Question

Given a URL, if it has any RSS nodes, then I am adding to the database.

e.g.:

For this URL, rssDoc.SelectNodes("rss/channel/item").Count is greater than zero.

But for the atom url, rssDoc.SelectNodes("rss/channel/item").count is equal to zero.

How can I check if the Atom/RSS URL has any nodes or not? I have tried for rssDoc.SelectNodes("feed/entry").Count, but is giving me zero count.

Public Shared Function HasRssItems(ByVal url as string) As Boolean
Dim myRequest As WebRequest
Dim myResponse As WebResponse
Try
    myRequest = System.Net.WebRequest.Create(url)
    myRequest.Timeout = 5000
    myResponse = myRequest.GetResponse()

    Dim rssStream As Stream = myResponse.GetResponseStream()
    Dim rssDoc As New XmlDocument()
    rssDoc.Load(rssStream)

    Return rssDoc.SelectNodes("rss/channel/item").Count > 0
Catch ex As Exception
    Return False
Finally
    myResponse.Close()
End Try

End Function

Answer 1

Your main problem here is that the XML “node path” on this line:

Return rssDoc.SelectNodes("rss/channel/item").Count > 0

is only valid for RSS feeds, not ATOM feeds.

One way I’ve got over this in the past is to use a simple function to convert an ATOM feed into an RSS feed. Of course, you could go the other way, or not convert at all, however, converting to a single format enables you to write one “generic” chunk of code that will pull out the various elements of a feed’s items that you may be interested in (i.e. date, title etc.)

There is an ATOM to RSS Converter article on Code Project that provides such a conversion, however, that is in C#. I have previously manually converted this to VB.NET myself, so here’s the VB.NET version:

Private Function AtomToRssConverter(ByVal atomDoc As XmlDocument) As XmlDocument
    Dim xmlDoc As XmlDocument = atomDoc
    Dim xmlNode As XmlNode = Nothing
    Dim mgr As New XmlNamespaceManager(xmlDoc.NameTable)
    mgr.AddNamespace("atom", "http://purl.org/atom/ns#")
    Const rssVersion As String = "2.0"
    Const rssLanguage As String = "en-US"
    Dim rssGenerator As String = "RDFFeedConverter"
    Dim memoryStream As New MemoryStream()
    Dim xmlWriter As New XmlTextWriter(memoryStream, Nothing)
    xmlWriter.Formatting = Formatting.Indented
    Dim feedTitle As String = ""
    Dim feedLink As String = ""
    Dim rssDescription As String = ""

    xmlNode = xmlDoc.SelectSingleNode("//atom:title", mgr)
    If xmlNode Is Nothing Then
          This looks like an ATOM v1.0 format, rather than ATOM v0.3.
        mgr.RemoveNamespace("atom", "http://purl.org/atom/ns#")
        mgr.AddNamespace("atom", "http://www.w3.org/2005/Atom")
    End If

    xmlNode = xmlDoc.SelectSingleNode("//atom:title", mgr)
    If Not xmlNode Is Nothing Then
        feedTitle = xmlNode.InnerText
    End If
    xmlNode = xmlDoc.SelectNodes("//atom:link/@href", mgr)(2)
    If Not xmlNode Is Nothing Then
        feedLink = xmlNode.InnerText
    End If
    xmlNode = xmlDoc.SelectSingleNode("//atom:tagline", mgr)
    If Not xmlNode Is Nothing Then
        rssDescription = xmlNode.InnerText
    End If
    xmlNode = xmlDoc.SelectSingleNode("//atom:subtitle", mgr)
    If Not xmlNode Is Nothing Then
        rssDescription = xmlNode.InnerText
    End If

    xmlWriter.WriteStartElement("rss")
    xmlWriter.WriteAttributeString("version", rssVersion)
    xmlWriter.WriteStartElement("channel")
    xmlWriter.WriteElementString("title", feedTitle)
    xmlWriter.WriteElementString("link", feedLink)
    xmlWriter.WriteElementString("description", rssDescription)
    xmlWriter.WriteElementString("language", rssLanguage)
    xmlWriter.WriteElementString("generator", rssGenerator)
    Dim items As XmlNodeList = xmlDoc.SelectNodes("//atom:entry", mgr)
    If items Is Nothing Then
        Throw New FormatException("Atom feed is not in expected format. ")
    Else
        Dim title As String = [String].Empty
        Dim link As String = [String].Empty
        Dim description As String = [String].Empty
        Dim author As String = [String].Empty
        Dim pubDate As String = [String].Empty
        For i As Integer = 0 To items.Count - 1
            Dim nodTitle As XmlNode = items(i)
            xmlNode = nodTitle.SelectSingleNode("atom:title", mgr)
            If Not xmlNode Is Nothing Then
                title = xmlNode.InnerText
            End If
            Try
                link = items(i).SelectSingleNode("atom:link[@rel= alternate ]", mgr).Attributes("href").InnerText
            Catch ex As Exception
                link = items(i).SelectSingleNode("atom:link", mgr).Attributes("href").InnerText
            End Try
            xmlNode = items(i).SelectSingleNode("atom:content", mgr)
            If Not xmlNode Is Nothing Then
                description = xmlNode.InnerText
            End If
            xmlNode = items(i).SelectSingleNode("//atom:name", mgr)
            If Not xmlNode Is Nothing Then
                author = xmlNode.InnerText
            End If
            xmlNode = items(i).SelectSingleNode("atom:issued", mgr)
            If Not xmlNode Is Nothing Then
                pubDate = xmlNode.InnerText
            End If
            xmlNode = items(i).SelectSingleNode("atom:updated", mgr)
            If Not xmlNode Is Nothing Then
                pubDate = xmlNode.InnerText
            End If
            xmlWriter.WriteStartElement("item")
            xmlWriter.WriteElementString("title", title)
            xmlWriter.WriteElementString("link", link)
            If pubDate.Length < 1 Then
                pubDate = Date.MinValue.ToString()
            End If
            xmlWriter.WriteElementString("pubDate", Convert.ToDateTime(pubDate).ToUniversalTime().ToString("ddd, dd MMM yyyy HH:mm:ss G\MT"))
            xmlWriter.WriteElementString("author", author)
            xmlWriter.WriteElementString("description", description)
            xmlWriter.WriteEndElement()
        Next
        xmlWriter.WriteEndElement()
        xmlWriter.Flush()
        xmlWriter.Close()
    End If
    Dim retDoc As New XmlDocument()
    Dim outStr As String = Encoding.UTF8.GetString(memoryStream.ToArray())
    retDoc.LoadXml(outStr)
    Return retDoc
End Function

Usage is fairly straight forward. Simply load in your ATOM feed into an XmlDocument object and pass it to this function, and you’ll get an XmlDocument object back, in RSS format!

If you’re interested, I’ve put an entire RSSReader class up on pastebin.com