工作中点滴记录

永远保持学徒心态
  博客园 :: 首页 :: 博问 :: 闪存 :: 新随笔 :: 联系 :: 订阅 订阅 :: 管理 ::
Rss内容读取

有时候会遇见要读取网站提供的rss，这时候需要用到XmlDocument类来实现。

以博客园为例，我的博客的rss地址是http://www.cnblogs.com/hfliyi/rss，把读取后的内容插入到数据库中，

代码如下：

table 
1 CREATE TABLE [Rss](
2     [id] [int] IDENTITY(1,1) primary key NOT NULL,
3     [link] [nvarchar](300) NULL,
4     [title] [nvarchar](200) NULL,
5     [summary] [nvarchar](max) NULL,
6     [author] [nvarchar](50) NULL,
7     [content] [nvarchar](max) NULL,
8     [published] [date] NULL,
9     )

操作代码：

操作代码 
  1 public partial class _Default : System.Web.UI.Page
  2 {
  3     protected void Page_Load(object sender, EventArgs e)
  4     {
  5         if (!IsPostBack)
  6         {
  7             WriteDataTable();
  8             BindGridView();
  9         }
 10     }
 11     public DataTable CreateXmlTable()
 12     {
 13         DataTable dt = new DataTable();
 14         dt.Columns.Add("Link", typeof(string));
 15         dt.Columns.Add("title", typeof(string));
 16         dt.Columns.Add("summary", typeof(string));
 17         dt.Columns.Add("author", typeof(string));
 18         dt.Columns.Add("content", typeof(string));
 19         dt.Columns.Add("published", typeof(string));
 20         return dt;
 21     }
 22 
 23     public void WriteDataTable()
 24     {
 25         DataTable dt = CreateXmlTable();
 26         string strRss = "http://www.cnblogs.com/hfliyi/rss";
 27         XmlDocument docment = new XmlDocument();
 28         docment.Load(strRss);
 29         XmlNodeList list = docment.GetElementsByTagName("entry");
 30         if (docment.HasChildNodes)
 31         {
 32             foreach (XmlNode var in list)
 33             {
 34                 DataRow dr = dt.NewRow();
 35                 if (var.HasChildNodes == true)
 36                 {
 37                     XmlNodeList objList = var.ChildNodes;
 38                     foreach (XmlNode v in objList)
 39                     {
 40                         if (v.Name.ToLower() == "title")
 41                         {
 42                             dr["title"] = v.InnerText;
 43                         }
 44                         if (v.Name.ToLower() == "id")
 45                         {
 46                             dr["link"] = v.InnerText;
 47                         }
 48                         if (v.Name.ToLower() == "summary")
 49                         {
 50                             dr["summary"] = v.InnerText;
 51                         }
 52                         if (v.Name.ToLower() == "author")
 53                         {
 54                             dr["author"] = v.InnerText;
 55                         }
 56                         if (v.Name.ToLower() == "content")
 57                         {
 58                             dr["content"] = v.InnerText;
 59                         }
 60                         if (v.Name.ToLower() == "published")
 61                         {
 62                             dr["published"] = v.InnerText;
 63                         }
 64                     }
 65                 }
 66                 dt.Rows.Add(dr);
 67             }
 68         }
 69         WriteToSQL(dt);
 70     }
 71 
 72     public void WriteToSQL(DataTable dt)
 73     {
 74 
 75         if (dt == null || dt.Rows.Count <= 0)
 76         {
 77             return;
 78         }
 79         for (int i = 0; i < dt.Rows.Count; i++)
 80         {
 81             RssModel model = new RssModel();
 82             model.Link = dt.Rows[i]["link"].ToString();
 83             model.Author = dt.Rows[i]["author"].ToString();
 84             model.Content = dt.Rows[i]["content"].ToString();
 85             model.Published = Convert.ToDateTime(dt.Rows[i]["published"].ToString());
 86             model.Summary = dt.Rows[i]["summary"].ToString();
 87             model.Title = dt.Rows[i]["title"].ToString();
 88             if (!IsExistsByLink(model.Link))
 89             {
 90                 ExcuteNonQuery(model);
 91             }
 92         }
 93     }
 94     public void ExcuteNonQuery(RssModel model)
 95     {
 96         string connectionString = ConfigurationManager.ConnectionStrings["Conn"].ConnectionString;
 97         using (SqlConnection con = new SqlConnection(connectionString))
 98         {
 99             con.Open();
100             SqlCommand cmd = con.CreateCommand();
101             cmd.CommandText = "INSERT INTO Rss([link],[title],[summary],[author],[content],[published]) VALUES(@link,@title,@summary,@author,@content,@published)";
102             SqlParameter[] sp ={ 
103             new SqlParameter("@link",SqlDbType.NVarChar,300),
104                     new SqlParameter("@title",SqlDbType.NVarChar,200),
105                 new SqlParameter("@summary",SqlDbType.NVarChar,4000),
106                 new SqlParameter("@author",SqlDbType.NVarChar,50),
107                 new SqlParameter("@content",SqlDbType.NVarChar,4000),
108                 new SqlParameter("@published",SqlDbType.Date)
109             };
110             sp[0].Value = model.Link;
111             sp[1].Value = model.Title;
112             sp[2].Value = model.Summary;
113             sp[3].Value = model.Author;
114             sp[4].Value = model.Content;
115             sp[5].Value = Convert.ToDateTime(model.Published);
116             cmd.Parameters.AddRange(sp);
117             cmd.ExecuteNonQuery();
118         }
119     }
120     public void BindGridView()
121     {
122         string connectionString = ConfigurationManager.ConnectionStrings["Conn"].ConnectionString;
123         using (SqlConnection con = new SqlConnection(connectionString))
124         {
125             SqlCommand cmd = con.CreateCommand();
126             cmd.CommandText = "SELECT * FROM RSS";
127             SqlDataAdapter da = new SqlDataAdapter(cmd);
128             DataSet ds = new DataSet();
129             da.Fill(ds);
130             this.gv_state.DataSource = ds.Tables[0];
131             this.gv_state.DataBind();
132         }
133     }
134     public bool IsExistsByLink(string link)
135     {
136         string ConnectionString = ConfigurationManager.ConnectionStrings["Conn"].ConnectionString.ToString();
137         using (SqlConnection con = new SqlConnection(ConnectionString))
138         {
139             con.Open();
140             string strSql = String.Format("SELECT COUNT(0) FROM RSS WHERE LINK='{0}'", link);
141             SqlCommand cmd = con.CreateCommand();
142             cmd.CommandText = strSql;
143             object ob = cmd.ExecuteScalar();
144             return Convert.ToInt32(ob) > 0;
145         }
146     }
147 
148 }
149 public class RssModel
150 {
151     public RssModel()
152     {
153     }
154     private string link;
155     public string Link
156     {
157         get { return link; }
158         set { link = value; }
159     }
160 
161     private string title;
162     public string Title
163     {
164         get { return title; }
165         set { title = value; }
166     }
167 
168     private string summary;
169     public string Summary
170     {
171         get { return summary; }
172         set { summary = value; }
173     }
174 
175     private string author;
176     public string Author
177     {
178         get { return author; }
179         set { author = value; }
180     }
181 
182     private string content;
183     public string Content
184     {
185         get { return content; }
186         set { content = value; }
187     }
188 
189     private DateTime published;
190     public DateTime Published
191     {
192         get { return published; }
193         set { published = value; }
194     }
195 }

前台源代码：

前台原代码 
 1             <asp:GridView ID="gv_state" runat="server" GridLines="None" BorderWidth="0px" CellPadding="0"
 2                 CellSpacing="1" align="center" AutoGenerateColumns="false">
 3                 <Columns>
 4                     <asp:TemplateField HeaderText="文章标题">
 5                         <ItemTemplate>
 6                             <a href='<%#Eval("link") %>' target="_blank">
 7                                 <%#Eval("title")%>
 8                             </a>
 9                         </ItemTemplate>
10                         <ItemStyle Width="20%" />
11                     </asp:TemplateField>
12                     <asp:TemplateField HeaderText="作者">
13                         <ItemTemplate>
14                             <%#((System.Data.DataRowView)Container.DataItem)["author"]%>
15                         </ItemTemplate>
16                         <ItemStyle Width="20%" />
17                     </asp:TemplateField>
18                     <asp:TemplateField HeaderText="发布日期">
19                         <ItemTemplate>
20                             <%#((System.Data.DataRowView)Container.DataItem)["published"]%>
21                         </ItemTemplate>
22                         <ItemStyle Width="20%" />
23                     </asp:TemplateField>
24                     <asp:TemplateField HeaderText="摘要">
25                         <ItemTemplate>
26                             <%#Eval("summary").ToString().Length>20?Eval("summary").ToString().Substring(0,20):Eval("summary")%>
27                         </ItemTemplate>
28                         <ItemStyle Width="20%" />
29                     </asp:TemplateField>
30                 </Columns>
31                 <RowStyle CssClass="tr3" Font-Size="12px" Height="28px" />
32                 <HeaderStyle CssClass="itable_title" />
33                 <EmptyDataTemplate>
34                     <tr class="itable_title">
35                         <th width="20%">
36                             文章标题
37                         </th>
38                         <th width="20%">
39                             作者
40                         </th>
41                         <th width="20%">
42                             发布日期
43                         </th>
44                         <th width="20%">
45                             摘要
46                         </th>
47                     </tr>
48                     <tr class="tr3">
49                         <td class="grid_no_result" colspan="4">
50                             <span>当前没有查询记录</span>
51                         </td>
52                     </tr>
53                 </EmptyDataTemplate>
54             </asp:GridView>

 例如读取新浪财经rss,代码如下：

View Code 
  1 public partial class Default2 : System.Web.UI.Page
  2 {
  3     protected void Page_Load(object sender, EventArgs e)
  4     {
  5         if (!IsPostBack)
  6         {
  7             ReadRss();
  8             BindGridView();
  9         }
 10     }
 11     public DataTable CreateXmlTable()
 12     {
 13         DataTable dt = new DataTable();
 14         dt.Columns.Add("Link", typeof(string));
 15         dt.Columns.Add("title", typeof(string));
 16         dt.Columns.Add("summary", typeof(string));
 17         dt.Columns.Add("author", typeof(string));
 18         dt.Columns.Add("content", typeof(string));
 19         dt.Columns.Add("published", typeof(string));
 20         return dt;
 21     }
 22     public void BindGridView()
 23     {
 24         string connectionString = ConfigurationManager.ConnectionStrings["Conn"].ConnectionString;
 25         using (SqlConnection con = new SqlConnection(connectionString))
 26         {
 27             SqlCommand cmd = con.CreateCommand();
 28             cmd.CommandText = "SELECT * FROM RSS WHERE summary='财经要闻汇总'";
 29             SqlDataAdapter da = new SqlDataAdapter(cmd);
 30             DataSet ds = new DataSet();
 31             da.Fill(ds);
 32             this.gv_state.DataSource = ds.Tables[0];
 33             this.gv_state.DataBind();
 34         }
 35     }
 36     public void ReadRss()
 37     {
 38         DataTable dt = CreateXmlTable();
 39         string rss = @"http://rss.sina.com.cn/roll/finance/hot_roll.xml";
 40         XmlDocument document = new XmlDocument();
 41         document.Load(rss);
 42         XmlNodeList list = document.GetElementsByTagName("item");
 43         if (document.HasChildNodes)
 44         {
 45             foreach (XmlNode var in list)
 46             {
 47                 DataRow dr = dt.NewRow();
 48                 if (var.HasChildNodes)
 49                 {
 50                     XmlNodeList v = var.ChildNodes;
 51                     foreach (XmlNode vv in v)
 52                     {
 53                         switch (vv.Name)
 54                         {
 55                             case "title":
 56                                 dr["title"] = vv.InnerText;
 57                                 break;
 58                             case "author":
 59                                 dr["author"] = vv.InnerText;
 60                                 break;
 61                             case "link":
 62                                 dr["Link"] = vv.InnerText;
 63                                 break;
 64                             case "category":
 65                                 dr["summary"] = vv.InnerText;
 66                                 break;
 67                             case "description":
 68                                 dr["content"] = vv.InnerText;
 69                                 break;
 70                             case "pubDate":
 71                                 dr["published"] = vv.InnerText;
 72                                 break;
 73                             default:
 74                                 break;
 75                         }
 76                     }
 77                 }
 78                 dt.Rows.Add(dr);
 79             }
 80             WriteToSQL(dt);
 81         }
 82     }
 83     public void ExcuteNonQuery(RssMod model)
 84     {
 85         string connectionString = ConfigurationManager.ConnectionStrings["Conn"].ConnectionString;
 86         using (SqlConnection con = new SqlConnection(connectionString))
 87         {
 88             con.Open();
 89             SqlCommand cmd = con.CreateCommand();
 90             cmd.CommandText = "INSERT INTO Rss([link],[title],[summary],[author],[content],[published]) VALUES(@link,@title,@summary,@author,@content,@published)";
 91             SqlParameter[] sp ={ 
 92             new SqlParameter("@link",SqlDbType.NVarChar,300),
 93                     new SqlParameter("@title",SqlDbType.NVarChar,200),
 94                 new SqlParameter("@summary",SqlDbType.NVarChar,4000),
 95                 new SqlParameter("@author",SqlDbType.NVarChar,50),
 96                 new SqlParameter("@content",SqlDbType.NVarChar,4000),
 97                 new SqlParameter("@published",SqlDbType.Date)
 98             };
 99             sp[0].Value = model.Link;
100             sp[1].Value = model.Title;
101             sp[2].Value = model.Summary;
102             sp[3].Value = model.Author;
103             sp[4].Value = model.Content;
104             sp[5].Value = Convert.ToDateTime(model.Published);
105             cmd.Parameters.AddRange(sp);
106             cmd.ExecuteNonQuery();
107         }
108     }
109     public bool IsExistsByLink(string link)
110     {
111         string ConnectionString = ConfigurationManager.ConnectionStrings["Conn"].ConnectionString.ToString();
112         using (SqlConnection con = new SqlConnection(ConnectionString))
113         {
114             con.Open();
115             string strSql = String.Format("SELECT COUNT(0) FROM RSS WHERE LINK='{0}'", link);
116             SqlCommand cmd = con.CreateCommand();
117             cmd.CommandText = strSql;
118             object ob = cmd.ExecuteScalar();
119             return Convert.ToInt32(ob) > 0;
120         }
121     }
122     public void WriteToSQL(DataTable dt)
123     {
124 
125         if (dt == null || dt.Rows.Count <= 0)
126         {
127             return;
128         }
129         for (int i = 0; i < dt.Rows.Count; i++)
130         {
131             RssMod model = new RssMod();
132             model.Link = dt.Rows[i]["link"].ToString();
133             model.Author = dt.Rows[i]["author"].ToString();
134             model.Content = dt.Rows[i]["content"].ToString();
135             model.Published = Convert.ToDateTime(dt.Rows[i]["published"].ToString());
136             model.Summary = dt.Rows[i]["summary"].ToString();
137             model.Title = dt.Rows[i]["title"].ToString();
138             if (!IsExistsByLink(model.Link))
139             {
140                 ExcuteNonQuery(model);
141             }
142         }
143     }
144 }
145 public class RssMod
146 {
147     public RssMod()
148     {
149     }
150     private string link;
151     public string Link
152     {
153         get { return link; }
154         set { link = value; }
155     }
156 
157     private string title;
158     public string Title
159     {
160         get { return title; }
161         set { title = value; }
162     }
163 
164     private string summary;
165     public string Summary
166     {
167         get { return summary; }
168         set { summary = value; }
169     }
170 
171     private string author;
172     public string Author
173     {
174         get { return author; }
175         set { author = value; }
176     }
177 
178     private string content;
179     public string Content
180     {
181         get { return content; }
182         set { content = value; }
183     }
184 
185     private DateTime published;
186     public DateTime Published
187     {
188         get { return published; }
189         set { published = value; }
190     }
191 }

 -------

读取博客园rss

Model 
 1 namespace NeoModel
 2 {
 3     public class RssReader
 4     {
 5         public RssReader()
 6         {
 7         }
 8         private int _id;
 9         public int ID
10         {
11             get { return _id; }
12             set { _id = value; }
13         }
14 
15         private string _title;
16         public string Title
17         {
18             get { return _title; }
19             set { _title = value; }
20         }
21 
22         private DateTime? _pubdate;
23         public DateTime? PubDate
24         {
25             get { return _pubdate; }
26             set { _pubdate = value; }
27         }
28 
29         private string _guid;
30         public string Guid
31         {
32             get { return _guid; }
33             set { _guid = value; }
34         }
35 
36         private string _description;
37         public string Description
38         {
39             get { return _description; }
40             set { _description = value; }
41         }
42     }
43 }
DAL 
 1 namespace NeoDAL
 2 {
 3     public class RssReaderDal
 4     {
 5         public RssReaderDal()
 6         {
 7         }
 8         /// <summary>
 9         /// 添加rss
10         /// </summary>
11         /// <param name="rss"></param>
12         /// <returns></returns>
13         public bool AddRssReader(NeoModel.RssReader rss)
14         {
15             string strSql = "Insert into RssReader(title,pubdate,[guid],[description]) values(@title,@pubdate,@guid,@description)";
16             SqlParameter[] sp = { 
17                                new SqlParameter("@title",rss.Title),
18                                new SqlParameter("@pubdate",rss.PubDate),
19                                new SqlParameter("@guid",rss.Guid),
20                                new SqlParameter("@description",rss.Description)
21                                };
22             return DbHelperSQL.ExecuteSql(strSql, sp) > 0;
23 
24         }
25         /// <summary>
26         /// 判断rss是否存在
27         /// </summary>
28         /// <param name="guid"></param>
29         /// <returns></returns>
30         public bool IsExistRssByGuid(string guid)
31         {
32             string strSql = "SELECT COUNT(0) FROM RssReader WHERE [guid]=@guid";
33             SqlParameter[] sp = { 
34                                 new SqlParameter("@guid",guid)
35                                 };
36             return Convert.ToInt32(DbHelperSQL.GetSingle(strSql, sp)) > 0;
37         }
38         /// <summary>
39         /// 
40         /// </summary>
41         /// <returns></returns>
42         public DataTable GetRss()
43         {
44             string strSql = "Select * from RssReader order by pubdate desc";
45             DataSet ds = DbHelperSQL.Query(strSql);
46             if (ds == null || ds.Tables.Count <= 0 || ds.Tables[0].Rows.Count <= 0)
47             {
48                 return new DataTable();
49             }
50             return ds.Tables[0];
51         }
52 
53     }
54 }
BLL 
 1 namespace NeoBLL
 2 {
 3     public class RssReader
 4     {
 5         NeoDAL.RssReaderDal dal = new NeoDAL.RssReaderDal();
 6         public RssReader() { }
 7 
 8         /// <summary>
 9         /// 
10         /// </summary>
11         /// <param name="rss"></param>
12         /// <returns></returns>
13         public bool AddRssReader(NeoModel.RssReader rss)
14         {
15             return dal.AddRssReader(rss);
16         }
17         /// <summary>
18         /// 
19         /// </summary>
20         /// <param name="guid"></param>
21         /// <returns></returns>
22         public bool IsExistRssByGuid(string guid)
23         {
24             return dal.IsExistRssByGuid(guid);
25         }
26         public DataTable GetRss()
27         {
28             return dal.GetRss();
29         }
30     }
31 }
页面源 
 1 <asp:Content ID="Content1" ContentPlaceHolderID="head" runat="server">
 2     <style type="text/css">
 3         .title
 4         {
 5             font-size: 11pt;
 6             margin: 5px 0;
 7             background: transparent url(../images/icon.rss.current.png) no-repeat 4px 50%;
 8             padding-left: 28px;
 9             word-break: break-word;
10             -webkit-user-select: text;
11         }
12         h3, h4
13         {
14             padding: 0;
15         }
16         a
17         {
18             color: #036;
19         }
20         h3
21         {
22             display: block;
23             -webkit-margin-before: 1em;
24             -webkit-margin-after: 1em;
25             -webkit-margin-start: 0px;
26             -webkit-margin-end: 0px;
27             font-weight: bold;
28         }
29         h4
30         {
31             display: block;
32             -webkit-margin-before: 1.33em;
33             -webkit-margin-after: 1.33em;
34             -webkit-margin-start: 0px;
35             -webkit-margin-end: 0px;
36         }
37         .updated
38         {
39             color: #666;
40             font-weight: normal;
41              padding-left:8px;
42             margin: 5px 0;
43         }
44         .description
45         {
46             margin: 14px 20px 20px 0;
47             padding-left:8px;
48             max-width: 850px;
49             line-height: 1.8;
50             font-size: 10pt;
51             word-break: break-word;
52         }
53         .actions
54         {
55             padding: 5px 8px;
56             background-color: #f4f5f5;
57             border-radius: 3px;
58              width:99%;
59         }
60         div
61         {
62             display: block;
63             width: 100%;
64         }
65         body
66         {
67             color: Black;
68             cursor: default;
69             font-size: 9pt;
70             font-family: Segoe UI, 微软雅黑 , Tahoma;
71         }
72     </style>
73 </asp:Content>
74 <asp:Content ID="Content2" ContentPlaceHolderID="MainContent" runat="server">
75     <asp:Repeater ID="reprss" runat="server">
76         <ItemTemplate>
77             <div style=" margin:10px; padding:5px; background-color:White; border:1px #ccc solid; border-radius:4px;">
78                 <div>
79                     <h3 class="title">
80                         <a href="<%#Eval("guid") %>" target="_blank">
81                             <%#Eval("title") %></a></h3>
82                     <h4 class="updated">
83                         <%#Eval("pubdate")%>
84                     </h4>
85                 </div>
86                 <div class="description">
87                     <%#Eval("description")%><br />
88                   
89                 </div>
90                 <div class="actions">
91                     <a href="<%#Eval("guid") %>"  target="_blank">打开页面</a>
92                 </div>
93             </div>
94         </ItemTemplate>
95     </asp:Repeater>
96 </asp:Content>
后台 
 1 namespace NeoBackground.Baidu
 2 {
 3     public partial class RssReader : System.Web.UI.Page
 4     {
 5         NeoBLL.RssReader bll = new NeoBLL.RssReader();
 6         protected void Page_Load(object sender, EventArgs e)
 7         {
 8             if (!IsPostBack)
 9             {
10                 // WriterRss();
11                 DataTable dt = bll.GetRss();
12                 this.reprss.DataSource = dt;
13                 this.reprss.DataBind();
14             }
15         }
16 
17 
18 
19         public void WriterRss()
20         {
21             string url = "http://feed.cnblogs.com/news/rss";
22             XmlDocument document = new XmlDocument();
23             document.Load(url);//
24             XmlNodeList list = document.GetElementsByTagName("item");
25             if (document.HasChildNodes)
26             {
27                 foreach (XmlNode xn in list)
28                 {
29                     if (xn.HasChildNodes)
30                     {
31 
32                         NeoModel.RssReader rss = new NeoModel.RssReader();
33                         XmlNodeList xlcd = xn.ChildNodes;
34                         foreach (XmlNode xmlchild in xlcd)
35                         {
36                             switch (xmlchild.Name)//节点的限定名字
37                             {
38                                 case "title":
39                                     rss.Title = xmlchild.InnerText;
40                                     break;
41                                 case "pubDate":
42                                     rss.PubDate = Convert.ToDateTime(xmlchild.InnerText);
43                                     break;
44                                 case "guid":
45                                     rss.Guid = xmlchild.InnerText;
46                                     break;
47                                 case "description":
48                                     rss.Description = xmlchild.InnerText;
49                                     break;
50                                 default:
51                                     break;
52                             }
53                         }
54                         if (!bll.IsExistRssByGuid(rss.Guid))
55                         {
56                             bll.AddRssReader(rss);
57                         }
58                     }
59                 }
60             }
61         }
62     }
63 }
RssReader 
 1 CREATE TABLE [dbo].[RssReader](
 2     [id] [int] IDENTITY(1,1) NOT NULL,
 3     [title] [nvarchar](500) NULL,
 4     [pubdate] [datetime] NULL,
 5     [guid] [nvarchar](500) NULL,
 6     [description] [ntext] NULL,
 7  CONSTRAINT [PK_RssReader] PRIMARY KEY CLUSTERED 
 8 (
 9     [id] ASC
10 )WITH (PAD_INDEX  = OFF, STATISTICS_NORECOMPUTE  = OFF, IGNORE_DUP_KEY = OFF, ALLOW_ROW_LOCKS  = ON, ALLOW_PAGE_LOCKS  = ON) ON [PRIMARY]
11 ) ON [PRIMARY] TEXTIMAGE_ON [PRIMARY]
12 
13 GO

 

posted on 2012-07-22 14:24  梦里故乡  阅读(1637)  评论(0)  编辑  收藏  举报