java正则表达式使用Demo

DEMO1:

//定义匹配表达式即正则表达式语句,

String regex = "^Java.*";

//定义匹配模式

Pattern pattern = Pattern.compile(regex);

//定义匹配器

Matcher matcher = pattern.matcher("Java不是人，是个啥啊!");

//判断是否

boolean b = matcher.matches();

//打印输出

System.out.println(b);

//定义匹配表达式即正则表达式语句,

String regex = "^Java.*";

//定义匹配模式

Pattern pattern = Pattern.compile(regex);

//定义匹配器

Matcher matcher = pattern.matcher("Java不是人，是个啥啊!");

//判断是否

boolean b = matcher.matches();

//打印输出

System.out.println(b);

demo2：

 

public class LearnRegexp {

    @Test
    public void testSearch() {
        String input = "hello1997&&2000";

        // 将一个正则表达式编译成Pattern对象
        Pattern pattern = Pattern.compile("\\w+");
        Matcher matcher = pattern.matcher(input);

        // matches尝试将整个字符序列与该模式匹配
        System.out.println(matcher.matches());

        // reset将matcher中的指针重新定位
        matcher.reset();
        // find 方法扫描整个字符串, 查找能否找到下一个符合该模式字符串
        while (matcher.find()) {
            String group = matcher.group();
            System.out.println(group);
        }
    }

    /**
     * 将所有的数字都替换成'#'
     */
    @Test
    public void testReplace() {
        String input = "1j2h3h4g5o";
        Matcher replace = Pattern.compile("[0-9]").matcher(input);
        input = replace.replaceAll("#");
        System.out.println(input);
    }

    /**
     * 将字符串按数字分割
     */
    @Test
    public void testSplit() {
        String input = "1j24h356h467g589o";
        String[] strings = input.split("\\d+");
        for (String str : strings) {
            System.out.println(str);
        }
    }
}

 

 

 

demo3:

 

/**
 * 模仿网络爬虫, 抓取网站html, 将里面所有的超链接都分析出来
 */
public class HtmlAnalyzer {

    private final String FILE_PATH = "/Users/jifang/save.txt";

    @Test
    public void client() throws IOException {
        String html = downloadHtml("http://www.163.com/", "gbk");
        // (?<=(href=\"))(?:[\w.\/\:\?\=\&]+)(?=\")  匹配url的正则
        Set<String> urlSet = analyzeHtml(html, "(?<=(href=\\\"))(?:[\\w.\\/\\:\\?\\=\\&]+)(?=\\\")");
        saveToFile(urlSet);
        System.out.println();
    }

    private String downloadHtml(String url, String charset) throws IOException {
        URL readUrl = new URL(url);
        BufferedReader reader = new BufferedReader(new InputStreamReader(readUrl.openStream(), charset));
        return CharStreams.toString(reader);
    }

    private Set<String> analyzeHtml(String html, String regex) {

        Set<String> urlSet = new HashSet<>();
        // 匹配url的正则表达式
        Matcher matcher = Pattern.compile(regex).matcher(html);
        while (matcher.find()) {
            String group = matcher.group();
            urlSet.add(group);
        }

        return urlSet;
    }

    private void saveToFile(Set<String> urlSet) throws IOException {
        PrintStream printer = new PrintStream(new FileOutputStream(FILE_PATH));
        for (String url : urlSet) {
            printer.println(url);
        }
        printer.flush();
        printer.close();
    }
}