这篇文章主要介绍了php实现专业获取网站seo信息类,实例分析了seoreport类针对网站seo信息检查与获取的技巧,非常具有实用价值,需要的朋友可以参考下
本文实例讲述了php实现专业获取网站SEO信息类。分享给大家供大家参考。具体如下：
这个seo类的功能包括：
- 检查指定的网站响应
- 获取从该网站主页的语言和其他meta标签数据的
- 获取网站的导入链接，从Alexa的流量排名
- 获取网站的导入链接，由谷歌索引的网页数量
- 获取网站的信任，从WOT排名。
- 获取，因为它是第一个注册的网站域名年龄
- 获取的Twitter网站页面的数量
- 获取的Facebook链接的网站页面
- 获取网站谷歌网页速度等级
- 获取网站的谷歌网页排名
* @copyright (c) 2009-2012 Open Classifieds Team
* @license GPL v3
* Based on seo report script http://www.php.cn/ && PHP class SEOstats
*
*/
class seoreport{
/**
*
* check if a url is online/alive
* @param string $url
* @return bool
*/
public static function is_alive($url)
{
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_BINARYTRANSFER, 1);
curl_setopt($ch, CURLOPT_HEADERFUNCTION, 'curlHeaderCallback');
curl_setopt($ch, CURLOPT_FAILONERROR, 1);
curl_exec ($ch);
$int_return_code = curl_getinfo($ch, CURLINFO_HTTP_CODE);
curl_close ($ch);
if ($int_return_code != 200 && $int_return_code != 302 && $int_return_code != 304)
{
return FALSE;
}
else return TRUE;
}
/**
* HTTP GET request with curl.
*
* @param string $url String, containing the URL to curl.
* @return string Returns string, containing the curl result.
*
*/
protected static function get_html($url)
{
$ch = curl_init($url);
curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);
curl_setopt($ch,CURLOPT_CONNECTTIMEOUT,5);
curl_setopt($ch,CURLOPT_FOLLOWLOCATION,1);
curl_setopt($ch,CURLOPT_MAXREDIRS,2);
if(strtolower(parse_url($url, PHP_URL_SCHEME)) == 'https')
{
curl_setopt($ch,CURLOPT_SSL_VERIFYPEER,1);
curl_setopt($ch,CURLOPT_SSL_VERIFYHOST,1);
}
$str = curl_exec($ch);
curl_close($ch);
return ($str)?$str:FALSE;
}
/**
*
* get the domain from any URL
* @param string $url
*/
public static function domain_name($url)
{
$nowww = ereg_replace('www\.','',$url);
$domain = parse_url($nowww);
if(!empty($domain["host"]))
return $domain["host"];
else
return $domain["path"];
}
/**
*
* get the metas from a url and the language of the site
* @param string $url
* @return array
*/
public static function meta_info($url)
{
//doesn't work at mediatemple
/*$html = new DOMDocument();
if(!$html->loadHtmlFile($url))
return FALSE;*/
if (!$html_content = self::get_html($url))
return FALSE;
$html = new DOMDocument();
$html->loadHtml($html_content);
$xpath = new DOMXPath( $html );
$url_info = array();
$langs = $xpath->query( '//html' );
foreach ($langs as $lang)
{
$url_info['language'] = $lang->getAttribute('lang');
}
$metas = $xpath->query( '//meta' );
foreach ($metas as $meta)
{
if ($meta->getAttribute('name'))
{
$url_info[$meta->getAttribute('name')] = $meta->getAttribute('content');
}
}
return $url_info;
}
/**
*
* Alexa rank
* @param string $url
* @return integer
*/
public static function alexa_rank($url)
{
$domain = self::domain_name($url);
$request = "http://data.alexa.com/data?cli=10&dat=s&url=" . $domain;
$data = self::get_html($request);
preg_match('/(About )?([\d,]+) result/si', $data, $l);
return ($l[2]) ? $l[2] : NULL;
}
/**
*
* web of trust rating
* @param string $url
* @reutn integer
*/
public static function WOT_rating($url)
{
$domain = self::domain_name($url);
$request = "http://api.mywot.com/0.4/public_query2?target=" . $domain;
$data = self::get_html($request);
preg_match_all('/
使用范例
立即学习“PHP免费学习笔记（深入）”；
