Created
September 12, 2012 12:11
-
-
Save petrkle/3706215 to your computer and use it in GitHub Desktop.
Simple tumblr image downloader.
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 | |
define('IMGDIR','./img'); | |
require('sites.php'); | |
foreach($sites as $site){ | |
$rss = get_rss('http://'.$site.'.tumblr.com/rss'); | |
if(count($rss)>0){ | |
if(!is_dir(IMGDIR.'/'.$site)){ | |
mkdir(IMGDIR.'/'.$site,0700,true); | |
} | |
foreach($rss as $item){ | |
if(preg_match('/\.jpg$/',$item['img'])){ | |
$fn = IMGDIR.'/'.$site.'/'.$item['date'].'.jpg'; | |
if(!is_file($fn)){ | |
print "$fn\n"; | |
$fp = fopen($fn,'w'); | |
fwrite($fp,file_get_contents($item['img'])); | |
fclose($fp); | |
} | |
} | |
} | |
} | |
} | |
function get_rss($url){ | |
print "$url\n"; | |
$entries = array(); | |
$dom = new DOMDocument(); | |
@$dom->loadXML(file_get_contents($url)); | |
$xpath = new DOMXPath($dom); | |
$nodes = $xpath->query("//item"); | |
foreach ($nodes as $node) { | |
$subdom = new DOMDocument(); | |
@$subdom->loadXML('<desc>'.html_entity_decode($node->nodeValue).'</desc>'); | |
$subxpath = new DOMXPath($subdom); | |
if(is_object($subxpath->query("//desc/img")->item(0))){ | |
$img = $subxpath->query("//desc/img")->item(0)->getAttribute('src'); | |
$guid = $xpath->query(".//guid",$node)->item(0)->nodeValue; | |
$date = strtotime($xpath->query(".//pubDate",$node)->item(0)->nodeValue); | |
array_push($entries,array('img'=>$img,'guid'=>$guid,'date'=>$date)); | |
} | |
} | |
return $entries; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment