我想在如下网页采集所有的帖子url地址
http://www.discuz.net/forum-10-1.html
帖子格式为
http://www.discuz.net/thread-3265731-1-1.html
只要url链接，得出的结果一行一个
回复讨论(解决方案) $url = 'http://www.discuz.net/forum-10-1.html';$ch = curl_init();curl_setopt($ch, curlopt_url,$url);curl_setopt($ch, curlopt_returntransfer, 1);curl_setopt($ch, curlopt_useragent, 'mozilla/5.0 (windows; u; windows nt 5.1; en-us; rv:1.9.2) gecko/20100115 firefox/3.6 (.net clr 3.5.30729)');$htmls = curl_exec($ch);curl_close($ch);$doc = new domdocument();libxml_use_internal_errors(true);$doc->loadhtml($htmls);$xpath = new domxpath($doc);$nodelist = $xpath->query('//a/@href');for ($i = 0; $i length; $i++) { if(preg_match('@\/thread\-@',$nodelist->item($i)->value,$match)){ echo $nodelist->item($i)->value.
; }}