如何从word文件.doc,docx,.xlsx,.pptx php中提取文本
可能有一种情况我们需要从word文档中获取文本以供将来使用,以搜索用户上传的文档中的字符串,例如在cv/resume中搜索,并发生一个常见问题,即如何获取文本,打开并阅读用户上传的Word文档,有一些有用的链接但不能解决整个问题。我们需要在上传时获取文本并将文本保存在数据库中,并且我们可以轻松地在数据库中进行搜索。
可能有一种情况我们需要从word文档中获取文本以供将来使用,以搜索用户上传的文档中的字符串,例如在cv/resume中搜索,并发生一个常见问题,即如何获取文本,打开并阅读用户上传的Word文档,有一些有用的链接但不能解决整个问题。我们需要在上传时获取文本并将文本保存在数据库中,并且我们可以轻松地在数据库中进行搜索。
这是一个简单的类,它为.doc / .docx,PHP docx阅读器做正确的工作:将MS Word Docx文件转换为文本。
class DocxConversion{
private $filename;
public function __construct($filePath) {
$this->filename = $filePath;
}
private function read_doc() {
$fileHandle = fopen($this->filename, "r");
$line = @fread($fileHandle, filesize($this->filename));
$lines = explode(chr(0x0D),$line);
$outtext = "";
foreach($lines as $thisline)
{
$pos = strpos($thisline, chr(0x00));
if (($pos !== FALSE)||(strlen($thisline)==0))
{
} else {
$outtext .= $thisline." ";
}
}
$outtext = preg_replace("/[^a-zA-Z0-9\s\,\.\-\n\r\t@\/\_\(\)]/","",$outtext);
return $outtext;
}
private function read_docx(){
$striped_content = '';
$content = '';
$zip = zip_open($this->filename);
if (!$zip || is_numeric($zip)) return false;
while ($zip_entry = zip_read($zip)) {
if (zip_entry_open($zip, $zip_entry) == FALSE) continue;
if (zip_entry_name($zip_entry) != "word/document.xml") continue;
$content .= zip_entry_read($zip_entry, zip_entry_filesize($zip_entry));
zip_entry_close($zip_entry);
}// end while
zip_close($zip);
$content = str_replace('</w:r></w:p></w:tc><w:tc>', " ", $content);
$content = str_replace('</w:r></w:p>', "\r\n", $content);
$striped_content = strip_tags($content);
return $striped_content;
}
/************************excel sheet************************************/
function xlsx_to_text($input_file){
$xml_filename = "xl/sharedStrings.xml"; //content file name
$zip_handle = new ZipArchive;
$output_text = "";
if(true === $zip_handle->open($input_file)){
if(($xml_index = $zip_handle->locateName($xml_filename)) !== false){
$xml_datas = $zip_handle->getFromIndex($xml_index);
$xml_handle = DOMDocument::loadXML($xml_datas, LIBXML_NOENT | LIBXML_XINCLUDE | LIBXML_NOERROR | LIBXML_NOWARNING);
$output_text = strip_tags($xml_handle->saveXML());
}else{
$output_text .="";
}
$zip_handle->close();
}else{
$output_text .="";
}
return $output_text;
}
/*************************power point files*****************************/
function pptx_to_text($input_file){
$zip_handle = new ZipArchive;
$output_text = "";
if(true === $zip_handle->open($input_file)){
$slide_number = 1; //loop through slide files
while(($xml_index = $zip_handle->locateName("ppt/slides/slide".$slide_number.".xml")) !== false){
$xml_datas = $zip_handle->getFromIndex($xml_index);
$xml_handle = DOMDocument::loadXML($xml_datas, LIBXML_NOENT | LIBXML_XINCLUDE | LIBXML_NOERROR | LIBXML_NOWARNING);
$output_text .= strip_tags($xml_handle->saveXML());
$slide_number++;
}
if($slide_number == 1){
$output_text .="";
}
$zip_handle->close();
}else{
$output_text .="";
}
return $output_text;
}
public function convertToText() {
if(isset($this->filename) && !file_exists($this->filename)) {
return "File Not exists";
}
$fileArray = pathinfo($this->filename);
$file_ext = $fileArray['extension'];
if($file_ext == "doc" || $file_ext == "docx" || $file_ext == "xlsx" || $file_ext == "pptx")
{
if($file_ext == "doc") {
return $this->read_doc();
} elseif($file_ext == "docx") {
return $this->read_docx();
} elseif($file_ext == "xlsx") {
return $this->xlsx_to_text();
}elseif($file_ext == "pptx") {
return $this->pptx_to_text();
}
} else {
return "Invalid File Type";
}
}
}
Document_file_format文档文件是二进制 blob。可以使用 fopen 读取它们。虽然.docx文件只是zip文件和xml文件zml文件xml文件在zipfile容器(源维基百科),你可以使用zip_open来读取它们。
以上类的用法
$docObj = new DocxConversion("test.doc");
//$docObj = new DocxConversion("test.docx");
//$docObj = new DocxConversion("test.xlsx");
//$docObj = new DocxConversion("test.pptx");
echo $docText= $docObj->convertToText();
从 DOC 文件
$filename = 'ypue file';
if ( file_exists($filename) ) {
if ( ($fh = fopen($filename, 'r')) !== false ) {
$headers = fread($fh, 0xA00);
$n1 = ( ord($headers[0x21C]) - 1 );
$n2 = ( ( ord($headers[0x21D]) - 8 ) * 256 );
$n3 = ( ( ord($headers[0x21E]) * 256 ) * 256 );
$n4 = ( ( ( ord($headers[0x21F]) * 256 ) * 256 ) * 256 );
$textLength = ($n1 + $n2 + $n3 + $n4);
$extracted_plaintext = fread($fh, $textLength);
echo nl2br($extracted_plaintext);
print_r(extract_emails_from($extracted_plaintext));
}
}
function extract_emails_from($string) {
preg_match_all("/[\._a-zA-Z0-9-]+@[\._a-zA-Z0-9-]+/i", $string, $matches);
return $matches[0];
}
来自 DOCX :
/*Name of the document file*/
$document = 'your file';
/**Function to extract text*/
function extracttext($filename) {
//Check for extension
$ext = end(explode('.', $filename));
//if its docx file
if($ext == 'docx')
$dataFile = "word/document.xml";
//else it must be odt file
else
$dataFile = "content.xml";
//Create a new ZIP archive object
$zip = new ZipArchive;
// Open the archive file
if (true === $zip->open($filename)) {
// If successful, search for the data file in the archive
if (($index = $zip->locateName($dataFile)) !== false) {
// Index found! Now read it to a string
$text = $zip->getFromIndex($index);
// Load XML from a string
// Ignore errors and warnings
$xml = DOMDocument::loadXML($text, LIBXML_NOENT | LIBXML_XINCLUDE | LIBXML_NOERROR | LIBXML_NOWARNING);
// Remove XML formatting tags and return the text
return strip_tags($xml->saveXML());
}
//Close the archive file
$zip->close();
}
// In case of failure return a message
return "File not found";
}
echo extracttext($document);