1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
namespace MalScraper\Model; |
4
|
|
|
|
5
|
|
|
define('MAX_FILE_SIZE', 100000000); |
6
|
|
|
|
7
|
|
|
use HtmlDomParser; |
8
|
|
|
|
9
|
|
|
/** |
10
|
|
|
* MainModel class. |
11
|
|
|
* |
12
|
|
|
* Base model for all model class. |
13
|
|
|
*/ |
14
|
|
|
class MainModel |
15
|
|
|
{ |
16
|
|
|
/** |
17
|
|
|
* MyAnimeList main URL. |
18
|
|
|
* |
19
|
|
|
* @var string |
20
|
|
|
*/ |
21
|
|
|
protected $_myAnimeListUrl = 'https://myanimelist.net'; |
22
|
|
|
|
23
|
|
|
/** |
24
|
|
|
* Trimmed HtmlDomParser. |
25
|
|
|
* |
26
|
|
|
* @var \simplehtmldom_1_5\simple_html_dom |
27
|
|
|
*/ |
28
|
|
|
protected $_parser; |
29
|
|
|
|
30
|
|
|
/** |
31
|
|
|
* Area to be parsed. |
32
|
|
|
* |
33
|
|
|
* @var string |
34
|
|
|
*/ |
35
|
|
|
protected $_parserArea; |
36
|
|
|
|
37
|
|
|
/** |
38
|
|
|
* Complete MyAnimeList page URL. |
39
|
|
|
* |
40
|
|
|
* @var string |
41
|
|
|
*/ |
42
|
|
|
protected $_url; |
43
|
|
|
|
44
|
|
|
/** |
45
|
|
|
* Error response. |
46
|
|
|
* |
47
|
|
|
* @var string|int |
48
|
|
|
*/ |
49
|
|
|
protected $_error; |
50
|
|
|
|
51
|
|
|
/** |
52
|
|
|
* Get URL header. |
53
|
|
|
* |
54
|
|
|
* @param string $url URL of full MyAnimeList page |
55
|
|
|
* |
56
|
|
|
* @return int |
57
|
|
|
*/ |
58
|
|
|
public static function getHeader($url) |
59
|
|
|
{ |
60
|
|
|
$file_headers = @get_headers($url); |
61
|
|
|
if (empty($file_headers) || $file_headers[0] == 'HTTP/1.1 404 Not Found') { |
62
|
|
|
return 404; |
63
|
|
|
} |
64
|
|
|
|
65
|
|
|
if (empty($file_headers) || $file_headers[0] == 'HTTP/1.1 403 Forbidden') { |
66
|
|
|
return 403; |
67
|
|
|
} |
68
|
|
|
|
69
|
|
|
return 200; |
70
|
|
|
} |
71
|
|
|
|
72
|
|
|
/** |
73
|
|
|
* Get trimmed HtmlDomParser class. |
74
|
|
|
* |
75
|
|
|
* @param string $url URL of full MyAnimeList page |
76
|
|
|
* @param string $contentDiv Specific area to be parsed |
77
|
|
|
* |
78
|
|
|
* @return \simplehtmldom_1_5\simple_html_dom |
79
|
|
|
*/ |
80
|
|
|
public static function getParser($url, $contentDiv, $additionalSetting = false) |
81
|
|
|
{ |
82
|
|
|
$html = HtmlDomParser::file_get_html($url)->find($contentDiv, 0); |
83
|
|
|
$html = !$additionalSetting ? $html : $html->next_sibling(); |
84
|
|
|
$html = $html->outertext; |
85
|
|
|
$html = str_replace('"', '\"', $html); |
86
|
|
|
$html = str_replace('<', '&l-t;', $html); // handle '<' |
87
|
|
|
$html = html_entity_decode($html, ENT_QUOTES, 'UTF-8'); |
88
|
|
|
$html = str_replace('&l-t;', '<', $html); |
89
|
|
|
$html = HtmlDomParser::str_get_html($html); |
90
|
|
|
|
91
|
|
|
return $html; |
92
|
|
|
} |
93
|
|
|
|
94
|
|
|
/** |
95
|
|
|
* Header error check. |
96
|
|
|
* |
97
|
|
|
* @param MainModel $model Any model |
98
|
|
|
* |
99
|
|
|
* @return void |
100
|
|
|
*/ |
101
|
|
|
public static function errorCheck($model) |
102
|
|
|
{ |
103
|
|
|
$className = self::getCleanClassName($model); |
104
|
|
|
|
105
|
|
|
if (strpos($className, 'Search') !== false) { |
106
|
|
|
if (strlen($model->_query) < 3) { |
107
|
|
|
$model->_error = 400; |
108
|
|
|
} |
109
|
|
|
} |
110
|
|
|
|
111
|
|
|
if (!$model->_error) { |
112
|
|
|
$header = self::getHeader($model->_url); |
113
|
|
|
if ($header == 200) { |
114
|
|
|
if ($className != 'UserListModel') { |
115
|
|
|
$additionalSetting = ($className == 'CharacterPeoplePictureModel'); |
116
|
|
|
$model->_parser = self::getParser($model->_url, $model->_parserArea, $additionalSetting); |
117
|
|
|
} |
118
|
|
|
} else { |
119
|
|
|
$model->_error = $header; |
120
|
|
|
} |
121
|
|
|
} |
122
|
|
|
} |
123
|
|
|
|
124
|
|
|
/** |
125
|
|
|
* Get clean class name. |
126
|
|
|
* |
127
|
|
|
* @param MainModel $model Any model |
128
|
|
|
* |
129
|
|
|
* @return string |
130
|
|
|
*/ |
131
|
|
|
public static function getCleanClassName($model) |
132
|
|
|
{ |
133
|
|
|
$className = get_class($model); |
134
|
|
|
$className = explode('\\', $className); |
135
|
|
|
|
136
|
|
|
return $className[count($className) - 1]; |
137
|
|
|
} |
138
|
|
|
} |
139
|
|
|
|