Java正则提取字符串中的URL链接

时间：2023-06-26 06:07:00 erni继电器rel37

提取URL链接

public static void main(String[] args) {

String data = "#在抖音上，记录美好生活#这大概就是冰雪美女吧…… http://v.douyin.com/eUWYth/ 复制此链接，打开【抖音短视频】，直接观看视频！";

Matcher matcher = Patterns.WEB_URL.matcher(data);

if (matcher.find()){

System.out.println(matcher.group());

}

#最终输出结果为

http://v.douyin.com/eUWYth

工具类

该工具类摘自android.util包下

import java.util.regex.Matcher;

import java.util.regex.Pattern;

/**

* Commonly used regular expression patterns.

public class Patterns {

/**

* Regular expression to match all IANA top-level domains.

* List accurate as of 2011/07/18. List taken from:

* http://data.iana.org/TLD/tlds-alpha-by-domain.txt

* This pattern is auto-generated by frameworks/ex/common/tools/make-iana-tld-pattern.py

* @deprecated Due to the recent profileration of gTLDs, this API is

* expected to become out-of-date very quickly. Therefore it is now

* deprecated.

@Deprecated

public static final String TOP_LEVEL_DOMAIN_STR =

"((aero|arpa|asia|a[cdefgilmnoqrstuwxz])"

"|(biz|b[abdefghijmnorstvwyz])"

"|(cat|com|coop|c[acdfghiklmnoruvxyz])"

"|d[ejkmoz]"

"|(edu|e[cegrstu])"

"|f[ijkmor]"

"|(gov|g[abdefghilmnpqrstuwy])"

"|h[kmnrtu]"

"|(info|int|i[delmnoqrst])"

"|(jobs|j[emop])"

"|k[eghimnprwyz]"

"|l[abcikrstuvy]"

"|(mil|mobi|museum|m[acdeghklmnopqrstuvwxyz])"

"|(name|net|n[acefgilopruz])"

"|(org|om)"

"|(pro|p[aefghklmnrstwy])"

"|qa"

"|r[eosuw]"

"|s[abcdeghijklmnortuvyz]"

"|(tel|travel|t[cdfghjklmnoprtvwz])"

"|u[agksyz]"

"|v[aceginu]"

"|w[fs]"

"|y[et]"

"|z[amw])";

/**

* Regular expression pattern to match all IANA top-level domains.

* @deprecated This API is deprecated. See {@link #TOP_LEVEL_DOMAIN_STR}.

@Deprecated

public static final Pattern TOP_LEVEL_DOMAIN =

Pattern.compile(TOP_LEVEL_DOMAIN_STR);

/**

* Regular expression to match all IANA top-level domains for WEB_URL.

* List accurate as of 2011/07/18. List taken from:

* http://data.iana.org/TLD/tlds-alpha-by-domain.txt

* This pattern is auto-generated by frameworks/ex/common/tools/make-iana-tld-pattern.py

* @deprecated This API is deprecated. See {@link #TOP_LEVEL_DOMAIN_STR}.

@Deprecated

public static final String TOP_LEVEL_DOMAIN_STR_FOR_WEB_URL =

"(?:"

+ "(?:aero|arpa|asia|a[cdefgilmnoqrstuwxz])"

+ "|(?:biz|b[abdefghijmnorstvwyz])"

+ "|(?:cat|com|coop|c[acdfghiklmnoruvxyz])"

+ "|d[ejkmoz]"

+ "|(?:edu|e[cegrstu])"

+ "|f[ijkmor]"

+ "|(?:gov|g[abdefghilmnpqrstuwy])"

+ "|h[kmnrtu]"

+ "|(?:info|int|i[delmnoqrst])"

+ "|(?:jobs|j[emop])"

+ "|k[eghimnprwyz]"

+ "|l[abcikrstuvy]"

+ "|(?:mil|mobi|museum|m[acdeghklmnopqrstuvwxyz])"

+ "|(?:name|net|n[acefgilopruz])"

+ "|(?:org|om)"

+ "|(?:pro|p[aefghklmnrstwy])"

+ "|qa"

+ "|r[eosuw]"

+ "|s[abcdeghijklmnortuvyz]"

+ "|(?:tel|travel|t[cdfghjklmnoprtvwz])"

+ "|u[agksyz]"

+ "|v[aceginu]"

+ "|w[fs]"

+ "|y[et]"

+ "|z[amw]))";

/**

* Regular expression to match all IANA top-level domains.

* List accurate as of 2015/11/24. List taken from:

* http://data.iana.org/TLD/tlds-alpha-by-domain.txt

* This pattern is auto-generated by frameworks/ex/common/tools/make-iana-tld-pattern.py

* @hide

static final String IANA_TOP_LEVEL_DOMAINS =

"(?:"

+ "|blackfriday|bloomberg|blue|bms|bmw|bnl|bnpparibas|boats|bom|bond|boo|boots|boutique"

+ "|buzz|bzh|b[abdefghijmnorstvwyz])"

+ "|express|e[cegrstu])"

+ "|f[ijkmor])"

+ "|glass|gle|global|globo|gmail|gmo|gmx|gold|goldpoint|golf|goo|goog|google|gop|gov|grainger"

+ "|h[kmnrtu])"

+ "|(?:ibm|icbc|ice|icu|ifm|iinet|immo|immobilien|industries|infiniti|info|ing|ink|institute"

+ "|mtn|mtpc|mtr|museum|mutuelle|m[acdeghklmnopqrstuvwxyz])"

+ "|nico|ninja|nissan|nokia|nra|nrw|ntt|nyc|n[acefgilopruz])"

+ "|(?:obi|office|okinawa|omega|one|ong|onl|online|ooo|oracle|orange|org|organic|osaka"

+ "|otsuka|ovh|om)"

+ "|protection|pub|p[aefghklmnrstwy])"

+ "|(?:qpon|quebec|qa)"

+ "|(?:ubs|university|uno|uol|u[agksyz])"

+ "|win|windows|wine|wme|work|works|world|wtc|wtf|w[fs])"

+ "|\u043c\u043e\u043d|\u043c\u043e\u0441\u043a\u0432\u0430|\u043e\u043d\u043b\u0430\u0439\u043d"

+ "|\u043e\u0440\u0433|\u0440\u0443\u0441|\u0440\u0444|\u0441\u0430\u0439\u0442|\u0441\u0440\u0431"

+ "|\u0627\u0644\u0627\u0631\u062f\u0646|\u0627\u0644\u062c\u0632\u0627\u0626\u0631|\u0627\u0644\u0633\u0639\u0648\u062f\u064a\u0629"

+ "|\u0627\u0644\u0645\u063a\u0631\u0628|\u0627\u0645\u0627\u0631\u0627\u062a|\u0627\u06cc\u0631\u0627\u0646"

+ "|\u0628\u0627\u0632\u0627\u0631|\u0628\u06be\u0627\u0631\u062a|\u062a\u0648\u0646\u0633"

+ "|\u0633\u0648\u062f\u0627\u0646|\u0633\u0648\u0631\u064a\u0629|\u0634\u0628\u0643\u0629"

+ "|\u0639\u0631\u0627\u0642|\u0639\u0645\u0627\u0646|\u0641\u0644\u0633\u0637\u064a\u0646"

+ "|\u0642\u0637\u0631|\u0643\u0648\u0645|\u0645\u0635\u0631|\u0645\u0644\u064a\u0633\u064a\u0627"

+ "|\u0645\u0648\u0642\u0639|\u0915\u0949\u092e|\u0928\u0947\u091f|\u092d\u093e\u0930\u0924"

+ "|\u0938\u0902\u0917\u0920\u0928|\u09ad\u09be\u09b0\u09a4|\u0a2d\u0a3e\u0a30\u0a24|\u0aad\u0abe\u0ab0\u0aa4"

+ "|\u0b87\u0ba8\u0bcd\u0ba4\u0bbf\u0baf\u0bbe|\u0b87\u0bb2\u0b99\u0bcd\u0b95\u0bc8|\u0b9a\u0bbf\u0b99\u0bcd\u0b95\u0baa\u0bcd\u0baa\u0bc2\u0bb0\u0bcd"

+ "|\u0c2d\u0c3e\u0c30\u0c24\u0c4d|\u0dbd\u0d82\u0d9a\u0dcf|\u0e04\u0e2d\u0e21|\u0e44\u0e17\u0e22"

+ "|\ub2f7\ucef4|\uc0bc\uc131|\ud55c\uad6d|xbox"

+ "|xn\\-\\-ygbi2ammx|xn\\-\\-zfr164b|xperia|xxx|xyz)"

/**

* Kept for backward compatibility reasons.

* @deprecated Deprecated since it does not include all IRI characters defined in RFC 3987

@Deprecated

public static final String GOOD_IRI_CHAR =

"a-zA-Z0-9\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF";

public static final Pattern IP_ADDRESS

= Pattern.compile(

"((25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[1-9])\\.(25[0-5]|2[0-4]"

+ "[0-9]|[0-1][0-9]{2}|[1-9][0-9]|[1-9]|0)\\.(25[0-5]|2[0-4][0-9]|[0-1]"

+ "[0-9]{2}|[1-9][0-9]|[1-9]|0)\\.(25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}"

+ "|[1-9][0-9]|[0-9]))");

/**

* Valid UCS characters defined in RFC 3987. Excludes space characters.

private static final String UCS_CHAR = "[" +

"\u00A0-\uD7FF" +

"\uF900-\uFDCF" +

"\uFDF0-\uFFEF" +

"\uD800\uDC00-\uD83F\uDFFD" +

"\uD840\uDC00-\uD87F\uDFFD" +

"\uD880\uDC00-\uD8BF\uDFFD" +

"\uD8C0\uDC00-\uD8FF\uDFFD" +

"\uD900\uDC00-\uD93F\uDFFD" +

"\uD940\uDC00-\uD97F\uDFFD" +

"\uD980\uDC00-\uD9BF\uDFFD" +

"\uD9C0\uDC00-\uD9FF\uDFFD" +

"\uDA00\uDC00-\uDA3F\uDFFD" +

"\uDA40\uDC00-\uDA7F\uDFFD" +

"\uDA80\uDC00-\uDABF\uDFFD" +

"\uDAC0\uDC00-\uDAFF\uDFFD" +

"\uDB00\uDC00-\uDB3F\uDFFD" +

"\uDB44\uDC00-\uDB7F\uDFFD" +

"&&[^\u00A0[\u2000-\u200A]\u2028\u2029\u202F\u3000]]";

/**

* Valid characters for IRI label defined in RFC 3987.

private static final String LABEL_CHAR = "a-zA-Z0-9" + UCS_CHAR;

/**

* Valid characters for IRI TLD defined in RFC 3987.

private static final String TLD_CHAR = "a-zA-Z" + UCS_CHAR;

/**

* RFC 1035 Section 2.3.4 limits the labels to a maximum 63 octets.

private static final String IRI_LABEL =

"[" + LABEL_CHAR + "](?:[" + LABEL_CHAR + "\\-]{0,61}[" + LABEL_CHAR + "]){0,1}";

/**

* RFC 3492 references RFC 1034 and limits Punycode algorithm output to 63 characters.

private static final String PUNYCODE_TLD = "xn\\-\\-[\\w\\-]{0,58}\\w";

private static final String TLD = "(" + PUNYCODE_TLD + "|" + "[" + TLD_CHAR + "]{2,63}" +")";

private static final String HOST_NAME = "(" + IRI_LABEL + "\\.)+" + TLD;

public static final Pattern DOMAIN_NAME

= Pattern.compile("(" + HOST_NAME + "|" + IP_ADDRESS + ")");

private static final String PROTOCOL = "(?i:http|https|rtsp):\\/\\/";

/* A word boundary or end of input. This is to stop foo.sure from matching as foo.su */

private static final String WORD_BOUNDARY = "(?:\\b|$|^)";

private static final String USER_INFO = "(?:[a-zA-Z0-9\\$\\-\\_\\.\\+\\!\\*\\'\$\$"

+ "\\,\\;\\?\\&\\=]|(?:\\%[a-fA-F0-9]{2})){1,64}(?:\\:(?:[a-zA-Z0-9\\$\\-\\_"

+ "\\.\\+\\!\\*\\'\$\$\\,\\;\\?\\&\\=]|(?:\\%[a-fA-F0-9]{2})){1,25})?\\@";

private static final String PORT_NUMBER = "\\:\\d{1,5}";

private static final String PATH_AND_QUERY = "\\/(?:(?:[" + LABEL_CHAR

+ "\\;\\/\\?\\:\\@\\&\\=\\#\\~" // plus optional query params

+ "\\-\\.\\+\\!\\*\\'\$\$\\,\\_])|(?:\\%[a-fA-F0-9]{2}))*";

/**

* Regular expression pattern to match most part of RFC 3987

* Internationalized URLs, aka IRIs.

public static final Pattern WEB_URL = Pattern.compile("("

+ "("

+ "(?:" + PROTOCOL + "(?:" + USER_INFO + ")?" + ")?"

+ "(?:" + DOMAIN_NAME + ")"

+ "(?:" + PORT_NUMBER + ")?"

+ ")"

+ "(" + PATH_AND_QUERY + ")?"

+ WORD_BOUNDARY

+ ")");

/**

* Regular expression that matches known TLDs and punycode TLDs

private static final String STRICT_TLD = "(?:" +

IANA_TOP_LEVEL_DOMAINS + "|" + PUNYCODE_TLD + ")";

/**

* Regular expression that matches host names using {@link #STRICT_TLD}

private static final String STRICT_HOST_NAME = "(?:(?:" + IRI_LABEL + "\\.)+"

+ STRICT_TLD + ")";

/**

* Regular expression that matches domain names using either {@link #STRICT_HOST_NAME} or

* {@link #IP_ADDRESS}

private static final Pattern STRICT_DOMAIN_NAME

= Pattern.compile("(?:" + STRICT_HOST_NAME + "|" + IP_ADDRESS + ")");

/**

* Regular expression that matches domain names without a TLD

private static final String RELAXED_DOMAIN_NAME =

"(?:" + "(?:" + IRI_LABEL + "(?:\\.(?=\\S))" +"?)+" + "|" + IP_ADDRESS + ")";

/**

* Regular expression to match strings that do not start with a supported protocol. The TLDs

* are expected to be one of the known TLDs.

private static final String WEB_URL_WITHOUT_PROTOCOL = "("

+ WORD_BOUNDARY

+ "(?

+ "("

+ "(?:" + STRICT_DOMAIN_NAME + ")"

+ "(?:" + PORT_NUMBER + ")?"

+ ")"

+ "(?:" + PATH_AND_QUERY + ")?"

+ WORD_BOUNDARY

+ ")";

/**

* Regular expression to match strings that start with a supported protocol. Rules for domain

* names and TLDs are more relaxed. TLDs are optional.

private static final String WEB_URL_WITH_PROTOCOL = "("

+ WORD_BOUNDARY

+ "(?:"

+ "(?:" + PROTOCOL + "(?:" + USER_INFO + ")?" + ")"

+ "(?:" + RELAXED_DOMAIN_NAME + ")?"

+ "(?:" + PORT_NUMBER + ")?"

+ ")"

+ "(?:" + PATH_AND_QUERY + ")?"

+ WORD_BOUNDARY

+ ")";

/**

* Regular expression pattern to match IRIs. If a string starts with http(s):// the expression

* tries to match the URL structure with a relaxed rule for TLDs. If the string does not start

* with http(s):// the TLDs are expected to be one of the known TLDs.

* @hide

public static final Pattern AUTOLINK_WEB_URL = Pattern.compile(

"(" + WEB_URL_WITH_PROTOCOL + "|" + WEB_URL_WITHOUT_PROTOCOL + ")");

/**

* Regular expression for valid email characters. Does not include some of the valid characters

* defined in RFC5321: #&~!^`{}/=$*?|

private static final String EMAIL_CHAR = LABEL_CHAR + "\\+\\-_%'";

/**

* Regular expression for local part of an email address. RFC5321 section 4.5.3.1.1 limits

* the local part to be at most 64 octets.

private static final String EMAIL_ADDRESS_LOCAL_PART =

"[" + EMAIL_CHAR + "]" + "(?:[" + EMAIL_CHAR + "\\.]{1,62}[" + EMAIL_CHAR + "])?";

/**

* Regular expression for the domain part of an email address. RFC5321 section 4.5.3.1.2 limits

* the domain to be at most 255 octets.

private static final String EMAIL_ADDRESS_DOMAIN =

"(?=.{1,255}(?:\\s|$|^))" + HOST_NAME;

/**

* Regular expression pattern to match email addresses. It excludes double quoted local parts

* and the special characters #&~!^`{}/=$*?| that are included in RFC5321.

* @hide

public static final Pattern AUTOLINK_EMAIL_ADDRESS = Pattern.compile("(" + WORD_BOUNDARY +

"(?:" + EMAIL_ADDRESS_LOCAL_PART + "@" + EMAIL_ADDRESS_DOMAIN + ")" +

WORD_BOUNDARY + ")"

);

public static final Pattern EMAIL_ADDRESS

= Pattern.compile(

"[a-zA-Z0-9\\+\\.\\_\\%\\-\\+]{1,256}" +

"\\@" +

"[a-zA-Z0-9][a-zA-Z0-9\\-]{0,64}" +

"(" +

"\\." +

"[a-zA-Z0-9][a-zA-Z0-9\\-]{0,25}" +

")+"

);

/**

* This pattern is intended for searching for things that look like they

* might be phone numbers in arbitrary text, not for validating whether

* something is in fact a phone number. It will miss many things that

* are legitimate phone numbers.

The pattern matches the following:

Optionally, a + sign followed immediately by one or more digits. Spaces, dots, or dashes

* may follow.

Optionally, sets of digits in parentheses, separated by spaces, dots, or dashes.

A string starting and ending with a digit, containing digits, spaces, dots, and/or dashes.

public static final Pattern PHONE

= Pattern.compile( // sdd = space, dot, or dash

"(\\+[0-9]+[\\- \\.]*)?" // +*

+ "(\$[0-9]+\$[\\- \\.]*)?" // ()*

+ "([0-9][0-9\\- \\.]+[0-9])"); // +

/**

* Convenience method to take all of the non-null matching groups in a

* regex Matcher and return them as a concatenated string.

* @param matcher The Matcher object from which grouped text will

* be extracted

* @return A String comprising all of the non-null matched

* groups concatenated together

public static final String concatGroups(Matcher matcher) {

StringBuilder b = new StringBuilder();

final int numGroups = matcher.groupCount();

for (int i = 1; i <= numGroups; i++) {

String s = matcher.group(i);

if (s != null) {

b.append(s);

}

return b.toString();

}

/**

* Convenience method to return only the digits and plus signs

* in the matching string.

* @param matcher The Matcher object from which digits and plus will

* be extracted

* @return A String comprising all of the digits and plus in

* the match

public static final String digitsAndPlusOnly(Matcher matcher) {

StringBuilder buffer = new StringBuilder();

String matchingRegion = matcher.group();

for (int i = 0, size = matchingRegion.length(); i < size; i++) {

char character = matchingRegion.charAt(i);

if (character == '+' || Character.isDigit(character)) {

buffer.append(character);

}

return buffer.toString();

}

/**

* Do not create this static utility class.

private Patterns() {}

}

锐单商城拥有海量元器件数据手册、IC替代型号，打造电子元器件IC百科大全！

Java正则提取字符串中的URL链接

相关文章