Beispiel #1
0
        public static List<ArticleType> SampleList()
        {
            string path = "C:\\Users\\Kgosi\\Documents\\Visual Studio 2012\\Projects\\TheOne\\TheOne\\App_Data\\Articles.xml";
            WebRequest request = WebRequest.Create(path);
            WebResponse response = request.GetResponse();
            StringBuilder sb = new StringBuilder("");
            Stream rssStream = response.GetResponseStream();
            XmlDocument rssDoc = new XmlDocument();
            rssDoc.Load(path);

            XmlNodeList rssItems = rssDoc.SelectNodes("Articles/Article");

            var itemList = new List<ArticleType>();

            for (int i = 0; i < rssItems.Count; i++)
            {
                var tempItem = new ArticleType();
                tempItem.imageUrl = rssItems[i]["ImageURL"].InnerText;
                tempItem.imageCaption = rssItems[i]["ImageCaption"].InnerText;
                tempItem.heading = rssItems[i]["Heading"].InnerText;
                tempItem.source = rssItems[i]["Source"].InnerText;
                tempItem.genre = rssItems[i]["Genre"].InnerText;
                tempItem.content = rssItems[i]["Content"].InnerText;
                tempItem.link = rssItems[i]["Link"].InnerText;

                if (Validators.ValidateArticle(tempItem))
                {
                    itemList.Add(tempItem);
                }
            }

            return itemList;
        }
Beispiel #2
0
        public static bool ValidateArticle(ArticleType article)
        {
            bool isValid = true;
            if (String.IsNullOrEmpty(article.heading) || String.IsNullOrEmpty(article.content))
            {
                isValid = false;
            }

            return isValid;
        }
Beispiel #3
0
        public static List<ArticleType> YahooList(string category)
        {
            var itemList = new List<ArticleType>();

            try
            {
                WebRequest request = WebRequest.Create("http://news.yahoo.com/rss/" + category);
                WebResponse response = request.GetResponse();
                StringBuilder sb = new StringBuilder("");
                Stream rssStream = response.GetResponseStream();
                XmlDocument rssDoc = new XmlDocument();
                rssDoc.Load(rssStream);

                XmlNodeList rssItems = rssDoc.SelectNodes("rss/channel/item");

                for (int i = 0; i < rssItems.Count; i++)
                {
                    var tempItem = new ArticleType();

                    //tempItem.isMain = (i == 0);

                    if (rssItems[i]["media:content"] != null)
                    {
                        var imageUrl = rssItems[i]["media:content"].Attributes[0].InnerText;
                        tempItem.imageUrl = imageUrl;//(tempItem.isMain) ? String.Concat("http", Regex.Split(imageUrl, "http")[2]) : imageUrl;
                    }
                    tempItem.heading = HttpUtility.HtmlDecode(rssItems[i]["title"].InnerText);
                    tempItem.link = rssItems[i]["link"].InnerText;
                    tempItem.content = HttpUtility.HtmlDecode(rssItems[i]["description"].InnerText);
                    tempItem.source = (rssItems[i]["source"] != null) ? String.Concat("Source : ", HttpUtility.HtmlDecode(rssItems[i]["source"].InnerText)) : String.Empty;
                    if (!String.IsNullOrEmpty(rssItems[i]["pubDate"].InnerText))
                    {
                        var pubDate = DateTime.Now.Subtract(DateTime.Parse(rssItems[i]["pubDate"].InnerText)).ToString();
                        tempItem.pubDate = Helpers.PublishDateTime(pubDate);
                    }

                    Regex regex = new Regex(@"</?\w+((\s+\w+(\s*=\s*(?:"".*?""|'.*?'|[^'"">\s]+))?)+\s*|\s*)/?>", RegexOptions.Singleline);

                    tempItem.content = Regex.Replace(tempItem.content, regex.ToString(), String.Empty);

                    if (Validators.ValidateArticle(tempItem))
                    {
                        itemList.Add(tempItem);
                    }
                }
            }
            catch (Exception)
            {
                //throw;
            }

            return itemList;
        }
Beispiel #4
0
        public static List<ArticleType> ReutersList(string category)
        {
            var itemList = new List<ArticleType>();
            var url = String.Empty;

            switch (category)
            {
                case "health":
                    url = "http://feeds.reuters.com/reuters/lifestyle";
                    break;
                case "tech":
                    url = "http://feeds.reuters.com/reuters/technologyNews";
                    break;
                case "business":
                    url = "http://feeds.reuters.com/reuters/businessNews";
                    break;
                case "entertainment":
                    url = "http://feeds.reuters.com/reuters/entertainment";
                    break;
                case "sports":
                    url = "http://feeds.reuters.com/reuters/sportsNews";
                    break;
                default:
                    url = "http://feeds.reuters.com/reuters/topNews";
                    break;
            }

            try
            {
                WebRequest request = WebRequest.Create("http://feeds.reuters.com/Reuters/worldNews");//WebRequest.Create(path);
                WebResponse response = request.GetResponse();
                StringBuilder sb = new StringBuilder("");
                Stream rssStream = response.GetResponseStream();
                XmlDocument rssDoc = new XmlDocument();
                rssDoc.Load(rssStream);

                XmlNodeList rssItems = rssDoc.SelectNodes("rss/channel/item");

                for (int i = 0; i < rssItems.Count; i++)
                {
                    var tempItem = new ArticleType();

                    tempItem.imageUrl = Regex.Match(rssItems[i].InnerXml, "<img.*?src=[\"'](.+?)[\"'].*?>", RegexOptions.IgnoreCase).Groups[1].Value;

                    tempItem.heading = HttpUtility.HtmlDecode(rssItems[i]["title"].InnerText);
                    tempItem.content = HttpUtility.HtmlDecode(rssItems[i]["description"].InnerText);
                    tempItem.link = rssItems[i]["link"].InnerText;

                    Regex regex = new Regex(@"</?\w+((\s+\w+(\s*=\s*(?:"".*?""|'.*?'|[^'"">\s]+))?)+\s*|\s*)/?>", RegexOptions.Singleline);

                    tempItem.content = Regex.Replace(tempItem.content, regex.ToString(), String.Empty);

                    if (Validators.ValidateArticle(tempItem))
                    {
                        itemList.Add(tempItem);
                    }
                }
            }
            catch (Exception)
            {

                //throw;
            }

            return itemList;
        }
        public static List<ArticleType> TimesLiveList(string category)
        {
            var itemList = new List<ArticleType>();
            var url = String.Empty;

            switch (category)
            {
                case "health":
                    url = "http://www.timeslive.co.za/lifestyle/?service=rss";
                    break;
                case "tech":
                    url = "http://www.timeslive.co.za/scitech/?service=rss";
                    break;
                case "business":
                    return null;
                case "entertainment":
                    url = "http://www.timeslive.co.za/entertainment/?service=rss";
                    break;
                case "sports":
                    url = "http://www.timeslive.co.za/sport/?service=rss";
                    break;
                default:
                    url = "http://www.timeslive.co.za/?service=rss";
                    break;
            }

            try
            {
                WebRequest request = WebRequest.Create(url);
                WebResponse response = request.GetResponse();
                StringBuilder sb = new StringBuilder("");
                Stream rssStream = response.GetResponseStream();
                XmlDocument rssDoc = new XmlDocument();
                rssDoc.Load(rssStream);

                XmlNodeList rssItems = rssDoc.SelectNodes("rss/channel/item");

                for (int i = 0; i < rssItems.Count; i++)
                {
                    var tempItem = new ArticleType();

                    //tempItem.imageUrl = Regex.Match(rssItems[i]["description"].InnerText, "<img.*?src=[\"'](.+?)[\"'].*?>", RegexOptions.IgnoreCase).Groups[1].Value;
                    tempItem.imageUrl = (rssItems[i]["enclosure"] != null) ? rssItems[i]["enclosure"].Attributes["url"].Value : String.Empty; ;
                    tempItem.heading = HttpUtility.HtmlDecode((rssItems[i]["title"].InnerText));
                    tempItem.content = HttpUtility.HtmlDecode(rssItems[i]["description"].InnerText);
                    tempItem.link = rssItems[i]["link"].InnerText;
                    //Regex regex = new Regex(@"</?\w+((\s+\w+(\s*=\s*(?:"".*?""|'.*?'|[^'"">\s]+))?)+\s*|\s*)/?>", RegexOptions.Singleline);
                    //tempItem.content = Regex.Replace(tempItem.content, regex.ToString(), String.Empty);
                    if (!String.IsNullOrEmpty(rssItems[i]["pubDate"].InnerText))
                    {
                        var pubDate = DateTime.Now.Subtract(DateTime.Parse(rssItems[i]["pubDate"].InnerText.Replace("\n", "").Trim())).ToString();
                        tempItem.pubDate = Helpers.PublishDateTime(pubDate);
                    }
                    tempItem.source = "Times LIVE";
                    if (Validators.ValidateArticle(tempItem))
                    {
                        itemList.Add(tempItem);
                    }
                }
            }
            catch (Exception)
            {

                //throw;
            }

            return itemList;
        }
        public static List<ArticleType> TwentyFourDotcom(string category)
        {
            var itemList = new List<ArticleType>();
            var url = String.Empty;

            switch (category)
            {
                case "health":
                    url = "http://feeds.health24.com/articles/health24/News/rss";
                    break;
                case "tech":
                    url = "http://feeds.news24.com/articles/News24/SciTech/rss";
                    break;
                case "business":
                    url = "http://feeds.24.com/articles/Fin24/News/rss";
                    break;
                case "entertainment":
                    url = "http://feeds.news24.com/articles/channel/news/rss";
                    break;
                case "sports":
                    url = "http://24.com.feedsportal.com/c/33816/f/607928/index.rss";
                    break;
                default:
                    url = "http://feeds.news24.com/articles/News24/TopStories/rss";
                    break;
            }

            try
            {
                WebRequest request = WebRequest.Create("http://mg.co.za/rss/");//WebRequest.Create(path);
                WebResponse response = request.GetResponse();
                StringBuilder sb = new StringBuilder("");
                Stream rssStream = response.GetResponseStream();
                XmlDocument rssDoc = new XmlDocument();
                rssDoc.Load(rssStream);

                XmlNodeList rssItems = rssDoc.SelectNodes("rss/channel/item");

                for (int i = 0; i < rssItems.Count; i++)
                {
                    var tempItem = new ArticleType();
                    if (rssItems[i]["media:content"] != null)
                    {
                        var imageUrl = rssItems[i]["media:content"].Attributes[0].InnerText;
                        tempItem.imageUrl = String.Concat("http", Regex.Split(imageUrl, "http")[2]);
                    }
                    tempItem.heading = HttpUtility.HtmlDecode(rssItems[i]["title"].InnerText);
                    tempItem.content = HttpUtility.HtmlDecode(rssItems[i]["description"].InnerText);
                    tempItem.source = (rssItems[i]["source"] != null) ? String.Concat("Source : ", HttpUtility.HtmlDecode(rssItems[i]["source"].InnerText)) : String.Empty;
                    tempItem.link = rssItems[i]["link"].InnerText;
                    //tempItem.pubDate = DateTime.Parse(rssItems[i]["pubdate"].InnerText);

                    Regex regex = new Regex(@"</?\w+((\s+\w+(\s*=\s*(?:"".*?""|'.*?'|[^'"">\s]+))?)+\s*|\s*)/?>", RegexOptions.Singleline);

                    tempItem.content = Regex.Replace(tempItem.content, regex.ToString(), String.Empty);

                    if (Validators.ValidateArticle(tempItem))
                    {
                        itemList.Add(tempItem);
                    }
                }
            }
            catch (Exception)
            {

               // throw;
            }

            return itemList;
        }
Beispiel #7
0
        public static List<ArticleType> BBCList(string category)
        {
            var itemList = new List<ArticleType>();
            var url = String.Empty;

            switch (category)
            {
                case "health":
                    url = "http://feeds.bbci.co.uk/health/rss.xml";
                    break;
                case "tech":
                    url = "http://feeds.bbci.co.uk/news/technology/rss.xml";
                    break;
                case "business":
                    url = "http://feeds.bbci.co.uk/news/business/rss.xml";
                    break;
                case "entertainment":
                    url = "http://feeds.bbci.co.uk/news/entertainment_and_arts/rss.xml";
                    break;
                case "sports":
                    url = "http://feeds.bbci.co.uk/sport/rss.xml";
                    break;
                default:
                    url = "http://feeds.bbci.co.uk/news/rss.xml";
                    break;
            }

            try
            {
                WebRequest request = WebRequest.Create("http://feeds.bbci.co.uk/news/rss.xml");//WebRequest.Create(path);
                WebResponse response = request.GetResponse();
                StringBuilder sb = new StringBuilder("");
                Stream rssStream = response.GetResponseStream();
                XmlDocument rssDoc = new XmlDocument();
                rssDoc.Load(rssStream);

                XmlNodeList rssItems = rssDoc.SelectNodes("rss/channel/item");

                for (int i = 0; i < rssItems.Count; i++)
                {
                    var tempItem = new ArticleType();
                    if (rssItems[i]["media:thumbnail"] != null)
                    {
                        if (rssItems[i]["media:thumbnail"].NextSibling != null)
                        {
                            var urls = rssItems[i]["media:thumbnail"].NextSibling;
                            tempItem.imageUrl = urls.Attributes["url"].InnerText;
                        }
                    }
                    tempItem.link = rssItems[i]["link"].InnerText;
                    tempItem.heading = HttpUtility.HtmlDecode((rssItems[i]["title"].InnerText));
                    tempItem.content = HttpUtility.HtmlDecode(rssItems[i]["description"].InnerText);
                    if (!String.IsNullOrEmpty(rssItems[i]["pubDate"].InnerText))
                    {
                        var pubDate = DateTime.Now.Subtract(DateTime.Parse(rssItems[i]["pubDate"].InnerText)).ToString();
                        tempItem.pubDate = Helpers.PublishDateTime(pubDate);
                    }
                    tempItem.source = "BBC News";

                    Regex regex = new Regex(@"</?\w+((\s+\w+(\s*=\s*(?:"".*?""|'.*?'|[^'"">\s]+))?)+\s*|\s*)/?>", RegexOptions.Singleline);

                    tempItem.content = Regex.Replace(tempItem.content, regex.ToString(), String.Empty);

                    if (Validators.ValidateArticle(tempItem))
                    {
                        itemList.Add(tempItem);
                    }
                }
            }
            catch (Exception)
            {
                //throw;
            }

            return itemList;
        }