Created
March 15, 2016 19:26
-
-
Save JacobDB/1556b2e92b84291dfdd8 to your computer and use it in GitHub Desktop.
Web scraper to convert TuneGenie in to RSS
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
$url = "http://wkqx.tunegenie.com/"; | |
$title = "WKQX RSS Feed"; | |
$description = "A constantly updated feed for WKQX's playlist"; | |
$userAgent = "Googlebot/2.1 (http://www.googlebot.com/bot.html)"; | |
header("Content-type: text/xml; charset=utf-8", true); | |
echo "<?xml version='1.0' encoding='UTF-8' ?>" . PHP_EOL; | |
echo "<rss version='2.0'>" . PHP_EOL; | |
echo "<channel>" . PHP_EOL; | |
echo "<title>{$title}</title>" . PHP_EOL; | |
echo "<link>{$url}</link>" . PHP_EOL; | |
echo "<description>{$description}</description>" . PHP_EOL; | |
$curl = curl_init($url); | |
curl_setopt($curl, CURLOPT_USERAGENT, $userAgent); | |
curl_setopt($curl, CURLOPT_AUTOREFERER, true); | |
curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true); | |
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1); | |
curl_setopt($curl, CURLOPT_TIMEOUT, 2); | |
$html = curl_exec($curl); | |
$html = @mb_convert_encoding($html, "HTML-ENTITIES", "utf-8"); | |
curl_close($curl); | |
$dom = new DOMDocument(); | |
@$dom->loadHTML($html); | |
$nodes = $dom->getElementsByTagName("*"); | |
$date = ""; | |
foreach ($nodes as $node) { | |
if ($node->getAttribute("class") == "large-9 small-8 columns hidden-on-close") { | |
$inodes = $node->childNodes; | |
foreach($inodes as $inode) { | |
if (isset($inode->attributes)) { | |
if ($inode->getAttribute("class") == "left") { | |
$iinodes = $inode->childNodes; | |
echo "<item>" . PHP_EOL; | |
$counter = 0; | |
foreach ($iinodes as $iinode) { | |
$counter++; | |
if ($counter == 2) { | |
echo "<title>" . htmlspecialchars($iinode->nodeValue) . "</title>" . PHP_EOL; | |
$iiinode = $iinode->childNodes; | |
foreach ($iiinode as $iiinode) { | |
if (isset($iiinode->attributes)) { | |
echo "<link>http://wkqx.tunegenie.com" . $iiinode->getAttribute("href") . "</link>" . PHP_EOL; | |
} | |
} | |
} elseif ($counter == 4) { | |
echo "<description>" . htmlspecialchars($iinode->nodeValue) . "</description>" . PHP_EOL; | |
} | |
} | |
if ($date) { | |
echo "<pubDate>" . date(DATE_RSS, $date) . "</pubDate>" . PHP_EOL; | |
} | |
echo '</item>' . PHP_EOL; | |
} | |
} | |
} | |
} | |
/* | |
if ($node->nodeName == "h2") { | |
$date = strtotime($node->nodeValue); | |
} | |
if ($node->nodeName == "dt") { | |
$inodes = $node->childNodes; | |
foreach ($inodes as $inode) { | |
if ($inode->nodeName == "a" && $inode->getAttribute("class") == "permalink") { | |
echo "<item>" . PHP_EOL; | |
echo "<title>" . @mb_convert_encoding(htmlspecialchars($inode->getAttribute("title")), "utf-8") . "</title>" . PHP_EOL; | |
echo "<link>" . $inode->getAttribute("href") . "</link>" . PHP_EOL; | |
if ($date) { | |
echo "<pubDate>" . date(DATE_RSS, $date) . "</pubDate>" . PHP_EOL; | |
} | |
echo '</item>' . PHP_EOL; | |
} | |
} | |
} | |
*/ | |
} | |
echo "</channel></rss>"; | |
?> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment