You are here
一个简单的例子教你如何用DRUPAL 采集
星期三, 2015-05-27 16:10 — adminshiping1
星期六, 08/11/2012 - 23:11 — 月亮不孤主
版本： DRUPAL 7
要采集的采集的页面：http://drupalgarden.cn/forum/1202.html
代码：～
<?php
function create_node($title,$uid,$body,$type){
$node->is_new=1;
$node->title = $title;
$node->uid =$uid;
$node->type=$type;
$node->body['und'][0]['value']= $body;
node_save($node);
print $node->nid;
}
function _get_contents($url,$img = FALSE){
$dir = pathinfo($url);
$host = $dir['dirname'];
$refer = $host.'/';
$ch = curl_init();
$user_agent = "Baiduspider+(+http://www.baidu.com/search/spider.htm)"; //伪装百度蜘蛛
curl_setopt ($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt ($ch, CURLOPT_REFERER, $refer);
curl_setopt ($ch, CURLOPT_TIMEOUT, 800);
curl_setopt($ch, CURLOPT_USERAGENT, $user_agent);
$file_contents = curl_exec($ch);
if($img == TRUE){
$content_length = curl_getinfo($ch,CURLINFO_CONTENT_LENGTH_DOWNLOAD);
$size = round($content_length / 1024, 2);
return $size;
}else{
curl_close($ch);
return $file_contents;
}
}
$url="http://drupalgarden.cn/forum/1202.html";
$content=_get_contents($url,$img = FALSE);
preg_match_all('/div class="forum-post-content">(.*?)<\/div>/is',$content, $a);
preg_match_all('/<h2 class="with-tabs">(.*?)<\/h2>/is',$content, $t);
$body=$a[1][0];
$title=$t[1][0];
$type='article';
$uid=1;
create_node($title,$uid,$body,$type);
?>你可以继续根据nid 弄个foreach 或者FOR 循环，你可以把龙马的论坛在5分钟内全部采集过来,龙马可别揍我：）
来自 http://drupalchina.cn/forum/1204.html
普通分类: