url:http://www.dengwz.com/project/new/application/index/model/ini_news_parser.class.php 将HTML页面转行成word并且保存 – PHP研发工程师_小邓PHP博客
小邓博客,一位正在奋斗的PHP开发工程师的学习经历分享!为高效PHP开发而努力奋斗

将HTML页面转行成word并且保存

PHP dengwz7788 2871℃ 0评论

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.

Deom演示:http://www.dengwz.com/phpword/  往里面贴一个URL就可以了

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

[php]

 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})|&#x.{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) == "&#x"){

$ar[$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);
}
}

[/php]

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。

[php]

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

[/php]

转载请注明:PHP研发工程师_小邓PHP博客 » 将HTML页面转行成word并且保存

喜欢 (7)or分享 (0)
发表我的评论
取消评论

表情

Hi,您需要填写昵称和邮箱!

  • 昵称 (必填)
  • 邮箱 (必填)
  • 网址