|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
namespace Openbuildings\Spiderling; |
|
4
|
|
|
|
|
5
|
|
|
/** |
|
6
|
|
|
* Load urls using Curl |
|
7
|
|
|
* |
|
8
|
|
|
* @package Openbuildings\Spiderling |
|
9
|
|
|
* @author Ivan Kerin |
|
10
|
|
|
* @copyright (c) 2013 OpenBuildings Ltd. |
|
11
|
|
|
* @license http://spdx.org/licenses/BSD-3-Clause |
|
12
|
|
|
*/ |
|
13
|
|
|
class Driver_Simple_RequestFactory_HTTP implements Driver_Simple_RequestFactory |
|
14
|
|
|
{ |
|
15
|
|
|
/** |
|
16
|
|
|
* The user agent to be used when performing the requests |
|
17
|
|
|
* @var string |
|
18
|
|
|
*/ |
|
19
|
|
|
protected $_user_agent = 'Spiderling Simple Driver'; |
|
20
|
|
|
|
|
21
|
|
|
/** |
|
22
|
|
|
* The last visited url address |
|
23
|
|
|
* @var string |
|
24
|
|
|
*/ |
|
25
|
|
|
protected $_current_url; |
|
26
|
|
|
|
|
27
|
|
|
/** |
|
28
|
|
|
* Getter / Setter for the user agent, used when performing the requests |
|
29
|
|
|
* @param string $user_agent |
|
30
|
|
|
* @return string|Driver_Simple_RequestFactory_HTTP |
|
31
|
|
|
*/ |
|
32
|
|
|
public function user_agent($user_agent = NULL) |
|
33
|
|
|
{ |
|
34
|
|
|
if ($user_agent !== NULL) |
|
35
|
|
|
{ |
|
36
|
|
|
$this->_user_agent = $user_agent; |
|
37
|
|
|
return $this; |
|
38
|
|
|
} |
|
39
|
|
|
return $this->_user_agent; |
|
40
|
|
|
} |
|
41
|
|
|
|
|
42
|
|
|
/** |
|
43
|
|
|
* Get the url of the last request |
|
44
|
|
|
* @return string |
|
45
|
|
|
*/ |
|
46
|
|
|
public function current_url() |
|
47
|
|
|
{ |
|
48
|
|
|
return $this->_current_url; |
|
49
|
|
|
} |
|
50
|
|
|
|
|
51
|
|
|
/** |
|
52
|
|
|
* Get the path (no protocol or host) of the last request |
|
53
|
|
|
* @return [type] [description] |
|
|
|
|
|
|
54
|
|
|
*/ |
|
55
|
|
|
public function current_path() |
|
56
|
|
|
{ |
|
57
|
|
|
$url = parse_url($this->current_url()); |
|
58
|
|
|
|
|
59
|
|
|
return $url['path'].(isset($url['query']) ? '?'.$url['query'] : ''); |
|
60
|
|
|
} |
|
61
|
|
|
|
|
62
|
|
|
/** |
|
63
|
|
|
* Perform the request, follow redirects, return the response |
|
64
|
|
|
* @param string $method |
|
65
|
|
|
* @param string $url |
|
66
|
|
|
* @param array $post |
|
67
|
|
|
* @return string |
|
68
|
|
|
*/ |
|
69
|
|
|
public function execute($method, $url, array $post = array()) |
|
70
|
|
|
{ |
|
71
|
|
|
$curl = curl_init($url); |
|
72
|
|
|
|
|
73
|
|
|
curl_setopt($curl, CURLOPT_FOLLOWLOCATION, TRUE); |
|
74
|
|
|
curl_setopt($curl, CURLOPT_RETURNTRANSFER, TRUE); |
|
75
|
|
|
curl_setopt($curl, CURLOPT_CUSTOMREQUEST, $method); |
|
76
|
|
|
curl_setopt($curl, CURLOPT_USERAGENT, $this->user_agent()); |
|
77
|
|
|
|
|
78
|
|
|
if ($post) |
|
|
|
|
|
|
79
|
|
|
{ |
|
80
|
|
|
curl_setopt($curl, CURLOPT_POSTFIELDS, $post); |
|
81
|
|
|
} |
|
82
|
|
|
|
|
83
|
|
|
$response = curl_exec($curl); |
|
84
|
|
|
|
|
85
|
|
|
if ($response === FALSE OR curl_getinfo($curl, CURLINFO_HTTP_CODE) !== 200) |
|
86
|
|
|
{ |
|
87
|
|
|
throw new Exception_Curl('Curl: Download Error: :error, status :status on url :url', array(':url' => $url, ':status' => curl_getinfo($curl, CURLINFO_HTTP_CODE), ':error' => curl_error($curl))); |
|
88
|
|
|
} |
|
89
|
|
|
|
|
90
|
|
|
$this->_current_url = urldecode(curl_getinfo($curl, CURLINFO_EFFECTIVE_URL)); |
|
91
|
|
|
|
|
92
|
|
|
return $response; |
|
93
|
|
|
} |
|
94
|
|
|
} |
|
95
|
|
|
|
This check marks PHPDoc comments that could not be parsed by our parser. To see which comment annotations we can parse, please refer to our documentation on supported doc-types.