php抓取神马搜索结果,php下通过curl抓取yahoo boss 搜索结果的实现代码

1.编写curl类，进行网页内容抓取

class CurlUtil

{

private $curl;

private $timeout = 10;

/**

* 初始化curl对象

*/

public function __construct()

{

$this->curl = curl_init();

curl_setopt($this->curl, CURLOPT_RETURNTRANSFER, 1);

curl_setopt($this->curl, CURLOPT_USERAGENT, "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1)");

curl_setopt($this->curl, CURLOPT_HEADER, false); //设定是否显示头信息

curl_setopt($this->curl, CURLOPT_NOBODY, false); //设定是否输出页面内容

curl_setopt($this->curl, CURLOPT_CONNECTTIMEOUT, $this->timeout);

curl_setopt($this->curl, CURLOPT_FOLLOWLOCATION, true);

curl_setopt($this->curl, CURLOPT_AUTOREFERER, true);

}

/**

* 注销函数 关闭curl对象

*/

public function __destruct()

{

curl_close($this->curl);

}

/**

* 获取网页的内容

*/

public function getWebPageContent($url)

{

curl_setopt($this->curl, CURLOPT_URL, $url);

return curl_exec($this->curl);

}

}

2.创建curl对象

$CurlUtil = new CurlUtil();

3.抓取yahoo搜索结果

function getYahooSearch(CurlUtil $curl, $key)

{

$key = urlencode($key);

$searchUrl = "http://boss.yahooapis.com/ysearch/web/v1/$key?appid=你的雅虎appid&lang=tzh&region=hk&abstract=long&count=20&format=json&start=0&count=10";

$josnStr = $curl->getWebPageContent($searchUrl);

$searchDataInfo = json_decode($josnStr, true);

$searchData = $searchDataInfo['ysearchresponse']['resultset_web'];

$returnArray = array();

if (!empty($searchData)) {

foreach ($searchData as $data) {

$returnArray[] = array("url" => $data['url'], "date" => $data['date'], 'title' => strip_tags($data['title']), 'description' => strip_tags($data['abstract']));

}

}

return $returnArray;

}

4.测试结果

var_dump(getYahooSearch($CurlUtil, "百度"));