import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Example {
public static void main(String[] args) {
final String regex = "(?<=\\<p\\>).+(?=\\<\\/p\\>)";
final String string = "<p>COVEMA</p>\n"
+ "<p>PALMERO</p>\n"
+ "<p>PLASTIFERRO</p>\n"
+ "<p>UOCRA</p>\n"
+ "<p>REPAS</p>\n"
+ "<p>BTU</p>\n"
+ "<p>PANEDILE</p>\n"
+ "<p>ELEPRINT</p>\n"
+ "<p>JOSÉ J. CHEDIACK</p>\n"
+ "<p>NIRO CONSTRUCCIONES</p>\n"
+ "<p>HELPORT</p>\n"
+ "<p>BISCAYNE</p>\n"
+ "<p>COARCO</p>\n"
+ "<p>ESUCO</p>\n"
+ "<p>CPC</p>\n"
+ "<p>TEL 3</p>\n"
+ "<p>CARTELLONE</p>\n"
+ "<p>MACRO</p>\n"
+ "<p>VIAL AGRO</p>\n"
+ "<p>ISOLUX CORSÁN</p>\n"
+ "<p>AFCP</p>\n"
+ "<p>FINNING</p>\n"
+ "<p>ROGGIO</p>\n"
+ "<p>ROVELLA CARRANZA</p>\n"
+ "<p>ACINDAR</p>\n"
+ "<p>IERIC</p>\n"
+ "<p>IGARRETA MÁQUINAS</p>\n"
+ "<p>RIVA</p>\n"
+ "<p>GRUPO ESTISOL</p>\n"
+ "<p>IECSA</p>\n"
+ "<p>ARMAFERRO</p>\n"
+ "<p>BRICONS</p>\n"
+ "<p>CNH INDUSTRIAL</p>\n"
+ "<p>PAOLINI</p>\n"
+ "<p>SERVIUR</p>\n"
+ "<p>SANDVIK</p>\n"
+ "<p>DECAVIAL</p>\n"
+ "<p>ODEBRECHT</p>\n"
+ "<p>ENAS</p>\n"
+ "<p>SITRA</p>\n"
+ "<p>SUPERCEMENTO</p>\n"
+ "<p>JCR</p>\n"
+ "<p>CONSTRUMEX</p>\n"
+ "<p>BRIALES</p>\n"
+ "<p>CAPUTO</p>\n"
+ "<p>LUCIANO</p>\n"
+ "<p>GALICIA</p>\n"
+ "<p>VICTOR CONTRERAS</p>\n"
+ "<p>SIKA ARGENTINA</p>\n"
+ "<p>CRIBA</p>\n"
+ "<p>BOETTO Y BUTTIGLIENGO</p>\n"
+ "<p>MILICIC</p>\n"
+ "<p>PERIODICO EL CONSTRUCTOR</p>\n"
+ "<p>PHONERENTAL</p>\n"
+ "<p>DOS ARROYOS</p>\n"
+ "<p>MARTINEZ Y DE LA FUENTE</p>\n"
+ "<p>AUSA</p>\n"
+ "<p>LUIS LOSI</p>\n"
+ "<p>AESA</p>\n"
+ "<p>CONSTRUCTORA SUDAMERICANA</p>\n"
+ "<p>PLANTEL</p>\n"
+ "<p>PCR</p>\n"
+ "<p>BANCO DE LA NACIÓN ARGENTINA</p>\n"
+ "<p>SUBTERRÁNEOS DE BUENOS AIRES</p>\n"
+ "<p>HOLA SIM</p>\n"
+ "<p>JOSÉ LUIS TRIVIÑO</p>\n"
+ "<p>TECHINT</p>\n"
+ "<p>EDUARDO COLOMBI</p>\n"
+ "<p>ALEMARSA</p>\n"
+ "<p>CENTRO CONSTRUCCIONES</p>\n"
+ "<p>TECNIPISOS</p>\n"
+ "<p>XAPOR</p>\n"
+ "<p>FONTANA NICASTRO</p>\n"
+ "<p>CONCRET-NOR</p>\n"
+ "<p>DYCASA</p>\n"
+ "<p>BURGWARDT</p>\n"
+ "<p>SULLAIR</p>\n"
+ "<p>FONDO FIDUCIARIO FEDERAL DE INFRAESTRUCTURA REGIONAL</p>\n"
+ "<p>FLOWTEX</p>\n"
+ "<p>PETERSEN THIELE Y CRUZ</p>\n"
+ "<p>LIHUÉ</p>\n"
+ "<p>IRAM</p>\n"
+ "<p>ESTUDIO YMAZ</p>\n"
+ "<p>VIDOGAR</p>\n"
+ "<p>BICE</p>\n"
+ "<p>ROMERO CAMMISA</p>\n"
+ "<p>BATIMAT</p>\n"
+ "<p>ALBA CAUCIÓN</p>\n"
+ "<p>PROBA</p>\n"
+ "<p>ICF</p>\n"
+ "<p>TECMA</p>\n"
+ "<p>ALESTE</p>\n"
+ "<p>DELEGACIÓN PROVINCIA DE BUENOS AIRES</p>\n"
+ "<p>HIDRAVIAL</p>\n"
+ "<p>BANCO CIUDAD</p>\n"
+ "<p>LAMANNA</p>";
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