Need urgent help on grab rss

tandiono · 10-02-2006, 09:19 AM

Im trying to grab rss from 2rss.com but it appear to be there's something wrong with the code. Really appreciate if anyone can help me out.

Here's the php code :

PHP Code:

  <?

 
set_time_limit(999999999);

 
error_reporting(0);

 
require_once('magpierss/rss_fetch.inc');

 
$cfg = parse_ini_file("../conf/config.ini", true);

 
$base = dirname(__FILE__);

 
    if (!count($cfg)) { die("Cannot parse config.ini file"); };

 
    foreach ($cfg as $cfgk=>$cfgv)

 
    {

 
        foreach ($cfgv as $cfgfk=>$cfgfv)

 
        {

 
            $cfgfk = strtolower($cfgfk);

 
            $cfgf["{$cfgk}/{$cfgfk}"] = $cfgfv;

 
        }

 
    }

 
    $cfg = array_merge($cfg, $cfgf);

 
 
 
//$db_host = "localhost";

 
//$db_user = "xxx";

 
//$db_pass = "xxx";

 
//$db_name = "xxx";

 
 
 
$m_link = mysql_connect ($cfg["db/hostname"], $cfg["db/username"], $cfg["db/password"]);

 
mysql_select_db ($cfg["db/database"], $m_link);

 
 
 
$num=0;

 
    function getlink ($str)

 
    {

 
        $link = substr ($str, 0, strlen($str)-2);

 
            $lnk = explode ('http://', $link);

 
            $link = 'http://'.$lnk[sizeof($lnk)-1];

 
        return $link;

 
    }

 
    

 
    function setlinks ($links, $catid)

 
    {

 
    Global $num;

 
        if (sizeof ($links)>=1)

 
        {

 
            foreach ($links as $link)

 
            {

 
                $feed = mysql_num_rows(mysql_query("select * from feeds WHERE feed_url='".$link."'"));

 
                if ($feed == 0)

 
                {

 
                    $num++;

 
                    $pos = mysql_fetch_assoc(mysql_query("select max(position) as posit from feeds"));

 
                    $position =  ($pos) ? $pos["posit"]+1 : 1;

????: NamePros.com http://www.namepros.com/programming/243450-need-urgent-help-on-grab-rss.html
 
                    mysql_query("INSERT INTO feeds VALUES (null, '', '', '".$catid."', '".$link."', '".$position."', '', '', '0', '2', '".time()."')");

 
                    $feedid = mysql_insert_id();

 
                    //

 
                    //

 
                    //

 
                    $rss = fetch_rss($link);

 
                        if ($rss && $rss->channel["title"]!='')

 
                        {

 
                            if ($rss->is_rss())

 
                            {

 
                                $type = "RSS ".$rss->is_rss();

 
                            }

 
                            else

 
                            {

 
                                $type = "ATOM ".$rss->is_atom();

 
                            }

 
                            

 
                            $add = mysql_query("UPDATE feeds set `name`='".addslashes(strip_tags($rss->channel["title"]))."', `description`='".addslashes(strip_tags($rss->channel["description"]))."', `type`='".$type."', `link`='".addslashes($rss->channel["link"])."' WHERE id='".$feedid."'");

 
                                if (!$add)

 
                                {

 
                                    mysql_query("DELETE FROM feeds WHERE id='".$feedid."'") or die(mysql_error());

 
                                }

 
                        }

 
                        else

 
                        {

 
                            mysql_query("DELETE FROM feeds WHERE id='".$feedid."'") or die(mysql_error());

 
                            $del++;

 
                        }

 
                }

 
            }

 
        }

 
    }

 
    

 
    function setcat ($catname, $tlcatname)

 
    {

 
        $tcat = mysql_fetch_assoc(mysql_query("SELECT * FROM cats WHERE name='".$tlcatname."'"));

 
        if ($tcat) {

 
            $toplevelid = $tcat["id"];

 
        }

 
        else

 
        {

 
            if ($tlcatname!='')

 
            {

 
            mysql_query("INSERT INTO cats VALUES (null, '0', '".$tlcatname."')");

 
            $toplevelid = mysql_insert_id();

 
            }

 
        }

 
        if ($catname=='')

 
        {

 
            return $toplevelid;

 
        }

 
        else

 
        {

 
            $pcat = mysql_fetch_assoc(mysql_query("SELECT * FROM cats WHERE parentid='".$toplevelid."' AND name='".$catname."'"));

 
            if ($pcat)

 
            {

 
                return $pcat["id"];

 
            }

 
            else

 
            {

 
                if ($catname!='')

 
                {

 
                mysql_query("INSERT INTO cats VALUES (null, '".$toplevelid."', '".$catname."')");

 
                return mysql_insert_id();

 
                }

 
            }        

 
        }

 
    }

 
    //$catn=1;

 
    //$page=2;

 
    for ($catn=1;$catn<=53;$catn++)

 
    {

 
    if ($num==100000) exit();

 
    $page=0;

 
        while ($page<=$max_page)

 
        {

 
        $page++;

 
                $url = "http://2rss.com/index.php?cat2=".$catn."&p=".$page;

 
            $handle = file_get_contents ($url);

 
            

 
            $isempty = (strpos($handle,"List empty")===FALSE) ? "noempty" : "empty";            

 
            $data_up = stristr($handle, "Top</a> ::");

 
            $data = substr($data_up, 0, strpos($data_up, "<script language=\"JavaScript\">"));

 
            

 
            $cats1 = explode("<br><br>", $data);

 
            ############### CATEGORIES ###################

 
            $cats2 = explode("::", strip_tags($cats1[0]));

 
            $tlcatname=$cats2[sizeof($cats2)-2];

 
                $tcn = explode ("[", $cats2[sizeof($cats2)-1]);

 
            $catname = eregi_replace(" ", "", $tcn[0]);

 
            $catid = setcat($catname, $tlcatname);

 
            ##############################################

 
            $data = $cats1[1];

 
            $temp = preg_match_all("(\<li style=\'margin-bottom: 5px;\'\>\<a href=\'index.php\?rss=([0-9]+)\'\>http:\/\/(.*[!-]))", $data, $out);            

 
            $links=array_map("getlink", $out[2]);

 
            //print "Category: [".$catn."] Page: [".$page."] Status: [".$isempty."] Links [".sizeof($links)."]<br>";

 
            setlinks ($links, $catid);

 
            // Set paging

 
            

 
            $pagg = stristr($data, "<strong>Page</strong>:");

 
            $paging = preg_match_all("(<a href=\'index.php\?cat2=([0-9]+)&p=([0-9]+)\'>([0-9]+)<\/a>)", $pagg, $pages);

????: NamePros.com http://www.namepros.com/showthread.php?t=243450
 
            $paging = $pages[3];

 
            $max_page = $paging[sizeof($paging)-1];

 
            if (!$max_page || $max_page==0 || $max_page=='') $max_page=1;

 
        }    

 
    }

 
?>

tandiono · 10-18-2006, 04:48 PM

Bump..

Anyonem, Pleaseeeee kindly help me.

flussie · 10-18-2006, 05:17 PM

I think this is wrong

Code:

$temp = preg_match_all("(\<li style=\'margin-bottom: 5px;\'\>\<a href=\'index.php\?rss=([0-9]+)\'\>http:\/\/(.*[!-]))", $data, $out);

The content which is returned doesn't contain any index.php links. They were replaced by rs_xxx.html files, and you should update the regex accordingly

tandiono · 10-18-2006, 05:24 PM

Originally Posted by flussie

I think this is wrong

Code:

$temp = preg_match_all("(\<li style=\'margin-bottom: 5px;\'\>\<a href=\'index.php\?rss=([0-9]+)\'\>http:\/\/(.*[!-]))", $data, $out);

The content which is returned doesn't contain any index.php links. They were replaced by rs_xxx.html files, and you should update the regex accordingly

????: NamePros.com http://www.namepros.com/showthread.php?t=243450
Do i have to change the index.php to rs_xxx.html as you mention?

Thanks

-------------

is the following code is allright?

Code:

$temp = preg_match_all("(\<li style=\'margin-bottom: 5px;\'\>\<a href=\'rs_xxx.html\?rss=([0-9]+)\'\>http:\/\/(.*[!-]))", $data, $out);

flussie · 10-18-2006, 05:37 PM

Try changing

$url = "http://2rss.com/index.php?cat2=".$catn."&p=".$page;
to
$url = "http://2rss.com/cat2_".$catn."_p".$page.".html";

and

$temp = preg_match_all("(\<li style=\'margin-bottom: 5px;\'\>\<a href=\'index.php\?rss=([0-9]+)\'\>http:\/\/(.*[!-]))", $data, $out);
to
$temp = preg_match_all("(\<li style=\'margin-bottom: 5px;\'\>\<a href=\'rss_([0-9]+)\.html\'\>http:\/\/(.*[!-]))", $data, $out);

????: NamePros.com http://www.namepros.com/showthread.php?t=243450
and

$paging = preg_match_all("(<a href=\'index.php\?cat2=([0-9]+)&p=([0-9]+)\'>([0-9]+)<\/a>)", $pagg, $pages);
to
$paging = preg_match_all("(<a href=\'cat2_([0-9]+)_p([0-9]+)\'>([0-9]+)<\/a>)", $pagg, $pages);

10-02-2006, 09:19 AM	THREAD STARTER #1 (permalink)
tandiono Tandiono.com Join Date: Jun 2005 Posts: 324	Need urgent help on grab rss Im trying to grab rss from 2rss.com but it appear to be there's something wrong with the code. Really appreciate if anyone can help me out. Here's the php code : PHP Code: <? set_time_limit(999999999); error_reporting(0); require_once('magpierss/rss_fetch.inc'); $cfg = parse_ini_file("../conf/config.ini", true); $base = dirname(__FILE__); if (!count($cfg)) { die("Cannot parse config.ini file"); }; foreach ($cfg as $cfgk=>$cfgv) { foreach ($cfgv as $cfgfk=>$cfgfv) { $cfgfk = strtolower($cfgfk); $cfgf["{$cfgk}/{$cfgfk}"] = $cfgfv; } } $cfg = array_merge($cfg, $cfgf); //$db_host = "localhost"; //$db_user = "xxx"; //$db_pass = "xxx"; //$db_name = "xxx"; $m_link = mysql_connect ($cfg["db/hostname"], $cfg["db/username"], $cfg["db/password"]); mysql_select_db ($cfg["db/database"], $m_link); $num=0; function getlink ($str) { $link = substr ($str, 0, strlen($str)-2); $lnk = explode ('http://', $link); $link = 'http://'.$lnk[sizeof($lnk)-1]; return $link; } function setlinks ($links, $catid) { Global $num; if (sizeof ($links)>=1) { foreach ($links as $link) { $feed = mysql_num_rows(mysql_query("select * from feeds WHERE feed_url='".$link."'")); if ($feed == 0) { $num++; $pos = mysql_fetch_assoc(mysql_query("select max(position) as posit from feeds")); $position = ($pos) ? $pos["posit"]+1 : 1; ????: NamePros.com http://www.namepros.com/programming/243450-need-urgent-help-on-grab-rss.html mysql_query("INSERT INTO feeds VALUES (null, '', '', '".$catid."', '".$link."', '".$position."', '', '', '0', '2', '".time()."')"); $feedid = mysql_insert_id(); // // // $rss = fetch_rss($link); if ($rss && $rss->channel["title"]!='') { if ($rss->is_rss()) { $type = "RSS ".$rss->is_rss(); } else { $type = "ATOM ".$rss->is_atom(); } $add = mysql_query("UPDATE feeds set `name`='".addslashes(strip_tags($rss->channel["title"]))."', `description`='".addslashes(strip_tags($rss->channel["description"]))."', `type`='".$type."', `link`='".addslashes($rss->channel["link"])."' WHERE id='".$feedid."'"); if (!$add) { mysql_query("DELETE FROM feeds WHERE id='".$feedid."'") or die(mysql_error()); } } else { mysql_query("DELETE FROM feeds WHERE id='".$feedid."'") or die(mysql_error()); $del++; } } } } } function setcat ($catname, $tlcatname) { $tcat = mysql_fetch_assoc(mysql_query("SELECT * FROM cats WHERE name='".$tlcatname."'")); if ($tcat) { $toplevelid = $tcat["id"]; } else { if ($tlcatname!='') { mysql_query("INSERT INTO cats VALUES (null, '0', '".$tlcatname."')"); $toplevelid = mysql_insert_id(); } } if ($catname=='') { return $toplevelid; } else { $pcat = mysql_fetch_assoc(mysql_query("SELECT * FROM cats WHERE parentid='".$toplevelid."' AND name='".$catname."'")); if ($pcat) { return $pcat["id"]; } else { if ($catname!='') { mysql_query("INSERT INTO cats VALUES (null, '".$toplevelid."', '".$catname."')"); return mysql_insert_id(); } } } } //$catn=1; //$page=2; for ($catn=1;$catn<=53;$catn++) { if ($num==100000) exit(); $page=0; while ($page<=$max_page) { $page++; $url = "http://2rss.com/index.php?cat2=".$catn."&p=".$page; $handle = file_get_contents ($url); $isempty = (strpos($handle,"List empty")===FALSE) ? "noempty" : "empty"; $data_up = stristr($handle, "Top</a> ::"); $data = substr($data_up, 0, strpos($data_up, "<script language=\"JavaScript\">")); $cats1 = explode("<br><br>", $data); ############### CATEGORIES ################### $cats2 = explode("::", strip_tags($cats1[0])); $tlcatname=$cats2[sizeof($cats2)-2]; $tcn = explode ("[", $cats2[sizeof($cats2)-1]); $catname = eregi_replace(" ", "", $tcn[0]); $catid = setcat($catname, $tlcatname); ############################################## $data = $cats1[1]; $temp = preg_match_all("(\<li style=\'margin-bottom: 5px;\'\>\<a href=\'index.php\?rss=([0-9]+)\'\>http:\/\/(.*[!-]))", $data, $out); $links=array_map("getlink", $out[2]); //print "Category: [".$catn."] Page: [".$page."] Status: [".$isempty."] Links [".sizeof($links)."]<br>"; setlinks ($links, $catid); // Set paging $pagg = stristr($data, "<strong>Page</strong>:"); $paging = preg_match_all("(<a href=\'index.php\?cat2=([0-9]+)&p=([0-9]+)\'>([0-9]+)<\/a>)", $pagg, $pages); ????: NamePros.com http://www.namepros.com/showthread.php?t=243450 $paging = $pages[3]; $max_page = $paging[sizeof($paging)-1]; if (!$max_page \|\| $max_page==0 \|\| $max_page=='') $max_page=1; } } ?> __________________ Tandiono.com \| Mikess.com \| WebsiteForum.net \| AudioForum.net \| ToysForum.net \| GadgetForum.net \| ClickBankForum.net \| ForumBoards.net \| ClickBanks.net

10-18-2006, 04:48 PM	THREAD STARTER #2 (permalink)
tandiono Tandiono.com Join Date: Jun 2005 Posts: 324	Bump.. Anyonem, Pleaseeeee kindly help me. __________________ Tandiono.com \| Mikess.com \| WebsiteForum.net \| AudioForum.net \| ToysForum.net \| GadgetForum.net \| ClickBankForum.net \| ForumBoards.net \| ClickBanks.net

10-18-2006, 05:37 PM	#5 (permalink)
flussie NamePros Regular Join Date: Sep 2005 Posts: 248	Try changing $url = "http://2rss.com/index.php?cat2=".$catn."&p=".$page; to $url = "http://2rss.com/cat2_".$catn."_p".$page.".html"; and $temp = preg_match_all("(\<li style=\'margin-bottom: 5px;\'\>\<a href=\'index.php\?rss=([0-9]+)\'\>http:\/\/(.[!-]))", $data, $out); to $temp = preg_match_all("(\<li style=\'margin-bottom: 5px;\'\>\<a href=\'rss_([0-9]+)\.html\'\>http:\/\/(.[!-]))", $data, $out); ????: NamePros.com http://www.namepros.com/showthread.php?t=243450 and $paging = preg_match_all("(<a href=\'index.php\?cat2=([0-9]+)&p=([0-9]+)\'>([0-9]+)<\/a>)", $pagg, $pages); to $paging = preg_match_all("(<a href=\'cat2_([0-9]+)_p([0-9]+)\'>([0-9]+)<\/a>)", $pagg, $pages); Last edited by flussie; 10-18-2006 at 05:52 PM.

10-18-2006, 05:17 PM	#3 (permalink)
flussie NamePros Regular Join Date: Sep 2005 Posts: 248	I think this is wrong Code: $temp = preg_match_all("(\<li style=\'margin-bottom: 5px;\'\>\<a href=\'index.php\?rss=([0-9]+)\'\>http:\/\/(.*[!-]))", $data, $out); The content which is returned doesn't contain any index.php links. They were replaced by rs_xxx.html files, and you should update the regex accordingly

Currently Active Users Viewing This Thread: 1 (0 members and 1 guests)