Under php grab yahoo boss search results by curl implementation code

  • 2020-05-09 18:13:17
  • OfStack

1. Write curl class to capture web content
 
class CurlUtil 
{ 
private $curl; 
private $timeout = 10; 
/** 
*  Initialize the curl object  
*/ 
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); // Sets whether to display header information  
curl_setopt($this->curl, CURLOPT_NOBODY, false); // Sets whether to output the page content  
curl_setopt($this->curl, CURLOPT_CONNECTTIMEOUT, $this->timeout); 
curl_setopt($this->curl, CURLOPT_FOLLOWLOCATION, true); 
curl_setopt($this->curl, CURLOPT_AUTOREFERER, true); 
} 
/** 
*  The cancellation function   Shut down curl object  
*/ 
public function __destruct() 
{ 
curl_close($this->curl); 
} 
/** 
*  Get the content of a web page  
*/ 
public function getWebPageContent($url) 
{ 
curl_setopt($this->curl, CURLOPT_URL, $url); 
return curl_exec($this->curl); 
} 
} 


2. Create curl objects
 
$CurlUtil = new CurlUtil(); 

3. Crawl yahoo search results
 
function getYahooSearch(CurlUtil $curl, $key) 
{ 
$key = urlencode($key); 
$searchUrl = "http://boss.yahooapis.com/ysearch/web/v1/$key?appid= Your yahoo! 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. Test results
var_dump (getYahooSearch ($CurlUtil, "baidu"));

Related articles: