《PHP學習：php實現(xiàn)將HTML頁面轉(zhuǎn)換成word并且保存的方法》要點：
本文介紹了PHP學習：php實現(xiàn)將HTML頁面轉(zhuǎn)換成word并且保存的方法，希望對您有用。如果有疑問，可以聯(lián)系我們。
PHP學習本文實例講述了php實現(xiàn)將HTML頁面轉(zhuǎn)換成word并且保存的方法.分享給大家供大家參考,具體如下：
PHP學習這里用使用到一個PHP的工具叫：PHPWord.
PHP學習生成Word的原理是,將堆規(guī)定好了的xml壓縮成一個zip包,并且把后綴名改成doc或者docx即可.
PHP學習所以使用PHPWord,需要你的PHP環(huán)境安裝zip.dll壓縮擴展,我寫了一個demo.
PHP學習功能說明：
PHP學習20150507 ― HTML中的<p>標簽和<ol>列表標簽的獲取
20150508 ― 新增獲取文章中的圖片功能
20150509 ― 新增行間距,并且過濾一下錯誤圖片
20150514 ― 新增表格處理,并且將代碼改成面向?qū)ο?br>
20150519 ― 新增GD庫處理網(wǎng)絡圖片
PHP學習
require_once 'PHPWord.php';
require_once 'SimpleHtmlDom.class.php';
class Word{
private $url;
private $LinetextArr = array();
public $CurrentDir;
public $error = array(); //錯誤數(shù)組
public $filename = null;
public $Allowtag = "p,ol,ul,table";
/**數(shù)據(jù)統(tǒng)計**/
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,這里考慮到多層table嵌套的情況
* @param $value HTMLDOM
* @param $i 遍歷層級
* **/
private function ParseTable($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,$UrlArr); //表示有網(wǎng)絡圖片,需要下載
if($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[] = $tmp;
}
}
/**
* 根據(jù)GD庫來獲取圖片的如果太多,進行比例壓縮
* **/
private function GD($src)
{
list($width, $height, $type, $attr) = getimagesize($src);
if($width > 800 || $height > 800 )
{
$width = $width/2;
$height = $height/2;
}
return array("width"=>$width,"height"=>$height);
}
/**
* 將Uincode編碼轉(zhuǎn)移回原來的字符
* **/
public function unescape($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);
}
/**
* 圖片下載
* @param $Src 目標資源
* @param $UrlArr 目標URL對應的數(shù)組
* **/
private function getImageFromNet($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(); //創(chuàng)建目錄,或者收集錯誤
$imgName = md5($UrlArr['path']).".".$ext['1'];
file_put_contents($this->ImgDir."/".$imgName,$file);
$this->DownImg++;
return $UrlArr['host']."/".$imgName;
}
return false;
}
/**
* 創(chuàng)建目錄
* **/
private function _mkdir()
{
if(!is_dir($this->ImgDir))
{
if(!mkdir($this->ImgDir,"7777"))
{
$this->error[] = error_get_last();
}
}
}
/**
* 構(gòu)造WordDom
* **/
private function CreateWordDom()
{
$PHPWord = new PHPWord();
$PHPWord->setDefaultFontName('宋體');
$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));
//數(shù)據(jù)進行處理
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()
{
$msg = "一共請求:{$this->HttpRequestTime}次,共下載的圖片有{$this->DownImg}張,并且下載完成大約使用時間:{$this->expendTime}秒,整個程序執(zhí)行大約消耗內(nèi)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');//輸出的類型
//Force the download
$header="Content-Disposition: attachment; filename=".$this->filename.";";
header($header);
@readfile($this->filename);
}
}
PHP學習上面的代碼重點感覺不是word生成,而是Simplehtmldom的使用,這是一個開源的HTML解析器,之前有提到,這幾天在看他的代碼,
PHP學習引出了兩個學習方向
PHP學習① 正在表達式
PHP學習② 這個擴展的函數(shù)整理
PHP學習看源代碼的收獲：
PHP學習PHP的異常是可以捕獲的,而且PHP的錯誤也是可以捕獲的.
PHP學習
error_get_last() //用這個函數(shù)可以捕獲頁面中的PHP錯誤,不謝.
PHP學習更多關于PHP相關內(nèi)容感興趣的讀者可查看本站專題：《php操作office文檔技巧總結(jié)(包括word,excel,access,ppt)》、《PHP數(shù)組(Array)操作技巧大全》、《php排序算法總結(jié)》、《PHP常用遍歷算法與技巧總結(jié)》、《PHP數(shù)據(jù)結(jié)構(gòu)與算法教程》、《php程序設計算法總結(jié)》、《PHP數(shù)學運算技巧總結(jié)》、《php正則表達式用法總結(jié)》、《PHP運算與運算符用法總結(jié)》、《php字符串(string)用法總結(jié)》及《php常見數(shù)據(jù)庫操作技巧匯總》
PHP學習希望本文所述對大家PHP程序設計有所幫助.
轉(zhuǎn)載請注明本頁網(wǎng)址：
http://www.snjht.com/jiaocheng/3053.html
