adron

Рейтинг
3
Регистрация
16.10.2006

пхп пример парсинг ссылок выдран из Snoopy класса

<?php


function strip_links($document) {
preg_match_all("'<a\s.*?href\s*=\s* # find <a href=
([\"\'])? # find single or double quote
(?(1) (.*?)\\1 | ([^\s\>]+)) # if quote found, match up to next matching
# quote, otherwise match up to next space
'isx",$document,$links);

$match=array();
while(list($key,$val) = each($links[2])) {
$val=trim($val);
if(!empty($val))
$match[] = $val;
}

while(list($key,$val) = each($links[3])) {
$val=trim($val);
if(!empty($val))
$match[] = $val;
}

return $match;
}


$links=strip_links( file_get_contents('ФАЙЛ С СЫЛКАМИ.txt') );
print_r($links);
?>

А вот из тулбара примерный код :)


<?
function _BF_SHR32($x, $bits) {
if ($bits==0) return $x;
if ($bits==32) return 0;
$y = ($x & 0x7FFFFFFF) >> $bits;
if (0x80000000 & $x) {
$y |= (1<<(31-$bits));
}
return $y;
}
function _pr_toHex8($num) {
return($num < 16 ? "0" : "").dechex($num);
}

function _pr_hexEncodeU32($num) {
$result = _pr_toHex8(_BF_SHR32($num,24));
$result .= _pr_toHex8(_BF_SHR32($num,16) & 255);
$result .= _pr_toHex8(_BF_SHR32($num,8) & 255);
return $result._pr_toHex8($num & 255);
}
function _pr_hash($value) {
$kindOfThingAnIdiotWouldHaveOnHisLuggage = 16909125;
$_pr_HASH_SEED = "Mining PageRank is AGAINST GOOGLE'S TERMS OF SERVICE. Yes, I'm talking to you, scammer.";
for($i = 0;$i < strlen($value);$i++ ) {
$kindOfThingAnIdiotWouldHaveOnHisLuggage ^= ord(substr($_pr_HASH_SEED,($i % strlen($_pr_HASH_SEED)),1)) ^ ord(substr($value,$i,1));
$kindOfThingAnIdiotWouldHaveOnHisLuggage = (_BF_SHR32($kindOfThingAnIdiotWouldHaveOnHisLuggage,23) | $kindOfThingAnIdiotWouldHaveOnHisLuggage << 9);
}
return _pr_hexEncodeU32($kindOfThingAnIdiotWouldHaveOnHisLuggage);
}

function getPageRank($aUrl)
{
$file='http://toolbarqueries.google.com/search?sourceid=navclient-ff&features=Rank&client=navclient-auto-ff&ch=8'._pr_hash($url).'&q=info:'.$url;
$data = file($file);
$rankarray = explode (':', $data[2]);
$rank = $rankarray[2];
return $rank;
}

?>
<? echo '!'.getPageRank($URL); ?>

Где URL адрес Вашего сайта