PHP将上传word文件，转化为Html格式，(多种转换方式)

方法一: 通过PHPOffice（推荐）

1: composer require phpoffice/phpword
/* 通过composer安装 PHPOffice 需要 或者用中国镜像:https://www.phpcomposer.com/ */
2: 安装成功可看到 vendor文件夹

3: 使用方法 :
<?php require 'vendor/autoload.php'; $phpWord = \PhpOffice\PhpWord\IOFactory::load('./4.docx'); $xmlWriter = \PhpOffice\PhpWord\IOFactory::createWriter($phpWord, "HTML"); $xmlWriter ->save('./ceshi.htm');

4:官方
/*
官方案例:https://phpword.readthedocs.io/en/latest/general.html
github: https://github.com/PHPOffice/PhpSpreadsheet
*/

方法二：通过python

```
from win32com import client as wc
import sys

def saveHtm():
# print(wordPath)
# print(htmPath)
wordPath='E:/1.doc'
htmPath='E:/1.htm'
word = wc.Dispatch('Word.Application')
print(word)
doc = word.Documents.Open('E:/1.doc')
doc.SaveAs("E:/1.htm", 8) //转化为htm格式
doc.SvaeAs("E:/1.fpt",17)

doc.Close()
word.Quit()

if name == 'main':
saveHtm()
```

方法三：同时Offic API直接在网页显示word文档

```

例
src="http://view.officeapps.live.com/op/view.aspxsrc=newteach.pbworks.com%2Ff%2Fele%2Bnewsletter.docx"

方法四:通过com组件

需要所在宿主机，有offic的环境，Linxu下不能使用
 
（不推荐）

<?php
/**
 * @desc   xmsb_wordToPdf         将word转换为pdf
 * @param  string    $wordPath    word原文件路径
 * @param  string    $outPath     pdf输出路径
 * @return string
 */
function xmsb_wordToPdf($wordPath, $outPath)
{
    // 原文件不存在则返回错误
    if(!file_exists($wordPath)) 
    {
        return 'word原文件不存在';
    }
    
    // 输出目录不存在则创建目录
    if(!file_exists($tmpPath = rtrim($outPath, basename($outPath))))
    {
        mkdir($tmpPath, 0777, true);
    }
    
    $filenamedoc = dirname(__FILE__)."/".$wordPath;
    $filenamepdf = dirname(__FILE__)."/".$outPath;
    
    // 删除已有同名文件
    if(file_exists($filenamepdf)) 
    {
        unlink($filenamepdf);
    }
    
    // 执行转换操作
    $word = new COM("word.Application") or die("Could not initialise Object");
    $word->Documents->Open($filenamedoc);
    $word->ActiveDocument->ExportAsFixedFormat($filenamepdf, 17, false, 0, 0, 0, 0, 7, true, true, 2, true, true, false);
    $word->Quit(false);
    unset($word);
    
    // 在页面中显示生成的pdf
    // header('Content-type: application/pdf');
    // header('filename='.$filenamepdf);
    // readfile($filenamepdf);
    
    return '转换成功';
}

// 测试运行
// echo xmsb_wordToPdf('./word/word1.docx', './pdf/output1.pdf');

function word2html($wordname,$htmlname)  
{  
    $word = new COM("word.application") or die("Unable to instanciate Word");  
    $word->Visible = 1;  
    $word->Documents->Open($wordname);  
    $word->Documents[1]->SaveAs($htmlname,8);  
    $word->Quit();  
    $word = null;  
    unset($word);  
    return '转换成功';
}  
 
// word2html('./word/cs.docx', './pdf/cs.html'); 

require 'vendor/autoload.php';

function changehtml($word,$htmlname,$url){
    $phpWord = \PhpOffice\PhpWord\IOFactory::load($word);

    //增加图片
    $image = __DIR__.$url;
    
    $section = $phpWord->addSection();
    $section->addImage($image,array("width"=>100,"height"=>100,"position"=>"absolute","bottom"=>"0px"));

    $xmlWriter = \PhpOffice\PhpWord\IOFactory::createWriter($phpWord, "HTML");
    $xmlWriter ->save($htmlname);
}

changehtml('./word/wo.docx', './pdf/wo.html','./word/gz.png'); 
?>

转载:https://blog.csdn.net/weixin_42971363/article/details/101156195