php下通过curl抓取yahoo boss 搜索结果的实现代码
作者:bea
1.编写curl类,进行网页内容抓取 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_seto
1.编写curl类,进行网页内容抓取
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
代码如下:
$CurlUtil = new CurlUtil();
3.抓取yahoo搜索结果
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®ion=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"));
有用 | 无用
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
代码如下:
$CurlUtil = new CurlUtil();
3.抓取yahoo搜索结果
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®ion=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"));
有用 | 无用
猜你喜欢
您可能感兴趣的文章:
- Warning: session_destroy() : Trying to destroy uninitialized sessionq错误
- php中session_unset与session_destroy的区别分析
- 不重新编译PHP为php增加openssl模块的方法
- php的memcached客户端memcached
- PHP模块 Memcached功能多于Memcache
- php模块memcache和memcached区别分析
- sphinx增量索引的一个问题
- 批量获取memcache值并按key的顺序返回的实现代码
- 提高define性能的php扩展hidef的安装和使用
- php学习笔记 php中面向对象三大特性之一[封装性]的应用
- php学习笔记 面向对象的构造与析构方法
- php学习笔记 类的声明与对象实例化
- php学习笔记 PHP面向对象的程序设计
- php学习笔记 数组的常用函数
- PHP中的函数嵌套层数限制分析
- PHP5中新增stdClass 内部保留类
- php中使用Akismet防止垃圾评论的代码
- php中通过虚代理实现延迟加载的实现代码
- php获取后台Job管理的实现代码