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的单引号和双引号 字符串效率
May 27 PHP
php foreach 参数强制类型转换的问题
Dec 10 PHP
PHP多进程编程实例
Oct 15 PHP
PHP图片处理之使用imagecopy函数添加图片水印实例
Nov 19 PHP
PHP array_key_exists检查键名或索引是否存在于数组中的实现方法
Jun 13 PHP
简单解决微信文章图片防盗链问题
Dec 17 PHP
PHP两种实现无级递归分类的方法
Mar 02 PHP
PHP SFTP实现上传下载功能
Jul 26 PHP
laravel实现分页样式替换示例代码(增加首、尾页)
Sep 22 PHP
浅析PHP中的闭包和匿名函数
Dec 25 PHP
PHP基于SPL实现的迭代器模式示例
Apr 22 PHP
laravel框架如何设置公共头和公共尾
Oct 22 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
PHP获取MAC地址的函数代码
2011/09/11 PHP
php基础教程
2015/08/26 PHP
PHP在线书签系统分享
2016/01/04 PHP
微信开发之获取JSAPI TICKET
2017/07/07 PHP
Nigma vs AM BO3 第一场2.13
2021/03/10 DOTA
innerhtml用法 innertext用法 以及innerHTML与innertext的区别
2009/10/26 Javascript
jquery 弹出层注册页面等(asp.net后台)
2010/06/17 Javascript
Web开发之JavaScript
2012/03/29 Javascript
JavaScript 数组详解
2013/10/10 Javascript
js离开或刷新页面检测(且兼容FF,IE,Chrome)
2014/03/05 Javascript
利用jquery操作Radio方法小结
2014/10/20 Javascript
JavaScript文本框脚本编写的注意事项
2016/01/25 Javascript
jQuery实现简单隔行变色的方法
2016/02/20 Javascript
关于JS中setTimeout()无法调用带参函数问题的解决方法
2016/06/21 Javascript
基于jQuery实现淡入淡出效果轮播图
2020/07/31 Javascript
JavaScript适配器模式详解
2017/10/19 Javascript
浅谈MUI框架中加载外部网页或服务器数据的方法
2018/01/31 Javascript
angular中子控制器向父控制器传值的实例
2018/10/08 Javascript
在Web关闭页面时发送Ajax请求的实现方法
2019/03/07 Javascript
vant时间控件使用方法详解
2020/12/24 Javascript
python实现基于信息增益的决策树归纳
2018/12/18 Python
python 通过麦克风录音 生成wav文件的方法
2019/01/09 Python
基于python的itchat库实现微信聊天机器人(推荐)
2019/10/29 Python
keras得到每层的系数方式
2020/06/15 Python
Python内置方法和属性应用:反射和单例(推荐)
2020/06/19 Python
Python中Pyspider爬虫框架的基本使用详解
2021/01/27 Python
6PM官网:折扣鞋、服装及配饰
2018/08/03 全球购物
Java面试题:Java类的Main方法如果是Private将会怎么样
2016/08/18 面试题
秋季运动会加油稿200字
2014/01/11 职场文书
十岁生日家长答谢词
2014/01/17 职场文书
2014学校领导四风对照检查材料思想汇报
2014/09/23 职场文书
自查自纠工作情况报告
2014/10/29 职场文书
2014年行政人事工作总结
2014/12/09 职场文书
活动宣传稿范文
2015/07/23 职场文书
2019关于垃圾分类处理的调查报告
2019/12/26 职场文书
python获取带有返回值的多线程
2022/05/02 Python