php数据采集源码,一个基于phpQuery的php通用采集类分享

一、采集类源码

/**

*通用列表采集类

*版本V1.3

*作者:JAE

*/

require_once '../phpQuery/phpQuery/phpQuery.php';

class QueryList{

private $pageURL;

private $regArr = array();

public $jsonArr = array();

private $regRange;

private $html;

/************************************************

* 参数: 页面地址 选择器数组 块选择器

* 【选择器数组】说明：格式array("名称"=>array("选择器","类型"),.......)

* 【类型】说明：值 "text" ,"html" ,"属性"

*【块选择器】：指 先按照规则 选出 几个大块 ，然后再分别再在块里面 进行相关的选择

*************************************************/

function QueryList($pageURL,$regArr=array(),$regRange='')

{

$this->pageURL = $pageURL;

//为了能获取https://

$ch = curl_init();

curl_setopt($ch, CURLOPT_URL,$this->pageURL);

curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);

curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, false);

curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);

$this->html = curl_exec($ch);

curl_close($ch);

if(!empty($regArr))

{

$this->regArr = $regArr;

$this->regRange = $regRange;

$this->getList();

}

}

function setQuery($regArr,$regRange='')

{

$this->jsonArr=array();

$this->regArr = $regArr;

$this->regRange = $regRange;

$this->getList();

}

private function getList()

{

$hobj = phpQuery::newDocumentHTML($this->html);

if(!empty($this->regRange))

{

$robj = pq($hobj)->find($this->regRange);

$i=0;

foreach($robj as $item)

{

while(list($key,$reg_value)=each($this->regArr))

{

$iobj = pq($item)->find($reg_value[0]);

switch($reg_value[1])

{

case 'text':

$this->jsonArr[$i][$key] = trim(pq($iobj)->text());

break;

case 'html':

$this->jsonArr[$i][$key] = trim(pq($iobj)->html());

break;

default:

$this->jsonArr[$i][$key] = pq($iobj)->attr($reg_value[1]);

break;

}

}

//重置数组指针

reset($this->regArr);

$i++;

}

}

else

{

while(list($key,$reg_value)=each($this->regArr))

{

$lobj = pq($hobj)->find($reg_value[0]);

$i=0;

foreach($lobj as $item)

{

switch($reg_value[1])

{

case 'text':

$this->jsonArr[$i++][$key] = trim(pq($item)->text());

break;

case 'html':

$this->jsonArr[$i++][$key] = trim(pq($item)->html());

break;

default:

$this->jsonArr[$i++][$key] = pq($item)->attr($reg_value[1]);

break;

}

}

}

}

}

function getJSON()

{

return json_encode($this->jsonArr);

}

}

二、使用例子

require 'Query/QueryList.class.php';

//采集OSC的代码分享列表，标题 链接 作者

$url = "http://www.oschina.net/code/list";

$reg = array("title"=>array(".code_title a:eq(0)","text"),"url"=>array(".code_title a:eq(0)","href"),"author"=>array("img","title"));

$rang = ".code_list li";

$hj = new QueryList($url,$reg,$rang);

$arr = $hj->jsonArr;

print_r($arr);

//如果还想采当前页面右边的 TOP40活跃贡献者 图像，得到JSON数据,可以这样写

$reg = array("portrait"=>array(".hot_top img","src"));

$hj->setQuery($reg);

$json = $hj->getJSON();

echo $json . "

---

";

//采OSC内容页内容

$url = "http://www.oschina.net/code/snippet_186288_23816";

$reg = array("title"=>array(".QTitle h1","text"),"con"=>array(".Content","html"));

$hj = new QueryList($url,$reg);

$arr = $hj->jsonArr;

print_r($arr);

//就举这么多例子吧，是不是用来做采集很方便