标签:
String num = "13988887777\nhaha";
String numRegex = "[1][3578]\\d{9}"; // 匹配手机号码
boolean b = num .matches(numRegex );
public static void split() {
String str1 = "itheima.java.jacob.meteor";
// 按“.”分割字符串
String regex1 = "\\.";
String str2 = "itheima java jacob \tmeteor";
// 按空白字符分割字符串
String regex2 = "\\s+";
String str3 = "itheimaeeejava$$jacoboooometeor";
// 按重复字符分割字符串
String regex3 = "(.)\\1+";
split (str1 , regex1 );
split (str2 , regex2 );
split (str3 , regex3 );
}
public static void split(String str, String regex) {
String[] arr = str.split(regex);
for (String string : arr ) {
System.out.print( string + " | ");
}
System.out.println();
}
String str1 = "itheima######java&&&&&&&meteor";
// 将将叠词替换成"-"
str1 = str1 .replaceAll("(.)\\1+" , "-" );
String str2 = "itheima######java&&&&&&&meteor";
// 将将叠词替换成其中的一个,多个######用#替换。
// 当在第二个参数中使用第一个正则参数中的组时,可以使用$编号来完成组的调用。\\1只能使用在正则表达式中。
str2 = str2 .replaceAll("(.)\\1+" , "$1" );
String str3 = "13988887777";
// 将电话中的中间四位替换成****;
str3 = str3 .replaceAll("(\\d{3})(\\d{4})(\\d{4})" , "$1****$3");
package regex;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class PatternDemo {
public static void main(String[] args) {
// 需求:获取字符串中由10个字母及以上组成的单词。
String str =
"Backslashes within string literals in Java source code are interpreted as required "
+ "by The Java Language Specification as either Unicode escapes (section 3.3) or other "
+ "character escapes (section 3.10.6) It is therefore necessary to double backslashes "
+ "in string literals that represent regular expressions to protect them from "
+ "interpretation by the Java bytecode compiler. The string literal b, "
+ "for example, matches a single backspace character when interpreted as a regular "
+ "expression, while b matches a word boundary. The string literal (hello) is illegal "
+ "and leads to a compile-time error; in order to match the string (hello) the string "
+ "literal (hello) must be used.";
// 定义规则。
String regex = "\\b[a-zA-Z]{10,}\\b";
// 1. 将正则字符串编译成正则对象。
Pattern p = Pattern.compile(regex );
// 2. 将正则对象和字符串相关联,并获取匹配器。
Matcher m = p.matcher(str);
// 3. 使用find的方法
/*
* m.lookingAt()方法从头匹配正则表达式一次。
* m.start()和m.end()分别能够获取匹配字符串的头尾索引值。
*/
while ( m.find()) {
System.out.println( m.group());
}
}
}
package regex;
import java.util.Arrays;
public class Text_Regex {
public static void main(String[] args) {
// 需求1:匹配电子邮箱
matchEmail();
/*
* 需求2:
* 把“我我.....我我.我....我.要.要要.....要.要学....学...学学....学.学编..编....编..编.编.程程.程...
* ..程.程程”
* 还原成:我要学编程。
*/
replace();
/*
* 需求3:
* 127.0.0.1 3.3.3.3 192.168.104.23 10.10.10.10
* 要求按照 ip地址的分类进行从小到大的排序。
*/
sortIP();
}
public static void sortIP() {
/*
* 思路:
* 由于需要按照数字排序,而字符串排序方式为字典顺序排序,所以先补零以获得同等长度IP地址字符串,再排序,最后还原。
*/
String ip = "127.0.0.1 3.3.3.3 192.168.104.23 10.10.10.10";
ip = ip.replaceAll( "(\\d+)", "00$1" );
ip = ip.replaceAll( "0*(\\d{3})", "$1" );
String[] ips = ip.split("\\s+");
Arrays.sort(ips );
for (String string : ips) {
string = string.replaceAll( "0*(\\d+)", "$1" );
System.out.println( string);
}
}
public static void replace() {
String str = "我我.....我我.我....我.要.要要.....要.要学....学...学学....学.学编..编....编..编.编.程程.程.....程.程程" ;
str = str.replaceAll( "\\.+", "" );
str = str.replaceAll( "(.)\\1+", "$1" );
System.out.println( str);
}
public static void matchEmail() {
String email = "jacobvv@163.com";
String regex = "\\w+@[a-zA-Z0-9]+(\\.[a-zA-Z]+){1,3}" ;
boolean b = email.matches( regex);
System.out.println( b);
}
}
package regex;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;
import java.util.HashSet;
import java.util.Set;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Text_NetSpider {
public static void main(String[] args) {
/*
* 需求:网络爬虫
* 获取某网页上的所有邮箱地址
*/
String url = "http://tieba.baidu.com/p/2720132008";
Set<String> email = null;
try {
email = getEmail(url );
} catch (IOException e) {
e.printStackTrace();
}
for (String string : email) {
System.out.println( string);
}
}
public static Set<String> getEmail(String urlStr ) throws IOException {
Set<String> email = new HashSet<String>();
String regex = "\\w+@[a-zA-Z0-9]+(\\.[a-zA-Z]+){1,3}" ;
Pattern p = Pattern.compile(regex );
URL url = new URL( urlStr);
URLConnection conn = url.openConnection();
BufferedReader br = new BufferedReader( new InputStreamReader(conn.getInputStream()));
String content = null;
while (( content = br.readLine()) != null) {
Matcher m = p.matcher(content);
while ( m.find()) {
email.add( m.group());
}
}
br.close();
return email;
}
}
String num = "13988887777\nhaha";
String numRegex = "[1][3578]\\d{9}"; // 匹配手机号码
boolean b = num .matches(numRegex );
public static void split() {
String str1 = "itheima.java.jacob.meteor";
// 按“.”分割字符串
String regex1 = "\\.";
String str2 = "itheima java jacob \tmeteor";
// 按空白字符分割字符串
String regex2 = "\\s+";
String str3 = "itheimaeeejava$$jacoboooometeor";
// 按重复字符分割字符串
String regex3 = "(.)\\1+";
split (str1 , regex1 );
split (str2 , regex2 );
split (str3 , regex3 );
}
public static void split(String str, String regex) {
String[] arr = str.split(regex);
for (String string : arr ) {
System.out.print( string + " | ");
}
System.out.println();
}
String str1 = "itheima######java&&&&&&&meteor";
// 将将叠词替换成"-"
str1 = str1 .replaceAll("(.)\\1+" , "-" );
String str2 = "itheima######java&&&&&&&meteor";
// 将将叠词替换成其中的一个,多个######用#替换。
// 当在第二个参数中使用第一个正则参数中的组时,可以使用$编号来完成组的调用。\\1只能使用在正则表达式中。
str2 = str2 .replaceAll("(.)\\1+" , "$1" );
String str3 = "13988887777";
// 将电话中的中间四位替换成****;
str3 = str3 .replaceAll("(\\d{3})(\\d{4})(\\d{4})" , "$1****$3");
package regex;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class PatternDemo {
public static void main(String[] args) {
// 需求:获取字符串中由10个字母及以上组成的单词。
String str =
"Backslashes within string literals in Java source code are interpreted as required "
+ "by The Java Language Specification as either Unicode escapes (section 3.3) or other "
+ "character escapes (section 3.10.6) It is therefore necessary to double backslashes "
+ "in string literals that represent regular expressions to protect them from "
+ "interpretation by the Java bytecode compiler. The string literal b, "
+ "for example, matches a single backspace character when interpreted as a regular "
+ "expression, while b matches a word boundary. The string literal (hello) is illegal "
+ "and leads to a compile-time error; in order to match the string (hello) the string "
+ "literal (hello) must be used.";
// 定义规则。
String regex = "\\b[a-zA-Z]{10,}\\b";
// 1. 将正则字符串编译成正则对象。
Pattern p = Pattern.compile(regex );
// 2. 将正则对象和字符串相关联,并获取匹配器。
Matcher m = p.matcher(str);
// 3. 使用find的方法
/*
* m.lookingAt()方法从头匹配正则表达式一次。
* m.start()和m.end()分别能够获取匹配字符串的头尾索引值。
*/
while ( m.find()) {
System.out.println( m.group());
}
}
}
package regex;
import java.util.Arrays;
public class Text_Regex {
public static void main(String[] args) {
// 需求1:匹配电子邮箱
matchEmail();
/*
* 需求2:
* 把“我我.....我我.我....我.要.要要.....要.要学....学...学学....学.学编..编....编..编.编.程程.程...
* ..程.程程”
* 还原成:我要学编程。
*/
replace();
/*
* 需求3:
* 127.0.0.1 3.3.3.3 192.168.104.23 10.10.10.10
* 要求按照 ip地址的分类进行从小到大的排序。
*/
sortIP();
}
public static void sortIP() {
/*
* 思路:
* 由于需要按照数字排序,而字符串排序方式为字典顺序排序,所以先补零以获得同等长度IP地址字符串,再排序,最后还原。
*/
String ip = "127.0.0.1 3.3.3.3 192.168.104.23 10.10.10.10";
ip = ip.replaceAll( "(\\d+)", "00$1" );
ip = ip.replaceAll( "0*(\\d{3})", "$1" );
String[] ips = ip.split("\\s+");
Arrays.sort(ips );
for (String string : ips) {
string = string.replaceAll( "0*(\\d+)", "$1" );
System.out.println( string);
}
}
public static void replace() {
String str = "我我.....我我.我....我.要.要要.....要.要学....学...学学....学.学编..编....编..编.编.程程.程.....程.程程" ;
str = str.replaceAll( "\\.+", "" );
str = str.replaceAll( "(.)\\1+", "$1" );
System.out.println( str);
}
public static void matchEmail() {
String email = "jacobvv@163.com";
String regex = "\\w+@[a-zA-Z0-9]+(\\.[a-zA-Z]+){1,3}" ;
boolean b = email.matches( regex);
System.out.println( b);
}
}
package regex;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;
import java.util.HashSet;
import java.util.Set;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Text_NetSpider {
public static void main(String[] args) {
/*
* 需求:网络爬虫
* 获取某网页上的所有邮箱地址
*/
String url = "http://tieba.baidu.com/p/2720132008";
Set<String> email = null;
try {
email = getEmail(url );
} catch (IOException e) {
e.printStackTrace();
}
for (String string : email) {
System.out.println( string);
}
}
public static Set<String> getEmail(String urlStr ) throws IOException {
Set<String> email = new HashSet<String>();
String regex = "\\w+@[a-zA-Z0-9]+(\\.[a-zA-Z]+){1,3}" ;
Pattern p = Pattern.compile(regex );
URL url = new URL( urlStr);
URLConnection conn = url.openConnection();
BufferedReader br = new BufferedReader( new InputStreamReader(conn.getInputStream()));
String content = null;
while (( content = br.readLine()) != null) {
Matcher m = p.matcher(content);
while ( m.find()) {
email.add( m.group());
}
}
br.close();
return email;
}
}
标签:
原文地址:http://blog.csdn.net/u010388781/article/details/51167764