电子版合同平台/国内好的seo网站

Java中，从Html代码中提取纯文本字符串，方法有很多种。

下面重点使用Java自带工具类，如何获取纯文本段及段在html代码中的坐标，直接上代码。

public class Html2TextUtil extends HTMLEditorKit.ParserCallback {private StringBuffer stringBuffer;private List<String> stringBufferList;private List<Integer> stringBufferPos;private static Html2TextUtil html2Text = new Html2TextUtil();public Html2TextUtil() {}public void parse(String str) {InputStream iin = new ByteArrayInputStream(str.getBytes());Reader in = new InputStreamReader(iin);stringBuffer = new StringBuffer();stringBufferList=new ArrayList<String>();stringBufferPos=new ArrayList<Integer>();ParserDelegator delegator = new ParserDelegator();try {delegator.parse(in, this, Boolean.TRUE);}catch (Exception e){}finally {if(in !=null){try {in.close();}catch (Exception ee){}}if(iin !=null){try {iin.close();}catch (Exception ee){}}}}public void handleText(char[] text, int pos) {String textStr=String.valueOf(text);if(textStr!=null&&!"".equals(textStr)){stringBufferList.add(textStr+"//坐标为："+pos);stringBufferPos.add(pos);}stringBuffer.append(text);}public String getText() {return stringBuffer.toString();}public Map<String,Object> getSplitText() {Map<String,Object> map=new Hashtable<String,Object>();map.put("text",stringBuffer.toString());map.put("textList",stringBufferList);map.put("textPos",stringBufferPos);return map;}public void flush() throws BadLocationException {}public void handleComment(char[] var1, int var2) {}public void handleStartTag(HTML.Tag var1, MutableAttributeSet var2, int var3) {}public void handleEndTag(HTML.Tag var1, int var2) {}public void handleSimpleTag(HTML.Tag var1, MutableAttributeSet var2, int var3) {}public void handleError(String var1, int var2) {}public void handleEndOfLineString(String var1) {}public static String getContent(String str) {html2Text.parse(str);return html2Text.getText();}public static  Map<String,Object> getContentMap(String str) {html2Text.parse(str);return html2Text.getSplitText();}public static void  main(String[] args){String s1 = "<p></p><p>考生注意：</p><p style=\"text-indent: 2em;\">1.本试卷分选择题和非选择题两部分。满分100分，考试时间90分钟。</p><p style=\"text-indent: 2em;\">2.答题前，考生务必用直径0. 5毫米黑色墨水签字笔将密封线内项目填写清楚。</p>";String result=new Html2TextUtil().getContent(s1);System.out.println("【原始html为】："+s1);System.out.println("【纯文本字符串为】："+result);System.out.println();Map<String,Object> htmlMap=new Html2TextUtil().getContentMap(s1);System.out.println("【原始html】："+s1);System.out.println("【纯文本段及文本坐标】：");List<String> list= (List<String>)htmlMap.get("textList");for(String str:list){System.out.println(str);}}}

运行结果截图：

详情，请参考http://www.zrscsoft.com/sitepic/12094.html