function slugify($text)
{
    // replace non letter or digits by -
    $text = preg_replace('~[^\pL\d]+~u', '-', $text);
    // transliterate
    $text = iconv('utf-8', 'us-ascii//TRANSLIT', $text);
    // remove unwanted characters
    $text = preg_replace('~[^-\w]+~', '', $text);
    // trim
    $text = trim($text, '-');
    // remove duplicate -
    $text = preg_replace('~-+~', '-', $text);
    // lowercase
    $text = strtolower($text);
    if (empty($text)) {
        return 'n-a';
    }
    return $text;
}

用例:

echo slugify('bu metinde ç ö ş ğ ü ı * # karakter $ @ ! ?  kullanılamaz');

输出:bu-metinde-c-o-s-g-u-i-karakter-kullanilamaz

这是另一个例子，例如“Title with strange characters ééé A X Z”变成了“Title -with-strange-characters-ee - A - X - Z”。

/**
 * Function used to create a slug associated to an "ugly" string.
 *
 * @param string $string the string to transform.
 *
 * @return string the resulting slug.
 */
public static function createSlug($string) {

    $table = array(
            'Š'=>'S', 'š'=>'s', 'Đ'=>'Dj', 'đ'=>'dj', 'Ž'=>'Z', 'ž'=>'z', 'Č'=>'C', 'č'=>'c', 'Ć'=>'C', 'ć'=>'c',
            'À'=>'A', 'Á'=>'A', 'Â'=>'A', 'Ã'=>'A', 'Ä'=>'A', 'Å'=>'A', 'Æ'=>'A', 'Ç'=>'C', 'È'=>'E', 'É'=>'E',
            'Ê'=>'E', 'Ë'=>'E', 'Ì'=>'I', 'Í'=>'I', 'Î'=>'I', 'Ï'=>'I', 'Ñ'=>'N', 'Ò'=>'O', 'Ó'=>'O', 'Ô'=>'O',
            'Õ'=>'O', 'Ö'=>'O', 'Ø'=>'O', 'Ù'=>'U', 'Ú'=>'U', 'Û'=>'U', 'Ü'=>'U', 'Ý'=>'Y', 'Þ'=>'B', 'ß'=>'Ss',
            'à'=>'a', 'á'=>'a', 'â'=>'a', 'ã'=>'a', 'ä'=>'a', 'å'=>'a', 'æ'=>'a', 'ç'=>'c', 'è'=>'e', 'é'=>'e',
            'ê'=>'e', 'ë'=>'e', 'ì'=>'i', 'í'=>'i', 'î'=>'i', 'ï'=>'i', 'ð'=>'o', 'ñ'=>'n', 'ò'=>'o', 'ó'=>'o',
            'ô'=>'o', 'õ'=>'o', 'ö'=>'o', 'ø'=>'o', 'ù'=>'u', 'ú'=>'u', 'û'=>'u', 'ý'=>'y', 'ý'=>'y', 'þ'=>'b',
            'ÿ'=>'y', 'Ŕ'=>'R', 'ŕ'=>'r', '/' => '-', ' ' => '-'
    );

    // -- Remove duplicated spaces
    $stripped = preg_replace(array('/\s{2,}/', '/[\t\n]/'), ' ', $string);

    // -- Returns the slug
    return strtolower(strtr($string, $table));


}

注意:我已经从wordpress和它的工作!!

像这样使用它:

echo sanitize('testing this link');

Code

//taken from wordpress
function utf8_uri_encode( $utf8_string, $length = 0 ) {
    $unicode = '';
    $values = array();
    $num_octets = 1;
    $unicode_length = 0;

    $string_length = strlen( $utf8_string );
    for ($i = 0; $i < $string_length; $i++ ) {

        $value = ord( $utf8_string[ $i ] );

        if ( $value < 128 ) {
            if ( $length && ( $unicode_length >= $length ) )
                break;
            $unicode .= chr($value);
            $unicode_length++;
        } else {
            if ( count( $values ) == 0 ) $num_octets = ( $value < 224 ) ? 2 : 3;

            $values[] = $value;

            if ( $length && ( $unicode_length + ($num_octets * 3) ) > $length )
                break;
            if ( count( $values ) == $num_octets ) {
                if ($num_octets == 3) {
                    $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]) . '%' . dechex($values[2]);
                    $unicode_length += 9;
                } else {
                    $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]);
                    $unicode_length += 6;
                }

                $values = array();
                $num_octets = 1;
            }
        }
    }

    return $unicode;
}

//taken from wordpress
function seems_utf8($str) {
    $length = strlen($str);
    for ($i=0; $i < $length; $i++) {
        $c = ord($str[$i]);
        if ($c < 0x80) $n = 0; # 0bbbbbbb
        elseif (($c & 0xE0) == 0xC0) $n=1; # 110bbbbb
        elseif (($c & 0xF0) == 0xE0) $n=2; # 1110bbbb
        elseif (($c & 0xF8) == 0xF0) $n=3; # 11110bbb
        elseif (($c & 0xFC) == 0xF8) $n=4; # 111110bb
        elseif (($c & 0xFE) == 0xFC) $n=5; # 1111110b
        else return false; # Does not match any model
        for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
            if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80))
                return false;
        }
    }
    return true;
}

//function sanitize_title_with_dashes taken from wordpress
function sanitize($title) {
    $title = strip_tags($title);
    // Preserve escaped octets.
    $title = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title);
    // Remove percent signs that are not part of an octet.
    $title = str_replace('%', '', $title);
    // Restore octets.
    $title = preg_replace('|---([a-fA-F0-9][a-fA-F0-9])---|', '%$1', $title);

    if (seems_utf8($title)) {
        if (function_exists('mb_strtolower')) {
            $title = mb_strtolower($title, 'UTF-8');
        }
        $title = utf8_uri_encode($title, 200);
    }

    $title = strtolower($title);
    $title = preg_replace('/&.+?;/', '', $title); // kill entities
    $title = str_replace('.', '-', $title);
    $title = preg_replace('/[^%a-z0-9 _-]/', '', $title);
    $title = preg_replace('/\s+/', '-', $title);
    $title = preg_replace('|-+|', '-', $title);
    $title = trim($title, '-');

    return $title;
}

function slugify($text)
{
    // replace non letter or digits by -
    $text = preg_replace('~[^\pL\d]+~u', '-', $text);
    // transliterate
    $text = iconv('utf-8', 'us-ascii//TRANSLIT', $text);
    // remove unwanted characters
    $text = preg_replace('~[^-\w]+~', '', $text);
    // trim
    $text = trim($text, '-');
    // remove duplicate -
    $text = preg_replace('~-+~', '-', $text);
    // lowercase
    $text = strtolower($text);
    if (empty($text)) {
        return 'n-a';
    }
    return $text;
}

用例:

echo slugify('bu metinde ç ö ş ğ ü ı * # karakter $ @ ! ?  kullanılamaz');

输出:bu-metinde-c-o-s-g-u-i-karakter-kullanilamaz

更新

由于这个答案引起了一些关注，我在这里添加了一些解释。

所提供的解决方案基本上将用-(连字符)替换除A-Z、A-Z、0-9和-(连字符)之外的所有内容。因此，它不能与其他unicode字符(URL段码/字符串的有效字符)正常工作。一种常见的情况是输入字符串包含非英语字符。

只有当您确信输入字符串不会包含unicode字符时才使用此解决方案，您可能希望这些字符成为output/slug的一部分。

如。“नारीशक्ति”将成为 "----------" ( 连字符)而不是“नारी——शक्ति”(有效的URL蛞蝓)。

回答

$slug = strtolower(trim(preg_replace('/[^A-Za-z0-9-]+/', '-', $string)));

既然通用顶级域名和idn被越来越多地使用，我不明白为什么URL不能包含Andrés。

只是rawurlencode $URL你想要代替。大多数浏览器在url中显示UTF-8字符(不是一些古老的IE6可能)和位。Ly / goo。gl可以用来使它短的情况下，如俄语和阿拉伯语，如果需要可能是出于广告的目的，或者只是写在广告中，就像用户会写在浏览器URL。

唯一的区别是空格“”，如果你不想允许使用这些空格，那么用“-”和“/”替换它们可能是个好主意。

<?php
function slugify($url)
{
    $url = trim($url);

    $url = str_replace(" ","-",$url);
    $url = str_replace("/","-slash-",$url);
    $url = rawurlencode($url);
}
?>

Url编码 http://www.hurtta.com/RU/%D0%9F%D1%80%D0%BE%D0%B4%D1%83%D0%BA%D1%82%D1%8B/

Url写成http://www.hurtta.com/RU/Продукты/