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
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
$ch = curl_init();
curl_setopt($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 < $nodeList->length; $i++) {
if(preg_match('@\/thread\-@',$nodeList->item($i)->value,$match)){
echo $nodeList->item($i)->value. "<br/>";
}
}