Created
August 30, 2018 20:51
-
-
Save matsubo/e6d35679558a7e50984fbc966b60dd73 to your computer and use it in GitHub Desktop.
fire uploader HTML scraping
This file contains 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 | |
ini_set('error_reporting', false); | |
require_once('htmlsql/snoopy.class.php'); | |
require_once('htmlsql/htmlsql.class.php'); | |
$id = $_REQUEST['id']; | |
$wsql = new htmlsql(); | |
$wsql->set_user_agent('Mozilla/5.0 (Windows; U; Windows NT 5.1; ja; rv:1.9.2) Gecko/20100115 Firefox/3.6 Jingoo/0.1.4 (.NET CLR 3.5.30729)'); | |
//print_r($wsql); | |
// connect to a URL | |
if (!$wsql->connect('url', sprintf('http://up.pandoravote.net/up%s/', $id))){ | |
throw new Exception('Error while connecting: ' . $wsql->error); | |
} | |
$wsql->query('SELECT * FROM td WHERE $class == "img"'); | |
?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"> | |
<channel> | |
<title>炎のアップローダ(3次エロ画像) RSS </title> | |
<link>http://matsu.teraren.com/blog/</link> | |
<atom:link href="http://matsu.teraren.com/fire/rss.php" rel="self" type="application/rss+xml" /> | |
<description>Fire uploader 2 RSS</description> | |
<pubDate><?php print date('r'); ?></pubDate> | |
<?php | |
foreach($wsql->fetch_array() as $row){ | |
$text = $row['text']; | |
if(preg_match('/(http:\/\/[^\']+)/', $text, $matches)){ | |
$image_url = $matches[1]; | |
} | |
if(preg_match('/([0-9a-zA-Z]+\.jpg)/', $text, $matches)){ | |
$filename = $matches[1]; | |
} | |
if(preg_match('#([0-9]{2})/([0-9]{2})/([0-9]{2})\([a-zA-Z]{3}\)([0-9]{2}:[0-9]{2})#', $text, $matches)){ | |
$date = '20'.$matches[1].'-'.$matches[2].'-'.$matches[3].' '.$matches[4].':00'; | |
$date_exp = date('r', strtotime($date)); | |
} | |
print "<item>\n"; | |
print "<guid>$image_url</guid>\n"; | |
print "<title>$filename</title>\n"; | |
print "<link>$image_url</link>\n"; | |
print "<description><img src="$image_url" /></description>\n"; | |
print "<pubDate>$date_exp</pubDate>\n"; | |
print "</item>\n"; | |
} | |
?> | |
</channel> | |
</rss> | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment