Regular Expression, Web Crawler

Package cn. itcast. regex. demo;/** regular expression. ** Regular expressions are used to manipulate string data. * Specific symbols are used for representation. * In order to grasp regular expressions, we must learn some symbols. ** Although simplified, it has poor readability. * ***/Public class RegexDemo {/*** @ param args */public static void main (String [] args) {String qq = "123k4567 "; // checkQQ (qq); String regex = "[1-9] [0-9] {4, 14}"; // regular expression. // Boolean B = qq. matches (regex); // System. out. println (qq + ":" + B); // String str = "aoooooooooob"; // String reg = "ao {4, 6} B"; // boolean B = str. matches (reg); // System. out. println (str + ":" + B);}/** requirement: Define a function to verify the QQ number. * Requirement: Length: 5 ~ 15. only numbers are allowed. 0 cannot start with */public static void checkQQ (String qq) {int len = qq. length (); if (len> = 5 & len <= 15) {if (! Qq. startsWith ("0") {try {long l = Long. parseLong (qq); System. out. println (l + ": Correct");} catch (NumberFormatException e) {System. out. println (qq + ": contains invalid characters") ;}} else {System. out. println (qq + ": cannot start with 0") ;}} else {System. out. println (qq + ": incorrect length ");}}}

Package cn. itcast. regex. demo; import java. util. regex. matcher; import java. util. regex. pattern; public class RegexDemo2 {/*** @ param args */public static void main (String [] args) {/** common operations of regular expressions on strings: * 1, match. * The matches method in the String class is actually used. ** 2. Cut. * Actually, the split method in the String class is used. ** 3. replace. * Actually, the replaceAll () method in the String class is used. ** 4. obtain it. **/FunctionDemo_4 ();}/** get * encapsulate the regular rules into objects. * Pattern p = Pattern. compile ("a * B"); * // associate a string using the matcher method of the regular object. Obtain the Matcher. * Matcher m = p. matcher ("aaaaab") for string operations. * // use the Matcher object method to perform string operations. * Boolean B = m. matches (); ***/public static void functionDemo_4 () {String str = "da jia hao, ming tian bu fang jia! "; String regex =" \ B [a-z] {3} \ B "; // 1, which encapsulates the regular expression into an object. Pattern p = Pattern. compile (regex); // 2. Obtain the vertex object through the regular object. Matcher m = p. matcher (str); // use the Matcher object method to operate the string. // Now that you want to get a word consisting of three letters, // search for it. Find (); System. out. println (str); while (m. find () {System. out. println (m. group (); // obtain the matched sub-sequence System. out. println (m. start () + ":" + m. end () ;}}/** replace */public static void functionDemo_3 () {String str = "zhangsanttxiaoqiangmmmmmmzhaoliu"; str = str. replaceAll ("(.) \ 1 + "," $1 "); System. out. println (str); String tel = "15800001111"; // 158 ***** 1111; tel = tel. replaceAll ("(\ d {3}) \ d {4} (\ d {4})", "$1 ***** $2 "); system. out. Println (tel);}/** cut. ** Group: (A) (B (C) */public static void functionDemo_2 () {String str = "zhangsanttttxiaoqiangmmmmmmzhaoliu"; String [] names = str. split ("(.) \ 1 + "); // str. split ("\\. "); for (String name: names) {System. out. println (name) ;}}/** demo match. */Public static void functionDemo_1 () {// check whether the matching mobile phone number is correct. String tel = "15800001111"; String regex = "1 [358] \ d {9}"; boolean B = tel. matches (regex); System. out. println (tel + ":" + B );}}

A pair of parentheses is added as a group. It can be referenced through the dollar match $.

Package cn. itcast. regex. test; import java. util. treeSet; public class RegexTest {/*** @ param args */public static void main (String [] args) {/** 1. Treating stuttering: I am... I am... I want... to be... yes .. learning... learn to compile... compile and compile .. compile .. cheng... cheng... process * 2, which sorts IP addresses. * 3. Verify the email address. */Test_3 ();} // verify the email address. Public static void test_3 () {String mail = "abc1@sina.com.cn"; String regex = "[a-zA-Z0-9 _] + @ [a-zA-Z0-9] + (\\. [a-zA-Z] {1, 3}) + "; regex =" \ w + (\\. \ w +) + "; // 1@1.1boolean B = mail. matches (regex); System. out. println (mail + ":" + B);}/** 1, to cure stuttering. */Public static void test_1 () {String str = "I am... I am... I want... to be... yes .. learning... learn to compile... compile and compile .. compile .. cheng... cheng... cheng "; // 1, in the string. remove. Replace. Str = str. replaceAll ("\. +", ""); System. out. println (str); // 2, replace the overlapping words. Str = str. replaceAll ("(.) \ 1 +", "$1"); System. out. println (str) ;}/ ** sort IP addresses. ** 192.168.10.34 127.0.0.1 3.3.3.3 105.70.11.55 */public static void test_2 () {String ip_str = "192.168.10.34 127.0.0.1 3.3.3.3 105.70.11.55"; // 1. In order to compare ip addresses in String order, as long as the number of digits in each segment of the ip address is the same. // Therefore, add zero and add multiple zeros for each digit. Add two zeros to each segment. ip_str = ip_str.replaceAll ("(\ d +)", "00 $1"); System. out. println (ip_str); // each segment is reserved with three digits. Ip_str = ip_str.replaceAll ("0 * (\ d {3})", "$1"); System. out. println (ip_str); // 1, switch the IP address out. String [] ips = ip_str.split ("+"); TreeSet
 
  
Ts = new TreeSet
  
   
(); For (String ip: ips) {// System. out. println (ip); ts. add (ip) ;}for (String ip: ts) {System. out. println (ip. replaceAll ("0 * (\ d +)", "$1 "));}}}
  
 

Web Crawler

Package cn. itcast. regex. test; import java. io. bufferedReader; import java. io. fileReader; import java. io. IOException; import java. io. inputStreamReader; import java.net. URL; import java. util. arrayList; import java. util. list; import java. util. regex. matcher; import java. util. regex. pattern;/** web crawler: in fact, a program is used to obtain data that meets the specified rules on the Internet. ** Crawl the email address. **/Public class RegexTest2 {/*** @ param args * @ throws IOException */public static void main (String [] args) throws IOException {List
 
  
List = getMailsByWeb (); for (String mail: list) {System. out. println (mail) ;}} public static List
  
   
GetMailsByWeb () throws IOException {// 1, read the source file. // BufferedReader bufr = new BufferedReader (new FileReader ("c: \ mail.html"); URL url = new URL ("http: // 192.168.1.100: 8080/myweb/mail.html "); BufferedReader bufIn = new BufferedReader (new InputStreamReader (url. openStream (); // 2, matching the read data rules. Obtain the data that meets the rule. String mail_regex = "\ w + (\. \ w +) +"; List
   
    
List = new ArrayList
    
     
(); Pattern p = Pattern. compile (mail_regex); String line = null; while (line = bufIn. readLine ())! = Null) {Matcher m = p. matcher (line); while (m. find () {// 3, store the data that meets the rules in the collection. List. add (m. group () ;}return list ;}public static List
     
      
GetMails () throws IOException {// 1, read the source file. BufferedReader bufr = new BufferedReader (new FileReader ("c: \ mail.html"); // 2, matching the read data rules. Obtain the data that meets the rule. String mail_regex = "\ w + (\. \ w +) +"; List
      
        List = new ArrayList
       
         (); Pattern p = Pattern. compile (mail_regex); String line = null; while (line = bufr. readLine ())! = Null) {Matcher m = p. matcher (line); while (m. find () {// 3, store the data that meets the rules in the collection. List. add (m. group () ;}} return list ;}}