Prob con PHPDIG

Stavo installando nel mio sito il motore di ricerca interno...finita l'installazione sono subito andato a fare la indicizzazione automatica del sito con il robot spider ecco il risultato:

Warning: fsockopen() has been disabled for security reasons in /membri/eternity6/phpdig/phpdig_functions.php3 on line 175

Warning: fsockopen() has been disabled for security reasons in /membri/eternity6/phpdig/phpdig_functions.php3 on line 175

Warning: fsockopen() has been disabled for security reasons in /membri/eternity6/phpdig/phpdig_functions.php3 on line 175
livello 0 : 0 ulteriori link


mhhh credo sia dovuto al fatto che altervista giri in safemode...C'è un modo per agirare il problema? Vi rimando qui il codice del file che segnala errore grazie in anticipo:

<?
// -------------PHPDIG-1.0-----------
// Here are functions used by phpdig
// Separed in sections
// Antoine Bajolet bajolet@toiletoine.net

//-------------STRING FUNCTIONS

//=================================================
//converts an iso date to an mysql date
function http_to_sqldate($date)
{
global $month_names;
if (eregi('(([a-z]{3})\, ([0-9]{1,2}) ([a-z]+) ([0-9]{4}) ([0-9:]{8}) ([a-z]+))',$date,$regs))
{
$month = sprintf('%02d',$month_names[strtolower($regs[4])]);
$year = sprintf('%04d',$regs[5]);
$day = sprintf('%02d',$regs[3]);
$hour = sprintf('%06d',str_replace(':','',$regs[6]));
return "$year$month$day$hour";
}
}
//=================================================
//returns a localized string
function msg($string='')
{
global $phpdig_mess;
return nl2br($phpdig_mess[$string]);
}

//print a localized string
function pmsg($string='')
{
global $phpdig_mess;
print nl2br($phpdig_mess[$string]);
}

//=================================================
//load the common words in an array
function common_words($file='')
{
$lines = @file($file);
if (is_array($lines))
{
while (list($id,$word) = each($lines))
$common[trim($word)] = 1;
}
else
$common['aaaa'] = 1;
return $common;
}

//=================================================
//highlight a string part
function highlight($word="",$string="")
{
if ($word)
return @eregi_replace("($word)","<B>\\1</B>",$string);
else
return $result;
}

//=================================================
//replace all characters with an accent
function stripaccents($chaine)
{
return( strtr( $chaine,
"ÀÁÂÃÄÅàáâãäåÒÓÔÕÖØòóôõöøÈÉÊËèéêëÇçÌÍÎÏìíîïÙÚÛÜùúû üÿÑñ",
"AAAAAAaaaaaaOOOOOOooooooEEEEeeeeCcIIIIiiiiUUUUuuu uyNn" ) );
}

//=================================================
//epure a string from all non alnum words (words can contain & and _ character)
function epure_text($text,$min_word_length=2)
{
$text = stripaccents(strtolower ($text));
$text = ereg_replace("[[:blank:]][0-9]+[[:blank:]]"," ",ereg_replace("[^[:alnum:]_&]+"," ",$text));
$text = ereg_replace("[[:blank:]][^ ]{1,$min_word_length}[[:blank:]]"," "," ".$text." ");
return trim(ereg_replace("[[:blank:]]+"," ",$text));
}

//=================================================
//advanced striptags function.
//returns text and title
function html_to_plain_text($text)
{
//htmlentities
global $spec;

//replace blank characters by spaces
$text = ereg_replace("[\r\n\t]+"," ",$text);
//extracts title
if ( eregi("<title>([^<>]*)</title>",$text,$regs) )
$title = $regs[1];
else
$title = "";
//delete content of head, script, and style tags
$text = eregi_replace("<head[^<>]*>.*</head>"," ",$text);
$text = eregi_replace("<script[^>]*>.*</script>"," ",$text);
$text = eregi_replace("<style[^>]*>.*</style>"," ",$text);
$text = eregi_replace("(<[a-z0-9 ]+>)","\\1 ",eregi_replace("(</[a-z0-9 ]+>)","\\1 ",$text));

//tries to replace htmlentities by ascii equivalent
reset ($spec);
while ($char = each($spec))
{
$text = eregi_replace ($char[0]."[;]?",$char[1],$text);
$title = eregi_replace ($char[0]."[;]?",$char[1],$title);
}
$text = ereg_replace('&#([0-9]+);',chr('\1').' ',$text);

//replace blank characters by spaces
$text = ereg_replace("[\r\n\t]+"," ",$text);
$text = eregi_replace("--|[{}();\"]+"," ",eregi_replace("</[a-z0-9]+>"," ",$text));

//replace any group of blank characters by an unique space
$text = ereg_replace("[[:blank:]]+"," ",strip_tags($text));
$retour['content'] = $text;
$retour['title'] = $title;
return $retour;
}

//=================================================
//purify urls from relative components like ./ or ../ and return an array
function url_purify($eval)
{
//delete special links
if (eregi("[/]?mailto[/]?javascript[/]?news:",$eval))
return -1;

$url = @parse_url($eval);

$path = str_replace("./","",ereg_replace("^[.]/","",ereg_replace("^[.]{2}/.*",'NOMATCH',ereg_replace("[^/]*/[.]{2}/","",ereg_replace("^[.]/","",ereg_replace("/+","/",$url['path']))))));

if (eregi('([^/]+)$',$path,$regs))
{
$file = $regs[1];
$path = str_replace($file,"",$path);
}

$retour['path'] = ereg_replace('(.*[^/])/?$','\\1/',ereg_replace('^/(.*)','\\1',ereg_replace("/+","/",$path)));

if ($url['query'])
{
$file .= "?".$url['query'];
$retour['as_query'] = 1;
}

$retour['file'] = $file;

//path outside site tree
if ($retour['path'] == "NOMATCH" or ereg("^redir[.]php3.*",$file))
return -1;

return $retour;
}

//-------------HTTP FUNCTIONS
//Test presence and type of an url
function test_url($url,$mode='simple')
{
global $phpdig_version;
$components = parse_url($url);
$host = $components["host"];
$port = (int)$components["port"];
$path = $components["path"];
$query = $components["query"];

if (!$port)
{
$cport = 80;
}


$fp = fsockopen($host,$cport);
if ($port)
$port = ":".$port;
else
$port ="";

if (!$fp) {
//host domain not found
$status = "NOHOST";
}
else {

if ($query)
$path .= "?".$query;

//small get
/*$req =
"GET $path HTTP/1.1
Host: $host$port

";
*/
$req = "
";

//complete get
$request =
"GET $path HTTP/1.1
Host: $host$port
Accept: */*
Accept-Charset: iso-8859-1
Accept-Encoding: identity
User-Agent: PhpDig/$phpdig_version (PHP; MySql)

";
fputs($fp,$request);
$answer = fgets($fp,4096);
//test return code
if (ereg("([2-3])[0-9]{2}", $answer,$regs) )
{
$code = $regs[1];
while ($answer)
{
if ($req1)
{
$cur_req = $req1;
unset($req1);
}
else
$cur_req = $req;

fputs($fp,$cur_req);
$answer = fgets($fp,4096);

//parse header location
if (ereg("Location: *(.*)",$answer,$regs) && $code == 3)
{
$redirs ++;
if ($redirs > 4)
{
$answer = "";
$status = "LOOP";
}
$path = $regs[1];
$newurl = parse_url($path);

if (!$newurl['host'] || $host == $newurl['host'])
$req1 = "GET ".$newurl["path"]." HTTP/1.1
Host: $host$port

";
}
//Parse content-type header
elseif (eregi("Content-Type: *(text/[a-z]*)",$answer,$regs))
{
if ($regs[1] == "text/html")
{
$status = "HTML";
}
elseif ($regs[1] == "text/")
{
$boucle = 0;
while($boucle < 3)
{
fputs($fp,$req);
$answer = fgets($fp,4096);
//test presence of <html> tag at the begining
if (eregi("<html",$answer))
{
$status = "HTML";
$boucle = 3;
}
$boucle++;
}
}
elseif ($regs[1] == "text/plain")
{
eregi('\.([a-z0-9]{1,4})$',$path,$extregs);
// extension txt or other ?
if (is_array($extregs) && !eregi('txt',$extregs[1]))
$status = "TEXT";
else
$status = "PLAINTEXT";
}
else
{
$status = "TEXT";
}
}
elseif (eregi('Last-Modified: *([a-z0-9,: ]+)',$answer,$regs))
{
//search last-modified header
$date = $regs[1];
}
if (!eregi('[a-z0-9]+',$answer))
$answer = "";
}
}
else
{
//errors 400 and 500
$status = "NOFILE";
}

fclose($fp);
}

//returns variable or array
if ($mode == 'date')
{
$return['status'] = $status;
$return['lm_date'] = $date;
return $return;
}
else
return $status;
}

//=================================================
//retrieve links from an url
function explore($url,$path="",$file ="")
{
$index = 0;

//tests the nofollow directive in robots tags
if ((test_robots_tags(@get_meta_tags($url.$path.$file )) & 5) == 0)
$file_content = @file($url.$path.$file);

if (is_array($file_content))
{
while (list($n,$eval) = each($file_content))
{
//search hrefs and frames src
while (eregi("(<frame[^>]*src|href)[[:blank:]]*=[[:blank:]]*[\'\"]?((([[a-z]{3,5}://)+(([.a-zA-Z0-9-])+(:[0-9]+)*))*([:%/?=&;\\,._a-zA-Z0-9-]*))[#\'\" ]?",$eval,$regs))
{
$eval = str_replace($regs[0],"",$eval);
//test no host or same than site
if ($regs[5] == "" || $url == 'http://'.$regs[5].'/')
{
if (substr($regs[8],0,1) == "/")
$links[$index] = url_purify($regs[8]);
else
$links[$index] = url_purify($path.$regs[8]);
if (is_array($links[$index]))
$index++;
else
unset($links[$index]);
}
}
}
return $links;
}
else
return -1;
}

//=================================================
//test a link, search if is a file or dir, exclude robots.txt directives
function detect_dir_html($link,$exclude='')
{
$test = test_url($link['url'].$link['path'].$link['file']);

//file
if ($test == 'HTML' or $test == 'PLAINTEXT')
$link['ok'] = 1;
//dir
elseif (test_url($link['url'].$link['path'].$link['file'].'/') == "HTML")
{
$link['path'] = ereg_replace ('/+$','/',$link['path'].$link['file'].'/');
$link['file'] = "";
$link['ok'] = 1;
}
//none
else
$link['ok'] = 0;

//test the exclude with robots.txt
if (test_robots($exclude,$link['path']) == 1 or $exclude['@ALL@'] == 1)
$link['ok'] = 0;

return $link;
}

//=================================================
//search robots.txt for a site
function test_robots_txt($site) //don't forget the end backslash
{
if (test_url($site.'robots.txt') == 'PLAINTEXT')
{
$robots = file($site.'robots.txt');
while (list($id,$line) = each($robots))
{
if (ereg('^user-agent:[ ]*([a-z0-9*]+)',strtolower($line),$regs))
$user_agent = $regs[1];
if (eregi('^disallow:[ ]*(/([a-z0-9_/-]*))',$line,$regs))
{
if (!ereg('/$',$regs[2]))
$regs[2] .= '/';

if ($regs[1] == '/')
$exclude[$user_agent]['@ALL@'] = 1;
else
$exclude[$user_agent][$regs[2]] = 1;
}
}
if (is_array($exclude['phpdig']))
return $exclude['phpdig'];
elseif (is_array($exclude['*']))
return $exclude['*'];
}
$exclude['@NONE@'] = 1;
return $exclude;
}

//=================================================
function test_robots($exclude,$path)
{
if (ereg('^[a-z0-9_/-]+/$',$path,$regs))
{
while (list($path_exclude) = each($exclude))
{
if (ereg('^'.$path_exclude,$path))
$result = 1;
}
return $result;
}
}

//=================================================
function test_robots_tags($tags)
{
if (is_array($tags))
{
while (list($id,$content) = each($tags))
{
if (eregi('robots',$id))
{
$directive = 0;

if (eregi('nofollow',$content))
$directive += 1;
if (eregi('noindex',$content))
$directive += 2;
if (eregi('none',$content))
$directive += 4;
//test the bitwise return > 0 : & 5 nofollow, & 6 noindex.
return $directive;
}
}
}
}
?>

Grazie in anticipo

dimenticavo anche il non meno importante

Warning: set_time_limit() has been disabled for security reasons in /membri/eternity6/phpdig/spider.php3 on line 9

....Lascio perdere il progetto?...Oppure carico le tabelle creandomele indicizzandomi il sito dalla versione che faccio girare sul mio PC?...In questo caso poi è possibile uppando il contenuto della tabella ad avere un risultato per lo meno simile?...