Using DocxToText to Extract Text from DOCX Files

public class ExcelReaderHelperWithoutOffice
{
    private const string ContentTypeNamespace = @"http://schemas.openxmlformats.org/package/2006/content-types";
    private XNamespace namespc = "http://schemas.openxmlformats.org/spreadsheetml/2006/main";
    private const string sheetXmlXPath = "/t:Types/t:Override[@ContentType=\"application/vnd.openxmlformats-officedocument.spreadsheetml.worksheet+xml\"]";
    private const string BodyXPath = "/w:workbook/w:body";
    private string xslxFile = "";
    private string sheet1FileLocation = "";

    public ExcelReaderHelperWithoutOffice(string fileName)
    {
        xslxFile = fileName;
        WaitHelper.WaitUntil(() => !IsFileLocked(),60000);
        if (IsFileLocked()) throw new Exception("File is locked");
    }

    public virtual bool IsFileLocked()
    {
        FileStream stream = null;
        try
        {
            stream = new FileInfo(xslxFile).Open(FileMode.Open, FileAccess.Read, FileShare.None);
        }
        catch (IOException)
        {
            //the file is unavailable because it is:
            //still being written to
            //or being processed by another thread
            //or does not exist (has already been processed)
            return true;
        }
        finally
        {
            if (stream != null)
                stream.Close();
        }
        return false;
    }

    public string ExtractCellText(string cellRef)
    {
        return ExtractAllText()[cellRef];
    }

    public Dictionary<string,string> ExtractRowText(int excelSheetRow)
    {
        if (string.IsNullOrEmpty(xslxFile)) throw new Exception("Input file not specified.");
        sheet1FileLocation = FindSheet1XmlLocation();
        if (string.IsNullOrEmpty(sheet1FileLocation)) throw new Exception("It is not a valid xslx file.");
        return ReadRowCellsXml(ExtractRowCellMap(excelSheetRow));
    }

    public Dictionary<string,string> ExtractAllText()
    {
        if (string.IsNullOrEmpty(xslxFile)) throw new Exception("Input file not specified.");
        sheet1FileLocation = FindSheet1XmlLocation();
        if (string.IsNullOrEmpty(sheet1FileLocation)) throw new Exception("It is not a valid xslx file.");
        return ReadAllCellsXml(ExtractFullCellMap());
    }

    #region FindSheet1XmlLocation()
    ///
    /// Gets location of the "Sheet1.xml" zip entry.
    ///
    /// Location of the "Sheet1.xml".
    private string FindSheet1XmlLocation()
    {
        ZipFile zip = new ZipFile(xslxFile);
        foreach (ZipEntry entry in zip)
        {
            // Find "[Content_Types].xml" zip entry
            if (string.Compare(entry.Name, "[Content_Types].xml", true) == 0)
            {
                System.IO.Stream contentTypes = zip.GetInputStream(entry);
                XmlDocument xmlDoc = new XmlDocument();
                xmlDoc.PreserveWhitespace = true;
                xmlDoc.Load(contentTypes);
                contentTypes.Close();

                //Create an XmlNamespaceManager for resolving namespaces

                XmlNamespaceManager nsmgr = new XmlNamespaceManager(xmlDoc.NameTable);
                nsmgr.AddNamespace("t", ContentTypeNamespace);

                // Find location of "document.xml"

                XmlNode node = xmlDoc.DocumentElement.SelectSingleNode(sheetXmlXPath, nsmgr);
                if (node != null)
                {
                    string location = ((XmlElement)node).GetAttribute("PartName");
                    return location.TrimStart(new char[] { '/' });
                }
                break;
            }
        }
        zip.Close();
        return null;
    }
    #endregion

    #region ExtractRowCellMap()
    ///
    /// Reads "sheet1.xml" zip entry.
    ///
    /// Gets the addresses to of text for cells that is stored in sharedStrings.xml
    private Dictionary<string, int> ExtractRowCellMap(int row)
    {
        Dictionary<string, int> result = new Dictionary<string, int>();
        ZipFile zip = new ZipFile(xslxFile);
        var xslxFileLocation = "xl/worksheets/sheet1.xml";
        foreach (ZipEntry entry in zip)
        {
            if (string.Compare(entry.Name, xslxFileLocation, true) == 0)
            {
                System.IO.Stream sheetXml = zip.GetInputStream(entry);
                XDocument xmlDoc =  XDocument.Load(sheetXml);
                var rowItem = xmlDoc.Descendants(namespc + "row").Where(x=>x.Attribute("r").Value == row.ToString());
                if (rowItem == null) throw new Exception("Specified row does not exist");
                var rowCells = rowItem.Descendants(namespc + "c");
                foreach (var cell in rowCells)
                {
                    int address = cell.Descendants(namespc + "v").Count() > 0
                            ? Convert.ToInt32(cell.Descendants(namespc + "v").First().Value.ToString()) : -1;
                    if (!result.ContainsKey(cell.Attribute("r").Value))
                        result.Add(cell.Attribute("r").Value, address);
                }
                break;
            }
        }
        zip.Close();
        return result;
    }
    #endregion

    #region ExtractFullCellMap()
    ///
    /// Reads "sheet1.xml" zip entry.
    ///
    /// Gets the addresses of text for all cells that is stored in sharedStrings.xml
    private Dictionary<string, int> ExtractFullCellMap()
    {
        Dictionary<string, int> result = new Dictionary<string, int>();
        ZipFile zip = new ZipFile(xslxFile);
        var xslxFileLocation = "xl/worksheets/sheet1.xml";
        foreach (ZipEntry entry in zip)
        {
            if (string.Compare(entry.Name, xslxFileLocation, true) == 0)
            {
                System.IO.Stream sheetXml = zip.GetInputStream(entry);
                XDocument xmlDoc = XDocument.Load(sheetXml);
                var rowItems = xmlDoc.Descendants(namespc + "row");
                if (rowItems == null || rowItems.Count() == 0) throw new Exception("No rows exist");
                foreach (var row in rowItems)
                {
                    var rowCells = rowItems.Descendants(namespc + "c");
                    foreach (var cell in rowCells)
                    {
                        int address = cell.Descendants(namespc + "v").Count() > 0
                             ? Convert.ToInt32(cell.Descendants(namespc + "v").First().Value.ToString()) : -1;
                        if (!result.ContainsKey(cell.Attribute("r").Value))
                            result.Add(cell.Attribute("r").Value, address);
                    }
                }
                break;
            }
        }
        zip.Close();
        return result;
    }
    #endregion

    #region ReadRowCellsXml()
    ///
    /// Reads "sharedStrings.xml" zip entry.
    ///
    /// Text contained in the cells.
    private Dictionary<string,string> ReadRowCellsXml(Dictionary<string, int> cellDataAddresses)
    {
        Dictionary<string,string> result = new Dictionary<string,string>();
        ZipFile zip = new ZipFile(xslxFile);
        var sharedStringsFileLocation = "xl/sharedStrings.xml";
        foreach (ZipEntry entry in zip)
        {
            if (string.Compare(entry.Name, sharedStringsFileLocation, true) == 0)
            {
                Stream sheetXml = zip.GetInputStream(entry);
                XDocument xmlDoc =  XDocument.Load(sheetXml);
                var root = xmlDoc.Descendants(namespc + "sst");
                var cellValues = root.Descendants(namespc + "si").Descendants(namespc + "t").Select(x=>x.Value).ToList();
                foreach (var cell in cellDataAddresses
                    .Where(c => c.Value >= 0 && c.Value < cellValues.Count))
                {
                    result.Add(cell.Key, cellValues[cell.Value]);
                }
                break;
            }
        }
        zip.Close();
        return result;
    }
    #endregion

    #region ReadAllCellsXml()
    ///
    /// Reads "sharedStrings.xml" zip entry.
    ///
    /// Text contained in the cells.
    private Dictionary<string,string> ReadAllCellsXml(Dictionary<string, int> cellDataAddresses)
    {
        Dictionary<string,string> result = new Dictionary<string,string>();
        ZipFile zip = new ZipFile(xslxFile);
        var sharedStringsFileLocation = "xl/sharedStrings.xml";
        foreach (ZipEntry entry in zip)
        {
            if (string.Compare(entry.Name, sharedStringsFileLocation, true) == 0)
            {
                Stream sheetXml = zip.GetInputStream(entry);
                XDocument xmlDoc =  XDocument.Load(sheetXml);
                var root = xmlDoc.Descendants(namespc + "sst");
                var cellValues = root.Descendants(namespc + "si").Descendants(namespc + "t").Select(x=>x.Value).ToList();
                foreach (var cell in cellDataAddresses
                    .Where(c => c.Value >= 0 && c.Value < cellValues.Count))
                {
                    result.Add(cell.Key, cellValues[cell.Value]);
                }
                break;
            }
        }
        zip.Close();
        return result;
    }
    #endregion

Hi,
If I use office 2016 docx file then it can not work. Please give me solution for version issue.

Found this 8 year old solution which fit my needs exactly! Nice and elegant and simple.

If i have images in word document its not showing in result.

thanx Jevgenij Pankov thats realy work for me but i have one more problam this is not read .doc file
can you help me for solve my problam

"Cannot find central directory"

Software Developer
Jayzon Ragasa
Baguio City, Philippines

Worked right away for me

Excellent

Dear All,
I am a newbie in C#.
I try to save the extracted text into a file.
Below is the code I wrote and I got error message: "This is an unclosed string".

Could anyone point out the string which is unclosed please?

Thank you very much Smile | :)

Best,
Hendra

C#

namespace ConsoleApplication1
{
    class Program
    {
        static void Main(string[] args)
        {
            try
            {
                DocxToText dtt = new DocxToText("Document_1.docx");
                string text = dtt.ExtractText();
                File.WriteAllText("Document_1.txt", text);
            }
            catch (Exception ex)
            {
                Console.WriteLine(ex.Message);
            }
            Console.ReadLine();
        }
    }
}

Hi,
You can replace this code and try again

private const string DocumentXmlXPath =
    "/t:Types/t:Override[@ContentType=\"application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml\"]";

Thanks and Regards,
Ketan

Hi, How can I read line numbers of text? for example for read tab, I use "tab" or for read page break use "br". How can I access to line numbers of text in docx file ?

Thank you very much for sharing this code. It is just what I was looking for in order to learn how to perform this operation and to satisfy a portion of a process I am currently writing.

Thank you!

Hi, I found your article excelent but I would like to know how can I call your class from a VB.NET project. Can you tell me? Thanks in advance.

Here is a slightly modified version of the class that works with Ionic.zip which does not need anything installing into the GAC.

C#

public class DocxToText
    {
        private const string ContentTypeNamespace =
            @"http://schemas.openxmlformats.org/package/2006/content-types";

        private const string WordprocessingMlNamespace =
            @"http://schemas.openxmlformats.org/wordprocessingml/2006/main";

        private const string DocumentXmlXPath =
            "/t:Types/t:Override[@ContentType=\"" +
            "application/vnd.openxmlformats-officedocument." +
            "wordprocessingml.document.main+xml\"]";

        private const string BodyXPath = "/w:document/w:body";

        private string docxFile = "";
        private string docxFileLocation = "";

        public DocxToText(string fileName)
        {
            docxFile = fileName;
        }

        #region ExtractText()
        /// 

        /// Extracts text from the Docx file.

        /// 

        /// Extracted text.

        public string ExtractText()
        {
            if (string.IsNullOrEmpty(docxFile))
                throw new Exception("Input file not specified.");

            // Usually it is "/word/document.xml"


            docxFileLocation = FindDocumentXmlLocation();

            if (string.IsNullOrEmpty(docxFileLocation))
                throw new Exception("It is not a valid Docx file.");

            return ReadDocumentXml();
        }
        #endregion

        #region FindDocumentXmlLocation()
        /// 

        /// Gets location of the "document.xml" zip entry.

        /// 

        /// Location of the "document.xml".

        private string FindDocumentXmlLocation()
        {
            using (ZipFile zip = new ZipFile(docxFile))
            {
                foreach (ZipEntry entry in zip)
                {
                    // Find "[Content_Types].xml" zip entry
                    if (string.Compare(entry.FileName, "[Content_Types].xml", true) == 0)
                    {
                        XmlDocument xmlDoc = new XmlDocument();
                        using (var stream = new MemoryStream())
                        {

                            entry.Extract(stream);
                            stream.Position = 0;

                            xmlDoc.PreserveWhitespace = true;
                            xmlDoc.Load(stream);
                        }

                        //Create an XmlNamespaceManager for resolving namespaces


                        XmlNamespaceManager nsmgr =
                            new XmlNamespaceManager(xmlDoc.NameTable);
                        nsmgr.AddNamespace("t", ContentTypeNamespace);

                        // Find location of "document.xml"


                        XmlNode node = xmlDoc.DocumentElement.SelectSingleNode(
                            DocumentXmlXPath, nsmgr);

                        if (node != null)
                        {
                            string location =
                                ((XmlElement)node).GetAttribute("PartName");
                            return location.TrimStart(new char[] { '/' });
                        }
                        break;
                    }
                }
            }
            return null;
        }
        #endregion

        #region ReadDocumentXml()
        /// 

        /// Reads "document.xml" zip entry.

        /// 

        /// Text containing in the document.

        private string ReadDocumentXml()
        {
            StringBuilder sb = new StringBuilder();

            using (ZipFile zip = new ZipFile(docxFile))
            {
                foreach (ZipEntry entry in zip)
                {
                    if (string.Compare(entry.FileName, docxFileLocation, true) == 0)
                    {
                        XmlDocument xmlDoc = new XmlDocument();
                        using (var stream = new MemoryStream())
                        {

                            entry.Extract(stream);
                            stream.Position = 0;

                            xmlDoc.PreserveWhitespace = true;
                            xmlDoc.Load(stream);
                        }

                        XmlNamespaceManager nsmgr =
                            new XmlNamespaceManager(xmlDoc.NameTable);
                        nsmgr.AddNamespace("w", WordprocessingMlNamespace);

                        XmlNode node =
                            xmlDoc.DocumentElement.SelectSingleNode(BodyXPath, nsmgr);

                        if (node == null)
                            return string.Empty;

                        sb.Append(ReadNode(node));

                        break;
                    }
                }
            }
            return sb.ToString();
        }
        #endregion

        #region ReadNode()
        /// 

        /// Reads content of the node and its nested childs.

        /// 

        /// XmlNode.

        /// Text containing in the node.

        private string ReadNode(XmlNode node)
        {
            if (node == null || node.NodeType != XmlNodeType.Element)
                return string.Empty;

            StringBuilder sb = new StringBuilder();
            foreach (XmlNode child in node.ChildNodes)
            {
                if (child.NodeType != XmlNodeType.Element) continue;

                switch (child.LocalName)
                {
                    case "t": // Text

                        sb.Append(child.InnerText.TrimEnd());

                        string space =
                            ((XmlElement)child).GetAttribute("xml:space");
                        if (!string.IsNullOrEmpty(space) &&
                            space == "preserve")
                            sb.Append(' ');

                        break;

                    case "cr":                          // Carriage return

                    case "br":                          // Page break

                        sb.Append(Environment.NewLine);
                        break;

                    case "tab":                         // Tab

                        sb.Append("\t");
                        break;

                    case "p":                           // Paragraph

                        sb.Append(ReadNode(child));
                        sb.Append(Environment.NewLine);
                        sb.Append(Environment.NewLine);
                        break;

                    default:
                        sb.Append(ReadNode(child));
                        break;
                }
            }
            return sb.ToString();
        }
        #endregion
    }

Your example is absolutely perfect, you saved me a lot of time, thank you. You know, when you provide something good for people, they immediately ask more. In this matter I ask how to extract text from PDF file. Only text is good enough, not images or other. Thanks, again.

Thank you Andrew,
I would look at the IFilter for PDF. Here is a link to the Adobe's IFilter for extracting texts from PDF files: http://www.adobe.com/support/downloads/detail.jsp?ftpID=2611[^].
Possibly there are some other implementations of the IFilter for PDF.

Regards,

Jevgenij Pankov

how to do the DOCX to HTML
Please help.

Thanks
Kunal D
India

Can you Please send the code for how to extract image from .docx file.
And how can we read the the document page wise.

thanks in Advance

Hi,

you can easily extract images from C# docx file with this C# Word library.

Here is a sample C# code that shows how to do it:

C#

// Use the component in free mode.
ComponentInfo.SetLicense("FREE-LIMITED-KEY");

// Load a document with images.
var document = DocumentModel.Load("DocumentWithImages.docx", LoadOptions.DocxDefault);

// Iterate over all images in the document.
foreach (Picture picture in document.GetChildElements(true, ElementType.Picture))
{
	// Generate random file name with appropriate file name extension.
	var path = Path.ChangeExtension(Path.GetRandomFileName(), picture.Format.ToString().ToLowerInvariant());
	// Write image stream to a file.
	File.WriteAllBytes(path, picture.PictureStream.ToArray());
}

Hi
We have used this file to parse resumes in our application. But I am noticing that there is a discrepancy.

For eg: OBJECTIVE is being parsed as oBJECTIVE. In some other conditions, there is a space being introduced where it is not required. Like Threshold is T hreshold.

Can u please help me find a solution? An early reply wud be appreciated as it has caused a serious issue at the client place.

Regards
Nivedita

I noticed the same issue with the spacing parsing when I tried using the code.
It adds an empty, single space character to the docx text string when it sees a "preserve" written in the xml: space tag of the main Word document.xml file. This is usually correct, but the only problem with this is that because of the way the main body text content of the word file is saved by Word, it occasionally saves a block of words in one tag and then another block in another, but cuts them off part way through a word.

Relevant part of my Word file unpacked in xml form: (have changed the '<' tags to brackets to stop the web browser from parsing and removing them).

(w:t xml:space="preserve"> the big bro(/wt)
(w:t xml:space="preserve> wn fox jumped over the lazy dog (/wt)

So when the text string parses this file, it will come out as
string lWordFile = "the big bro wn fox jumped over the lazy dog.

It doesn't sound major but if you are implementing a system involving searching for words then it won't work properly, as the most common separator used to distinguish one word from another is the character space between them. There must be a solution as the MS Word application is able to open the docx file back from this saved state without the extra character spaces showing. I'll post a solution if I come up with one!

modified 28-Dec-12 12:12pm.

Solution (alternative method):

Microsoft.Office.Interop.Word.Application word = new Microsoft.Office.Interop.Word.Application();
object miss = System.Reflection.Missing.Value;
object path = @"C:\DOC\myDocument.docx";
object readOnly = true;
Microsoft.Office.Interop.Word.Document docs = word.Documents.Open(ref path, ref miss, ref readOnly, ref miss, ref miss, ref miss, ref miss, ref miss, ref miss, ref miss, ref miss, ref miss, ref miss, ref miss, ref miss, ref miss);
string totaltext = "";
for (int i = 0; i < docs.Paragraphs.Count; i++)
{
totaltext += " \r\n "+ docs.Paragraphs[i+1].Range.Text.ToString();
}
Console.WriteLine(totaltext);
docs.Close();
word.Quit();

Hi Thanks for this code. Input file is locked in IIS. How to release it?

Thanks once again.

Kavi

Hi,

The file is locked by IIS if it is being served to the clients - i.e. opened for reading. As far as I know, it can be unlocked if to restart the Application Pool serving the web site (or web application). You can do it in the IIS Manager. If it doesn't help - the last chance - to restart IIS services.

If it's not the case - there are some tools, like Sysinternal's Process Explorer, that can find and close file handles opened by IIS.

Regards,

Jevgenij

Thanks. I know this but thought to put this Q if any other option exsist, since i can not reset IIS every time in my application.

Thanks once again.

Kavi

Tagged as

Stats

Using DocxToText to Extract Text from DOCX Files

Introduction

DocxToText Class

Conclusion

History

License

Comments and Discussions