php利用phpword读取word

1. 本次案例使用的phpword版本0.17.0

1.下载phpword

创建composer.json文件，内容如下,然后找到项目文件夹，cmd执行命令：composer install 下载文件

{
"require": {
"phpoffice/phpword": "v0.17.*"
}
}

2.phpword 重要名词解释

section(部分) : phpword中将word文档分为若干个section(部分)

element(元素) : 每个section包含若干个element(元素)、文本、图片，元素分为文本元素、表格元素、其他（未涉及不做讨论）

textRun(文本元素) : 每个文本集合包含多个文本

text(文本) : 为字符或者图片

table(表格元素) : 每个表格元素包含多个行 row

row(行) : 每个行包含多个列 cell

cell(列) : 每个列包含多个textRun(文本元素) 这里没错，就是包含多个文本元素（表格元素也可以但是没人在word表格的某一个格里再来一个表格吧）

各个节点之间的关系图

3.执行代码

<?php
/*** Created by PhpStorm.* User: chengyanping* Date: 2021/5/19* Time: 13:14*/
require_once './vendor/autoload.php';
ini_set('display_errors', true);
ini_set('max_execution_time', '0');
error_reporting(E_ALL ^ E_WARNING ^ E_NOTICE);class WordService
{public  function importWord($info){$word  = self::getWord($info);
//        print_r($word);return $word;}/*** 获取word文档内容* @param string $path* @return array*/public static function getWord($path = ''){//加载word文档，使用phpword处理$phpWord = \PhpOffice\PhpWord\IOFactory::load($path);//        print_R($phpWord);exit();return self::getNodeContent($phpWord);}/*** 根据word主节点获取分节点内容* @param $word* @return array*/public static function getNodeContent($word){$return = [];//分解部分foreach ($word->getSections() as $section){if ($section instanceof \PhpOffice\PhpWord\Element\Section) {//分解元素foreach ($section->getElements() as $element){//文本元素if ($element instanceof \PhpOffice\PhpWord\Element\TextRun) {$text = '';foreach ($element->getElements() as $ele) {$text .= self::getTextNode($ele);}$return[] = $text;}//表格元素else if ($element instanceof \PhpOffice\PhpWord\Element\Table) {foreach ($element->getRows() as $ele){$return[] = self::getTableNode($ele);}}//保留文本元素else if ($element instanceof \PhpOffice\PhpWord\Element\PreserveText) {//当是预留文本的时候$text='';foreach ($element->getText() as $ele=>$value){$text .= $value;}$return[] = $text;}}}}return $return;}/*** 获取文档节点内容* @param $node* @return string*/public static function getTextNode($node){$return = '';//处理文本if ($node instanceof \PhpOffice\PhpWord\Element\Text){$return .= $node->getText();}//处理图片else if ($node instanceof \PhpOffice\PhpWord\Element\Image){$return .= self::pic2text($node);}//处理文本元素else if ($node instanceof \PhpOffice\PhpWord\Element\TextRun) {foreach ($node->getElements() as $ele) {$return .= self::getTextNode($ele);}}//处理保留文本else if ($node instanceof \PhpOffice\PhpWord\Element\PreserveText) {$return .= $node->getText();}return $return;}/*** 获取表格节点内容* @param $node* @return string*/public static function getTableNode($node){$return = '';//处理行if ($node instanceof \PhpOffice\PhpWord\Element\Row) {foreach ($node->getCells() as $ele){$return .= self::getTableNode($ele);}}//处理列else if ($node instanceof \PhpOffice\PhpWord\Element\Cell) {foreach ($node->getElements() as $ele){$return .= self::getTextNode($ele);}}return $return;}/*** 处理word文档中base64格式图片* @param $node* @return string*/public static function pic2text($node){//获取图片编码$imageData = $node->getImageStringData(true);//添加图片html显示标头$imageData = 'data:' . $node->getImageType() . ';base64,' . $imageData;$return = '<img src="'.$imageData.'">';return $return;}/*** 处理word文档中base64格式图片* @param $node* @return string*/public static function pic2file($node){//图片地址(一般为word文档地址+在word中的锚点位置)$imageSrc  = 'images/' . md5($node->getSource()) . '.' . $node->getImageExtension();$imageData = $node->getImageStringData(true);//将图片保存在本地file_put_contents($imageSrc, base64_decode($imageData));return $imageSrc;}/*** 将word转化为html(转换存储html文件后展示)* @param $path* @throws \PhpOffice\PhpWord\Exception\Exception*/public static function word2html($path){$phpWord = FileImportService::getOne($path);//转为html处理$xmlWriter  = \PhpOffice\PhpWord\IOFactory::createWriter($phpWord, "HTML");$path = pathinfo($path);$fileName = $path['dirname'] . '/' . $path['filename'] . '.html';$xmlWriter->save($fileName);$html = file_get_contents($fileName);echo $html;die;}public function deleteFile($filePath){if (file_exists($filePath)) {$tt=unlink($filePath);return $tt;}else {return false;}}}

参考文献：1.https://github.com/PHPOffice/PHPWord

2.https://phpword-zh.readthedocs.io/zh_CN/latest/intro.html

参考文章：https://www.cnblogs.com/haizizhu/p/13808155.html