public 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 ($imgcontent) {
$mht->AddContents($files[$i], $mht->GetMimeType($image), $imgcontent);
}
} else {
echo "file:" . $image . " not exist!<br />";
}
}
return $mht->GetFile();
}
function CreateDOC($link, $filename)
{
// Creating Object, which will generate mht
$MhtFileMaker = new MhtFileMaker();
// Plug in images to file
// RegEx, which pull out image path
preg_match_all('@<img(.*)?src="([^"]+)"@ui', $link, $matches);
// For future implementation of links
// preg_match_all('@<a(.*)?href="([^"]+)"@ui', $link, $mat);
// print_r($mat[2]);
$link = preg_replace('@<script(.*)?</script>@ui', "", $link);
preg_match_all('@<link(.*)?href="([^"]+)"@ui', $link, $styles);
foreach ($styles[2] as $style) {
$cont = @file_get_contents($style);
if ($cont !== false) {
$link .= "<style>{$cont}</style>";
}
}
// print_r($link);
foreach ($matches[4] as $img) {
$img_tmp = $img;
$img_tmp_old = $img;
// Change image pathes, if they are not in Web
if (strpos($img_tmp, "http") === FALSE) {
$img_tmp = "img/" . $img_tmp;
}
// Allocate image path WITHOUT domain address
$img_array = explode("//", $img_tmp);
$img_name_only = $img_array[1];
$img_name_only = explode("/", $img_name_only);
unset($img_name_only[0]);
$img_name_only = implode("/", $img_name_only);
// Change image path to relative path (without domain)
$link = str_replace($img_tmp_old, $img_name_only, $link);
// Add image to final file
$MhtFileMaker->AddFile($img_tmp, $img_name_only, 'utf-8');
}
// Create final file
$MhtFileMaker->AddContents($link, "text/html");
// Save file
$MhtFileMaker->MakeFile($filename);
}
function getWordDocument($content, $absolutePath = "", $isEraseLink = false)
{
$mht = new MhtFileMaker();
if ($isEraseLink) {
$content = preg_replace('/<a\\s*.*?\\s*>(\\s*.*?\\s*)<\\/a>/i', '$1', $content);
}
$images = array();
$files = array();
$matches = array();
if (preg_match_all('/<img[^>]*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://') {
} else {
$imgPath = "http://" . $_SERVER['HTTP_HOST'] . "/" . $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();
}