php实现专业获取网站SEO信息类实例


Posted in PHP onApril 02, 2015

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

<?php
/**
 *
 * SEO report for different metrics
 *
 * @category SEO
 * @author Chema <chema@garridodiaz.com>
 * @copyright (c) 2009-2012 Open Classifieds Team
 * @license GPL v3
 * Based on seo report script http://www.phpeasycode.com && 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('/<POPULARITY URL="(.*?)" TEXT="([\d]+)"\/>/si', $data, $p);
    return ($l[2]) ? $l[2] : NULL;
  }
  /**
   *
   * Alexa inbounds link
   * @param string $url
   * @return integer
   */
  public static function alexa_links($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('/<LINKSIN NUM="([\d]+)"\/>/si', $data, $l);
    return ($l[1]) ? $l[1] : NULL;
  }
  /**
   * Returns total amount of results for any Google search,
   * requesting the deprecated Websearch API.
   *
   * @param    string    $query   String, containing the search query.
   * @return    integer          Returns a total count.
   */
  public static function google_pages($url)
  {
    //$query = self::domain_name($url);
    $url = 'http://ajax.googleapis.com/ajax/services/search/web?v=1.0&rsz=1&q='.$url;
    $str = self::get_html($url);
    $data = json_decode($str);
    return (!isset($data->responseData->cursor->estimatedResultCount))
        ? '0'
        : intval($data->responseData->cursor->estimatedResultCount);
  }
  /**
   *
   * gets the inbounds links from a site
   * @param string $url
   * @param integer
   */
  public static function google_links($url)
  {
    $request   = "http://www.google.com/search?q=" . urlencode("link:" . $url) . "&hl=en";
    $data     = self::get_html($request);
    preg_match('/<div id=resultStats>(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('/<application name="(\d+)" r="(\d+)" c="(\d+)"\/>/si', $data, $regs);
    $trustworthiness = ($regs[2][0]) ? $regs[2][0] : NULL;
    return (is_numeric($trustworthiness))? $trustworthiness:NULL;
  }
   
  /**
   *
   * how old is the domain?
   * @param string $domain
   * @return integer unixtime
   */
  public static function domain_age($domain)
  {
    $request = "http://reports.internic.net/cgi/whois?whois_nic=" . $domain . "&type=domain";
    $data   = self::get_html($request);
    preg_match('/Creation Date: ([a-z0-9-]+)/si', $data, $p);
    return (!$p[1])?FALSE:strtotime($p[1]);
  }
  /**
   *
   * counts how many tweets about the url
   * @param string $url
   * @return integer
   */
  public static function tweet_count($url)
  {
    $url = urlencode($url);
    $twitterEndpoint = "http://urls.api.twitter.com/1/urls/count.json?url=%s";
    $fileData = file_get_contents(sprintf($twitterEndpoint, $url));
    $json = json_decode($fileData, true);
    unset($fileData);        // free memory
    return (is_numeric($json['count']))? $json['count']:NULL;
  }
  /**
   * Returns the total amount of Facebook Shares for a single page
   *
   * @link     https://graph.facebook.com/
   * @param     string   The URL to check.
   * @return    integer  Returns the total amount of Facebook
   */
  public static function facebook_shares($q)
  {
    //Execution and result of Json
    $str = self::get_html('http://graph.facebook.com/?id='.urlencode($q));
    $data = json_decode($str);
    //Return only number of facebook shares
    $r = $data->shares;
    return ($r != NULL) ? $r : intval('0');
  }
  /**
   *
   * get the pagespeed rank over 100
   * @param string $url
   * @return integer
   */
  public static function page_speed($url)
  {
    $url = 'https://developers.google.com/_apps/pagespeed/run_pagespeed?url='.$url.'&format=json';
    $str = self::get_html($url);
    $data = json_decode($str);
    return intval($data->results->score);
  }
  /**
   *
   * get google page rank
   * @param string $url
   * @return integer
   */
  public static function page_rank($url)
  {
     $query = "http://toolbarqueries.google.com/tbr?client=navclient-auto&ch=".self::CheckHash(self::HashURL($url)). "&features=Rank&q=info:".$url."&num=100&filter=0";
      $data = self::get_html($query);//die(print_r($data));
    $pos  = strpos($data, "Rank_");
    if($pos === false)
    {
      return NULL;
    }
    else
    {
      $pagerank = substr($data, $pos + 9);
      return $pagerank;
    }
  }
  // functions for google pagerank
  /**
   * To calculate PR functions
   */
  public static function StrToNum($Str, $Check, $Magic)
  {
    $Int32Unit = 4294967296; // 2^32
    $length = strlen($Str);
    for ($i = 0; $i < $length; $i++) {
      $Check *= $Magic;
      //If the float is beyond the boundaries of integer (usually +/- 2.15e+9 = 2^31),
      // the result of converting to integer is undefined
      // refer to http://www.php.net/manual/en/language.types.integer.php
      if ($Check >= $Int32Unit) {
        $Check = ($Check - $Int32Unit * (int) ($Check / $Int32Unit));
        //if the check less than -2^31
        $Check = ($Check < -2147483648) ? ($Check + $Int32Unit) : $Check;
      }
      $Check += ord($Str{$i});
    }
    return $Check;
  }
  /**
   * Genearate a hash for a url
   */
  public static function HashURL($String)
  {
    $Check1 = self::StrToNum($String, 0x1505, 0x21);
    $Check2 = self::StrToNum($String, 0, 0x1003F);
    $Check1 >>= 2;
    $Check1 = (($Check1 >> 4) & 0x3FFFFC0 ) | ($Check1 & 0x3F);
    $Check1 = (($Check1 >> 4) & 0x3FFC00 ) | ($Check1 & 0x3FF);
    $Check1 = (($Check1 >> 4) & 0x3C000 ) | ($Check1 & 0x3FFF);
    $T1 = (((($Check1 & 0x3C0) << 4) | ($Check1 & 0x3C)) <<2 ) | ($Check2 & 0xF0F );
    $T2 = (((($Check1 & 0xFFFFC000) << 4) | ($Check1 & 0x3C00)) << 0xA) | ($Check2 & 0xF0F0000 );
    return ($T1 | $T2);
  }
  /**
   * genearate a checksum for the hash string
   */
  public static function CheckHash($Hashnum)
  {
    $CheckByte = 0;
    $Flag = 0;
    $HashStr = sprintf('%u', $Hashnum) ;
    $length = strlen($HashStr);
    for ($i = $length - 1; $i >= 0; $i --) {
      $Re = $HashStr{$i};
      if (1 === ($Flag % 2)) {
        $Re += $Re;
        $Re = (int)($Re / 10) + ($Re % 10);
      }
      $CheckByte += $Re;
      $Flag ++;
    }
    $CheckByte %= 10;
    if (0 !== $CheckByte) {
      $CheckByte = 10 - $CheckByte;
      if (1 === ($Flag % 2) ) {
        if (1 === ($CheckByte % 2)) {
          $CheckByte += 9;
        }
        $CheckByte >>= 1;
      }
    }
    return '7'.$CheckByte.$HashStr;
  }
}

使用范例

<?php
include 'seoreport.php';
ini_set('max_execution_time', 180);
  $url = (isset($_GET['url']))?$_GET['url']:'http://phpclasses.org';
  $meta_tags = seoreport::meta_info($url);
  //die(var_dump($meta_tags));
  //first check if site online
  if ($meta_tags!==FALSE)
  {
    $stats = array();
    $stats['meta'] = $meta_tags;
    $stats['alexa']['rank'] = seoreport::alexa_rank($url);
    $stats['alexa']['links'] = seoreport::alexa_links($url);
    $stats['domain']['WOT_rating'] = seoreport::WOT_rating($url);  
    $stats['domain']['domain_age'] = seoreport::domain_age($url);  
    $stats['social']['twitter'] = seoreport::tweet_count($url);  
    $stats['social']['facebook'] = seoreport::facebook_shares($url);
    $stats['google']['page_rank'] = seoreport::page_rank($url);
    $stats['google']['page_speed'] = seoreport::page_speed($url);
    $stats['google']['pages'] = seoreport::google_pages($url);
    $stats['google']['links'] = seoreport::google_links($url);
    var_dump($stats);
  }
  else 'Site not online. '.$url;

希望本文所述对大家的php程序设计有所帮助。

PHP 相关文章推荐
PHP与MySQL开发中页面出现乱码的一种解决方法
Jul 29 PHP
PHP JSON格式数据交互实例代码详解
Jan 13 PHP
php中explode与split的区别介绍
Oct 03 PHP
PHP加密3DES报错 Call to undefined function: mcrypt_module_open() 如何解决
Apr 17 PHP
Yii中的cookie的发送和读取
Jul 27 PHP
php实现背景图上添加圆形logo图标的方法
Nov 17 PHP
Yii框架实现图片上传的方法详解
May 20 PHP
phpcms配置列表页以及获得文章发布时间
Jul 04 PHP
php实现基于pdo的事务处理方法示例
Jul 21 PHP
PHP封装的数据库模型Model类完整示例【基于PDO】
Mar 14 PHP
Yii框架模拟组件调用注入示例
Nov 11 PHP
PHP获取当前时间不准确问题解决方案
Aug 14 PHP
php获得网站访问统计信息类Compete API用法实例
Apr 02 #PHP
php实现从上传文件创建缩略图的方法
Apr 02 #PHP
php调用KyotoTycoon简单实例
Apr 02 #PHP
PHP中数据类型转换的三种方式
Apr 02 #PHP
php在apache环境下实现gzip配置方法
Apr 02 #PHP
PHP中使用socket方式GET、POST数据实例
Apr 02 #PHP
php获取百度收录、百度热词及百度快照的方法
Apr 02 #PHP
You might like
简单易用的计数器(数据库)
2006/10/09 PHP
制作特殊字的脚本
2006/06/26 Javascript
jQuery的链式调用浅析
2010/12/03 Javascript
Ext JS 4官方文档之三 -- 类体系概述与实践
2012/12/16 Javascript
为什么要在引入的css或者js文件后面加参数的详细讲解
2013/05/03 Javascript
在服务端(Page.Write)调用自定义的JS方法详解
2013/08/09 Javascript
JavaScript中实现异步编程模式的4种方法
2014/09/24 Javascript
javascript获取元素离文档各边距离的方法
2015/02/13 Javascript
jQuery带时间的日期控件代码分享
2015/08/26 Javascript
JavaScript function函数种类详解
2016/02/22 Javascript
JS及PHP代码编写八大排序算法
2016/07/12 Javascript
浅谈JS正则表达式的RegExp对象和括号的使用
2016/07/28 Javascript
利用jquery禁止外层滚动条的滚动
2017/01/05 Javascript
Angular2使用Augury来调试Angular2程序
2017/05/21 Javascript
详解angularjs popup-table 弹出框表格指令
2017/09/20 Javascript
了解ESlint和其相关操作小结
2018/05/21 Javascript
详解在Node.js中发起HTTP请求的5种方法
2019/01/10 Javascript
vue 需求 data中的数据之间的调用操作
2020/08/05 Javascript
如何使用 JavaScript 操作浏览器历史记录 API
2020/11/24 Javascript
[43:57]LGD vs Mineski 2018国际邀请赛小组赛BO2 第二场 8.19
2018/08/21 DOTA
[49:58]完美世界DOTA2联赛PWL S3 Magma vs DLG 第一场 12.18
2020/12/19 DOTA
Python装饰器模式定义与用法分析
2018/08/06 Python
python pandas cumsum求累计次数的用法
2019/07/29 Python
Windows 下python3.8环境安装教程图文详解
2020/03/11 Python
scrapy与selenium结合爬取数据(爬取动态网站)的示例代码
2020/09/28 Python
Python可视化工具如何实现动态图表
2020/10/23 Python
Spartoo比利时:欧洲时尚购物网站
2017/12/06 全球购物
家乐福台湾线上购物网:Carrefour台湾
2020/09/15 全球购物
写给保洁员表扬信
2014/01/08 职场文书
优良学风班总结材料
2014/02/08 职场文书
办公设备采购方案
2014/03/16 职场文书
合作意向书格式及范文
2014/03/31 职场文书
小学模范班主任事迹材料
2014/05/13 职场文书
初三毕业感言
2015/07/31 职场文书
Python列表删除重复元素与图像相似度判断及删除实例代码
2021/05/07 Python
JS前端可扩展的低代码UI框架Sunmao使用详解
2022/07/23 Javascript