I needed to get my new linkdirectory’s pages indexed and crawled and google needs some stimulation.
So I take a blogger subdomain,
and a 700 category php link directory
and make a table PLD_TAGCLOUD(CAT_ID, POSTED, TAG, FULLPATH)
CREATE TABLE `PLD_TAGCLOUD` (
`ID` BIGINT( 11 ) NOT NULL ,
`CAT_ID` DOUBLE NOT NULL ,
`POSTED` DOUBLE NOT NULL ,
`LEVEL` DOUBLE NOT NULL ,
`TAG` VARCHAR( 250 ) NOT NULL ,
`FULLPATH` VARCHAR( 250 ) NOT NULL ,
PRIMARY KEY ( `ID` )
) ENGINE = MYISAM
I fill the table with a recursive tree traversal on the category table where “tag” is the ‘title’ field,
and I get the FULLPATH url by using the domain root and the path generated by traversing the tree :
function connect() {
$DB_USER = "";
$DB_PASSWORD = "";
$DB_HOST = "";
$DB_DATA = "";
$link = mysql_connect($DB_HOST, $DB_USER, $DB_PASSWORD) or $error = mysql_error();
if (!$link) {
echo $error;
exit;
} else {
mysql_select_db($DB_DATA, $link) or $error = mysql_error();
return $link;
}
}
$link = connect();
$del="DELETE FROM `PLD_TAGCLOUD`";
$mydel = mysql_query($del, $link) or die(mysql_error());
@mysql_close($link);
$root='http://links.trismegistos.net';
$content .= read(0, $root, 1);
function read($rootid, $pathid, $thislevel) {
$link = connect();
$myqry = "SELECT * FROM `PLD_CATEGORY` WHERE `PARENT_ID`='".$rootid."'";
$myres = mysql_query($myqry, $link) or die(mysql_error());
if(mysql_num_rows($myres)<1) return;
while($row=mysql_fetch_assoc($myres)) {
$thispath= $pathid ."/".$row['TITLE_URL'];
$link2 = connect();
$add="INSERT INTO `PLD_TAGCLOUD` (`CAT_ID`, `LEVEL`, `TAG`, `FULLPATH`) VALUES ('".$row['ID']."', '".$thislevel."', '".htmlentities($row['TITLE'], ENT_QUOTES)."' ,'".$thispath."/')";
$addit = mysql_query($add, $link2) or die(mysql_error());
@mysql_close($link2);
read($row['ID'], $thispath, $thislevel+1);
}
@mysql_close($link);
}
note : I also use a field level to store the depth of a category-page (o for root, 1 for main categories and mine goes down to 4)
Then we make a simple routine to grab the first record for posted=0,
grab the url
grab the title
grab 3 posts off of google-blogsearch on the TITLE, add em to an email,
add a link to the category page url,
mail(email, subject, message-body, headers)
and ofcourse the coupe-de-grace, the cronjob, 700 posts, 4 per hour, so in about 170 hours my entire site is listed on a nice juicy blog. Just for the hell of it i put the links of the blogsearch on ‘follow’ so my poor victims get a link as well.
function connect() {
$DB_USER = "";
$DB_PASSWORD = "";
$DB_HOST = "";
$DB_DATA = "";
$link = mysql_connect($DB_HOST, $DB_USER, $DB_PASSWORD) or $error = mysql_error();
if (!$link) {
echo $error;
exit;
} else {
mysql_select_db($DB_DATA, $link) or $error = mysql_error();
return $link;
}
}
$link = connect();
$myqry = "SELECT * FROM `PLD_TAGCLOUD` WHERE `POSTED`='0' ORDER BY ID DESC";
$myres = mysql_query($myqry, $link) or die(mysql_error());
if(mysql_num_rows($myres)<1) return;
while($row=mysql_fetch_assoc($myres)) {
$myurl = $row['FULLPATH'];
$mykey = urlencode($row['TAG']);
$link2 = connect();
$add="UPDATE `PLD_TAGCLOUD` SET `POSTED`='1' WHERE `ID`='".$row['ID']."'";
$addit = mysql_query($add, $link2) or die(mysql_error());
@mysql_close($link2);
break;
}
@mysql_close($link);
$xmlSource="http://blogsearch.google.com/blogsearch_feeds?hl=en&c2coff=1&lr=&safe=active&as_drrb=q&as_qdr=d&q=".$mykey."&ie=utf-8&num=3&output=rss";
$title="";
$link="";
$description="";
$author="";
$pubDate="";
$currentElement="";
$nieuwsitems = array();
function startElement($parser,$name,$attr){
if(strcmp($name,"item")==0){
$GLOBALS['title']="";
$GLOBALS['link']="";
$GLOBALS['description']="";
$GLOBALS['author']="";
$GLOBALS['pubDate']="";
}
$GLOBALS['currentElement']=$name;
if(strcmp($name,"link")==0){ $GLOBALS['href']=$attr["href"]; }
}
function endElement($parser,$name){
$elements=array('title','link','description','author','pubDate');
if(strcmp($name,"item")==0){
foreach($elements as $element){
$temp[$element] = $GLOBALS[$element];
}
$GLOBALS['nieuwsitems'][]=$temp;
$GLOBALS['title']="";
$GLOBALS['link']="";
$GLOBALS['description']="";
$GLOBALS['author']="";
$GLOBALS['pubDate']="";
}
if(strcmp($name,"item")==0){
$GLOBALS['title']="";
$GLOBALS['link']="";
$GLOBALS['description']="";
$GLOBALS['author']="";
$GLOBALS['pubDate']="";
}
}
function characterData($parser, $data) {
$elements = array ('title', 'link', 'description','author','pubDate');
foreach ($elements as $element) {
if ($GLOBALS["currentElement"] == $element) {
$GLOBALS[$element] .= $data;
}
}
}
function parseFile(){
global $xmlSource,$nieuwsitems;
$xml_parser=xml_parser_create();
xml_set_element_handler($xml_parser,"startElement","endElement");
xml_set_character_data_handler($xml_parser,"characterData");
xml_parser_set_option($xml_parser,XML_OPTION_CASE_FOLDING,false);
if(!($fp=fopen($xmlSource,"r"))){
die("Cannot open $xmlSource ");
}
while(($data=fread($fp,4096))){
if(!xml_parse($xml_parser,$data,feof($fp))){
die(sprintf("XML error at line %d column %d ",
xml_get_current_line_number($xml_parser),
xml_get_current_column_number($xml_parser)));
}
}
xml_parser_free($xml_parser);
return $nieuwsitems;
}
$result = parseFile();
foreach($result as $arr){
$strResult .= '< hr />';
$strResult .= '< h4>'.$arr["title"].'< /h4>'.$arr["description"].'< br />"'.$arr["title"].' ('.parse_url($arr["link"], PHP_URL_HOST).')< br />< br />';
}
$strResult .= '< br /> < a href="'.$myurl.'" title="'.$mykey.'">trismegistos links : '.$mykey.'< /a>< br />';
$email='juustout.linkdirectory@blogger.com';
$subject = $mykey;
mail($email,$subject,$strResult, "MIME-Version: 1.0\n"."Content-type: text/html; charset=iso-8859-1");
echo $strResult;
(note the html markup in the last lines is < br />, if you cut and paste it, remove the space or you get a mess, also note the extra header in the php mail function, makes it possible to post html-marked up text (otherwise you get flat text posted and your site looks like ****).
