"; System.out.println(s); System.out.println(StringEscapeUtils.unescapeHtml(s)); Stringtemp=s.replaceAll(" ",""); temp=temp.replaceAll("\\s+",""); temp=StringEscapeUtils.unescapeHtml(temp); temp=langs(temp,false); System.out.println(temp);// // Stringstr="/hao.html";// Stringregex="\\w+.html";//// //编译正则表达式// Patternpattern=Pattern.compile(regex);//// //指定要匹配的字符串// Matchermatcher=pattern.matcher(str);// //booleanfind();//尝试查找与该模式匹配的输入序列的下一个子序列// booleanresult=matcher.find();// System.out.println(result);//// System.out.println(matcher.group()); } publicstaticvoidreadFiles(Stringpath){ Filefile=newFile(path); BufferedReaderreader=null; StringBufferbuffer=newStringBuffer(); try{ reader=newBufferedReader(newFileReader(file)); StringtempStr=""; while((tempStr=reader.readLine())!=null){ buffer.append(tempStr); buffer.append("\r\n"); } reader.close(); parseStr(buffer.toString()); }catch(IOExceptione){ e.printStackTrace(); } } publicstaticvoidparseStr(Stringstr){ Stringregex="
.*?
"; Patternpattern=Pattern.compile(regex); Matchermatcher=pattern.matcher(str); //booleanfind();//尝试查找与该模式匹配的输入序列的下一个子序列 while(matcher.find()){ //Stringstr1=matcher.group(); //System.out.println(str1); //parse1(str1); } } publicstaticStringparse1(Stringstr){ Stringregex="<.*?>"; Patternpattern=Pattern.compile(regex); Matchermatcher=pattern.matcher(str); Stringres=matcher.replaceAll(""); regex=" "; pattern=Pattern.compile(regex); matcher=pattern.matcher(res); res=matcher.replaceAll(""); regex="\\s"; pattern=Pattern.compile(regex); matcher=pattern.matcher(res); res=matcher.replaceAll(""); returnres; }}Copyright © 2025