MySpace bulletins to RSS

Sep 27, 2007 php
This post is more than 18 months old. Since technology changes too rapidly, this content may be out of date (but that's not always the case). Please remember to verify any technical or programming information with the current release.

So I’m sick of myspace… or so I say to myself. So now I log in about half the time as I did before… and this is because I’ve made the following script. It logs in and grabs each bulletin from your top bulletins. Then, it creates an RSS feed from them.

Let’s check it out:

$ch = curl_init();
// setup and configure
$randnum = rand(1,9999999);
curl_setopt($ch, CURLOPT_COOKIEJAR, "cookiejar-$randnum");
curl_setopt($ch, CURLOPT_COOKIEFILE, "cookiejar-$randnum");
curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv: Gecko/20061204 Firefox/");
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_POST, 0);
// get homepage for login page token
curl_setopt($ch, CURLOPT_URL,"");
$page = curl_exec($ch);
// find it....
$token = $token[1];
// do login
$YOUR_EMAIL = '[email protected]';
$YOUR_PASSWORD = 'yourpassword';
curl_setopt($ch, CURLOPT_URL,"{$token}");
curl_setopt($ch, CURLOPT_REFERER, "");
curl_setopt($ch, CURLOPT_HTTPHEADER, Array("Content-Type: application/x-www-form-urlencoded"));
curl_setopt($ch, CURLOPT_POST, 1);
$postfields = "email=" . urlencode($YOUR_EMAIL);
$postfields .= "&password=" . urlencode($YOUR_PASSWORD);
$postfields .= '&ctl00%24Main%24SplashDisplay%24login%24loginbutton.x=38&ctl00%24Main%24SplashDisplay%24login%24loginbutton.y=15';
curl_setopt($ch, CURLOPT_POSTFIELDS,$postfields);
$page = curl_exec($ch);
//check for skip this advertisement
//<a href=";Mytoken=BA2B1E4D-950A-454A-BA25B1D55F6D1C1727874571">Skip this Advertisement &amp;raquo;</a>
preg_match("/<a href=\"(.*?)\">Skip this Advertisement/", $page, $redirpage);
if (isset($redirpage[1])) {
  curl_setopt($ch, CURLOPT_REFERER,";MyToken={$token}");
  curl_setopt($ch, CURLOPT_URL,$redirpage[1]);
  curl_setopt($ch, CURLOPT_POST, 0);
  $page = curl_exec($ch);
// check login error
if(strpos($page,"You Must Be Logged-In to do That!") !== false){
// login error
  print 'login error';
  return 2;
// LOGGED IN, now let's play
// find edit profile link (with token attached)
//preg_match("/ id=\"ctl00_Main_ctl00_Welcome1_EditMyProfileHyperLink\" href=\"([^\"]+)\"/",$page,$redirpage);
//$redirpage = $redirpage[1];
// go there (edit profile)
//curl_setopt($ch, CURLOPT_URL, $redirpage);
//$page = curl_exec($ch);
//echo $page; // do whatever you need to do
// clean up
//comment this
//$page = file_get_contents('src.txt');
preg_match('/<h5 class="heading">\s+My Bulletin Space\s+<\/h5>\s+<div style="padding:2px;">(.*?)(<tr>(.*?)<\/tr>\s+)<\/table>(.*?)<\/div>/s', $page, $found);
// cuz i suck
preg_match_all('/<tr>(.*?)<\/tr>/s', $found[2], $tds);
$rss = new simpleXMLElement('<rss version="2.0"></rss>');
$channel = $rss->addChild('channel');
$channel->addChild('title', "Bulletins for Myspace");
$channel->addChild('description', 'RSS feed for MySpace bulletins');
$channel->addChild('language', 'en-us');
$channel->addChild('pubDate', date('r'));
$channel->addChild('lastBuildDate', date('r'));
foreach ($tds[0] as $td) {
  preg_match('/href=\'(.*?)\'/', $td, $match);
  //$match[1] is the url
  curl_setopt($ch, CURLOPT_URL,$match[1]);
  curl_setopt($ch, CURLOPT_POST, 0);
  $page = curl_exec($ch);
  preg_match('/<table id="betterb">(.*?)<\/table>/s', $page, $bul);
  $bul = preg_replace('/<\/?t[r|d|h].*?>/', '', $bul[0]);
  //build subject
  preg_match("/Subject:(.*?)Body/s", $bul, $titlematch);
  $title= trim(htmlentities(strip_tags($titlematch[1])));
  //build title
  preg_match("/Date:(.*?)Subject/s", $bul, $datematch);
  $predate= htmlentities(strip_tags($datematch[1]));
  $pubdate = date('r', strtotime($predate));
  $item = $channel->addChild('item');
  $bul = trim($bul);
  $bul = html_entity_decode($bul);
  $bul = html_entity_decode($bul);
  $bul = htmlentities($bul);
  $item->addChild('title', "Bulletin from: " . $title);
  $item->addChild('description', $bul);
  $item->addChild('pubDate', $pubDate);
$fp = fopen('/yourhosthere/myspace/bulletins.xml', 'w');
fputs($fp, $rss->asXML());

This code was heavily inspired from another blog posting - but I can’t seem to remember their page anymore :(

I’m still having an issue with google reader saying that some of the bulletins are new when they’re not. I’m not sure if it is something in my script yet or if its something on the bulletins themselves… :( any input would be appreciated.

Go to All Posts