|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
declare(strict_types=1); |
|
4
|
|
|
|
|
5
|
|
|
namespace AOE\Crawler\CrawlStrategy; |
|
6
|
|
|
|
|
7
|
|
|
/* |
|
8
|
|
|
* (c) 2020 AOE GmbH <[email protected]> |
|
9
|
|
|
* |
|
10
|
|
|
* This file is part of the TYPO3 Crawler Extension. |
|
11
|
|
|
* |
|
12
|
|
|
* It is free software; you can redistribute it and/or modify it under |
|
13
|
|
|
* the terms of the GNU General Public License, either version 2 |
|
14
|
|
|
* of the License, or any later version. |
|
15
|
|
|
* |
|
16
|
|
|
* For the full copyright and license information, please read the |
|
17
|
|
|
* LICENSE.txt file that was distributed with this source code. |
|
18
|
|
|
* |
|
19
|
|
|
* The TYPO3 project - inspiring people to share! |
|
20
|
|
|
*/ |
|
21
|
|
|
|
|
22
|
|
|
use GuzzleHttp\Exception\RequestException; |
|
23
|
|
|
use Psr\Http\Message\ResponseInterface; |
|
24
|
|
|
use Psr\Http\Message\UriInterface; |
|
25
|
|
|
use Psr\Log\LoggerAwareInterface; |
|
26
|
|
|
use Psr\Log\LoggerAwareTrait; |
|
27
|
|
|
use TYPO3\CMS\Core\Http\RequestFactory; |
|
28
|
|
|
use TYPO3\CMS\Core\Utility\GeneralUtility; |
|
29
|
|
|
|
|
30
|
|
|
/** |
|
31
|
|
|
* Calls Guzzle / CURL (based on TYPO3 settings) for fetching a URL. |
|
32
|
|
|
*/ |
|
33
|
|
|
class GuzzleExecutionStrategy implements LoggerAwareInterface, CrawlStrategy |
|
34
|
|
|
{ |
|
35
|
|
|
use LoggerAwareTrait; |
|
36
|
|
|
|
|
37
|
|
|
/** |
|
38
|
|
|
* Sets up a CURL / Guzzle Request for fetching the request. |
|
39
|
|
|
* |
|
40
|
|
|
* @return bool|mixed |
|
41
|
|
|
*/ |
|
42
|
1 |
|
public function fetchUrlContents(UriInterface $url, string $crawlerId) |
|
43
|
|
|
{ |
|
44
|
1 |
|
$reqHeaders = $this->buildRequestHeaders($crawlerId); |
|
45
|
|
|
|
|
46
|
1 |
|
$options = ['headers' => $reqHeaders]; |
|
47
|
1 |
|
if ($url->getUserInfo()) { |
|
48
|
|
|
$options['auth'] = explode(':', $url->getUserInfo()); |
|
49
|
|
|
} |
|
50
|
|
|
try { |
|
51
|
1 |
|
$url = (string) $url; |
|
52
|
1 |
|
$response = $this->getResponse($url, $options); |
|
53
|
1 |
|
$contents = $response->getBody()->getContents(); |
|
54
|
1 |
|
return unserialize($contents); |
|
55
|
|
|
} catch (RequestException $e) { |
|
56
|
|
|
$response = $e->getResponse(); |
|
57
|
|
|
$message = ($response ? $response->getStatusCode() : 0) |
|
58
|
|
|
. chr(32) |
|
59
|
|
|
. ($response ? $response->getReasonPhrase() : $e->getMessage()); |
|
60
|
|
|
|
|
61
|
|
|
$this->logger->debug( |
|
62
|
|
|
sprintf('Error while opening "%s" - ' . $message, $url), |
|
63
|
|
|
['crawlerId' => $crawlerId] |
|
64
|
|
|
); |
|
65
|
|
|
return $message; |
|
66
|
|
|
} |
|
67
|
|
|
} |
|
68
|
|
|
|
|
69
|
|
|
protected function getResponse(string $url, array $options): ResponseInterface |
|
70
|
|
|
{ |
|
71
|
|
|
return GeneralUtility::makeInstance(RequestFactory::class) |
|
72
|
|
|
->request( |
|
73
|
|
|
$url, |
|
74
|
|
|
'GET', |
|
75
|
|
|
$options |
|
76
|
|
|
); |
|
77
|
|
|
} |
|
78
|
|
|
|
|
79
|
|
|
/** |
|
80
|
|
|
* Builds HTTP request headers. |
|
81
|
|
|
*/ |
|
82
|
1 |
|
private function buildRequestHeaders(string $crawlerId): array |
|
83
|
|
|
{ |
|
84
|
|
|
return [ |
|
85
|
1 |
|
'Connection' => 'close', |
|
86
|
1 |
|
'X-T3Crawler' => $crawlerId, |
|
87
|
1 |
|
'User-Agent' => 'TYPO3 crawler', |
|
88
|
|
|
]; |
|
89
|
|
|
} |
|
90
|
|
|
} |
|
91
|
|
|
|
AOEpeople /
crawler
