PHP把网页保存为word文件的三种方法 |
一PHP教程成word的两种思路或原理 1.利用windows下面的 com组件 二、利用windows下面的com组件 原理:com作为PHP的一个扩展类,安装过office的服务器会自动调用word.application的com,可以自动生成文档,PHP官方文档手册:http://www.php.net/manual/en/class.com.php 使用官方实例: 复制代码 代码如下: <?php // starting word $word = new COM("word.application") or die("Unable to instantiate Word"); echo "Loaded Word, version {$word->Version}\n"; //bring it to front $word->Visible = 1; //open an empty document $word->Documents->Add(); //do some weird stuff $word->Selection->TypeText("This is a test..."); $word->Documents[1]->SaveAs("Useless test.doc"); //closing word $word->Quit(); //free the object $word = null; ?> 个人建议:com实例后的方法都需要查找官方文档才知道什么意思,编辑器没有代码提示,非常不方便,另外这个效率也不是很高,不推荐使用 三、利用PHP将内容写入doc文件之中 1.生成mht格式(和HTML很相似)写入word
复制代码 代码如下: /**
* 根据HTML代码获取word文档内容 * 创建一个本质为mht的文档,该函数会分析文件内容并从远程下载页面中的图片资源 * 该函数依赖于类MhtFileMaker * 该函数会分析img标签,提取src的属性值 。但是,src的属性值必须被引号包围,否则不能提取 * * @param string $content HTML内容 * @param string $absolutePath 网页的绝对路径 。如果HTML内容里的图片路径为相对路径,那么就需要填写这个参数,来让该函数自动填补成绝对路径 。这个参数最后需要以/结束 * @param bool $isEraseLink 是否去掉HTML内容中的链接 */ function getWordDocument( $content , $absolutePath = "" , $isEraseLink = true ) { $mht = new MhtFileMaker(); if ($isEraseLink) $content = preg_replace(/<a\s*.*?\s*>(\s*.*?\s*)<\/a>/i , $1 , $content); //去掉链接 $images = array(); $files = array(); $matches = array(); //这个算法要求src后的属性值必须使用引号括起来 if ( preg_match_all(/<img[.\n]*?src\s*?=\s*?[\"\](.*?)[\"\](.*?)\/>/i,$content ,$matches ) ) { $arrPath = $matches[1]; for ( $i=0;$i<count($arrPath);$i++) { $path = $arrPath[$i]; $imgPath = trim( $path ); if ( $imgPath != "" ) { $files[] = $imgPath; if( substr($imgPath,0,7) == http://) { //绝对链接,不加前缀 } else { $imgPath = $absolutePath.$imgPath; } $images[] = $imgPath; } } } $mht->AddContents("tmp.html",$mht->GetMimeType("tmp.html"),$content); for ( $i=0;$i<count($images);$i++) { $image = $images[$i]; if ( @fopen($image , r) ) { $imgcontent = @file_get_contents( $image ); if ( $content ) $mht->AddContents($files[$i],$mht->GetMimeType($image),$imgcontent); } else { echo "file:".$image." not exist!<br />"; } } return $mht->GetFile(); } 这个函数的主要功能其实就是分析HTML代码中的所有图片地址,并且依次下载下来 。获取到了图片的内容以后,调用MhtFileMaker类,将图片添加到mht文件中 。具体的添加细节,封装在MhtFileMaker类中了 。 使用方法1:远程调用 复制代码 代码如下: $url= http://www.***.com;
$content = file_get_contents($url); $fileContent = getWordDocument($content,"http://www.yoursite.com/Music/etc/"); $fp = fopen("test.doc", w); fwrite($fp, $fileContent); fclose($fp); 其中,$content变量应该是HTML源代码,后面的链接应该是能填补HTML代码中图片相对路径的URL地址
使用方法2:本地生成调用 复制代码 代码如下: header("Cache-Control: no-cache, must-revalidate"); header("Pragma: no-cache"); $wordStr = PHP教程网站--jb51.net; $fileContent = getWordDocument($wordStr); $fileName = iconv("utf-8", "GBK", ‘PHP教程 . _. $intro . _ . rand(100, 999)); header("Content-Type: application/doc"); header("Content-Disposition: attachment; filename=" . $fileName . ".doc"); echo $fileContent; 注意,在使用这个函数之前,您需要先包含类MhtFileMaker,这个类可以帮助我们生成Mht文档 。 复制代码 代码如下: <?php
/*********************************************************************** Class: Mht File Maker Version: 1.2 beta Date: 02/11/2007 Author: Wudi <wudicgi@yahoo.de> Description: The class can make .mht file. ***********************************************************************/ class MhtFileMaker{ var $config = array(); var $headers = array(); var $headers_exists = array(); var $files = array(); var $boundary; var $dir_base; var $page_first; function MhtFile($config = array()){ } function SetHeader($header){ $this->headers[] = $header; $key = strtolower(substr($header, 0, strpos($header, :))); $this->headers_exists[$key] = TRUE; } function SetFrom($from){ $this->SetHeader("From: $from"); } function SetSubject($subject){ $this->SetHeader("Subject: $subject"); } function SetDate($date = NULL, $istimestamp = FALSE){ if ($date == NULL) { $date = time(); } if ($istimestamp == TRUE) { $date = date(D, d M Y H:i:s O, $date); } $this->SetHeader("Date: $date"); } function SetBoundary($boundary = NULL){ if ($boundary == NULL) { $this->boundary = -- . strtoupper(md5(mt_rand())) . _MULTIPART_MIXED; } else { $this->boundary = $boundary; } } function SetBaseDir($dir){ $this->dir_base = str_replace("\\", "/", realpath($dir)); } function SetFirstPage($filename){ $this->page_first = str_replace("\\", "/", realpath("{$this->dir_base}/$filename")); } function AutoAddFiles(){ if (!isset($this->page_first)) { exit (Not set the first page.); } $filepath = str_replace($this->dir_base, , $this->page_first); $filepath = http://mhtfile . $filepath; $this->AddFile($this->page_first, $filepath, NULL); $this->AddDir($this->dir_base); } function AddDir($dir){ $handle_dir = opendir($dir); while ($filename = readdir($handle_dir)) { if (($filename!=.) && ($filename!=..) && ("$dir/$filename"!=$this->page_first)) { if (is_dir("$dir/$filename")) { $this->AddDir("$dir/$filename"); } elseif (is_file("$dir/$filename")) { $filepath = str_replace($this->dir_base, , "$dir/$filename"); $filepath = http://mhtfile . $filepath; $this->AddFile("$dir/$filename", $filepath, NULL); } } } closedir($handle_dir); } function AddFile($filename, $filepath = NULL, $encoding = NULL){ if ($filepath == NULL) { $filepath = $filename; } $mimetype = $this->GetMimeType($filename); $filecont = file_get_contents($filename); $this->AddContents($filepath, $mimetype, $filecont, $encoding); } function AddContents($filepath, $mimetype, $filecont, $encoding = NULL){ if ($encoding == NULL) { $filecont = chunk_split(base64_encode($filecont), 76); $encoding = base64; } $this->files[] = array(filepath => $filepath, mimetype => $mimetype, filecont => $filecont, encoding => $encoding); } function CheckHeaders(){ if (!array_key_exists(date, $this->headers_exists)) { $this->SetDate(NULL, TRUE); } if ($this->boundary == NULL) { $this->SetBoundary(); } } function CheckFiles(){ if (count($this->files) == 0) { return FALSE; } else { return TRUE; } } function GetFile(){ $this->CheckHeaders(); if (!$this->CheckFiles()) { exit (No file was added.); } $contents = implode("\r\n", $this->headers); $contents .= "\r\n"; $contents .= "MIME-Version: 1.0\r\n"; $contents .= "Content-Type: multipart/related;\r\n"; $contents .= "\tboundary=\"{$this->boundary}\";\r\n"; $contents .= "\ttype=\"" . $this->files[0][mimetype] . "\"\r\n"; $contents .= "X-MimeOLE: Produced By Mht File Maker v1.0 beta\r\n"; $contents .= "\r\n"; $contents .= "This is a multi-part message in MIME format.\r\n"; $contents .= "\r\n"; foreach ($this->files as $file) { $contents .= "--{$this->boundary}\r\n"; $contents .= "Content-Type: $file[mimetype]\r\n"; $contents .= "Content-Transfer-Encoding: $file[encoding]\r\n"; $contents .= "Content-Location: $file[filepath]\r\n"; $contents .= "\r\n"; $contents .= $file[filecont]; $contents .= "\r\n"; } $contents .= "--{$this->boundary}--\r\n"; return $contents; } function MakeFile($filename){ $contents = $this->GetFile(); $fp = fopen($filename, w); fwrite($fp, $contents); fclose($fp); } function GetMimeType($filename){ $pathinfo = pathinfo($filename); switch ($pathinfo[extension]) { case htm: $mimetype = text/html; break; case html: $mimetype = text/html; break; case txt: $mimetype = text/plain; break; case cgi: $mimetype = text/plain; break; case php: $mimetype = text/plain; break; case css: $mimetype = text/css; break; case jpg: $mimetype = image/jpeg; break; case jpeg: $mimetype = image/jpeg; break; case jpe: $mimetype = image/jpeg; break; case gif: $mimetype = image/gif; break; case png: $mimetype = image/png; break; default: $mimetype = application/octet-stream; break; } return $mimetype; } } ?> 点评:这种方法的缺点是不支持批量生成下载,因为一个页面只能有一个header,(无论远程使用还是本地生成声明header页面只能输出一个header),即使你循环生成,结果还是只有一个word生成(当然你可以修改上面的方式来实现) 2.纯HTML格式写入word 原理: 利用ob_start把html页面先存储起来(解决一下页面多个header问题,可以批量生成),然后在写入doc文档内容利用 代码: 复制代码 代码如下: <?php class word { function start() { ob_start(); echo <html xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns="http://www.w3.org/TR/REC-html40">; } function save($path) { echo "</html>"; $data = ob_get_contents(); ob_end_clean(); $this->wirtefile ($path,$data); } function wirtefile ($fn,$data) { $fp=fopen($fn,"wb"); fwrite($fp,$data); fclose($fp); } } 复制代码 代码如下: $html = <table width=600 cellpadding="6" cellspacing="1" bgcolor="#336699"> <tr bgcolor="White"> <td>PHP10086</td> <td><a href="http://www.jb51.net" target="_blank" >http://www.jb51.net</a></td> </tr> <tr bgcolor="red"> <td>PHP10086</td> <td><a href="http://www.jb51.net" target="_blank" >http://www.jb51.net</a></td> </tr> <tr bgcolor="White"> <td colspan=2 > PHP10086<br> 最靠谱的PHP技术分享网站 <img src="http://www.jb51.net/wp-content/themes/WPortal-Blue/images/logo.gif"> </td> </tr> </table> ; //批量生成 for($i=1;$i<=3;$i++){ $word = new word(); $word->start(); //$html = "aaa".$i; $wordname = PHP教程网站--jb51.net.$i.".doc"; echo $html; $word->save($wordname); ob_flush();//每次执行前刷新缓存 flush(); } 个人点评:这种方法效果最好,原因有三个: 第一代码比较简洁,很容易理解 |