我正在尝试从Word文档中获取纯文本。具体来说,xpath使我感到困扰。如何选择<p>标签?以下是我的代码:
public static string TextDump(Package package)
{
StringBuilder builder = new StringBuilder();
XmlDocument xmlDoc = new XmlDocument();
xmlDoc.Load(package.GetPart(new Uri("/word/document.xml", UriKind.Relative)).GetStream());
foreach (XmlNode node in xmlDoc.SelectNodes("/descendant::w:t"))
{
builder.AppendLine(node.InnerText);
}
return builder.ToString();
}