Java与正则表达式

Java与正则表达式

正则

正则

规则

匹配字符串

语法规则

正则语法

普通字符

普通字符

转义字符

\n

\t

\^

\$

\(

\)

\{

\}

\?

\+

\*

|

\\

\[

\]

标准字符集合

\d

\w

\s

.

\n

[\s\S]

\n

自定义字符集合

[]

[ab5@v]

a

b

5

@

v

[^ab5@v]

a

b

5

@

v

[f-k]

f-k

[^f-k]

f-k

[f-k0-3]

f-k

0-3

[^f-k0-3]

f-k

0-3

[]

-

^

[]

^

[]

-

[\d.\-+]

-

+

量词

{n}

{m,n}

{m,}

?

+

{1,}

*

{0,}

默认

?

1[358]\d{9}

([\w\-\.]+)@([0-9a-zA-Z\-]+)(\.[a-zA-Z]{2,4}){1,2}

字符边界

^

$

\b

\b

\w

选择符与分组

|

()

()

()

(

(?:exp)

()

()

()

\nnn

(\w{2})\1

toto

dodo

gogo

(img)\w+\1

零宽断言(预搜索)

占有字符

零宽度

(?=exp)

后面能够

(?!exp)

后面不能

(?<=exp)

前面能够

(?<\!exp)

前面不能

[a-z]+(?=ing)

[a-z]+(?=\d+)

[a-z]+(?!\d+)

(?<=(href=\"))

href="

Java Pattern与Matcher

java.util.regex

Pattern

Matcher

Pattern

Pattern pattern = Pattern.compile("\\w+");

Matcher matcher = pattern.matcher(input);

Matcher

CharSequence

/**
* Created by jifang on 15/12/15.
*/
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);
}
}
}

String

小实验-抓取网页中所有的超链接

/**
* 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
* Created by jifang on 15/12/15.
*/
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();
}
}

<dependency>
<groupId>com.google.guava</groupId>
<artifactId>guava</artifactId>
<version>18.0</version>
</dependency>