using DocumentFormat.OpenXml.Packaging; public static string TextFromWord(string path)
{
const string wordmlNamespace = "http://schemas.openxmlformats.org/wordprocessingml/2006/main";
StringBuilder textBuilder = new StringBuilder();
using (WordprocessingDocument wdDoc = WordprocessingDocument.Open(path, false))
{
// Manage namespaces to perform XPath queries.
NameTable nt = new NameTable();
XmlNamespaceManager nsManager = new XmlNamespaceManager(nt);
nsManager.AddNamespace("w", wordmlNamespace);
// Get the document part from the package.
// Load the XML in the document part into an XmlDocument instance.
XmlDocument xdoc = new XmlDocument(nt);
xdoc.Load(wdDoc.MainDocumentPart.GetStream());
XmlNodeList paragraphNodes = xdoc.SelectNodes("//w:p", nsManager);
foreach (XmlNode paragraphNode in paragraphNodes)
{
XmlNodeList textNodes = paragraphNode.SelectNodes(".//w:t", nsManager);
foreach (System.Xml.XmlNode textNode in textNodes)
{
textBuilder.Append(textNode.InnerText);
}
textBuilder.Append(Environment.NewLine);
}
}
var result = textBuilder.ToString();
return result;
}
异常情况:抛出异常:文件包含损坏的数据
解决办法:把doc文件转化为docx文件,可搜索在线转化网站。之后就可以使用docx文件。
|
请发表评论