Java 如何使用HTMLDocument查找属性?
HTML的术语可能与XML的术语不同,但下面是一个HTML文档,从中检索属性。这里属性a1、a2、a3是主体标记的一部分Java 如何使用HTMLDocument查找属性?,java,html,dom,attributes,Java,Html,Dom,Attributes,HTML的术语可能与XML的术语不同,但下面是一个HTML文档,从中检索属性。这里属性a1、a2、a3是主体标记的一部分 <html> <head> Hello World </head> <body a1="ABC" a2="3974" a3="A1B2"> <------These attributes <H1>Start He
<html>
<head>
Hello World
</head>
<body a1="ABC" a2="3974" a3="A1B2"> <------These attributes
<H1>Start Here<H1>
<p>This is the body</p>
</body>
</html>
你好,世界
我不知道HtmlKit
,但是使用regex可以获得类似的结果
public static void main(String[] args) throws UnirestException {
String html = "<html>\r\n" +
" <head>\r\n" +
" Hello World\r\n" +
" </head>\r\n" +
" <body a1=\"ABC\" a2=\"3974\" a3=\"A1B2\">\r\n" +
" <H1>Start Here<H1>\r\n" +
" <p>This is the body</p>\r\n" +
" </body>\r\n" +
"</html>";
Pattern regexBodyPattern = Pattern.compile("<body[^>]*>", Pattern.MULTILINE);
Matcher matcher = regexBodyPattern.matcher(html);
while(matcher.find()) {
String bodyTag = matcher.group();
Pattern regexBodyAttrPattern = Pattern.compile("(\\S*)=(\\\"\\w*\\\")", Pattern.MULTILINE);
Matcher attrMatcher = regexBodyAttrPattern.matcher(bodyTag);
while(attrMatcher.find()) {
System.out.println("Key :: "+attrMatcher.group(1)+" , Value "+attrMatcher.group(2));
}
}
}
也许这会有帮助:
import java.io.*;
import java.net.*;
import java.util.*;
import javax.swing.*;
import javax.swing.text.*;
import javax.swing.text.html.*;
class AttributeHTML
{
public static void main(String[] args)
{
EditorKit kit = new HTMLEditorKit();
Document doc = kit.createDefaultDocument();
// The Document class does not yet handle charset's properly.
doc.putProperty("IgnoreCharsetDirective", Boolean.TRUE);
try
{
// Create a reader on the HTML content.
Reader rd = getReader(args[0]);
// Parse the HTML.
kit.read(rd, doc, 0);
// Iterate through the elements of the HTML document.
ElementIterator it = new ElementIterator(doc);
Element elem = null;
while ( (elem = it.next()) != null )
{
if (elem.getName().equals("body"))
{
AttributeSet as = elem.getAttributes();
Enumeration enum1 = as.getAttributeNames();
while( enum1.hasMoreElements() )
{
Object name = enum1.nextElement();
Object value = as.getAttribute( name );
System.out.println( "\t" + name + " : " + value );
}
}
}
}
catch (Exception e)
{
e.printStackTrace();
}
System.exit(1);
}
// Returns a reader on the HTML data. If 'uri' begins
// with "http:", it's treated as a URL; otherwise,
// it's assumed to be a local filename.
static Reader getReader(String uri)
throws IOException
{
// Retrieve from Internet.
if (uri.startsWith("http:"))
{
URLConnection conn = new URL(uri).openConnection();
return new InputStreamReader(conn.getInputStream());
}
// Retrieve from file.
else
{
return new FileReader(uri);
}
}
}
测试使用:
java AttributeHTML yourFile.html
要检索属性,可以提供自己的ParserCallback
import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.io.Reader;
import java.util.ArrayList;
import java.util.Enumeration;
import java.util.List;
import javax.swing.text.MutableAttributeSet;
import javax.swing.text.html.HTML.Tag;
import javax.swing.text.html.HTMLEditorKit.ParserCallback;
import javax.swing.text.html.parser.ParserDelegator;
public class HTMLParserTest2
{
public static void main(String args[]) throws Exception {
Reader reader = new FileReader("d:/temp/Example.html");
BufferedReader br = new BufferedReader(reader);
System.out.println(HTMLParserTest2.extractTagsAttributes(br));
// output : [title-_implied_=true, body-a1=ABC, body-a2=3974, body-a3=A1B2]
System.exit(0);
}
public static List<String> extractTagsAttributes(Reader r) throws IOException {
final ArrayList<String> list = new ArrayList<String>();
ParserDelegator parserDelegator = new ParserDelegator();
ParserCallback parserCallback = new ParserCallback() {
@Override
public void handleText(final char[] data, final int pos) { }
@Override
public void handleStartTag(Tag tag, MutableAttributeSet attribute, int pos) {
Enumeration<?> e=attribute.getAttributeNames();
while(e.hasMoreElements()) {
Object name=e.nextElement();
Object value=attribute.getAttribute(name);
list.add(tag.toString() + "-" + name + "=" +value);
}
}
@Override
public void handleEndTag(Tag t, final int pos) { }
@Override
public void handleSimpleTag(Tag t, MutableAttributeSet a, final int pos) { }
@Override
public void handleComment(final char[] data, final int pos) { }
@Override
public void handleError(final java.lang.String errMsg, final int pos) { }
};
parserDelegator.parse(r, parserCallback, true);
return list;
}
}
导入java.io.BufferedReader;
导入java.io.FileReader;
导入java.io.IOException;
导入java.io.Reader;
导入java.util.ArrayList;
导入java.util.Enumeration;
导入java.util.List;
导入javax.swing.text.MutableAttributeSet;
导入javax.swing.text.html.html.Tag;
导入javax.swing.text.html.HTMLEditorKit.ParserCallback;
导入javax.swing.text.html.parser.ParserDelegator;
公共类HTMLParserTest2
{
公共静态void main(字符串args[])引发异常{
Reader Reader=newfilereader(“d:/temp/Example.html”);
BufferedReader br=新的BufferedReader(读卡器);
System.out.println(HTMLParserTest2.extractTagsAttributes(br));
//输出:[title-_=true,body-a1=ABC,body-a2=3974,body-a3=A1B2]
系统出口(0);
}
公共静态列表ExtractTagsAttribute(读取器r)引发IOException{
最终ArrayList=新ArrayList();
ParserDelegator ParserDelegator=新的ParserDelegator();
ParserCallback ParserCallback=新的ParserCallback(){
@凌驾
public void handleText(final char[]数据,final int pos){}
@凌驾
public void handleStartTag(标记标记,可变属性集属性,int pos){
枚举e=attribute.getAttributeNames();
而(e.hasMoreElements()){
对象名称=e.nextElement();
对象值=attribute.getAttribute(名称);
list.add(tag.toString()+“-”+name+“=”+value);
}
}
@凌驾
public void handleEndTag(Tag t,final int pos){}
@凌驾
public void handleSimpleTag(标记t,可变属性集a,final int pos){}
@凌驾
public void handleComment(final char[]data,final int pos){}
@凌驾
public void handleError(final java.lang.String errMsg,final int pos){}
};
parse(r,parserCallback,true);
退货清单;
}
}
寻找与HTML5兼容的现代解析器。Java有很多,谢谢。我唯一关心的是,如果内容发生变化,可能需要修改regex模式。(不确定,因为没有太多使用它。)@Unhandled Exception如果必须查找body标记的属性,则此正则表达式将用于读取所有属性。谢谢。这就是我试图做的,但显然失败得很惨。效果很好。
import java.io.*;
import java.net.*;
import java.util.*;
import javax.swing.*;
import javax.swing.text.*;
import javax.swing.text.html.*;
class AttributeHTML
{
public static void main(String[] args)
{
EditorKit kit = new HTMLEditorKit();
Document doc = kit.createDefaultDocument();
// The Document class does not yet handle charset's properly.
doc.putProperty("IgnoreCharsetDirective", Boolean.TRUE);
try
{
// Create a reader on the HTML content.
Reader rd = getReader(args[0]);
// Parse the HTML.
kit.read(rd, doc, 0);
// Iterate through the elements of the HTML document.
ElementIterator it = new ElementIterator(doc);
Element elem = null;
while ( (elem = it.next()) != null )
{
if (elem.getName().equals("body"))
{
AttributeSet as = elem.getAttributes();
Enumeration enum1 = as.getAttributeNames();
while( enum1.hasMoreElements() )
{
Object name = enum1.nextElement();
Object value = as.getAttribute( name );
System.out.println( "\t" + name + " : " + value );
}
}
}
}
catch (Exception e)
{
e.printStackTrace();
}
System.exit(1);
}
// Returns a reader on the HTML data. If 'uri' begins
// with "http:", it's treated as a URL; otherwise,
// it's assumed to be a local filename.
static Reader getReader(String uri)
throws IOException
{
// Retrieve from Internet.
if (uri.startsWith("http:"))
{
URLConnection conn = new URL(uri).openConnection();
return new InputStreamReader(conn.getInputStream());
}
// Retrieve from file.
else
{
return new FileReader(uri);
}
}
}
java AttributeHTML yourFile.html
import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.io.Reader;
import java.util.ArrayList;
import java.util.Enumeration;
import java.util.List;
import javax.swing.text.MutableAttributeSet;
import javax.swing.text.html.HTML.Tag;
import javax.swing.text.html.HTMLEditorKit.ParserCallback;
import javax.swing.text.html.parser.ParserDelegator;
public class HTMLParserTest2
{
public static void main(String args[]) throws Exception {
Reader reader = new FileReader("d:/temp/Example.html");
BufferedReader br = new BufferedReader(reader);
System.out.println(HTMLParserTest2.extractTagsAttributes(br));
// output : [title-_implied_=true, body-a1=ABC, body-a2=3974, body-a3=A1B2]
System.exit(0);
}
public static List<String> extractTagsAttributes(Reader r) throws IOException {
final ArrayList<String> list = new ArrayList<String>();
ParserDelegator parserDelegator = new ParserDelegator();
ParserCallback parserCallback = new ParserCallback() {
@Override
public void handleText(final char[] data, final int pos) { }
@Override
public void handleStartTag(Tag tag, MutableAttributeSet attribute, int pos) {
Enumeration<?> e=attribute.getAttributeNames();
while(e.hasMoreElements()) {
Object name=e.nextElement();
Object value=attribute.getAttribute(name);
list.add(tag.toString() + "-" + name + "=" +value);
}
}
@Override
public void handleEndTag(Tag t, final int pos) { }
@Override
public void handleSimpleTag(Tag t, MutableAttributeSet a, final int pos) { }
@Override
public void handleComment(final char[] data, final int pos) { }
@Override
public void handleError(final java.lang.String errMsg, final int pos) { }
};
parserDelegator.parse(r, parserCallback, true);
return list;
}
}