DocxToTextDemo

最新推荐文章于 2024-06-26 00:31:52 发布

weixin_30466953

最新推荐文章于 2024-06-26 00:31:52 发布

阅读量60

点赞数

文章标签： php c#

原文链接：http://www.cnblogs.com/xszlo/archive/2013/02/23/2923350.html

版权

文件结构

+DocxToTextDemo

+bin

+Debug

-DocxToTextDemo.vshost.exe

-ICSharpCode.SharpZipLib.dll

+Release

-DocxToTextDemo.exe

-ICSharpCode.SharpZipLib.dll

-DocxToText.cs

-DocxToTextDemo.csproj

-Form1.cs

-Form1.Designer.cs

-Form1.resx

+obj

+Debug

+TempPE

-Program.cs

+Properties

-AssemblyInfo.cs

-Resources.Designer.cs

-Resources.resx

-Settings.Designer.cs

-Settings.settings

-DocxToTextDemo.sln

-DocxToTextDemo.suo

说明

通过本程序可以直接抽取docx后缀名的word文件，生成txt内容小S资料屋

// DocxToText.cs

using System;

using System.IO;

using System.Text;

using System.Xml;

using ICSharpCode.SharpZipLib.Zip;

namespace DocxToTextDemo

{

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()

/// <summary>

/// Extracts text from the Docx file.

/// </summary>

/// <returns>Extracted text.</returns>

public string ExtractText()

{

if (string.IsNullOrEmpty(docxFile))

throw new Exception("Input file not specified.");小S资料屋

// 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()

/// <summary>

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

/// </summary>

/// <returns>Location of the "document.xml".</returns>

private string FindDocumentXmlLocation()

{

ZipFile zip = new ZipFile(docxFile);

foreach (ZipEntry entry in zip)

{

// Find "[Content_Types].xml" zip entry

if (string.Compare(entry.Name, "[Content_Types].xml", true) == 0)

{

Stream contentTypes = zip.GetInputStream(entry);

XmlDocument xmlDoc = new XmlDocument();

xmlDoc.PreserveWhitespace = true;

xmlDoc.Load(contentTypes);

contentTypes.Close();

//Create an XmlNamespaceManager for resolving namespaces小S资料屋

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;

}

zip.Close();

return null;

}

#endregion

#region ReadDocumentXml()

/// <summary>

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

/// </summary>

/// <returns>Text containing in the document.</returns>

private string ReadDocumentXml()

{

StringBuilder sb = new StringBuilder();

ZipFile zip = new ZipFile(docxFile);

foreach (ZipEntry entry in zip)

{

if (string.Compare(entry.Name, docxFileLocation, true) == 0)

{

Stream documentXml = zip.GetInputStream(entry);

XmlDocument xmlDoc = new XmlDocument();

xmlDoc.PreserveWhitespace = true;

xmlDoc.Load(documentXml);

documentXml.Close();

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;

}

zip.Close();

return sb.ToString();

}

#endregion小S资料屋

#region ReadNode()

/// <summary>

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

/// </summary>

/// <param name="node">XmlNode.</param>

/// <returns>Text containing in the node.</returns>

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);

break;

default:

sb.Append(ReadNode(child));

break;

}

return sb.ToString();

}

#endregion

}

DocxToTextDemo

“相关推荐”对你有帮助么？