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

 1 function _get_fake_apider($url) {
 2         $ch = curl_init();
 3         $ip = '115.239.211.112';  //百度蜘蛛
 4         $timeout = 15;
 5         curl_setopt($ch,CURLOPT_URL,$url);
 6         curl_setopt($ch,CURLOPT_TIMEOUT, $timeout);
 7         //伪造百度蜘蛛IP  
 8         curl_setopt($ch,CURLOPT_HTTPHEADER,array('X-FORWARDED-FOR:'.$ip.'','CLIENT-IP:'.$ip.'')); 
 9         //伪造百度蜘蛛头部
10         curl_setopt($ch,CURLOPT_USERAGENT,"Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)");
11         curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);
12         curl_setopt($ch,CURLOPT_HEADER,0);
13         curl_setopt ($ch, CURLOPT_REFERER, "http://www.baidu.com/ ");   //构造来路
14         curl_setopt($ch,CURLOPT_CONNECTTIMEOUT,$timeout);        
15         $content = curl_exec($ch);
16         return $content;
17     }