在某些情况下,我们可能需要从Word文档中获取文本以供将来在用户上传的文档中搜索字符串,例如在cv / resumes中进行搜索,并出现一个常见的问题,即如何获取文本,打开并阅读用户上载Word文档时,有一些有用的链接,但不能解决整个问题。我们需要在上载时获取文本并将文本保存在数据库中,以便在数据库中轻松搜索。
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_formatDoc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zipfile容器中的xml文件(源Wikipedia),您可以使用zip_open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();