|
1
|
|
|
<?php declare(strict_types = 1); |
|
2
|
|
|
|
|
3
|
|
|
namespace Wolnosciowiec\WebProxy\Providers\Proxy; |
|
4
|
|
|
|
|
5
|
|
|
use Goutte\Client; |
|
6
|
|
|
use Symfony\Component\DomCrawler\Crawler; |
|
7
|
|
|
use Wolnosciowiec\WebProxy\Entity\ProxyServerAddress; |
|
8
|
|
|
|
|
9
|
|
|
/** |
|
10
|
|
|
* @package Wolnosciowiec\WebProxy\Providers\Proxy |
|
11
|
|
|
*/ |
|
12
|
|
|
class FreeProxyListProvider implements ProxyProviderInterface |
|
13
|
|
|
{ |
|
14
|
|
|
/** |
|
15
|
|
|
* @var Client $client |
|
16
|
|
|
*/ |
|
17
|
|
|
private $client; |
|
18
|
|
|
|
|
19
|
|
|
public function __construct(Client $client) |
|
20
|
|
|
{ |
|
21
|
|
|
$this->client = $client; |
|
22
|
|
|
} |
|
23
|
|
|
|
|
24
|
|
|
/** |
|
25
|
|
|
* @inheritdoc |
|
26
|
|
|
*/ |
|
27
|
|
|
public function collectAddresses(): array |
|
28
|
|
|
{ |
|
29
|
|
|
$crawler = $this->client->request('GET', 'http://free-proxy-list.net'); |
|
30
|
|
|
$rows = $crawler->filter('#proxylisttable tr'); |
|
31
|
|
|
|
|
32
|
|
|
$addresses = $rows->each(function (Crawler $node) { |
|
33
|
|
|
$collection = $node->filter('td'); |
|
34
|
|
|
|
|
35
|
|
|
// cells mapping |
|
36
|
|
|
$lastVerificationTime = @$collection->getNode(7)->textContent; |
|
37
|
|
|
$proxyType = @$collection->getNode(4)->textContent; |
|
38
|
|
|
$proxyPort = (int)@$collection->getNode(1)->textContent; |
|
39
|
|
|
$proxyIP = @$collection->getNode(0)->textContent; |
|
40
|
|
|
$proxySchema =@ $collection->getNode(6)->textContent == 'yes' ? 'https' : 'http'; |
|
41
|
|
|
|
|
42
|
|
|
if (!$proxyIP || !$proxyPort || strlen($lastVerificationTime) === 0 || !$proxyType) { |
|
43
|
|
|
return null; |
|
44
|
|
|
} |
|
45
|
|
|
|
|
46
|
|
|
if ($this->isEnoughFresh($lastVerificationTime) === false) { |
|
47
|
|
|
return null; |
|
48
|
|
|
} |
|
49
|
|
|
|
|
50
|
|
|
if ($proxyType != 'elite proxy') { |
|
51
|
|
|
return null; |
|
52
|
|
|
} |
|
53
|
|
|
|
|
54
|
|
|
$address = new ProxyServerAddress(); |
|
55
|
|
|
$address->setAddress($proxyIP); |
|
56
|
|
|
$address->setPort($proxyPort); |
|
57
|
|
|
$address->setSchema($proxySchema); |
|
58
|
|
|
|
|
59
|
|
|
return $address; |
|
60
|
|
|
}); |
|
61
|
|
|
|
|
62
|
|
|
return array_filter($addresses); |
|
63
|
|
|
} |
|
64
|
|
|
|
|
65
|
|
|
/** |
|
66
|
|
|
* @param string $time eg. "2 seconds", "1 minute", "2 minutes" |
|
67
|
|
|
* @return bool |
|
68
|
|
|
*/ |
|
69
|
|
|
private function isEnoughFresh(string $time): bool |
|
70
|
|
|
{ |
|
71
|
|
|
$parts = explode(' ', $time); |
|
72
|
|
|
$multiply = 60 * 60 * 24 * 2; |
|
73
|
|
|
|
|
74
|
|
|
if (in_array($parts[1], ['minute', 'minutes'])) { |
|
75
|
|
|
$multiply = 60; |
|
76
|
|
|
} |
|
77
|
|
View Code Duplication |
elseif (in_array($parts[1], ['hour', 'hours'])) { |
|
|
|
|
|
|
78
|
|
|
$multiply = 60 * 60; |
|
79
|
|
|
} |
|
80
|
|
View Code Duplication |
elseif (in_array($parts[1], ['day', 'days'])) { |
|
|
|
|
|
|
81
|
|
|
$multiply = 60 * 60 * 24; |
|
82
|
|
|
} |
|
83
|
|
|
elseif (in_array($parts[1], ['second', 'seconds'])) { |
|
84
|
|
|
$multiply = 1; |
|
85
|
|
|
} |
|
86
|
|
|
|
|
87
|
|
|
return ((int)$parts[0] * $multiply) <= (60 * 5); // 5 minutes |
|
88
|
|
|
} |
|
89
|
|
|
} |
|
90
|
|
|
|
Wolnosciowiec /
webproxy
Loading history...
Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation.
You can also find more detailed suggestions in the “Code” section of your repository.