c# – 使用XPath和WebBrowser Control选择多个节点
作者：互联网
在C#WinForms示例应用程序中,我使用WebBrowser控件和JavaScript-XPath来选择单个节点,并通过以下代码更改该节点.innerHtml：
private void MainForm_Load(object sender, EventArgs e)
{
webBrowser1.DocumentText = @"
<html>
<head>
<script src=""http://svn.coderepos.org/share/lang/javascript/javascript-xpath/trunk/release/javascript-xpath-latest-cmp.js""></script>
</head>
<body>
<img alt=""0764547763 Product Details""
src=""http://ecx.images-amazon.com/images/I/51AK1MRIi7L._AA160_.jpg"">
<hr/>
<h2>Product Details</h2>
<ul>
<li><b>Paperback:</b> 648 pages</li>
<li><b>Publisher:</b> Wiley; Unlimited Edition edition (October 15, 2001)</li>
<li><b>Language:</b> English</li>
<li><b>ISBN-10:</b> 0764547763</li>
</ul>
</body>
</html>
";
}
private void cmdTest_Click(object sender, EventArgs e)
{
string xPath = "//li";
string code = string.Format("document.evaluate('{0}', document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;", xPath);
var li = webBrowser1.Document.InvokeScript("eval", new object[] { code }) as mshtml.IHTMLElement;
li.innerHTML = string.Format("<span style='text-transform: uppercase;font-family:verdana;color:green;'>{0}</span>", li.innerText);
}
运行此代码的结果如下：
现在,我想使用相同的技术在< ul>下选择多个< li>节点.节点和我写的：
xPath = "//ul//*";
code = string.Format("document.evaluate('{0}', document, null, XPathResult.ORDERED_NODE_ITERATOR_TYPE, null);", xPath);
var allLI = webBrowser1.Document.InvokeScript("eval", new object[] { code }) as mshtml.IHTMLElementCollection;
但是allLI变量的返回值为NULL.
如果我会写的
xPath = "//ul//*";
code = string.Format("document.evaluate('{0}', document, null, XPathResult.ORDERED_NODE_ITERATOR_TYPE, null);", xPath);
var allLI = webBrowser1.Document.InvokeScript("eval", new object[] { code });
那么返回的allLI变量不是null,它的值类型是COM对象,但是这个COM对象可以强制转换为哪种更具体的类型对我来说还不清楚.
有没有办法通过这里使用技术选择多个节点？
[EDITED]
xPath =“ul // *”;
至
xPath =“// ul // *”;
[加成]
我在我的示例HTML中添加了两个javaScript函数：
<script type=""text/javascript"">
function GetElementsText (XPath) {
var xPathRes = document.evaluate ( XPath, document, null, XPathResult.ORDERED_NODE_ITERATOR_TYPE, null);
var nextElement = xPathRes.iterateNext ();
var text = """";
while (nextElement) {
text += nextElement.innerText;
nextElement = xPathRes.iterateNext ();
}
return text;
};
function GetElements (XPath) {
var xPathRes = document.evaluate ( XPath, document, null, XPathResult.ORDERED_NODE_ITERATOR_TYPE, null);
var nextElement = xPathRes.iterateNext ();
var elements = new Object();
var elementIndex = 1;
while (nextElement) {
elements[elementIndex++] = nextElement;
nextElement = xPathRes.iterateNext ();
}
return elements;
};
</script>
现在,当我在cmd_TestClick方法中运行以下C#代码行时：
var text = webBrowser1.Document.InvokeScript("eval", new object[] { "GetElementsText('//ul')" });
我正在获取所有li元素的文本：
"Paperback: 648 pages \r\nPublisher: Wiley; Unlimited Edition edition (October 15, 2001) \r\nLanguage: English \r\nISBN-10: 0764547763 "
当我在cmd_TestClick方法中运行以下C#代码行时：
var elements = webBrowser1.Document.InvokeScript("eval", new object[] { "GetElements('//ul')" });
我正在获取COM对象,我无法将其转换为IEnumerable< mshtml.IHtmlElement> .
有没有办法在C#代码中处理返回的HTML节点的javaScript集合
var elements = webBrowser1.Document.InvokeScript("eval", new object[] { "GetElements('//ul')" });
？
解决方法:
我找到了解决方案,这里是代码：
using System;
using System.Collections.Generic;
using System.Reflection;
using System.Windows.Forms;
namespace myTest.WinFormsApp
{
public partial class MainForm : Form
{
public MainForm()
{
InitializeComponent();
}
private void MainForm_Load(object sender, EventArgs e)
{
webBrowser1.DocumentText = @"
<html>
<body>
<img alt=""0764547763 Product Details""
src=""http://ecx.images-amazon.com/images/I/51AK1MRIi7L._AA160_.jpg"">
<hr/>
<h2>Product Details</h2>
<ul>
<li><b>Paperback:</b> 648 pages</li>
<li><b>Publisher:</b> Wiley; Unlimited Edition edition (October 15, 2001)</li>
<li><b>Language:</b> English</li>
<li><b>ISBN-10:</b> 0764547763</li>
</html>
";
}
private void cmdTest_Click(object sender, EventArgs e)
{
var processor = new WebBrowserControlXPathQueriesProcessor(webBrowser1);
// change attributes of the first element of the list
{
var li = processor.GetHtmlElement("//li");
li.innerHTML = string.Format("<span style='text-transform: uppercase;font-family:verdana;color:green;'>{0}</span>", li.innerText);
}
// change attributes of the second and subsequent elements of the list
var list = processor.GetHtmlElements("//ul//li");
int index = 1;
foreach (var li in list)
{
if (index++ == 1) continue;
li.innerHTML = string.Format("<span style='text-transform: uppercase;font-family:verdana;color:blue;'>{0}</span>", li.innerText);
}
}
/// <summary>
/// Enables IE WebBrowser control to evaluate XPath queries
/// by injecting http://svn.coderepos.org/share/lang/javascript/javascript-xpath/trunk/release/javascript-xpath-latest-cmp.js
/// and to return XPath queries results to the calling C# code as strongly typed
/// mshtml.IHTMLElement and IEnumerable<mshtml.IHTMLElement>
/// </summary>
public class WebBrowserControlXPathQueriesProcessor
{
private System.Windows.Forms.WebBrowser _webBrowser;
public WebBrowserControlXPathQueriesProcessor(System.Windows.Forms.WebBrowser webBrowser)
{
_webBrowser = webBrowser;
injectScripts();
}
private void injectScripts()
{
// Thanks to: https://stackoverflow.com/questions/7998996/how-to-inject-javascript-in-webbrowser-control
HtmlElement head = _webBrowser.Document.GetElementsByTagName("head")[0];
HtmlElement scriptEl = _webBrowser.Document.CreateElement("script");
mshtml.IHTMLScriptElement element = (mshtml.IHTMLScriptElement)scriptEl.DomElement;
element.src = "http://svn.coderepos.org/share/lang/javascript/javascript-xpath/trunk/release/javascript-xpath-latest-cmp.js";
head.AppendChild(scriptEl);
string javaScriptText = @"
function GetElements (XPath) {
var xPathRes = document.evaluate ( XPath, document, null, XPathResult.ORDERED_NODE_ITERATOR_TYPE, null);
var nextElement = xPathRes.iterateNext ();
var elements = new Object();
var elementIndex = 1;
while (nextElement) {
elements[elementIndex++] = nextElement;
nextElement = xPathRes.iterateNext ();
}
elements.length = elementIndex -1;
return elements;
};
";
scriptEl = _webBrowser.Document.CreateElement("script");
element = (mshtml.IHTMLScriptElement)scriptEl.DomElement;
element.text = javaScriptText;
head.AppendChild(scriptEl);
}
/// <summary>
/// Gets Html element's mshtml.IHTMLElement object instance using XPath query
/// </summary>
public mshtml.IHTMLElement GetHtmlElement(string xPathQuery)
{
string code = string.Format("document.evaluate('{0}', document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;", xPathQuery);
return _webBrowser.Document.InvokeScript("eval", new object[] { code }) as mshtml.IHTMLElement;
}
/// <summary>
/// Gets Html elements' IEnumerable<mshtml.IHTMLElement> object instance using XPath query
/// </summary>
public IEnumerable<mshtml.IHTMLElement> GetHtmlElements(string xPathQuery)
{
// Thanks to: https://stackoverflow.com/questions/5278275/accessing-properties-of-javascript-objects-using-type-dynamic-in-c-sharp-4
var comObject = _webBrowser.Document.InvokeScript("eval", new object[] { string.Format("GetElements('{0}')", xPathQuery) });
Type type = comObject.GetType();
int length = (int)type.InvokeMember("length", BindingFlags.GetProperty, null, comObject, null);
for (int i = 1; i <= length; i++)
{
yield return type.InvokeMember(i.ToString(), BindingFlags.GetProperty, null, comObject, null) as mshtml.IHTMLElement;
}
}
}
}
}
以下是代码运行结果：
我已将信用’引用到我的代码内联.如果你发现我错过了一些,请在评论中指出我,我会添加它们.
如果您知道更好的解决方案 – 更短的代码,更有效的代码 – 请评论和/或发布您的答案.
标签：javascript,xpath,webbrowser-control,evaluate,c-2 来源： https://codeday.me/bug/20190930/1837223.html