|
|
} |
|
103
|
|
|
} |
|
104
|
|
|
|
It seems like the type of the argument is not accepted by the function/method which you are calling.
In some cases, in particular if PHP’s automatic type-juggling kicks in this might be fine. In other cases, however this might be a bug.
We suggest to add an explicit type cast like in the following example: