Here is a quick example of how to parse an RSS feed in C# using Linq (.NET 3.5 and higher). It is a basic example implemented as a static method in a console application; however, for a real project you may want to create a set of classes to provide a more OO approach.
For this example I am using two objects to hold the RSS item’s data (code in listing 1 and 2).
Listing 1 – RssEnclosure Object
I use this object to hold RSS enclosures (<enclosure />); which provide a way of attaching multimedia content to RSS feeds (found in podcast feeds).
/// <summary>
/// RssEnclosure object
/// </summary>
public class RssEnclosure
{
private string _url;
private double _length;
private string _itemType;
/// <summary>
/// Set/Get url
/// </summary>
public string Url
{
set { _url = value; }
get { return _url; }
}
/// <summary>
/// Set/Get Length
/// </summary>
public double Length
{
set { _length = value; }
get { return _length; }
}
/// <summary>
/// Set/Get itemType
/// </summary>
public string ItemType
{
set { _itemType = value; }
get { return _itemType; }
}
}
Listing 2 – RssItem Object
This object holds your basic RSS item information.
/// <summary>
/// Generic RssItem
/// </summary>
public class RssItem
{
private string _title;
private string _link;
private string _description;
private string _pubDate;
private string _guid;
private string _comments;
private string _author;
private RssEnclosure _enclosure;
/// <summary>
/// Default constructor
/// </summary>
public RssItem()
{
this.Initialize("", "", "", "", "","","",new RssEnclosure());
}
/// <summary>
/// Second constructor
/// </summary>
/// <param name="title">title</param>
/// <param name="link">link</param>
/// <param name="description">description</param>
/// <param name="pubDate">pubDate</param>
/// <param name="guid">guid</param>
/// <param name="author">author</param>
/// <param name="comment">comment</param>
/// <param name="enclosure">enclosure</param>
public RssItem(string title, string link, string description,
string pubDate, string guid,
string comment, string author,
RssEnclosure enclosure)
{
this.Initialize(title, link, description, pubDate,
guid,comment,author,enclosure);
}
/// <summary>
/// Initialize private fields
/// </summary>
/// <param name="title">title</param>
/// <param name="link">link</param>
/// <param name="description">description</param>
/// <param name="pubDate">pubDate</param>
/// <param name="guid">guid</param>
/// <param name="author">author</param>
/// <param name="comment">comment</param>
/// <param name="enclosure">enclosure</param>
private void Initialize(string title, string link, string description,
string pubDate, string guid,
string comment, string author,
RssEnclosure enclosure)
{
_title = title;
_link = link;
_description = description;
_pubDate = pubDate;
_guid = guid;
_comments = "";
_author = "";
_enclosure = new RssEnclosure();
}
#region "Public properties"
///<summary>
///Set/Get title
///</summary>
public string Title
{
set { this._title = value; }
get { return this._title; }
}
///<summary>
///Set/Get link
///</summary>
public string Link
{
set { this._link = value; }
get { return this._link; }
}
///<summary>
///Set/Get description
///</summary>
public string Description
{
set { this._description = value; }
get { return this._description; }
}
///<summary>
///Set/Get pubDate
///</summary>
public string PubDate
{
set { this._pubDate = value; }
get { return this._pubDate; }
}
///<summary>
///Set/Get guid
///</summary>
public string Guid
{
set { this._guid = value; }
get { return this._guid; }
}
/// <summary>
/// Set/Get comment
/// </summary>
public string Comments
{
set { _comments = value; }
get { return _comments; }
}
/// <summary>
/// Set/Get author
/// </summary>
public string Author
{
set { _author = value; }
get { return _author; }
}
/// <summary>
/// Set/Get enclosure
/// </summary>
public RssEnclosure Enclosure
{
set { _enclosure = value; }
get { return _enclosure; }
}
#endregion
}
Listing 3 - The RSS Parsing Method
public static void ParseRss(string feed)
{
ArrayList items = new ArrayList();
var doc = XElement.Load(feed).Elements("channel");
foreach (var itemnodes in doc)
{
foreach (var i in itemnodes.Elements())
{
if (i.Name.LocalName == "item")
{
if (i.HasElements)
{
RssItem rssitem = new RssItem();
foreach (var n in i.Elements())
{
switch (n.Name.LocalName.ToLower())
{
case "title": rssitem.Title = n.Value;
break;
case "link": rssitem.Link = n.Value;
break;
case "description": rssitem.Description = n.Value;
break;
case "author": rssitem.Author = n.Value;
break;
case "pubDate": rssitem.PubDate = n.Value;
break;
case "comments":
rssitem.Comments = (n.Value.Length > 0 ? n.Value : "");
break;
case "enclosure":
RssEnclosure e = new RssEnclosure();
if (n.HasAttributes)
{
e.Url = n.Attribute("url").Value;
e.ItemType = n.Attribute("type").Value;
double len = 0;
double.TryParse(n.Attribute("length").Value, out len);
e.Length = len;
}
rssitem.Enclosure = e;
break;
case "guid": rssitem.Guid = n.Value;
break;
}
}
items.Add(rssitem);
}
}
}
}
//Print content in the console
foreach (RssItem i in items)
{
Console.WriteLine(i.Title);
Console.WriteLine(i.Link);
Console.WriteLine();
Console.WriteLine();
}
}
Usage:
Just call the function passing an RSS feed and it will print in the console.
ParseRss("rss feed");
