อันนี้โครงสร้าง xml ครับของที่จะดึงข้อมูล
Code
<item>
<title><![CDATA[ABCDEFG]]></title>
<link><![CDATA[http://www.XXXXX.net/detail/aaaaa/aaaaa/XXX.html]]></link>
<description><![CDATA[HHHHHHHHHHHHHHHHHHHHHHHHHHH]]></description>
<pubDate>Fri, 22 Feb 2013 06:00:25 </pubDate>
<enclosure url="http://www.XXXXXXX.net/media/img/size4/2013/02/21/XXXXXXXXXXXXX.jpg" type="image/jpeg"/>
</item>
ตอนนี้มันดึงจากอันนี้ได้ครับ
Code
<item>
<title>XXXXXXXXXXXXXXXXXXXXXXXXX</title>
<guid isPermaLink="false">http://www.thairath.co.th/content/eco/328182</guid>
<description>"XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXx</description>
<link>http://www.XXXXX.com/XXXXX/XXX/XXXXX</link>
<enclosure url="/XXX/XXX/XXX/02/21/328182/XXXXXX/XXX.jpg" type="image/jpeg"/>
<pubDate>Fri, 22 Feb 2013 05:30:00 +0700</pubDate>
</item>
อันนี้สคลิปที่ใช้ครับ
Code
<?php
if(!defined('IN_DISCUZ')) {
exit('Access Denied');
}
include("kom_config.inc.php");
$rss_post_dir = DISCUZ_ROOT . './data/rss_post';
if(!is_dir($rss_post_dir)) mkdir($rss_post_dir,0777);
if(!is_dir($rss_post_dir.'/mark')) mkdir($rss_post_dir.'/mark',0777);
//if(!is_dir($rss_post_dir.'/images')) mkdir($rss_post_dir.'/images',0777);
if (!isset($kom['data'])) {
return;
}
foreach ($kom['data'] as $dd) {
$count=0;
if (isset($dd['rss'])&&isset($dd['fid'])) {
$dom = new DOMDocument();
if ($dom->load($dd['rss'])) {
$datas = $dom->getElementsByTagName("item");
foreach($datas as $data) {
$attach_img=array();
if (isset($dd['limit'])&&$count>=$dd['limit']) {break;}
$title = trim($data->getElementsByTagName("title")->item(0)->nodeValue);
$link = trim($data->getElementsByTagName("link")->getElementsByTagName("CDATA")->item(0)->nodeValue);
if (isset($dd['keywords'])&&count($dd['keywords'])>0) {
$skip=1;
foreach ($dd['keywords'] as $k) {
if (preg_match("/{$k}/i",$title)) {
$skip=0;
}
}
if ($skip==1) {continue;}
}
if (!isset($dd['content_var'])||$dd['content_var']=='') {$dd['content_var']='description';}
if (preg_match("/^(.+):(.+)$/",$dd['content_var'],$match)) {
$description = trim($data->getElementsByTagNameNS('*',$match[2])->item(0)->nodeValue);
if ($description=='') {return;}
} else {
$description = trim($data->getElementsByTagName($dd['content_var'])->item(0)->nodeValue);
}
if (isset($dd['convert_bbcode'])&&$dd['convert_bbcode']=='1') {
$description = BBCODE($description);
// cache image
$arr=preg_match_all("|(\[img\]([^>]+)\[\/img\])|U",$description,$match,PREG_SET_ORDER);
if (count($match)>0) {
$markfile=DISCUZ_ROOT . './data/rss_post/mark/'.parse_url($link,PHP_URL_HOST).'.txt';
if(!file_exists($markfile)||strpos(file_get_contents($markfile) ,$link) === false){
foreach ($match as $img) {
$imgpath=DISCUZ_ROOT . './data/attachment/forum';
if(!is_dir($imgpath.'/'.date('Ym'))) make_dir($imgpath.'/'.date('Ym'));
if(!is_dir($imgpath.'/'.date('Ym').'/'.date('d'))) make_dir($imgpath.'/'.date('Ym').'/'.date('d'));
$imagedata = file_get_contents($img[2]);
$ext = addslashes(strtolower(substr(strrchr($img[2], '.'), 1, 10)));
$filename = strtolower(substr(strrchr($img[2], '/'), 1));
$attachment=date('Ym').'/'.date('d').'/'.date('His').strtolower(random(16)).'.'.$ext;
$imagefile = $imgpath.'/'.$attachment;
$imageurl = $_G['siteurl'] .(substr($_G['siteurl'],-1)=='/'?'':'/').$imagefile;
$f = fopen($imagefile,'w');
fwrite($f,$imagedata);
fclose($f);
list($width, $height, $type, $attr) = getimagesize($imagefile);
// insert new image
$arr = array(
'tid'=>0,
'pid'=>0,
'uid'=>0,
'tableid'=>0,
'downloads'=>0,
);
DB::insert('forum_attachment',$arr);
$aid = DB::insert_id();
// edit content
$description=str_replace("{$img[1]}","[attach]{$aid}[/attach]",$description);
// queue order
$attach_img[] = array(
'aid'=>$aid,
'filename'=>$filename,
'filesize'=>filesize($imagefile),
'attachment'=>$attachment,
'width'=>$width
);
}
}
}
}
$description = addslashes($description);
if (!isset($dd['image_var'])||$dd['image_var']=='') {$image='';} else {
if ($domDocument->getElementsByTagName($dd['image_var'])->length!=0)
{
$image=trim($data->getElementsByTagName($dd['image_var'])->item(0)->getAttribute('url'));
} else {$image='';}
}
$time = strtotime(trim($data->getElementsByTagName("pubDate")->item(0)->nodeValue));
$title = str_replace(array('\\','\''),array('\\\\','\\\''),$title);
$markfile=DISCUZ_ROOT . './data/rss_post/mark/'.parse_url($link,PHP_URL_HOST).'.txt';
if(!file_exists($markfile)||strpos(file_get_contents($markfile) ,$link) === false){
$f = fopen($markfile,'a');
fwrite($f,$link."\n");
fclose($f);
if ($dd['module']==''||!isset($dd['module'])) {
$content = $description;
$content.= '
ขอบคุณข่าวจาก : <a class="external" rel="nofollow" href="/outling.php?l=http://'.parse_url($link,PHP_URL_HOST).'" target="blank" title="'.parse_url($link,PHP_URL_HOST).'">'.parse_url($link,PHP_URL_HOST).'</a>';
} elseif ($dd['module']=='kom') {
$image=trim($data->getElementsByTagName('enclosure')->item(0)->getAttribute('url'));
$image = str_replace('120.jpg','630.jpg',$image);
$content = file_get_contents($link);
$content = explode('<div id="details" class="page">',$content);
$content = $content[1];
$content = explode('</p></p>',$content);
$content = $content[0];
$content = str_replace(array('\\','\'','<br />','</p>'),array('\\\\','\\\'',"\r\n","\r\n"),$content);
$content = strip_tags($content);
$content.='';
}
// save image
if ($image!='') {
$imgpath=DISCUZ_ROOT . './data/attachment/forum';
if(!is_dir($imgpath.'/'.date('Ym'))) make_dir($imgpath.'/'.date('Ym'));
if(!is_dir($imgpath.'/'.date('Ym').'/'.date('d'))) make_dir($imgpath.'/'.date('Ym').'/'.date('d'));
$imagedata = file_get_contents($image);
$ext = addslashes(strtolower(substr(strrchr($image, '.'), 1, 10)));
$filename = strtolower(substr(strrchr($img[2], '/'), 1));
$attachment=date('Ym').'/'.date('d').'/'.date('His').strtolower(random(16)).'.'.$ext;
$imagefile = $imgpath.'/'.$attachment;
$imageurl = $_G['siteurl'] .(substr($_G['siteurl'],-1)=='/'?'':'/').$imagefile;
$f = fopen($imagefile,'w');
fwrite($f,$imagedata);
fclose($f);
list($width, $height, $type, $attr) = getimagesize($imagefile);
// insert new image
$arr = array(
'tid'=>0,
'pid'=>0,
'uid'=>0,
'tableid'=>0,
'downloads'=>0,
);
DB::insert('forum_attachment',$arr);
$aid = DB::insert_id();
// edit content
$content = '[attach]'.$aid.'[/attach]'.$content;
// queue order
$attach_img[] = array(
'aid'=>$aid,
'filename'=>$filename,
'filesize'=>filesize($imagefile),
'attachment'=>$attachment,
'width'=>$width
);
}
$count++;
$poster = DB::result_first("SELECT username FROM ".DB::table('common_member')." WHERE uid='{$kom['poster_uid']}'");
$arr = array(
'fid'=>$dd['fid'],
'author'=>$poster,
'authorid'=>$kom['poster_uid'],
'subject'=>$title,
'dateline'=>$time,
'lastpost'=>$time,
'lastposter'=>$poster,
'status'=>32,
'stamp'=>-1,
'icon'=>-1,
);
DB::insert('forum_thread',$arr);
$tid = DB::insert_id();
$pid = insertpost(array(
'fid'=>$dd['fid'],
'tid'=>$tid,
'first'=>1,
'author'=>$poster,
'authorid'=>$kom['poster_uid'],
'subject'=>$title,
'dateline'=>$time,
'message'=>$content,
'useip'=>'127.0.0.1',
'invisible'=>0,
'anonymous'=>0,
'usesig'=>1,
'htmlon'=>1,
'bbcodeoff'=>0,
'smileyoff'=>0,
'parseurloff'=>0,
'attachment'=>'0',
'tags'=>'',
));
DB::query("UPDATE ".DB::table('forum_forum')." SET threads=threads+1,posts=posts+1,todayposts=todayposts+1,lastpost='".strval($tid) .' '.$title .' '.$time .' '.$poster."' WHERE fid='{$dd['fid']}'", 'UNBUFFERED');
DB::query("UPDATE ".DB::table('common_member_count')." SET posts=posts+1,threads=threads+1 WHERE uid='{$kom['poster_uid']}'", 'UNBUFFERED');
$first_img=0;
// insert image
foreach ($attach_img as $ai) {
$tableid=$tid%10;
DB::query("UPDATE ".DB::table('forum_attachment')." SET tid='{$tid}',pid='{$pid}',uid={$kom['poster_uid']},tableid='{$tableid}' WHERE aid='{$ai['aid']}'", 'UNBUFFERED');
$arr = array(
'aid'=>$ai['aid'],
'tid'=>$tid,
'pid'=>$pid,
'uid'=>$kom['poster_uid'],
'dateline'=>$_G['timestamp'],
'filename'=>$ai['filename'],
'filesize'=>$ai['filesize'],
'attachment'=>$ai['attachment'],
'remote'=>0,
'description'=>'',
'readperm'=>0,
'price'=>0,
'isimage'=>1,
'width'=>$ai['width'],
'thumb'=>0,
'picid'=>0
);
DB::insert('forum_attachment_'.$tableid,$arr);
DB::query("UPDATE ".DB::table('forum_post')." SET attachment=attachment+1 WHERE pid='{$pid}'", 'UNBUFFERED');
DB::query("UPDATE ".DB::table('forum_thread')." SET attachment=attachment+1 WHERE tid='{$tid}'", 'UNBUFFERED');
if ($first_img==0) {
DB::insert('forum_threadimage', array(
'tid' => $tid,
'attachment' => $ai['attachment'],
'remote' => 0
));
$first_img=1;
}
}
}
}
} else {
}
}
}
function ()
{
$bbcode = array(
"/\<([bius])\>/is" => "[$1]",
"/\<center\>/is" => "[align=center]",
"/\<\/center\>/is" => "[/align]",
"/\<strong\>/is" => "",
"/\<\/strong\>/is" => "",
"/\<em\>/is" => "<i>",
"/\<\/em\>/is" => "</i>",
"/\<code\>/is" => "<div>",
"/\<\/code\>/is" => "</font></div>",
"/\<small\>/is" => "<small>",
"/\<\/small\>/is" => "</small>",
"/\<script[^>]*\>.*\<\/script\>/is" => "",
"/\<font[^>]*\>/is" => "",
"/\<h([0-9]+)[^>]*\>/" => "[h$1]",
"/\<\/h([0-9]+)[^>]*\>/" => "[/h$1]",
"/\<\/font\>/is" => "",
"/\<span[^>]*\>/is" => "",
"/\<\/span\>/is" => "",
"/\<table[^>]*\>/is" => "[table=50%]",
"/\<\/table\>/is" => "[/table]",
"/\<\/tr\>/is" => "[/tr]",
"/\<\/td\>/is" => "[/td]",
"/\<tr[^>]*\>/is" => "[tr]",
"/\<td[^>]*\>/is" => "[td]",
"/\<div[^>]*\>/is" => "[p=30, 2, left]",
"/\<\/div\>/is" => "[/p]",
"/\<p[^>]*>/is" => "[p=30, 2, left]",
"/\<\/p\>/is" => "[/p]",
"/\<img[^>]*src=[\"\']([^\s'\"<>]+)[\"\'][^>]*\>/is" => "<img src=$1>",
"/\<\/img\>/is" => "[/img]",
"/\<a[^>]*href=[\"\']([^\s'\"<>]+)[\"\'][^>]*\>/is" => "[url=$1]",
"/\<\/a\>/is" => "[/url]",
"/\<ol[^>]*\>/is" => "[list=1]",
"/\<ul[^>]*\>/is" => "<ul>",
"/\<li[^>]*\>/is" => "[*]",
"/\<\/li\>/is" => "",
"/\<\/ul\>/is" => "</ul>",
"/\<\/ol\>/is" => "[/list]",
"/\<br[^>]*\>/is" => "\n",
"/\<blockquote[^>]*\>/is" => "<div style=padding-left:20px><blockquote><strong>Quote:</strong><div class=code>",
"/\<\/blockquote\>/is" => "</div></blockquote></div>",
"/\<\/blockquote\>/is" => "[/quote]",
"/\<object[^>]*\>/is" => "",
"/\<\/object\>/is" => "",
"/\<param[^>]*\>/is" => "",
"/\<\/param\>/is" => "",
"/\<embed[^>]*src=[\"\'](http\:\/\/www\.youtube\.com\/watch\?v\=\/[^\s'\"<>]+)[\"\'][^>]*\>/is" => "[media=x,500,375]$1[/media]",
"/\<embed[^>]*src=[\"\']http\:\/\/www\.youtube\.com\/v\/([^\s'\"<>]+)[\"\'][^>]*\>/is" => "[media=x,500,375]http://www.youtube.com/watch?v=$1[/media]"
);
$text = preg_replace(array_keys($bbcode), array_values($bbcode), $input);
$strfind = array(' ', '<', '>', '&');
$strreplace = array(' ', '<', '>', '&');
$text = str_replace($strfind, $strreplace, $text);
return htmlspecialchars_decode($text);
}
function make_dir($dir, $index = true) {
$res = true;
if(!is_dir($dir)) {
$res = @mkdir($dir, 0777);
$index && @touch($dir.'/index.html');
}
return $res;
}
?>
ช่วยแนะนำหน่อยนะครับว่า ถ้าจะดึงข้อมูลจากใน tag <link><+[CDATA[http://www.XXXXX.net/detail/aaaaa/aaaaa/XXX.html]]></link>
จะต้องเพิ่มส่วนไหนเข้าไป ผมศึกษาอยู่ แต่จากสคลิปค่อนข้างจะยากเกินสำหรับมือใหม่อย่างผม ยังไงต้องขอคำแนะนำจากผู้มีประสบการณ์ด้วยครับ
Tag : PHP
Load balance : Server 02
