0
我有两个富文本框和两个按钮在我的屏幕上。第一个按钮从URL抓取HTML,然后将HTML转换为位于富文本框1中的XML。VB.NET〜需要帮助解析在richtextbox中加载的XML(从URL加载)
第二个按钮是从富文本框1中获取XML,然后解析它以获取所有输入元素由他们的ID。
我的问题是我的解析器没有做任何事情。我的猜测是我没有从第一个富文本框中获取XML。
从富文本框中抓取XML的最佳方式是将其加载到内存中,然后解析XML以获取所有ID标记?
这是我的代码 - 感谢您的任何帮助。
Imports mshtml
Imports System.Text
Imports System.Net
Imports System.Xml
Imports System.IO
Imports System.Xml.XPath
Public Class Scraper
Private Sub Scraper_Load(ByVal sender As System.Object, ByVal e As System.EventArgs) Handles MyBase.Load
End Sub
Private Sub Button1_Click(ByVal sender As System.Object, ByVal e As System.EventArgs) Handles Button1.Click
' Note: This example uses two Chilkat products: Chilkat HTTP
' and Chilkat HTML-to-XML. The "Chilkat Bundle" can be licensed
' at a price that is less than purchasing each product individually.
' The "Chilkat Bundle" provides licenses to all existing Chilkat components. Also, new-version upgrades are always free.
Dim http As New Chilkat.Http()
' Any string argument automatically begins the 30-day trial.
Dim success As Boolean
success = http.UnlockComponent("30-day trial")
If (success <> True) Then
TextBox1.Text = TextBox1.Text & http.LastErrorText & vbCrLf
Exit Sub
End If
Dim html As String
html = http.QuickGetStr("http://www.quiltingboard.com/register.php")
If (html = vbNullString) Then
TextBox1.Text = TextBox1.Text & http.LastErrorText & vbCrLf
Exit Sub
End If
Dim htmlToXml As New Chilkat.HtmlToXml()
' Any string argument automatically begins the 30-day trial.
success = htmlToXml.UnlockComponent("30-day trial")
If (success <> True) Then
TextBox1.Text = TextBox1.Text & htmlToXml.LastErrorText & vbCrLf
Exit Sub
End If
' Indicate the charset of the output XML we'll want.
htmlToXml.XmlCharset = "utf-8"
' Set the HTML:
htmlToXml.Html = html
' Convert to XML:
Dim xml As String
xml = htmlToXml.ToXml()
' Save the XML to a file.
' Make sure your charset here matches the charset
' used for the XmlCharset property.
htmlToXml.WriteStringToFile(xml, "out.xml", "utf-8")
RichTextBox1.Text = xml
End Sub
Private Sub LoopThroughXmlDoc(ByVal nodeList As XmlNodeList)
For Each elem As XmlElement In nodeList
If elem.HasChildNodes Then
LoopThroughXmlDoc(elem.ChildNodes)
Else
'' Extract the information
If elem.HasAttribute("id") Then
'elem.Attributes("AssetID").Value.ToString()
ElseIf elem.HasAttribute("name") Then
'elem.Attributes("AttributeID").Value.ToString()
End If
End If
Next
End Sub
Private Sub Button2_Click_1(ByVal sender As System.Object, ByVal e As System.EventArgs) Handles Button2.Click
Dim doc As XmlDocument = New XmlDocument
doc.Load("xmlFile.xml")
Dim nodeList As XmlNodeList = doc.GetElementsByTagName("input")
LoopThroughXmlDoc(nodeList)
End Sub
End Class
感谢Competent_tech – user1096419 2012-07-15 20:58:54