mrb arkadaşlar bi arama motoru üzerinde çalışıyorum
arama motoru örümcekle çalışıyor sitenin içeriğini örümcekler çekiyor
fakat indexlediği siteler türkçe karakter sorunu oluyor
Arkadaşlar yardımcı olursanız çok makbule geçer
Bu kodla alakalı bişeymi arkadaşlar
function get_links($file, $url, $can_leave_domain, $base) {
$chunklist = array ();
// The base URL comes from either the meta tag or the current URL.
if (!empty($base)) {
$url = $base;
}
$links = array ();
$regs = Array ();
$checked_urls = Array();
preg_match_all("/href\s*=\s*[\'\"]?([+:%\/\?~=&;\\\(\),._a-zA-Z0-9-]*)(#[.a-zA-Z0-9-]*)?[\'\" ]?(\s*rel\s*=\s*[\'\"]?(nofollow)[\'\"]?)?/i", $file, $regs, PREG_SET_ORDER);
foreach ($regs as $val) {
if ($checked_urls[$val[1]]!=1 && !isset ($val[4])) { //if nofollow is not set
if (($a = $this->url_purify($val[1], $url, $can_leave_domain)) != '') {
$links[] = $a;
}
$checked_urls[$val[1]] = 1;
}
}
preg_match_all("/(frame[^>]*src[[:blank:]]*)=[[:blank:]]*[\'\"]?(([[a-z]{3,5}:\/\/(([.a-zA-Z0-9-])+(:[0-9]+)*))*([+:%\/?=&;\\\(\),._ a-zA-Z0-9-]*))(#[.a-zA-Z0-9-]*)?[\'\" ]?/i", $file, $regs, PREG_SET_ORDER);
foreach ($regs as $val) {
if ($checked_urls[$val[1]]!=1 && !isset ($val[4])) { //if nofollow is not set
if (($a = url_purify($val[1], $url, $can_leave_domain)) != '') {
$links[] = $a;
}
$checked_urls[$val[1]] = 1;
}
}
preg_match_all("/(window[.]location)[[:blank:]]*=[[:blank:]]*[\'\"]?(([[a-z]{3,5}:\/\/(([.a-zA-Z0-9-])+(:[0-9]+)*))*([+:%\/?=&;\\\(\),._ a-zA-Z0-9-]*))(#[.a-zA-Z0-9-]*)?[\'\" ]?/i", $file, $regs, PREG_SET_ORDER);
foreach ($regs as $val) {
if ($checked_urls[$val[1]]!=1 && !isset ($val[4])) { //if nofollow is not set
if (($a = url_purify($val[1], $url, $can_leave_domain)) != '') {
$links[] = $a;
}
$checked_urls[$val[1]] = 1;
}
}
preg_match_all("/(http-equiv=['\"]refresh['\"] *content=['\"][0-9]+;url)[[:blank:]]*=[[:blank:]]*[\'\"]?(([[a-z]{3,5}:\/\/(([.a-zA-Z0-9-])+(:[0-9]+)*))*([+:%\/?=&;\\\(\),._ a-zA-Z0-9-]*))(#[.a-zA-Z0-9-]*)?[\'\" ]?/i", $file, $regs, PREG_SET_ORDER);
foreach ($regs as $val) {
if ($checked_urls[$val[1]]!=1 && !isset ($val[4])) { //if nofollow is not set
if (($a = url_purify($val[1], $url, $can_leave_domain)) != '') {
$links[] = $a;
}
$checked_urls[$val[1]] = 1;
}
}
preg_match_all("/(window[.]open[[:blank:]]*[(])[[:blank:]]*[\'\"]?(([[a-z]{3,5}:\/\/(([.a-zA-Z0-9-])+(:[0-9]+)*))*([+:%\/?=&;\\\(\),._ a-zA-Z0-9-]*))(#[.a-zA-Z0-9-]*)?[\'\" ]?/i", $file, $regs, PREG_SET_ORDER);
foreach ($regs as $val) {
if ($checked_urls[$val[1]]!=1 && !isset ($val[4])) { //if nofollow is not set
if (($a = url_purify($val[1], $url, $can_leave_domain)) != '') {
$links[] = $a;
}
$checked_urls[$val[1]] = 1;
}
}