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: 国产亚洲综合色就色 | 欧美国产亚洲精品a第一页 欧美国产一区二区二区 | 中文字幕亚洲一区二区三区 | 国产精品九九免费视频 | 久久国产乱子伦精品免费看 | 国产免费网 | 一区二区视频网 | 美女免费黄网站 | 干在线视频 | 成人91在线| 欧美特黄高清免费观看的 | 美女黄的全免费 | 国内自拍网红在线综合 | 成人免费看片视频色多多 | 天天干精品 | 色就色综合 | 激情综合在线 | 国产女人在线 | 99这里只有精品6 | 国语对白一区二区三区 | 国产91在线九色 | 美女网站色在线观看 | 黄色资源视频 | 人人做天天爱夜夜爽中字 | 美女被男人扒开下面无遮无挡 | 成人免费看www网址入口 | 成年人激情网站 | 91视频免费网址 | 国产黄大片 | 中文字幕精品视频在线 | 精品久久久久久久久久中文字幕 | 999精品免费视频 | 国产婷婷色综合成人精品 | 91视频无限看 | 亚洲天码中文字幕第一页 | 国产色一区 | 亚洲欧美精品久久 | 国产一区二区高清在线 | 五月天色婷婷综合 | 亚洲图片视频在线 | 国产精品亚洲自在线播放页码 |