欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页  >  IT编程

php下通过curl抓取yahoo boss 搜索结果的实现代码

程序员文章站 2022-06-08 22:15:57
1.编写curl类,进行网页内容抓取 复制代码 代码如下: class curlutil { private $curl; private $timeout = 10; /...
1.编写curl类,进行网页内容抓取
复制代码 代码如下:

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
复制代码 代码如下:

$curlutil = new curlutil();

3.抓取yahoo搜索结果
复制代码 代码如下:

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"));