import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Example {
public static void main(String[] args) {
final String regex = "(?<=\\<h1\\>).+(?=\\<\\/h1\\>)";
final String string = "<h1>COVEMA</h1>\n"
+ "<h1>PALMERO</h1>\n"
+ "<h1>PLASTIFERRO</h1>\n"
+ "<h1>UOCRA</h1>\n"
+ "<h1>REPAS</h1>\n"
+ "<h1>BTU</h1>\n"
+ "<h1>PANEDILE</h1>\n"
+ "<h1>ELEPRINT</h1>\n"
+ "<h1>JOSÉ J. CHEDIACK</h1>\n"
+ "<h1>NIRO CONSTRUCCIONES</h1>\n"
+ "<h1>HELPORT</h1>\n"
+ "<h1>BISCAYNE</h1>\n"
+ "<h1>COARCO</h1>\n"
+ "<h1>ESUCO</h1>\n"
+ "<h1>CPC</h1>\n"
+ "<h1>TEL 3</h1>\n"
+ "<h1>CARTELLONE</h1>\n"
+ "<h1>MACRO</h1>\n"
+ "<h1>VIAL AGRO</h1>\n"
+ "<h1>ISOLUX CORSÁN</h1>\n"
+ "<h1>AFCP</h1>\n"
+ "<h1>FINNING</h1>\n"
+ "<h1>ROGGIO</h1>\n"
+ "<h1>ROVELLA CARRANZA</h1>\n"
+ "<h1>ACINDAR</h1>\n"
+ "<h1>IERIC</h1>\n"
+ "<h1>IGARRETA MÁQUINAS</h1>\n"
+ "<h1>RIVA</h1>\n"
+ "<h1>GRUPO ESTISOL</h1>\n"
+ "<h1>IECSA</h1>\n"
+ "<h1>ARMAFERRO</h1>\n"
+ "<h1>BRICONS</h1>\n"
+ "<h1>CNH INDUSTRIAL</h1>\n"
+ "<h1>PAOLINI</h1>\n"
+ "<h1>SERVIUR</h1>\n"
+ "<h1>SANDVIK</h1>\n"
+ "<h1>DECAVIAL</h1>\n"
+ "<h1>ODEBRECHT</h1>\n"
+ "<h1>ENAS</h1>\n"
+ "<h1>SITRA</h1>\n"
+ "<h1>SUPERCEMENTO</h1>\n"
+ "<h1>JCR</h1>\n"
+ "<h1>CONSTRUMEX</h1>\n"
+ "<h1>BRIALES</h1>\n"
+ "<h1>CAPUTO</h1>\n"
+ "<h1>LUCIANO</h1>\n"
+ "<h1>GALICIA</h1>\n"
+ "<h1>VICTOR CONTRERAS</h1>\n"
+ "<h1>SIKA ARGENTINA</h1>\n"
+ "<h1>CRIBA</h1>\n"
+ "<h1>BOETTO Y BUTTIGLIENGO</h1>\n"
+ "<h1>MILICIC</h1>\n"
+ "<h1>PERIODICO EL CONSTRUCTOR</h1>\n"
+ "<h1>PHONERENTAL</h1>\n"
+ "<h1>DOS ARROYOS</h1>\n"
+ "<h1>MARTINEZ Y DE LA FUENTE</h1>\n"
+ "<h1>AUSA</h1>\n"
+ "<h1>LUIS LOSI</h1>\n"
+ "<h1>AESA</h1>\n"
+ "<h1>CONSTRUCTORA SUDAMERICANA</h1>\n"
+ "<h1>PLANTEL</h1>\n"
+ "<h1>PCR</h1>\n"
+ "<h1>BANCO DE LA NACIÓN ARGENTINA</h1>\n"
+ "<h1>SUBTERRÁNEOS DE BUENOS AIRES</h1>\n"
+ "<h1>HOLA SIM</h1>\n"
+ "<h1>JOSÉ LUIS TRIVIÑO</h1>\n"
+ "<h1>TECHINT</h1>\n"
+ "<h1>EDUARDO COLOMBI</h1>\n"
+ "<h1>ALEMARSA</h1>\n"
+ "<h1>CENTRO CONSTRUCCIONES</h1>\n"
+ "<h1>TECNIPISOS</h1>\n"
+ "<h1>XAPOR</h1>\n"
+ "<h1>FONTANA NICASTRO</h1>\n"
+ "<h1>CONCRET-NOR</h1>\n"
+ "<h1>DYCASA</h1>\n"
+ "<h1>BURGWARDT</h1>\n"
+ "<h1>SULLAIR</h1>\n"
+ "<h1>FONDO FIDUCIARIO FEDERAL DE INFRAESTRUCTURA REGIONAL</h1>\n"
+ "<h1>FLOWTEX</h1>\n"
+ "<h1>PETERSEN THIELE Y CRUZ</h1>\n"
+ "<h1>LIHUÉ</h1>\n"
+ "<h1>IRAM</h1>\n"
+ "<h1>ESTUDIO YMAZ</h1>\n"
+ "<h1>VIDOGAR</h1>\n"
+ "<h1>BICE</h1>\n"
+ "<h1>ROMERO CAMMISA</h1>\n"
+ "<h1>BATIMAT</h1>\n"
+ "<h1>ALBA CAUCIÓN</h1>\n"
+ "<h1>PROBA</h1>\n"
+ "<h1>ICF</h1>\n"
+ "<h1>TECMA</h1>\n"
+ "<h1>ALESTE</h1>\n"
+ "<h1>DELEGACIÓN PROVINCIA DE BUENOS AIRES</h1>\n"
+ "<h1>HIDRAVIAL</h1>\n"
+ "<h1>BANCO CIUDAD</h1>\n"
+ "<h1>LAMANNA</h1>";
final Pattern pattern = Pattern.compile(regex, Pattern.MULTILINE);
final Matcher matcher = pattern.matcher(string);
while (matcher.find()) {
System.out.println("Full match: " + matcher.group(0));
for (int i = 1; i <= matcher.groupCount(); i++) {
System.out.println("Group " + i + ": " + matcher.group(i));
}
}
}
}
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Java, please visit: https://docs.oracle.com/javase/7/docs/api/java/util/regex/Pattern.html