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
实现树状结构的两种方法
Oct 09 PHP
php下实现在指定目录搜索指定类型文件的函数
Oct 03 PHP
Apache+php+mysql在windows下的安装与配置图解(最新版)
Nov 30 PHP
php面向对象全攻略 (十五) 多态的应用
Sep 30 PHP
php生成随机密码的几种方法
Jan 17 PHP
深入掌握include_once与require_once的区别
Jun 17 PHP
彻底删除thinkphp3.1案例blog标签的方法
Dec 05 PHP
在Windows系统下使用PHP生成Word文档的教程
Jul 03 PHP
PHP模板引擎Smarty内建函数foreach,foreachelse用法分析
Apr 11 PHP
PHP文件下载实例代码浅析
Aug 17 PHP
php检测mysql表是否存在的方法小结
Jul 20 PHP
弹出模态框modal的实现方法及实例
Sep 19 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 无限级分类学习参考之对ecshop无限级分类的解析 带详细注释
2010/03/23 PHP
简单了解WordPress开发中update_option()函数的用法
2016/01/11 PHP
php上传大文件设置方法
2016/04/14 PHP
Yii2结合Workerman的websocket示例详解
2018/09/10 PHP
javascript showModalDialog 内跳转页面的问题
2010/11/25 Javascript
js 判断控件获得焦点的示例代码
2014/03/04 Javascript
javascript中使用正则计算中文长度的例子
2014/04/29 Javascript
javascript单例模式的简单实现方法
2015/07/25 Javascript
详解JavaScript中jQuery和Ajax以及JSONP的联合使用
2015/08/13 Javascript
JavaScrip常见的一些算法总结
2015/12/28 Javascript
基于MVC5和Bootstrap的jQuery TreeView树形控件(一)之数据支持json字符串、list集合
2016/08/11 Javascript
原生js实现放大镜
2017/02/20 Javascript
react-native之ART绘图方法详解
2017/08/08 Javascript
vue-cli3 karma单元测试的实现
2019/01/18 Javascript
JavaScript强制类型转换和隐式类型转换操作示例
2019/05/01 Javascript
微信小程序云开发使用方法新手初体验
2019/05/16 Javascript
vue多页面项目中路由使用history模式的方法
2019/09/23 Javascript
[02:46]完美世界DOTA2联赛PWL DAY4集锦
2020/11/03 DOTA
Python数据结构之顺序表的实现代码示例
2017/11/15 Python
python字符串的方法与操作大全
2018/01/30 Python
python读出当前时间精度到秒的代码
2019/07/05 Python
python字符串格式化方式解析
2019/10/19 Python
详解Python实现进度条的4种方式
2020/01/15 Python
利用Tensorflow的队列多线程读取数据方式
2020/02/05 Python
keras中的loss、optimizer、metrics用法
2020/06/15 Python
Amara德国:家居饰品、设计师品牌和豪华礼品
2019/05/20 全球购物
职业规划书如何设计?
2014/01/09 职场文书
采购部经理岗位职责
2014/02/10 职场文书
争先创优公开承诺书
2014/08/30 职场文书
商铺门面租房协议书
2014/10/21 职场文书
初婚初育证明范本
2014/11/24 职场文书
2014年优秀班主任工作总结
2014/12/16 职场文书
山楂树之恋观后感
2015/06/11 职场文书
幼儿园秋季开学通知
2015/07/16 职场文书
毕业感言怎么写
2015/07/31 职场文书
辞职信怎么写?
2019/05/21 职场文书