I need to read file details, especially, Authors, Title, Subject, from new Office files (.docx, .xlsx). I found this article from MS, which also has some methods - http://msdn.microsoft.com/en-us/library/bb739835%28v=office.12%29.aspx But I can seem to make this work. Method I'm using is:
public static string WDRetrieveCoreProperty(string docName, string propertyName)
{
// Given a document name and a core property, retrieve the value of the property.
// Note that because this code uses the SelectSingleNode method,
// the search is case sensitive. That is, looking for "Author" is not
// the same as looking for "author".
const string corePropertiesSchema = "http://schemas.openxmlformats.org/package/2006/metadata/core-properties";
const string dcPropertiesSchema = "http://purl.org/dc/elements/1.1/";
const string dcTermsPropertiesSchema = "http://purl.org/dc/terms/";
string propertyValue = string.Empty;
using (WordprocessingDocument wdPackage = WordprocessingDocument.Open(docName, true))
{
// Get the core properties part (core.xml).
CoreFilePropertiesPart corePropertiesPart = wdPackage.CoreFilePropertiesPart;
// Manage namespaces to perform XML XPath queries.
NameTable nt = new NameTable();
XmlNamespaceManager nsManager = new XmlNamespaceManager(nt);
nsManager.AddNamespace("cp", corePropertiesSchema);
nsManager.AddNamespace("dc", dcPropertiesSchema);
nsManager.AddNamespace("dcterms", dcTermsPropertiesSchema);
// Get the properties from the package.
XmlDocument xdoc = new XmlDocument(nt);
// Load the XML in the part into an XmlDocument instance.
xdoc.Load(corePropertiesPart.GetStream());
string searchString = string.Format("//cp:coreProperties/{0}", propertyName);
XmlNode xNode = xdoc.SelectSingleNode(searchString, nsManager);
if (!(xNode == null))
{
propertyValue = xNode.InnerText;
}
}
return propertyValue;
}
So I'm calling this method like:
WDRetrieveCoreProperty(textBox1.Text, "Authors");
// textBox1 has path to some .docx file
But it always returns null. So what is wrong with this?