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<p>标签和<ol>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})|.{4};|\d+;|.+/u",$str,$r);
 $ar = $r[0];
 foreach($ar as $k=>$v) {
 if(substr($v,0,2) == "%u"){
 $ar[$k] = iconv("ucs-2be","utf-8",pack("h4",substr($v,-4)));
 }
 elseif(substr($v,0,3) == ""){
 $ar[$k] = iconv("ucs-2be","utf-8",pack("h4",substr($v,3,-1)));
 }
 elseif(substr($v,0,2) == ""){
 $ar[$k] = iconv("ucs-2be","utf-8",pack("n",substr($v,2,-1)));
 }
 }
 return join("",$ar);
}
 /**
 * 图片下载
 * @param $src 目标资源
 * @param $urlarr 目标url对应的数组
 * **/
 private function getimagefromnet($src,$urlarr)
 {
 $file = basename($urlarr['path']);
 $ext = explode('.',$file);
 $this->imgdir = $this->currentdir."/".$urlarr['host'];
 $_supportedimagetypes = array('jpg', 'jpeg', 'gif', 'png', 'bmp', 'tif', 'tiff');
 if(isset($ext['1']) && in_array($ext['1'],$_supportedimagetypes))
 {
 $file = file_get_contents($src);
 $this->httprequestarr[] = $src;
 $this->httprequesttime++;
 $this->_mkdir(); //创建目录，或者收集错误
 $imgname = md5($urlarr['path']).".".$ext['1'];
 file_put_contents($this->imgdir."/".$imgname,$file);
 $this->downimg++;
 return $urlarr['host']."/".$imgname;
 }
 return false;
 }
 /**
 * 创建目录
 * **/
 private function _mkdir()
 {
 if(!is_dir($this->imgdir))
 {
 if(!mkdir($this->imgdir,"7777"))
 {
 $this->error[] = error_get_last();
 }
 }
 }
 /**
 * 构造worddom
 * **/
 private function createworddom()
 {
 $phpword = new phpword();
 $phpword->setdefaultfontname('宋体');
 $phpword->setdefaultfontsize("11");
 $styletable = array('bordersize'=>6, 'bordercolor'=>'006699', 'cellmargin'=>120);
 // new portrait section
 $section = $phpword->createsection();
 $section->addtext($this->details(),array(),array('spacing'=>120));
 //数据进行处理
 foreach($this->linetextarr as $key=>$linearr)
 {
 if(isset($linearr['tag']))
 {
 if($linearr['tag'] == "li")
 {
 $section->addlistitem($linearr['text'],0,"","",array('spacing'=>120));
 }
 else if($linearr['tag'] == "img")
 {
 $section->addimage($linearr['src'],array('width'=>$linearr['width'], 'height'=>$linearr['height'], 'align'=>'center'));
 }
 else if($linearr['tag'] == "p")
 {
 $section->addtext($linearr['text'],array(),array('spacing'=>120));
 }
 }
 else if($key == "table")
 {
 $phpword->addtablestyle('myowntablestyle', $styletable);
 $table = $section->addtable("myowntablestyle");
 foreach($linearr as $key=>$tr)
 {
 $table->addrow();
 foreach($tr as $ky=>$td)
 {
 $table->addcell(2000)->addtext($td['text']);
 }
 }
 }
 }
 $this->downfile($phpword);
 }
 public function details()
 {
 $msg = "一共请求:{$this->httprequesttime}次,共下载的图片有{$this->downimg}张,并且下载完成大约使用时间:{$this->expendtime}秒,整个程序执行大约消耗内存是:{$this->expendmemory}kb,";
 return $msg;
 }
 public function downfile($phpword)
 {
 if(empty($this->filename))
 {
 $urlarr = parse_url($this->url);
 $this->filename = $urlarr['host'].".docx";
 }
 // save file
 $objwriter = phpword_iofactory::createwriter($phpword, 'word2007');
 $objwriter->save($this->filename);
 header("pragma: public");
 header("expires: 0");
 header("cache-control: must-revalidate, post-check=0, pre-check=0");
 header("cache-control: public");
 header("content-description: file transfer");
 //use the switch-generated content-type
 header('content-type: application/msword');//输出的类型
 //force the download
 $header="content-disposition: attachment; filename=".$this->filename.";";
 header($header);
 @readfile($this->filename);
 }
}

上面的代码重点感觉不是word生成，而是simplehtmldom的使用，这是一个开源的html解析器，之前有提到，这几天在看他的代码，

引出了两个学习方向

① 正在表达式

② 这个扩展的函数整理

看源代码的收获：

php的异常是可以捕获的，而且php的错误也是可以捕获的。

error_get_last() //用这个函数可以捕获页面中的php错误，不谢。

更多关于php相关内容感兴趣的读者可查看本站专题：《php操作office文档技巧总结(包括word,excel,access,ppt)》、《php数组(array)操作技巧大全》、《php排序算法总结》、《php常用遍历算法与技巧总结》、《php数据结构与算法教程》、《php程序设计算法总结》、《php数学运算技巧总结》、《php正则表达式用法总结》、《php运算与运算符用法总结》、《php字符串(string)用法总结》及《php常见数据库操作技巧汇总》

希望本文所述对大家php程序设计有所帮助。