ASP.NET數(shù)據(jù)采集的實(shí)現(xiàn)淺析
作者:孤獨(dú)的冰 
  ASP.NET數(shù)據(jù)采集的實(shí)現(xiàn)向你介紹了如何通過(guò)程序?qū)崿F(xiàn)ASP.NET數(shù)據(jù)采集的功能,程序中使用了for循環(huán)來(lái)實(shí)現(xiàn),希望對(duì)你有所幫助。
 這是我自己寫的一個(gè)ASP.NET數(shù)據(jù)采集程序,是采集一個(gè)人才網(wǎng)里面人才的信息,第一次寫B(tài)log,寫的不好不要見笑。
- //先按照下面的字段創(chuàng)建一個(gè)數(shù)據(jù)表 ,以便ASP.NET數(shù)據(jù)采集的歸納
 - 以下為引用的內(nèi)容:
 - public partial class Form2 : Form
 - {
 - public Form2()
 - {
 - InitializeComponent();
 - }
 - //姓名
 - public static string XM = "";
 - //年齡
 - public static string nl = "";
 - //性別
 - public static string XB = "";
 - //身高
 - public static string SG = "";
 - //政治面貌
 - public static string mm = "";
 - //民族
 - public static string MZ = "";
 - //學(xué)歷
 - public static string XL = "";
 - //婚姻狀況
 - public static string HK = "";
 - //所學(xué)專業(yè)
 - public static string ZY = "";
 - //工作經(jīng)驗(yàn)
 - public static string GZJY = "";
 - //在職單位
 - public static string ZZDW = "";
 - //在職職位
 - public static string ZZZW = "";
 - //工作經(jīng)歷
 - public static string GZJL = "";
 - //要求月薪
 - public static string YX = "";
 - //工作性質(zhì)
 - public static string GZXZ = "";
 - //求職意向
 - public static string QZYX = "";
 - //具體職務(wù)
 - public static string JTZW = "";
 - //期望工作地
 - public static string QWGZD = "";
 - //教育情況,語(yǔ)言水平,技術(shù)專長(zhǎng)
 - public static string QT = "";
 - private void button1_Click(object sender, EventArgs e)
 - {
 - label1.Text = "正在采集數(shù)據(jù)……";
 - //遍歷數(shù)據(jù)的頁(yè)數(shù)
 - for (int i = 1; i ﹤=50; i++)
 - {
 - CJ("http://www.xcjob.cn/renli.asp?pageno=" + i);
 - }
 - label1.Text = "恭喜你采集完成!";
 - MessageBox.Show("恭喜你采集完成!");
 - }
 - //ASP.NET數(shù)據(jù)采集之采集數(shù)據(jù)類
 - private void CJ(string Url)
 - {
 - //獲得頁(yè)面源文件(Html)
 - string strWebContent = YM(Url);
 - //按照Html里面的標(biāo)簽 取出和數(shù)據(jù)有關(guān)的那段源碼
 - int iBodyStart = strWebContent.IndexOf("﹤body", 0);
 - int aaa = strWebContent.IndexOf("關(guān)鍵字:", iBodyStart);
 - int iTableStart = strWebContent.IndexOf("﹤table", aaa);
 - int iTableEnd = strWebContent.IndexOf("﹤/table﹥", iTableStart);
 - string strWeb = strWebContent.Substring(iTableStart, iTableEnd - iTableStart);
 - //生成HtmlDocument
 - HtmlElementCollection htmlTR = HtmlTR_Content(strWeb, "tr");
 - foreach (HtmlElement tr in htmlTR)
 - {
 - try
 - {
 - //姓名
 - XM = tr.GetElementsByTagName("a")[0].InnerText;
 - //獲得詳細(xì)信息頁(yè)面的網(wǎng)址
 - string a = tr.GetElementsByTagName("a")[0].GetAttribute("href").ToString();
 - a = "http://www.xcjob.cn" + a.Substring(11);
 - Content(a);
 - }
 - catch { }
 - }
 - }
 - //ASP.NET數(shù)據(jù)采集之采集詳細(xì)數(shù)據(jù)類
 - private void Content(string URL)
 - {
 - try
 - {
 - string strWebContent = YM(URL);
 - //按照Html里面的標(biāo)簽 取出和數(shù)據(jù)有關(guān)的那段源碼
 - int iBodyStart = strWebContent.IndexOf("﹤body", 0);
 - int iTableStart = strWebContent.IndexOf("瀏覽次數(shù)", iBodyStart);
 - int iTableEnd = strWebContent.IndexOf("﹤table", iTableStart);
 - int dd = strWebContent.IndexOf("﹤/table﹥", iTableEnd);
 - string strWeb = strWebContent.Substring(iTableEnd, dd - iTableEnd + 8);
 - HtmlElementCollection htmlTR = HtmlTR_Content(strWeb, "table");
 - foreach (HtmlElement tr in htmlTR)
 - {
 - try
 - {
 - //年齡
 - nl = tr.GetElementsByTagName("tr")[1].GetElementsByTagName("td")[1].InnerText;
 - //性別
 - string XB_SG = tr.GetElementsByTagName("tr")[1].GetElementsByTagName("td")[3].InnerText;
 - XB = XB_SG.Substring(0, 1);
 - //身高
 - SG = XB_SG.Substring(11);
 - //政治面貌
 - mm = tr.GetElementsByTagName("tr")[2].GetElementsByTagName("td")[1].InnerText;
 - //民族
 - MZ = tr.GetElementsByTagName("tr")[2].GetElementsByTagName("td")[3].InnerText;
 - //學(xué)歷
 - XL = tr.GetElementsByTagName("tr")[3].GetElementsByTagName("td")[1].InnerText;
 - //婚煙狀況
 - HK = tr.GetElementsByTagName("tr")[3].GetElementsByTagName("td")[3].InnerText;
 - //所學(xué)專業(yè)
 - ZY = tr.GetElementsByTagName("tr")[5].GetElementsByTagName("td")[1].InnerText;
 - //工作經(jīng)驗(yàn)
 - GZJY = tr.GetElementsByTagName("tr")[5].GetElementsByTagName("td")[3].InnerText;
 - //在職單位
 - ZZDW = tr.GetElementsByTagName("tr")[6].GetElementsByTagName("td")[1].InnerText;
 - //在職職位
 - ZZZW = tr.GetElementsByTagName("tr")[6].GetElementsByTagName("td")[3].InnerText;
 - //工作經(jīng)歷
 - GZJY = tr.GetElementsByTagName("tr")[7].GetElementsByTagName("td")[1].InnerText;
 - //要求月薪
 - YX = tr.GetElementsByTagName("tr")[9].GetElementsByTagName("td")[1].InnerText;
 - //工作性質(zhì)
 - GZXZ = tr.GetElementsByTagName("tr")[9].GetElementsByTagName("td")[3].InnerText;
 - //求職意向
 - QZYX = tr.GetElementsByTagName("tr")[10].GetElementsByTagName("td")[1].InnerText;
 - //具體職務(wù)
 - JTZW = tr.GetElementsByTagName("tr")[10].GetElementsByTagName("td")[3].InnerText;
 - //期望工作地
 - QWGZD = tr.GetElementsByTagName("tr")[11].GetElementsByTagName("td")[1].InnerText;
 - //教育情況,語(yǔ)言水平,技術(shù)專長(zhǎng)
 - QT = tr.GetElementsByTagName("tr")[13].GetElementsByTagName("td")[1].InnerText;
 - insert();
 - }
 - catch
 - { }
 - }
 - }
 - catch { }
 - }
 - //將數(shù)據(jù)插入數(shù)據(jù)庫(kù)
 - private void insert()
 - {
 - try
 - {
 - string str = "Provider=Microsoft.Jet.OleDb.4.0;Data Source=Data.mdb";
 - string sql = "insert into 人才信息 (姓名,年齡,性別,身高,政治面貌,民族,學(xué)歷,婚煙狀況,所學(xué)專業(yè),";
 - sql += "工作經(jīng)驗(yàn),在職單位,在職職位,工作經(jīng)歷,要求月薪,工作性質(zhì),求職意向,具體職務(wù),期望工作地,其他) values ";
 - sql += "('" + XM + "'," + nl + ",'"
 - + XB + "','" + SG + "','" + mm + "','" + MZ + "','"
 - + XL + "','" + HK + "','" + ZY + "','" + GZJY + "','"
 - + ZZDW + "','" + ZZZW + "',";
 - sql += "'" + GZJY + "','" + YX + "','"
 - + GZXZ + "','" + QZYX + "','" + JTZW + "','" + QWGZD + "','" + QT + "')";
 - OleDbConnection con = new OleDbConnection(str);
 - OleDbCommand com = new OleDbCommand(sql, con);
 - con.Open();
 - com.ExecuteNonQuery();
 - con.Close();
 - }
 - catch { }
 - }
 - //返回一個(gè)HtmlElementCollection,然后進(jìn)行查詢內(nèi)容
 - private HtmlElementCollection HtmlTR_Content(string strWeb, string tj)
 - {
 - try
 - {
 - //生成HtmlDocument
 - WebBrowser webb = new WebBrowser();
 - webb.Navigate("about:blank");
 - //window.document返回一個(gè)htmldocument對(duì)象,表示對(duì)一個(gè)html文檔的操作
 - //htmldocument對(duì)象是在xmldocument基礎(chǔ)上建立的,具有xmldocument的一切方法屬性
 - HtmlDocument htmldoc = webb.Document.OpenNew(true);
 - htmldoc.Write(strWeb);
 - HtmlElementCollection htmlTR = htmldoc.GetElementsByTagName(tj);
 - return htmlTR;
 - }
 - catch { return null; }
 - }
 - //獲得網(wǎng)址原代碼
 - private string YM(string Url)
 - {
 - string strResult = "";
 - try
 - {
 - HttpWebRequest request = (HttpWebRequest)WebRequest.Create(Url);
 - request.Method = "GET";
 - HttpWebResponse response = (HttpWebResponse)request.GetResponse();
 - Stream streamReceive = response.GetResponseStream();
 - Encoding encoding = Encoding.GetEncoding("GB2312");
 - StreamReader streamReader = new StreamReader(streamReceive, encoding);
 - strResult = streamReader.ReadToEnd();
 - }
 - catch { }
 - return strResult;
 - }
 - }
 
這個(gè)ASP.NET數(shù)據(jù)采集程序?qū)懙牟皇翘?,是用for循環(huán)遍歷出來(lái)的,效率不是太高,可以使用多線程實(shí)現(xiàn)ASP.NET數(shù)據(jù)采集,那么希望對(duì)你了解ASP.NET數(shù)據(jù)采集有所幫助。
【編輯推薦】
責(zé)任編輯:仲衡 
                    來(lái)源:
                    中國(guó)站長(zhǎng)站
 














 
 
 
 
 
 
 