1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
|
<?php
/**
* Extract title from an HTML document.
*
* @param string $html HTML content where to look for a title.
*
* @return bool|string Extracted title if found, false otherwise.
*/
function html_extract_title($html)
{
if (preg_match('!<title.*?>(.*?)</title>!is', $html, $matches)) {
return trim(str_replace("\n", '', $matches[1]));
}
return false;
}
/**
* Determine charset from downloaded page.
* Priority:
* 1. HTTP headers (Content type).
* 2. HTML content page (tag <meta charset>).
* 3. Use a default charset (default: UTF-8).
*
* @param array $headers HTTP headers array.
* @param string $htmlContent HTML content where to look for charset.
* @param string $defaultCharset Default charset to apply if other methods failed.
*
* @return string Determined charset.
*/
function get_charset($headers, $htmlContent, $defaultCharset = 'utf-8')
{
if ($charset = headers_extract_charset($headers)) {
return $charset;
}
if ($charset = html_extract_charset($htmlContent)) {
return $charset;
}
return $defaultCharset;
}
/**
* Extract charset from HTTP headers if it's defined.
*
* @param array $headers HTTP headers array.
*
* @return bool|string Charset string if found (lowercase), false otherwise.
*/
function headers_extract_charset($headers)
{
if (! empty($headers['Content-Type']) && strpos($headers['Content-Type'], 'charset=') !== false) {
preg_match('/charset="?([^; ]+)/i', $headers['Content-Type'], $match);
if (! empty($match[1])) {
return strtolower(trim($match[1]));
}
}
return false;
}
/**
* Extract charset HTML content (tag <meta charset>).
*
* @param string $html HTML content where to look for charset.
*
* @return bool|string Charset string if found, false otherwise.
*/
function html_extract_charset($html)
{
// Get encoding specified in HTML header.
preg_match('#<meta .*charset=["\']?([^";\'>/]+)["\']? */?>#Usi', $html, $enc);
if (!empty($enc[1])) {
return strtolower($enc[1]);
}
return false;
}
/**
* Count private links in given linklist.
*
* @param array $links Linklist.
*
* @return int Number of private links.
*/
function count_private($links)
{
$cpt = 0;
foreach ($links as $link) {
$cpt = $link['private'] == true ? $cpt + 1 : $cpt;
}
return $cpt;
}
|
