快捷導(dǎo)航

.NET從優(yōu)酷專輯中采集所有視頻及信息（VB.NET代碼）

更新時(shí)間：2010年02月07日 11:50:59 作者：

因?yàn)橄胱鲆粋€(gè)視頻點(diǎn)播類的網(wǎng)站，所以開始研究視頻采集。

這個(gè)方法就是提取優(yōu)酷的專輯ID，然后一個(gè)個(gè)ID進(jìn)行循環(huán)采集網(wǎng)頁代碼，從中提取title標(biāo)簽和VID，沒什么技術(shù)含量。=..=
采集中應(yīng)用.NET中的HttpWebRequest和HttpWebResponse類，代碼分析用了正則表達(dá)式。
這個(gè)代碼效率不是很好，一個(gè)網(wǎng)頁的解析時(shí)間在0.5~2秒之間，不適合大量采集。也許將它轉(zhuǎn)換成JavaScript速度會(huì)快一點(diǎn)吧。
暫時(shí)就研究這么多，代碼直接發(fā)出來給大家共享一下。

代碼VB.NET，新建一個(gè)窗體frmMain，添加一個(gè)TextBox，一個(gè)ListBox，兩個(gè)Button，復(fù)制下面的代碼：

復(fù)制代碼代碼如下:

 
Imports System.Net 
Imports System.IO 
Imports System.Text 
Imports System.Text.RegularExpressions 
Public Class frmMain 
Structure VList 
Dim id As Integer 
Dim title As String 
Dim vid1 As String 
Dim vid2 As String 
Overloads Function ToString() As String 
Return String.Format("{0}:<{1}> [{2}]", id, title, vid1) 
End Function 
End Structure 
Dim myList As New List(Of VList) 
Private Sub Button1_Click(ByVal sender As System.Object, ByVal e As System.EventArgs) Handles Button1.Click 
' 防止重復(fù)創(chuàng)建變量 
Dim wr1 As HttpWebRequest 
Dim wr2 As HttpWebResponse 
Dim ret As String 
Dim reg As Match 
Dim g As Group 
Dim preVid As String = "" '上一個(gè)VID 
Dim nowid As Integer = 0 '當(dāng)前的視頻集數(shù) 
Dim listUrl As String = TextBox1.Text '獲取專輯URL，如 http://www.youku.com/playlist_show/id_2350764.html 
Dim tarUrl As String = "http://v.youku.com/v_playlist/f{0}" '{0}ListID 
reg = Regex.Match(listUrl, "playlist_show/id_(\d+).*\.html") 
If Not reg.Success Then 
MsgBox("專輯列表提取失??！") 
Exit Sub 
End If 
g = reg.Groups(1) 
tarUrl = String.Format(tarUrl, g.Value) & "o{1}p{0}.html" '{0}集數(shù) {1}排序 
wr1 = HttpWebRequest.Create(TextBox1.Text) 
wr2 = wr1.GetResponse 
ret = New StreamReader(wr2.GetResponseStream, Encoding.GetEncoding(wr2.CharacterSet)).ReadToEnd 
reg = Regex.Match(ret, "<title>(.+) - 專輯 - 優(yōu)酷視頻</title>") 
If Not reg.Success Then 
MsgBox("專輯名稱提取失敗！") 
Else 
g = reg.Groups(1) 
MsgBox("專輯名：《" & g.Value & "》") 
End If 
Do 
' 從Web流中獲取頁面文本 
wr1 = HttpWebRequest.Create(String.Format(tarUrl, nowid, "0")) '按倒序方式查找視頻 
wr2 = wr1.GetResponse 
ret = New StreamReader(wr2.GetResponseStream, Encoding.GetEncoding(wr2.CharacterSet)).ReadToEnd 
'TextBox2.Text = ret 
' 創(chuàng)建一個(gè)臨時(shí)視頻列表變量 
Dim nlist As New VList 
nlist.id = nowid '獲取ID 
' 獲取videoId 
reg = Regex.Match(ret, "var\s+videoId\s*=\s*""(\d+)""\s*;") 
If Not reg.Success Then Exit Do 
g = reg.Groups(1) 
' 如果VID等于上一個(gè)VID最退出 
If g.Value = preVid Then Exit Do 
nlist.vid1 = g.Value 
' 獲取videoId2 
reg = Regex.Match(ret, "var\s+videoId2\s*=\s*""((\w|=)+)""\s*;") '"var\s+videoId2\s*=\s*""(\w+)""\s*;") 
If Not reg.Success Then Exit Do 
g = reg.Groups(1) 
nlist.vid2 = g.Value 
' 獲取標(biāo)題 
reg = Regex.Match(ret, "<title>(.+) - (.+) - 視頻 - 優(yōu)酷視頻 - 在線觀看 - </title>") 
If Not reg.Success Then 
nlist.title = "{名稱查找錯(cuò)誤}" 
Else 
g = reg.Groups(2) 
nlist.title = g.Value 
End If 
' 收尾工作 
myList.Add(nlist) '添加到總列表中 
preVid = nlist.vid1 '記錄最后一個(gè)VID 
wr2.Close() 
Me.Text = nowid & " : 處理完成！" 
nowid += 1 
Loop 
wr2.Close() 
MsgBox(nowid & " 個(gè)視頻全部采集處理完成！") 
Button2_Click(sender, e) 
End Sub 
Private Sub Button2_Click(ByVal sender As System.Object, ByVal e As System.EventArgs) Handles Button2.Click 
ListBox1.Items.Clear() 
For Each ls As VList In myList 
ListBox1.Items.Add(String.Format("{0}:<{1}> [{2}]", ls.id, ls.title, ls.vid1)) 
Next 
myList.Clear() 
End Sub 

End Class 