phpQuery用法总结

项目下载地址：http://code.google.com/p/phpquery/

获取内容的方法:

第一种:newDocumentFile

phpQuery::newDocumentFile($url);

第二种:

$content = file_get_contents($url); 
$htmlObj = phpQuery::newDocumentHTML($content);

---

获取网页内容:

第一种:获取html节点

pq('title')->html()

第二种:获取script内容(会分数组)

pq("script")->getString();  

---

突破防爬虫

function _get_fake_apider($url) {
        $ch = curl_init();
        $ip = '115.239.211.112';  //百度蜘蛛
        $timeout = 15;
        curl_setopt($ch,CURLOPT_URL,$url);
        curl_setopt($ch,CURLOPT_TIMEOUT, $timeout);
        //伪造百度蜘蛛IP  
        curl_setopt($ch,CURLOPT_HTTPHEADER,array('X-FORWARDED-FOR:'.$ip.'','CLIENT-IP:'.$ip.'')); 
        //伪造百度蜘蛛头部
        curl_setopt($ch,CURLOPT_USERAGENT,"Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)");
        curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);
        curl_setopt($ch,CURLOPT_HEADER,0);
        curl_setopt ($ch, CURLOPT_REFERER, "http://www.baidu.com/ ");   //构造来路
        curl_setopt($ch,CURLOPT_CONNECTTIMEOUT,$timeout);        
        $content = curl_exec($ch);
        return $content;
    }