Search a WordPress XML export for text in pages/posts.

WordPress Xml Content Search.cs

// For running in LINQPad.

var typesToExclude = new List<string>() { "nav_menu_item", "attachment" };
var typesToInclude = new List<string>() { "page", "post" };

var searchTerm = "example.com/wp-content/uploads";

var xmlPath = @"C:\Users\jskemp\Downloads\example.wordpress.2016-01-22.xml";

var xml = XDocument.Load(xmlPath);

var xmlItems = xml
	.Root.Element("channel")
	.Elements("item");

("Items in XML: " + xmlItems.Count()).Dump();

XNamespace wpNs = "http://wordpress.org/export/1.2/";
XNamespace contentNs = "http://purl.org/rss/1.0/modules/content/";

xmlItems = xmlItems
	//.Where(i => !typesToExclude.Contains(i.Element(wpNs + "post_type").Value))
	.Where(i => typesToInclude.Contains(i.Element(wpNs + "post_type").Value))
	;

xmlItems.Count().Dump();

xmlItems
	.Where(i => i.Element(contentNs + "encoded").Value.Contains(searchTerm))
	.OrderByDescending(i => i.Element(wpNs + "post_date").Value)
	.Select (i => new { title = i.Element("title").Value, guid = i.Element("guid").Value, content = i.Element(contentNs + "encoded"), date = i.Element(wpNs + "post_date").Value })
	.Dump();