一区二区久久-一区二区三区www-一区二区三区久久-一区二区三区久久精品-麻豆国产一区二区在线观看-麻豆国产视频

asp.net(c#)做一個網(wǎng)頁數(shù)據(jù)采集工具

通過這個軟件一兩天就完成了幾千產(chǎn)品數(shù)據(jù)的錄入,可見很多工作不是一味用人工去做,作為一個程序員,就是要讓很多讓那些經(jīng)常做重復(fù)性的、繁瑣的工作中的人解放出來。下面只是寫了一些核心代碼,而且采集必須要和對應(yīng)網(wǎng)站相掛鉤,作者:鄭少群

復(fù)制代碼 代碼如下:
//提取產(chǎn)品列表頁中產(chǎn)品最終頁的網(wǎng)頁
private void button1_Click(object sender, EventArgs e)
{
if (textBox1.Text.Trim() == "" || textBox2.Text.Trim() == "")
{
MessageBox.Show("網(wǎng)址和域名不能為空!", "信息提示", MessageBoxButtons.OK, MessageBoxIcon.Information);
return;
}
try
{
string Html = inc.GetHtml("http://study.pctoday.NET.cn");
//ArrayList al = inc.GetMatchesStr(Html, "<a[^>]*?>.*?</a>");
ArrayList al = inc.GetMatchesStr(Html, @"href/s*=/s*(?:[/'/""/s](?<1>[^/""/']*)[/'/""])");//提取鏈接


" title="Replica Watches:">Replica Watches Buy Full Quality Popular Luxury Watches at Amazing Price, Your One Stop Discount Swiss Watches StoreExclusive Replica Rolex Watches, Tag Heuer Watches Replica, Cartier Watches online Sale!
StringBuilder sb = new StringBuilder();
foreach (object var in al)
{
string a = var.ToString().Replace("/"", "").Replace("'", "");
a = Regex.Replace(a, "href=", "", RegexOptions.IgnoreCase | RegexOptions.Multiline);
if (a.StartsWith("/"))
a = textBox2.Text.Trim() + a;
if (!a.StartsWith("http://"))
a = "http://" + a;
sb.Append(a + "/r/n");
}
textBox5.Text = sb.ToString();//把提取到網(wǎng)址輸出到一個textBox,每個鏈接占一行



MessageBox.Show("共提取" + al.Count.ToString() + "個鏈接", "信息提示", MessageBoxButtons.OK, MessageBoxIcon.Information);

}
catch (Exception err)
{
MessageBox.Show("提取出錯!原因:" + err.Message, "信息提示", MessageBoxButtons.OK, MessageBoxIcon.Information);
}

}




//把采集的產(chǎn)品頁面html代碼進(jìn)行字符串處理,提取需要的代碼,最后保存到本地一個access數(shù)據(jù)庫中,同時提取產(chǎn)品圖片地址并自動現(xiàn)在圖片到本地images文件夾下

private void backgroundWorker1_DoWork(object sender, DoWorkEventArgs e)
{
//填充產(chǎn)品表
Database.ExecuteNonQuery("delete from Tb_Product");
DataTable dt2 = new DataTable();
OleDbConnection conn = new OleDbConnection(Database.ConnectionStrings);
OleDbDataAdapter da = new OleDbDataAdapter("select * from Tb_Product", conn);
OleDbCommandBuilder cb = new OleDbCommandBuilder(da);
da.Fill(dt2);
dt2.Rows.Clear();

BackgroundWorker worker = (BackgroundWorker)sender;//這個是做一個進(jìn)度條

string[] Urls = textBox5.Text.Trim().ToLower().Replace("/r/n", ",").Split(',');
DataTable dt = new DataTable();
StringBuilder ErrorStr = new StringBuilder();
string html = "", ImageDir = AppDomain.CurrentDomain.BaseDirectory + "Images//";

//循環(huán)每次采集網(wǎng)址
for (int i = 0; i < Urls.Length; i++)
{
try
{
if (!worker.CancellationPending)
{
if (Urls[i] == "")
return;
html = inc.GetHtml(Urls[i]);//獲取該url的html代碼
DataRow NewRow = dt2.NewRow();

//產(chǎn)品名
string ProductName = html.Substring(html.IndexOf("<title>") + 7);
NewRow["ProductName"] = ProductName.Remove(ProductName.IndexOf("</title>")).Trim();

//產(chǎn)品編號
NewRow["ModelId"] = NewRow["ProductName"].ToString().Substring(NewRow["ProductName"].ToString().IndexOf("Model:") + 6).Trim();

//產(chǎn)品介紹,這些都是根據(jù)不同網(wǎng)站的html做相應(yīng)的修改
string Introduce = html.Substring(html.IndexOf("Product Details") + 26);
Introduce = Introduce.Remove(Introduce.IndexOf("</table>") + 8).Trim()

NewRow["Introduce"] = Introduce;



" title="Replica Watches:">Replica Watches Buy Full Quality Popular Luxury Watches at Amazing Price, Your One Stop Discount Swiss Watches StoreExclusive Replica Rolex Watches, Tag Heuer Watches Replica, Cartier Watches online Sale!
//下載圖片
string ProductImage = html.Substring(html.IndexOf("align=center><img") + 17);
ProductImage = textBox2.Text.Trim() + ProductImage.Substring(ProductImage.IndexOf("src=/"") + 5);
ProductImage = ProductImage.Remove(ProductImage.IndexOf("/""));
try
{
inc.DownFile(ProductImage, ImageDir + ProductImage.Substring(ProductImage.LastIndexOf("/") + 1));
}
catch (Exception)
{
ErrorStr.Append("下載圖片失敗,圖片地址:" + ImageDir + ProductImage.Substring(ProductImage.LastIndexOf("/") + 1) + "/r/n");
}


dt2.Rows.Add(NewRow);

//Thread.Sleep(100);
worker.ReportProgress((i + 1) * 100 / Urls.Length, i);
toolStripStatusLabel1.Text = "處理進(jìn)度:" + (i + 1).ToString() + "/" + Urls.Length.ToString();//進(jìn)度條
}

}
catch (Exception err)
{
ErrorStr.Append("采集錯誤:" + err.Message + ";網(wǎng)址:" + Urls[i] + "/r/n");
}
}
da.Update(dt2);
DataBind(dt2);
ShowError(ErrorStr.ToString());
}

/// <summary>
/// ASPX頁面生成靜態(tài)Html頁面,作者:鄭少群
/// </summary>
public static string GetHtml(string url)
{
StreamReader sr = null;
string str = null;
//讀取遠(yuǎn)程路徑
WebRequest request = WebRequest.Create(url);
HttpWebResponse response = (HttpWebResponse)request.GetResponse();
sr = new StreamReader(response.GetResponseStream(), Encoding.GetEncoding(response.CharacterSet));
str = sr.ReadToEnd();
sr.Close();
return str;
}


// 提取HTML代碼中的網(wǎng)址
public static ArrayList GetMatchesStr(string htmlCode, string strRegex)
{
ArrayList al = new ArrayList();

Regex r = new Regex(strRegex, RegexOptions.IgnoreCase | RegexOptions.Multiline);
MatchCollection m = r.Matches(htmlCode);

for (int i = 0; i < m.Count; i++)
{
bool rep = false;
string strNew = m[i].ToString();

// 過濾重復(fù)的URL
foreach (string str in al)
{
if (strNew == str)
{
rep = true;
break;
}
}

if (!rep) al.Add(strNew);
}

al.Sort();

return al;
}

public static void DownFile(string Url, string Path)
{

HttpWebRequest request = (HttpWebRequest)WebRequest.Create(Url);
HttpWebResponse response = (HttpWebResponse)request.GetResponse();
Stream stream = response.GetResponseStream();
long size = response.ContentLength;
//創(chuàng)建文件流對象
using (FileStream fs = new FileStream(Path, FileMode.OpenOrCreate, FileAccess.Write))
{
byte[] b = new byte[1025];
int n = 0;
while ((n = stream.Read(b, 0, 1024)) > 0)
{
fs.Write(b, 0, n);
}
}
}

AspNet技術(shù)asp.net(c#)做一個網(wǎng)頁數(shù)據(jù)采集工具,轉(zhuǎn)載需保留來源!

鄭重聲明:本文版權(quán)歸原作者所有,轉(zhuǎn)載文章僅為傳播更多信息之目的,如作者信息標(biāo)記有誤,請第一時間聯(lián)系我們修改或刪除,多謝。

主站蜘蛛池模板: 国产区成人精品视频 | 五月深爱婷婷 | 91探花福利精品国产自产在线 | 激情五月网站 | 77788色淫网站免费观看 | 黄视频网站大全 | 亚洲精品日韩中文字幕久久久 | 99久久伊人一区二区yy5099 | 精品视频久久 | 色偷偷尼玛图亚洲综合 | 人人狠狠综合久久亚洲88 | 一木道一二三区精品 | 在线成人 | 国产成人精品亚洲 | 国产成人精品免费视频大全可播放的 | 亚洲一区 在线播放 | 一区二区三区四区五区六区 | 伊人宗合网| 欧美一级激情 | 99视频这里有精品 | 四虎在线最新地址4hu | 在线观看一区二区精品视频 | 国产色中色 | 国产一区二区三区免费 | 亚洲欧美久久婷婷爱综合一区天堂 | www.91自拍 | 就操网| 国产成人激烈叫床声视频对白 | 在线看黄网址 | 国产精品免费精品自在线观看 | 99久久伊人 | 国产99久久久久久免费看 | 国产欧美性综合视频性刺激 | 六月丁香婷婷综合 | 色婷婷中文字幕在线一区天堂 | 天天色天天射综合网 | 九一国产精品 | 亚洲一区二区中文字5566 | 丁香婷婷综合五月六月 | 国产一级特黄aa级特黄裸毛片 | 亚洲午夜视频在线 |