C# 如何使用C控制台多rss提要阅读器检查机柜标记

我已经创建了C控制台应用程序，它读取多个RSS提要URL，然后获取值并放入数据库

现在我经常遇到wordpress rss提要生成器的问题，其中文章图像带有标记框

如何获取和解析文章图像url，若在源代码附件中，我用代码读取描述标签中的所有图像url

以下是我在数据库中读写的代码：

using (var xmlReader = XmlReader.Create(izvorURLX))
{
    var rssFormatter = new Rss20FeedFormatter();
    rssFormatter.ReadFrom(xmlReader);
    foreach (SyndicationItem syndicationItem in rssFormatter.Feed.Items)
    {
    Console.OutputEncoding = Encoding.UTF8;
    string link = syndicationItem.Links[0].Uri.ToString();
    var statCat1 = Convert.ToString((""));
    foreach (var kategorija in syndicationItem.Categories.Take(1))
    {
    statCat1 = (kategorija.Name);  
    }
    var rr = syndicationItem.AttributeExtensions.Values;
    var LastIZV1 = rssFormatter.Feed.LastUpdatedTime.DateTime;
    var SiteTitle = rssFormatter.Feed.Title.Text;
    var itemFD = Convert.ToString(syndicationItem.Summary.Text);
    string clitemFD = Regex.Replace(itemFD, @"<[^>]*>", String.Empty, RegexOptions.IgnoreCase).Trim();
    var ItemItem = Convert.ToString(rssFormatter.Feed.Items);
    var ff = rssFormatter.Feed.Items.ToString();
    var datumIZV0 = syndicationItem.PublishDate.DateTime;
    var nula = Convert.ToDateTime("01.01.0001 00:00:00");
    var datumIZVX = Convert.ToDateTime(DateTime.Now);
     if (datumIZV0 == nula)
    {
    datumIZVX = Convert.ToDateTime(DateTime.Now);
    }
     else
    {
    datumIZVX = Convert.ToDateTime(datumIZV0);
    }
    XmlDocument doc = new XmlDocument();
    doc.Load(izvorURLX);
    var imgSRC = Convert.ToString("");
    var reg1 = new Regex("src=(?:\"|\')?(?<imgSrc>[^>]*[^/].?:bmp|jpg|jpeg|gif|png))(?:\"|\')?");
    var match1 = reg1.Match(itemFD);
    if (match1.Success)
     {
     Uri UrlImage = new Uri(match1.Groups["imgSrc"].Value, UriKind.Absolute);
    imgSRC = UrlImage.ToString();
    }
    var feedXML = Convert.ToString(izvorURLX);
    int KatX = Convert.ToInt32(KatIzv);
    var statTitle = Convert.ToString(syndicationItem.Title.Text);
    var statLink = Convert.ToString(syndicationItem.Links[0].Uri);
    SqlConnection conn = new SqlConnection("Server=localhost\\SQLEXPRESS;Database=RSSFeedAgregator;Integrated Security=true");
    conn.Open();
    var FeedID = Convert.ToInt32(0);
    var LastinDB = Convert.ToDateTime("01.01.0001 00:00:00");
    string FeedInDB = Convert.ToString("a");
    using (SqlCommand cmdX2 = new SqlCommand("SELECT Feed_ID, Izvor, LastUpd, feed, Kategorija, iID, izvTitle, statCat FROM [dbo].[tbl_feeds]", conn))
    {
    SqlDataReader readerX = cmdX2.ExecuteReader();
    while (readerX.Read())
    {
    Console.OutputEncoding = Encoding.UTF8;
    var feedTxt = Convert.ToString(readerX["feed"]);
    FeedID = Convert.ToInt32(readerX["Feed_ID"]);
    LastinDB = Convert.ToDateTime(readerX["LastUpd"]);
    FeedInDB = Convert.ToString(readerX["feed"]);
    }
    readerX.Close();
    }
     bool inList = DB.Contains(clitemFD);
     var statIMG = Convert.ToString("");
     if (inList == false)
     {
    Console.WriteLine("false: Ne postoi");
    using (SqlCommand cmd1 = new SqlCommand("INSERT INTO tbl_feeds VALUES (" + "@Izvor, @LastUpd, @feed, @Kategorija, @iID, @izvTitle, @statCat, @statTitle, @statLink, @statImage)", conn))
    {
    cmd1.Parameters.AddWithValue("@Izvor", feedXML);
    cmd1.Parameters.AddWithValue("@LastUpd", datumIZVX);
    cmd1.Parameters.AddWithValue("@feed", clitemFD);
    cmd1.Parameters.AddWithValue("@Kategorija", KatX);
    cmd1.Parameters.AddWithValue("@iID", IzvID);
    cmd1.Parameters.AddWithValue("@izvTitle", SiteTitle);
    cmd1.Parameters.AddWithValue("@statCat", statCat1);
    cmd1.Parameters.AddWithValue("@statTitle", statTitle);
    cmd1.Parameters.AddWithValue("@statLink", statLink);
    cmd1.Parameters.AddWithValue("@statImage", imgSRC);
    int rows = cmd1.ExecuteNonQuery();
    Console.WriteLine("Uspesno dodadeno nov zapis !");
     }
    conn.Close();
    }
    else
    {
    Console.WriteLine("true: Postoi");
    }
    }  
    }

对不起，我的代码太长了，但我希望大家能帮助我更好地理解这件事

更新

我还发现了这段代码，这段代码读取附件URL，但只要重复阅读，如果源代码有10篇文章，这段代码读取10次所有10个img URL，并在数据库中保存最后一个

XmlNodeList items = doc.SelectNodes("//item") ;

for (int i = 0; i < items.Count; i++)
{
var   encImg = (items[i].SelectSingleNode("enclosure").Attributes["url"].Value);
}

---

任何人都可以将此代码修改为工作属性？

老实说，我不能很好地理解您的代码，因此我建议您将代码制表/排序

为此，可以使用Ctrl+K+Ctrl+D

您可以检查更多快捷方式

一旦这样说，您就可以使用以下代码行轻松找到附件url：

string link = "";
foreach (SyndicationItem syndicationItem in rssFormatter.Feed.Items)
{
    Console.OutputEncoding = Encoding.UTF8;
    // You have to check if `syndicationItem.Links` has more than 1 element.
    if (syndicationItem.Links.Count > 0)
    {
        // this is the line that shows you the url of the "enclosure" tag:
        link = syndicationItem.Links[1].Uri.ToString();
    }

    // Prints the Image's src.
    Console.WriteLine("Image src: " + link);
}

前面的代码打印我：

Image src: http://a1on.mk/wp-content/uploads/2017/07/turcija-ucenici.jpg
Image src: http://a1on.mk/wp-content/uploads/2017/07/vlada-18juli.jpg
Image src: http://a1on.mk/wp-content/uploads/2017/07/tomas-greminger.jpg
Image src: http://a1on.mk/wp-content/uploads/2014/08/toplo.jpg
Image src: http://a1on.mk/wp-content/uploads/2017/06/grncarov.gif
Image src: http://a1on.mk/wp-content/uploads/2015/04/uprava-finansiska-policija.gif
Image src: http://a1on.mk/wp-content/uploads/2017/05/pritvor-turska.jpg
Image src: http://a1on.mk/wp-content/uploads/2017/07/kosarkari-do20.jpg
Image src: http://a1on.mk/wp-content/uploads/2017/07/vardar-fk-nat.jpg
Image src: http://a1on.mk/wp-content/uploads/2017/07/burgas.jpg

---

不要那样做。你需要使用一个HTML解析器。而且，你的Convert.ToString调用毫无意义。使用First而不是奇怪的循环。我不是专家，你能编写代码如何调用enclosure标记吗？因为我的代码从未定义过外壳读取。感谢Convert.ToString是因为我将所有值作为字符串放入数据库中，然后我也作为字符串读取，而不是XML文件。