php实现将HTML页面转换成word并且保存的方法

本文实例讲述了php实现将HTML页面转换成word并且保存的方法。分享给大家供大家参考，具体如下：

这里用使用到一个PHP的工具叫：PHPWord。

生成Word的原理是，将堆规定好了的xml压缩成一个zip包，并且把后缀名改成doc或者docx即可。

所以使用PHPWord，需要你的PHP环境安装zip.dll压缩扩展，我写了一个demo.

功能说明：

20150507 ― HTML中的

标签和

列表标签的获取
20150508 ― 新增获取文章中的图片功能
20150509 ― 新增行间距，并且过滤一下错误图片
20150514 ― 新增表格处理，并且将代码改成面向对象
20150519 ― 新增GD库处理网络图片

    require_once 'PHPWord.php';
    require_once 'SimpleHtmlDom.class.php';
    class Word{
     private $url;
     private $LinetextArr = array();
     public $CurrentDir;
     public $error = array(); //错误数组
     public $filename = null;
     public $Allowtag = "p,ol,ul,table";
     /**数据统计**/
     public $DownImg = 0;
     public $expendTime = 0;
     public $HttpRequestTime = 0;
     public $ContentLen = 0;
     public $HttpRequestArr = array();
     public $expendmemory = 0;
     public function __construct($url)
     {
     $startTime = $this->_Time();
     $startMemory = $this->_memory();
     $this->url = $url;
     $UrlArr = parse_url($this->url);
     $this->host = $UrlArr["scheme"]."://".$UrlArr['host'];
     $this->CurrentDir = getcwd();
     $this->LinetextArr["table"] = array();
     $html = new simple_html_dom($this->url);
     $this->HttpRequestArr[] = $this->url;
     $this->HttpRequestTime++;
     foreach($html->find($this->Allowtag) as $key=>$value)
     {
     if($value->tag == "table")
     {
     $this->ParseTable($value,0,$this->LinetextArr["table"]);
     }
     else
     {
     $this->AnalysisHtmlDom($value);
     }
     $this->error[] = error_get_last();
     }
     $endTime = $this->_Time();
     $endMemory = $this->_memory();
     $this->expendTime = round(($endTime-$startTime),2); //微秒
     $this->expendmemory = round(($endMemory-$startMemory)/1000,2); //bytes
     $this->CreateWordDom();
     }
     private function _Time()
     {
     return array_sum(explode(" ", microtime()));
     }
     private function _memory()
     {
     return memory_get_usage();
     }
     /**
     * 解析HTML中的Table,这里考虑到多层table嵌套的情况
     * @param $value HTMLDOM
     * @param $i 遍历层级
     * **/
     private function ParseTable($value,$i,$Arr)
     {
     if($value->firstChild() && in_array($value->firstChild()->tag,array("table","tbody","thead","tfoot","tr")))
     {
     foreach($value->children as $k=>$v)
     {
     $this->ParseTable($v,$i++,$Arr);
     }
     }
     else
     {
     foreach($value->children as $k=>$v)
     {
     if($v->firstChild() && $v->firstChild()->tag != "table")
     {
     $Arr[$i][] = array("tag"=>$v->tag,"text"=>trim($v->plaintext));
     }
     if(!$v->firstChild())
     {
     $Arr[$i][] = array("tag"=>$v->tag,"text"=>trim($v->plaintext));
     }
     }
     }
     }
     /**
     * 解析HTML里面的表情
     * @param $value HTMLDOM
     * **/
     private function AnalysisHtmlDom($value)
     {
     $tmp = array();
     if($value->has_child())
     {
     foreach($value->children as $k=>$v)
     {
     $this->AnalysisHtmlDom($v);
     }
     }
     else
     {
     if($value->tag == "a")
     {
     $tmp = array("tag"=>$value->tag,"href"=>$value->href,"text"=>$value->innertext);
     }
     else if($value->tag == "img")
     {
     $src = $this->unescape($value->src);
     $UrlArr = parse_url($src);
     if(!isset($UrlArr['host']))
     {
     $src = $this->host.$value->src;
     $UrlArr = parse_url($src);
     }
     $src = $this->getImageFromNet($src,$UrlArr); //表示有网络图片，需要下载
     if($src)
     {
      $imgsArr = $this->GD($src);
      $tmp = array("tag"=>$value->tag,"src"=>$src,"text"=>$value->alt,"width"=>$imgsArr['width'],"height"=>$imgsArr['height']); }
     }
     else
     {
     $tmp = array("tag"=>$value->tag,"text"=>strip_tags($value->innertext));
     }
     $this->LinetextArr[] = $tmp;
     }
     }
     /**
     * 根据GD库来获取图片的如果太多，进行比例压缩
     * **/
     private function GD($src)
     {
     list($width, $height, $type, $attr) = getimagesize($src);
     if($width > 800 || $height > 800 )
     {
     $width = $width/2;
     $height = $height/2;
     }
     return array("width"=>$width,"height"=>$height);
     }
     /**
     * 将Uincode编码转移回原来的字符
     * **/
     public function unescape($str) {
     $str = rawurldecode($str);
     preg_match_all("/(?:%u.{4})|&#