What is the best regular expression to check if a string is a valid URL?

Question

How can I check if a given string is a valid URL address?

My knowledge of regular expressions is basic and doesn't allow me to choose from the hundreds of regular expressions I've already seen on the web.

Answer 1

I wrote my URL (actually IRI, internationalized) pattern to comply with RFC 3987 (http://www.faqs.org/rfcs/rfc3987.html). These are in PCRE syntax.

For absolute IRIs (internationalized):

/^[a-z](?:[-a-z0-9\+\.])*:(?:\/\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:])*@)?(?:\[(?:(?:(?:[0-9a-f]{1,4}:){6}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|::(?:[0-9a-f]{1,4}:){5}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:){4}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,1}[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:){3}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,2}[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:){2}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,3}[0-9a-f]{1,4})?::[0-9a-f]{1,4}:(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,4}[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,5}[0-9a-f]{1,4})?::[0-9a-f]{1,4}|(?:(?:[0-9a-f]{1,4}:){0,6}[0-9a-f]{1,4})?::)|v[0-9a-f]+\.[-a-z0-9\._~!\$&'\(\)\*\+,;=:]+)\]|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3}|(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=])*)(?::[0-9]*)?(?:\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@]))*)*|\/(?:(?:(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@]))+)(?:\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@]))*)*)?|(?:(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@]))+)(?:\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@]))*)*|(?!(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@])))(?:\?(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@])|[\x{E000}-\x{F8FF}\x{F0000}-\x{FFFFD}\x{100000}-\x{10FFFD}\/\?])*)?(?:\#(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@])|[\/\?])*)?$/i

To also allow relative IRIs:

/^(?:[a-z](?:[-a-z0-9\+\.])*:(?:\/\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:])*@)?(?:\[(?:(?:(?:[0-9a-f]{1,4}:){6}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|::(?:[0-9a-f]{1,4}:){5}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:){4}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,1}[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:){3}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,2}[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:){2}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,3}[0-9a-f]{1,4})?::[0-9a-f]{1,4}:(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,4}[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,5}[0-9a-f]{1,4})?::[0-9a-f]{1,4}|(?:(?:[0-9a-f]{1,4}:){0,6}[0-9a-f]{1,4})?::)|v[0-9a-f]+\.[-a-z0-9\._~!\$&'\(\)\*\+,;=:]+)\]|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3}|(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=])*)(?::[0-9]*)?(?:\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@]))*)*|\/(?:(?:(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@]))+)(?:\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@]))*)*)?|(?:(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@]))+)(?:\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@]))*)*|(?!(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@])))(?:\?(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@])|[\x{E000}-\x{F8FF}\x{F0000}-\x{FFFFD}\x{100000}-\x{10FFFD}\/\?])*)?(?:\#(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@])|[\/\?])*)?|(?:\/\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:])*@)?(?:\[(?:(?:(?:[0-9a-f]{1,4}:){6}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|::(?:[0-9a-f]{1,4}:){5}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:){4}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,1}[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:){3}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,2}[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:){2}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,3}[0-9a-f]{1,4})?::[0-9a-f]{1,4}:(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,4}[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,5}[0-9a-f]{1,4})?::[0-9a-f]{1,4}|(?:(?:[0-9a-f]{1,4}:){0,6}[0-9a-f]{1,4})?::)|v[0-9a-f]+\.[-a-z0-9\._~!\$&'\(\)\*\+,;=:]+)\]|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3}|(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=])*)(?::[0-9]*)?(?:\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@]))*)*|\/(?:(?:(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@]))+)(?:\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@]))*)*)?|(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=@])+)(?:\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@]))*)*|(?!(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@])))(?:\?(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@])|[\x{E000}-\x{F8FF}\x{F0000}-\x{FFFFD}\x{100000}-\x{10FFFD}\/\?])*)?(?:\#(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}!\$&'\(\)\*\+,;=:@])|[\/\?])*)?)$/i

How they were compiled (in PHP):

<?php

/* Regex convenience functions (character class, non-capturing group) */
function cc($str, $suffix = '', $negate = false) {
    return '[' . ($negate ? '^' : '') . $str . ']' . $suffix;
}
function ncg($str, $suffix = '') {
    return '(?:' . $str . ')' . $suffix;
}

/* Preserved from RFC3986 */

$ALPHA = 'a-z';
$DIGIT = '0-9';
$HEXDIG = $DIGIT . 'a-f';

$sub_delims = '!\\$&\'\\(\\)\\*\\+,;=';
$gen_delims = ':\\/\\?\\#\\[\\]@';
$reserved = $gen_delims . $sub_delims;
$unreserved = '-' . $ALPHA . $DIGIT . '\\._~';

$pct_encoded = '%' . cc($HEXDIG) . cc($HEXDIG);

$dec_octet = ncg(implode('|', array(
    cc($DIGIT),
    cc('1-9') . cc($DIGIT),
    '1' . cc($DIGIT) . cc($DIGIT),
    '2' . cc('0-4') . cc($DIGIT),
    '25' . cc('0-5')
)));

$IPv4address = $dec_octet . ncg('\\.' . $dec_octet, '{3}');

$h16 = cc($HEXDIG, '{1,4}');
$ls32 = ncg($h16 . ':' . $h16 . '|' . $IPv4address);

$IPv6address = ncg(implode('|', array(
    ncg($h16 . ':', '{6}') . $ls32,
    '::' . ncg($h16 . ':', '{5}') . $ls32,
    ncg($h16, '?') . '::' . ncg($h16 . ':', '{4}') . $ls32,
    ncg($h16 . ':' . $h16, '?') . '::' . ncg($h16 . ':', '{3}') . $ls32,
    ncg(ncg($h16 . ':', '{0,2}') . $h16, '?') . '::' . ncg($h16 . ':', '{2}') . $ls32,
    ncg(ncg($h16 . ':', '{0,3}') . $h16, '?') . '::' . $h16 . ':' . $ls32,
    ncg(ncg($h16 . ':', '{0,4}') . $h16, '?') . '::' . $ls32,
    ncg(ncg($h16 . ':', '{0,5}') . $h16, '?') . '::' . $h16,
    ncg(ncg($h16 . ':', '{0,6}') . $h16, '?') . '::',
)));

$IPvFuture = 'v' . cc($HEXDIG, '+') . cc($unreserved . $sub_delims . ':', '+');

$IP_literal = '\\[' . ncg(implode('|', array($IPv6address, $IPvFuture))) . '\\]';

$port = cc($DIGIT, '*');

$scheme = cc($ALPHA) . ncg(cc('-' . $ALPHA . $DIGIT . '\\+\\.'), '*');

/* New or changed in RFC3987 */

$iprivate = '\x{E000}-\x{F8FF}\x{F0000}-\x{FFFFD}\x{100000}-\x{10FFFD}';

$ucschar = '\x{A0}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFEF}' .
    '\x{10000}-\x{1FFFD}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}' .
    '\x{40000}-\x{4FFFD}\x{50000}-\x{5FFFD}\x{60000}-\x{6FFFD}' .
    '\x{70000}-\x{7FFFD}\x{80000}-\x{8FFFD}\x{90000}-\x{9FFFD}' .
    '\x{A0000}-\x{AFFFD}\x{B0000}-\x{BFFFD}\x{C0000}-\x{CFFFD}' .
    '\x{D0000}-\x{DFFFD}\x{E1000}-\x{EFFFD}';

$iunreserved = '-' . $ALPHA . $DIGIT . '\\._~' . $ucschar;

$ipchar = ncg($pct_encoded . '|' . cc($iunreserved . $sub_delims . ':@'));

$ifragment = ncg($ipchar . '|' . cc('\\/\\?'), '*');

$iquery = ncg($ipchar . '|' . cc($iprivate . '\\/\\?'), '*');

$isegment_nz_nc = ncg($pct_encoded . '|' . cc($iunreserved . $sub_delims . '@'), '+');
$isegment_nz = ncg($ipchar, '+');
$isegment = ncg($ipchar, '*');

$ipath_empty = '(?!' . $ipchar . ')';
$ipath_rootless = ncg($isegment_nz) . ncg('\\/' . $isegment, '*');
$ipath_noscheme = ncg($isegment_nz_nc) . ncg('\\/' . $isegment, '*');
$ipath_absolute = '\\/' . ncg($ipath_rootless, '?'); // Spec says isegment-nz *( "/" isegment )
$ipath_abempty = ncg('\\/' . $isegment, '*');

$ipath = ncg(implode('|', array(
    $ipath_abempty,
    $ipath_absolute,
    $ipath_noscheme,
    $ipath_rootless,
    $ipath_empty
))) . ')';

$ireg_name = ncg($pct_encoded . '|' . cc($iunreserved . $sub_delims . '@'), '*');

$ihost = ncg(implode('|', array($IP_literal, $IPv4address, $ireg_name)));
$iuserinfo = ncg($pct_encoded . '|' . cc($iunreserved . $sub_delims . ':'), '*');
$iauthority = ncg($iuserinfo . '@', '?') . $ihost . ncg(':' . $port, '?');

$irelative_part = ncg(implode('|', array(
    '\\/\\/' . $iauthority . $ipath_abempty . '',
    '' . $ipath_absolute . '',
    '' . $ipath_noscheme . '',
    '' . $ipath_empty . ''
)));

$irelative_ref = $irelative_part . ncg('\\?' . $iquery, '?') . ncg('\\#' . $ifragment, '?');

$ihier_part = ncg(implode('|', array(
    '\\/\\/' . $iauthority . $ipath_abempty . '',
    '' . $ipath_absolute . '',
    '' . $ipath_rootless . '',
    '' . $ipath_empty . ''
)));

$absolute_IRI = $scheme . ':' . $ihier_part . ncg('\\?' . $iquery, '?');

$IRI = $scheme . ':' . $ihier_part . ncg('\\?' . $iquery, '?') . ncg('\\#' . $ifragment, '?');

$IRI_reference = ncg($IRI . '|' . $irelative_ref);

Edit 7 March 2011: Because of the way PHP handles backslashes in quoted strings, these are unusable by default. You'll need to double-escape backslashes except where the backslash has a special meaning in regex. You can do that this way:

$escape_backslash = '/(?<!\\)\\(?![\[\]\\\^\$\.\|\*\+\(\)QEnrtaefvdwsDWSbAZzB1-9GX]|x\{[0-9a-f]{1,4}\}|\c[A-Z]|)/';
$absolute_IRI = preg_replace($escape_backslash, '\\\\', $absolute_IRI);
$IRI = preg_replace($escape_backslash, '\\\\', $IRI);
$IRI_reference = preg_replace($escape_backslash, '\\\\', $IRI_reference);

Answer 2

I've just written up a blog post for a great solution for recognizing URLs in most used formats such as:

• www.google.com
• http://www.google.com
• mailto:somebody@google.com
• somebody@google.com
• www.url-with-querystring.com/?url=has-querystring

The regular expression used is:

/((([A-Za-z]{3,9}:(?:\/\/)?)(?:[-;:&=\+\$,\w]+@)?[A-Za-z0-9.-]+|(?:www.|[-;:&=\+\$,\w]+@)[A-Za-z0-9.-]+)((?:\/[\+~%\/.\w-_]*)?\??(?:[-\+=&;%@.\w_]*)#?(?:[\w]*))?)/

Answer 3

What platform? If using .NET, use System.Uri.TryCreate, not a regex.

For example:

static bool IsValidUrl(string urlString)
{
    Uri uri;
    return Uri.TryCreate(urlString, UriKind.Absolute, out uri)
        && (uri.Scheme == Uri.UriSchemeHttp
         || uri.Scheme == Uri.UriSchemeHttps
         || uri.Scheme == Uri.UriSchemeFtp
         || uri.Scheme == Uri.UriSchemeMailto
            /*...*/);
}

// In test fixture...

[Test]
void IsValidUrl_Test()
{
    Assert.True(IsValidUrl("http://www.example.com"));
    Assert.False(IsValidUrl("javascript:alert('xss')"));
    Assert.False(IsValidUrl(""));
    Assert.False(IsValidUrl(null));
}

(Thanks to @Yoshi for the tip about javascript:)

Answer 4

Mathias Bynens has a great article on the best comparison of a lot of regular expressions: In search of the perfect URL validation regex

The best one posted is a little long, but it matches just about anything you can throw at it.

JavaScript version

/^(?:(?:(?:https?|ftp):)?\/\/)(?:\S+(?::\S*)?@)?(?:(?!(?:10|127)(?:\.\d{1,3}){3})(?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))|(?:(?:[a-z0-9\u00a1-\uffff][a-z0-9\u00a1-\uffff_-]{0,62})?[a-z0-9\u00a1-\uffff]\.)+(?:[a-z\u00a1-\uffff]{2,}\.?))(?::\d{2,5})?(?:[/?#]\S*)?$/i

PHP version (uses % symbol as delimiter)

%^(?:(?:(?:https?|ftp):)?\/\/)(?:\S+(?::\S*)?@)?(?:(?!(?:10|127)(?:\.\d{1,3}){3})(?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))|(?:(?:[a-z0-9\x{00a1}-\x{ffff}][a-z0-9\x{00a1}-\x{ffff}_-]{0,62})?[a-z0-9\x{00a1}-\x{ffff}]\.)+(?:[a-z\x{00a1}-\x{ffff}]{2,}\.?))(?::\d{2,5})?(?:[/?#]\S*)?$%iuS

Answer 5

Here's what RegexBuddy uses.

(\b(https?|ftp|file)://)?[-A-Za-z0-9+&@#/%?=~_|!:,.;]+[-A-Za-z0-9+&@#/%=~_|]

It matches these below (inside the ** ** marks):

**http://www.regexbuddy.com**  
**http://www.regexbuddy.com/**  
**http://www.regexbuddy.com/index.html**  
**http://www.regexbuddy.com/index.html?source=library**  
**http://www.regexbuddy.com/index.html?source=library#copyright**  

You can download RegexBuddy at http://www.regexbuddy.com/download.html.

Answer 6

With regard to eyelidness' answer post that reads "This is based on my reading of the URI specification.": Thanks Eyelidness, yours is the perfect solution I sought, as it is based on the URI spec! Superb work. :)

I had to make two amendments. The first to get the regexp to match IP address URLs correctly in PHP (v5.2.10) with the preg_match() function.

I had to add one more set of parenthesis to the line above "IP Address" around the pipes:

)|((\d|[1-9]\d|1\d{2}|2[0-4][0-9]|25[0-5])\.){3}(?#

Not sure why.

I have also reduced the top level domain minimum length from 3 to 2 letters to support .co.uk and similar.

Final code:

/^(https?|ftp):\/\/(?#                                      protocol
)(([a-z0-9$_\.\+!\*\'\(\),;\?&=-]|%[0-9a-f]{2})+(?#         username
)(:([a-z0-9$_\.\+!\*\'\(\),;\?&=-]|%[0-9a-f]{2})+)?(?#      password
)@)?(?#                                                     auth requires @
)((([a-z0-9]\.|[a-z0-9][a-z0-9-]*[a-z0-9]\.)*(?#             domain segments AND
)[a-z][a-z0-9-]*[a-z0-9](?#                                 top level domain  OR
)|((\d|[1-9]\d|1\d{2}|2[0-4][0-9]|25[0-5])\.){3}(?#
    )(\d|[1-9]\d|1\d{2}|2[0-4][0-9]|25[0-5])(?#             IP address
))(:\d+)?(?#                                                port
))(((\/+([a-z0-9$_\.\+!\*\'\(\),;:@&=-]|%[0-9a-f]{2})*)*(?# path
)(\?([a-z0-9$_\.\+!\*\'\(\),;:@&=-]|%[0-9a-f]{2})*)(?#      query string
)?)?)?(?#                                                   path and query string optional
)(#([a-z0-9$_\.\+!\*\'\(\),;:@&=-]|%[0-9a-f]{2})*)?(?#      fragment
)$/i

This modified version was not checked against the URI specification so I can't vouch for it's compliance, it was altered to handle URLs on local network environments and two digit TLDs as well as other kinds of Web URL, and to work better in the PHP setup I use.

As PHP code:

define('URL_FORMAT', 
'/^(https?):\/\/'.                                         // protocol
'(([a-z0-9$_\.\+!\*\'\(\),;\?&=-]|%[0-9a-f]{2})+'.         // username
'(:([a-z0-9$_\.\+!\*\'\(\),;\?&=-]|%[0-9a-f]{2})+)?'.      // password
'@)?(?#'.                                                  // auth requires @
')((([a-z0-9]\.|[a-z0-9][a-z0-9-]*[a-z0-9]\.)*'.                      // domain segments AND
'[a-z][a-z0-9-]*[a-z0-9]'.                                 // top level domain  OR
'|((\d|[1-9]\d|1\d{2}|2[0-4][0-9]|25[0-5])\.){3}'.
'(\d|[1-9]\d|1\d{2}|2[0-4][0-9]|25[0-5])'.                 // IP address
')(:\d+)?'.                                                // port
')(((\/+([a-z0-9$_\.\+!\*\'\(\),;:@&=-]|%[0-9a-f]{2})*)*'. // path
'(\?([a-z0-9$_\.\+!\*\'\(\),;:@&=-]|%[0-9a-f]{2})*)'.      // query string
'?)?)?'.                                                   // path and query string optional
'(#([a-z0-9$_\.\+!\*\'\(\),;:@&=-]|%[0-9a-f]{2})*)?'.      // fragment
'$/i');

Here is a test program in PHP which validates a variety of URLs using the regex:

<?php

define('URL_FORMAT',
'/^(https?):\/\/'.                                         // protocol
'(([a-z0-9$_\.\+!\*\'\(\),;\?&=-]|%[0-9a-f]{2})+'.         // username
'(:([a-z0-9$_\.\+!\*\'\(\),;\?&=-]|%[0-9a-f]{2})+)?'.      // password
'@)?(?#'.                                                  // auth requires @
')((([a-z0-9]\.|[a-z0-9][a-z0-9-]*[a-z0-9]\.)*'.                      // domain segments AND
'[a-z][a-z0-9-]*[a-z0-9]'.                                 // top level domain  OR
'|((\d|[1-9]\d|1\d{2}|2[0-4][0-9]|25[0-5])\.){3}'.
'(\d|[1-9]\d|1\d{2}|2[0-4][0-9]|25[0-5])'.                 // IP address
')(:\d+)?'.                                                // port
')(((\/+([a-z0-9$_\.\+!\*\'\(\),;:@&=-]|%[0-9a-f]{2})*)*'. // path
'(\?([a-z0-9$_\.\+!\*\'\(\),;:@&=-]|%[0-9a-f]{2})*)'.      // query string
'?)?)?'.                                                   // path and query string optional
'(#([a-z0-9$_\.\+!\*\'\(\),;:@&=-]|%[0-9a-f]{2})*)?'.      // fragment
'$/i');

/**
 * Verify the syntax of the given URL. 
 * 
 * @access public
 * @param $url The URL to verify.
 * @return boolean
 */
function is_valid_url($url) {
  if (str_starts_with(strtolower($url), 'http://localhost')) {
    return true;
  }
  return preg_match(URL_FORMAT, $url);
}


/**
 * String starts with something
 * 
 * This function will return true only if input string starts with
 * niddle
 * 
 * @param string $string Input string
 * @param string $niddle Needle string
 * @return boolean
 */
function str_starts_with($string, $niddle) {
      return substr($string, 0, strlen($niddle)) == $niddle;
}


/**
 * Test a URL for validity and count results.
 * @param url url
 * @param expected expected result (true or false)
 */

$numtests = 0;
$passed = 0;

function test_url($url, $expected) {
  global $numtests, $passed;
  $numtests++;
  $valid = is_valid_url($url);
  echo "URL Valid?: " . ($valid?"yes":"no") . " for URL: $url. Expected: ".($expected?"yes":"no").". ";
  if($valid == $expected) {
    echo "PASS\n"; $passed++;
  } else {
    echo "FAIL\n";
  }
}

echo "URL Tests:\n\n";

test_url("http://localserver/projects/public/assets/javascript/widgets/UserBoxMenu/widget.css", true);
test_url("http://www.google.com", true);
test_url("http://www.google.co.uk/projects/my%20folder/test.php", true);
test_url("https://myserver.localdomain", true);
test_url("http://192.168.1.120/projects/index.php", true);
test_url("http://192.168.1.1/projects/index.php", true);
test_url("http://projectpier-server.localdomain/projects/public/assets/javascript/widgets/UserBoxMenu/widget.css", true);
test_url("https://2.4.168.19/project-pier?c=test&a=b", true);
test_url("https://localhost/a/b/c/test.php?c=controller&arg1=20&arg2=20", true);
test_url("http://user:password@localhost/a/b/c/test.php?c=controller&arg1=20&arg2=20", true);

echo "\n$passed out of $numtests tests passed.\n\n";

?>

Thanks again to eyelidness for the regex!

Answer 7

The post Getting parts of a URL (Regex) discusses parsing a URL to identify its various components. If you want to check if a URL is well-formed, it should be sufficient for your needs.

If you need to check if it's actually valid, you'll eventually have to try to access whatever's on the other end.

In general, though, you'd probably be better off using a function that's supplied to you by your framework or another library. Many platforms include functions that parse URLs. For example, there's Python's urlparse module, and in .NET you could use the System.Uri class's constructor as a means of validating the URL.

Answer 8

This might not be a job for regexes, but for existing tools in your language of choice. You probably want to use existing code that has already been written, tested, and debugged.

In PHP, use the parse_url function.

Perl: URI module.

Ruby: URI module.

.NET: 'Uri' class

Regexes are not a magic wand you wave at every problem that happens to involve strings.

Answer 9

This will match all URLs

• with or without http/https
• with or without www

...including sub-domains and those new top-level domain name extensions such as .museum, .academy, .foundation etc. which can have up to 63 characters (not just .com, .net, .info etc.)

(([\w]+:)?//)?(([\d\w]|%[a-fA-f\d]{2,2})+(:([\d\w]|%[a-fA-f\d]{2,2})+)?@)?([\d\w][-\d\w]{0,253}[\d\w]\.)+[\w]{2,63}(:[\d]+)?(/([-+_~.\d\w]|%[a-fA-f\d]{2,2})*)*(\?(&?([-+_~.\d\w]|%[a-fA-f\d]{2,2})=?)*)?(#([-+_~.\d\w]|%[a-fA-f\d]{2,2})*)?

Because today maximum length of the available top-level domain name extension is 13 characters such as .international, you can change the number 63 in expression to 13 to prevent someone misusing it.

as javascript

var urlreg=/(([\w]+:)?\/\/)?(([\d\w]|%[a-fA-f\d]{2,2})+(:([\d\w]|%[a-fA-f\d]{2,2})+)?@)?([\d\w][-\d\w]{0,253}[\d\w]\.)+[\w]{2,63}(:[\d]+)?(\/([-+_~.\d\w]|%[a-fA-f\d]{2,2})*)*(\?(&?([-+_~.\d\w]|%[a-fA-f\d]{2,2})=?)*)?(#([-+_~.\d\w]|%[a-fA-f\d]{2,2})*)?/;

$('textarea').on('input',function(){
  var url = $(this).val();
  $(this).toggleClass('invalid', urlreg.test(url) == false)
});

$('textarea').trigger('input');

textarea{color:green;}
.invalid{color:red;}

<script src="https://ajax.googleapis.com/ajax/libs/jquery/2.1.1/jquery.min.js"></script>
<textarea>http://www.google.com</textarea>
<textarea>http//www.google.com</textarea>
<textarea>googlecom</textarea>
<textarea>https://www.google.com</textarea>

Wikipedia Article: List of all internet top-level domains

Answer 10

Non-validating URI-reference Parser

For reference purposes, here's the IETF Spec: (TXT | HTML). In particular, Appendix B. Parsing a URI Reference with a Regular Expression demonstrates how to parse a valid regex. This is described as,

for an example of a non-validating URI-reference parser that will take any given string and extract the URI components.

Here's the regex they provide:

 ^(([^:/?#]+):)?(//([^/?#]*))?([^?#]*)(\?([^#]*))?(#(.*))?

As someone else said, it's probably best to leave this to a lib/framework you're already using.

Answer 11

^(http:\/\/www\.|https:\/\/www\.|http:\/\/|https:\/\/)?[a-z0-9]+([\-\.]{1}[a-z0-9]+)*\.[a-z]{2,5}(:[0-9]{1,5})?(\/.*)?$

live demo: https://regex101.com/r/HUNasA/2

I have tested various expressions to match my requirements.

As a user I can hit browser search bar with following strings:

valid urls

• https://www.google.com
• http://www.google.com
• http://google.com/
• https://google.com/
• www.google.com
• google.com
• https://www.google.com.ua
• http://www.google.com.ua
• http://google.com.ua
• https://google.com.ua/
• www.google.com.ua
• google.com.ua
• https://mail.google.com
• http://mail.google.com
• mail.google.com

invalid urls

• http://google
• https://google.c
• google
• google.
• .google
• .google.com
• goole.c
• ...

Answer 12

The best regular expression for URL for me would be:

"(([\w]+:)?//)?(([\d\w]|%[a-fA-F\d]{2,2})+(:([\d\w]|%[a-fA-f\d]{2,2})+)?@)?([\d\w][-\d\w]{0,253}[\d\w]\.)+[\w]{2,4}(:[\d]+)?(/([-+_~.\d\w]|%[a-fA-f\d]{2,2})*)*(\?(&?([-+_~.\d\w]|%[a-fA-f\d]{2,2})=?)*)?(#([-+_~.\d\w]|%[a-fA-f\d]{2,2})*)?"

Answer 13

Here is a good rule that covers all possible cases: ports, params and etc

/(https?:\/\/(?:[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?\.)+[a-z0-9][a-z0-9-]{0,61}[a-z0-9])(:?\d*)\/?([a-z_\/0-9\-#.]*)\??([a-z_\/0-9\-#=&]*)/g

Answer 14

I wrote a little groovy version that you can run

it matches the following URLs (which is good enough for me)

public static void main(args) {
    String url = "go to http://www.m.abut.ly/abc its awesome"
    url = url.replaceAll(/https?:\/\/w{0,3}\w*?\.(\w*?\.)?\w{2,3}\S*|www\.(\w*?\.)?\w*?\.\w{2,3}\S*|(\w*?\.)?\w*?\.\w{2,3}[\/\?]\S*/ , { it ->
        "woof${it}woof"
    })
    println url 
}

http://google.com
http://google.com/help.php
http://google.com/help.php?a=5

http://www.google.com
http://www.google.com/help.php
http://www.google.com?a=5

google.com?a=5
google.com/help.php
google.com/help.php?a=5

http://www.m.google.com/help.php?a=5 (and all its permutations)
www.m.google.com/help.php?a=5 (and all its permutations)
m.google.com/help.php?a=5 (and all its permutations)

The important thing for any URLs that don't start with http or www is that they must include a / or ?

I bet this can be tweaked a little more but it does the job pretty nice for being so short and compact... because you can pretty much split it in 3:

find anything that starts with http:

https?:\/\/w{0,3}\w*?\.\w{2,3}\S*

find anything that starts with www:

www\.\w*?\.\w{2,3}\S*

or find anything that must have a text then a dot then at least 2 letters and then a ? or /:

\w*?\.\w{2,3}[\/\?]\S*

Answer 15

I was not able to find the regex I was looking for so I modified a regex to fullfill my requirements, and apparently it seems to work fine now. My requirements were:

• Match URLs w/o protocol (www.gooogle.com)
• Match URLs with query parameters and path (http://subdomain.web-site.com/cgi-bin/perl.cgi?key1=value1&key2=value2e)
• Don't match URLs where there are not acceptable characters (e.g. "'£), for instance: (www.google.com/somthing"/somethingmore)

Here what I came up with, any suggestion is appreciated:

@Test
    public void testWebsiteUrl(){
        String regularExpression = "((http|ftp|https):\\/\\/)?[\\w\\-_]+(\\.[\\w\\-_]+)+([\\w\\-\\.,@?^=%&:/~\\+#]*[\\w\\-\\@?^=%&/~\\+#])?";

        assertTrue("www.google.com".matches(regularExpression));
        assertTrue("www.google.co.uk".matches(regularExpression));
        assertTrue("http://www.google.com".matches(regularExpression));
        assertTrue("http://www.google.co.uk".matches(regularExpression));
        assertTrue("https://www.google.com".matches(regularExpression));
        assertTrue("https://www.google.co.uk".matches(regularExpression));
        assertTrue("google.com".matches(regularExpression));
        assertTrue("google.co.uk".matches(regularExpression));
        assertTrue("google.mu".matches(regularExpression));
        assertTrue("mes.intnet.mu".matches(regularExpression));
        assertTrue("cse.uom.ac.mu".matches(regularExpression));

        assertTrue("http://www.google.com/path".matches(regularExpression));
        assertTrue("http://subdomain.web-site.com/cgi-bin/perl.cgi?key1=value1&key2=value2e".matches(regularExpression));
        assertTrue("http://www.google.com/?queryparam=123".matches(regularExpression));
        assertTrue("http://www.google.com/path?queryparam=123".matches(regularExpression));

        assertFalse("www..dr.google".matches(regularExpression));

        assertFalse("www:google.com".matches(regularExpression));

        assertFalse("https://www@.google.com".matches(regularExpression));

        assertFalse("https://www.google.com\"".matches(regularExpression));
        assertFalse("https://www.google.com'".matches(regularExpression));

        assertFalse("http://www.google.com/path'".matches(regularExpression));
        assertFalse("http://subdomain.web-site.com/cgi-bin/perl.cgi?key1=value1&key2=value2e'".matches(regularExpression));
        assertFalse("http://www.google.com/?queryparam=123'".matches(regularExpression));
        assertFalse("http://www.google.com/path?queryparam=12'3".matches(regularExpression));

    }

Answer 16

        function validateURL(textval) {
            var urlregex = new RegExp(
            "^(http|https|ftp)\://([a-zA-Z0-9\.\-]+(\:[a-zA-Z0-9\.&%\$\-]+)*@)*((25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9])\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[0-9])|localhost|([a-zA-Z0-9\-]+\.)*[a-zA-Z0-9\-]+\.(com|edu|gov|int|mil|net|org|biz|arpa|info|name|pro|aero|coop|museum|[a-zA-Z]{2}))(\:[0-9]+)*(/($|[a-zA-Z0-9\.\,\?\'\\\+&%\$#\=~_\-]+))*$");
            return urlregex.test(textval);
        }

Matches http://site.com/dir/file.php?var=moo | ftp://user:pass@site.com:21/file/dir

Non-Matches site.com | http://site.com/dir//

Answer 17

function validateURL(textval) {
            var urlregex = new RegExp(
            "^(http|https|ftp)\://[a-zA-Z0-9\-\.]+\.[a-zA-Z]{2,3}(:[a-zA-Z0-9]*)?/?([a-zA-Z0-9\-\._\?\,\'/\\\+&%\$#\=~])*$");
            return urlregex.test(textval);
        }

Matches http://www.asdah.com/~joe | ftp://ftp.asdah.co.uk:2828/asdah%20asdah.gif | https://asdah.gov/asdh-ah.as

Answer 18

If you really search for the ultimate match, you probably find it on "A Good Url Regular Expression?".

But a regex that really matches all possible domains and allows anything that is allowed according to RFCs is horribly long and unreadable, trust me ;-)

Answer 19

I hope it's helpful for you...

^(http|https):\/\/+[\www\d]+\.[\w]+(\/[\w\d]+)?

Answer 20

Here is a regex I made which extracts the different parts from an URL:

^((?:(?:http|ftp|ws)s?|sftp):\/\/?)?([^:/\s.#?]+\.[^:/\s#?]+|localhost)(:\d+)?((?:\/\w+)*\/)?([\w\-.]+[^#?\s]+)?([^#]+)?(#[\w-]*)?$

((?:(?:http|ftp|ws)s?|sftp):\/\/?)?(group 1): extracts the protocol
([^:/\s.#?]+\.[^:/\s#?]+|localhost)(group 2): extracts the hostname
(:\d+)?(group 3): extracts the port number
((?:\/\w+)*\/)?([\w\-.]+[^#?\s]+)?(groups 4 & 5): extracts the path part
([^#]+)?(group 6): extracts the query part
(#[\w-]*)?(group 7): extracts the hash part

For every part of the regex listed above, you can remove the ending ? to force it (or add one to make it facultative). You can also remove the ^ at the beginning and $ at the end of the regex so it won't need to match the whole string.

See it on regex101.

Note: this regex is not 100% safe and may accept some strings which are not necessarily valid URLs but it does indeed validate some criterias. Its main goal was to extract the different parts of an URL not to validate it.

Answer 21

I use this regex:

((https?:)?//)?(([\d\w]|%[a-fA-f\d]{2,2})+(:([\d\w]|%[a-fA-f\d]{2,2})+)?@)?([\d\w][-\d\w]{0,253}[\d\w]\.)+[\w]{2,63}(:[\d]+)?(/([-+_~.\d\w]|%[a-fA-f\d]{2,2})*)*(\?(&?([-+_~.\d\w]|%[a-fA-f\d]{2,2})=?)*)?(#([-+_~.\d\w]|%[a-fA-f\d]{2,2})*)?

To support both:

http://stackoverflow.com
https://stackoverflow.com

And:

//stackoverflow.com

Answer 22

Here's a ready-to-go Java version from the Android source code. This is the best one I've found.

public static final Matcher WEB  = Pattern.compile(new StringBuilder()                 
.append("((?:(http|https|Http|Https|rtsp|Rtsp):")                      
.append("\\/\\/(?:(?:[a-zA-Z0-9\\$\\-\\_\\.\\+\\!\\*\\'\\(\\)")                         
.append("\\,\\;\\?\\&\\=]|(?:\\%[a-fA-F0-9]{2})){1,64}(?:\\:(?:[a-zA-Z0-9\\$\\-\\_")                         
.append("\\.\\+\\!\\*\\'\\(\\)\\,\\;\\?\\&\\=]|(?:\\%[a-fA-F0-9]{2})){1,25})?\\@)?)?")                         
.append("((?:(?:[a-zA-Z0-9][a-zA-Z0-9\\-]{0,64}\\.)+")   // named host                            
.append("(?:")   // plus top level domain                         
.append("(?:aero|arpa|asia|a[cdefgilmnoqrstuwxz])")                         
.append("|(?:biz|b[abdefghijmnorstvwyz])")                         
.append("|(?:cat|com|coop|c[acdfghiklmnoruvxyz])")                         
.append("|d[ejkmoz]")                         
.append("|(?:edu|e[cegrstu])")                         
.append("|f[ijkmor]")                         
.append("|(?:gov|g[abdefghilmnpqrstuwy])")                         
.append("|h[kmnrtu]")                         
.append("|(?:info|int|i[delmnoqrst])")                         
.append("|(?:jobs|j[emop])")                         
.append("|k[eghimnrwyz]")                         
.append("|l[abcikrstuvy]")                         
.append("|(?:mil|mobi|museum|m[acdghklmnopqrstuvwxyz])")                         
.append("|(?:name|net|n[acefgilopruz])")                         
.append("|(?:org|om)")                         
.append("|(?:pro|p[aefghklmnrstwy])")                         
.append("|qa")                         
.append("|r[eouw]")                         
.append("|s[abcdeghijklmnortuvyz]")                         
.append("|(?:tel|travel|t[cdfghjklmnoprtvwz])")                         
.append("|u[agkmsyz]")                         
.append("|v[aceginu]")                         
.append("|w[fs]")                         
.append("|y[etu]")                         
.append("|z[amw]))")                         
.append("|(?:(?:25[0-5]|2[0-4]") // or ip address                                                 
.append("[0-9]|[0-1][0-9]{2}|[1-9][0-9]|[1-9])\\.(?:25[0-5]|2[0-4][0-9]")                             
.append("|[0-1][0-9]{2}|[1-9][0-9]|[1-9]|0)\\.(?:25[0-5]|2[0-4][0-9]|[0-1]")                         
.append("[0-9]{2}|[1-9][0-9]|[1-9]|0)\\.(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}")                         
.append("|[1-9][0-9]|[0-9])))")                         
.append("(?:\\:\\d{1,5})?)") // plus option port number                             
.append("(\\/(?:(?:[a-zA-Z0-9\\;\\/\\?\\:\\@\\&\\=\\#\\~")  // plus option query params                         
.append("\\-\\.\\+\\!\\*\\'\\(\\)\\,\\_])|(?:\\%[a-fA-F0-9]{2}))*)?")                         
.append("(?:\\b|$)").toString()                 
).matcher("");

Answer 23

I've been working on an in-depth article discussing URI validation using regular expressions. It is based on RFC3986.

Regular Expression URI Validation

Although the article is not yet complete, I have come up with a PHP function which does a pretty good job of validating HTTP and FTP URLs. Here is the current version:

// function url_valid($url) { Rev:20110423_2000
//
// Return associative array of valid URI components, or FALSE if $url is not
// RFC-3986 compliant. If the passed URL begins with: "www." or "ftp.", then
// "http://" or "ftp://" is prepended and the corrected full-url is stored in
// the return array with a key name "url". This value should be used by the caller.
//
// Return value: FALSE if $url is not valid, otherwise array of URI components:
// e.g.
// Given: "http://www.jmrware.com:80/articles?height=10&width=75#fragone"
// Array(
//    [scheme] => http
//    [authority] => www.jmrware.com:80
//    [userinfo] =>
//    [host] => www.jmrware.com
//    [IP_literal] =>
//    [IPV6address] =>
//    [ls32] =>
//    [IPvFuture] =>
//    [IPv4address] =>
//    [regname] => www.jmrware.com
//    [port] => 80
//    [path_abempty] => /articles
//    [query] => height=10&width=75
//    [fragment] => fragone
//    [url] => http://www.jmrware.com:80/articles?height=10&width=75#fragone
// )
function url_valid($url) {
    if (strpos($url, 'www.') === 0) $url = 'http://'. $url;
    if (strpos($url, 'ftp.') === 0) $url = 'ftp://'. $url;
    if (!preg_match('/# Valid absolute URI having a non-empty, valid DNS host.
        ^
        (?P<scheme>[A-Za-z][A-Za-z0-9+\-.]*):\/\/
        (?P<authority>
          (?:(?P<userinfo>(?:[A-Za-z0-9\-._~!$&\'()*+,;=:]|%[0-9A-Fa-f]{2})*)@)?
          (?P<host>
            (?P<IP_literal>
              \[
              (?:
                (?P<IPV6address>
                  (?:                                                (?:[0-9A-Fa-f]{1,4}:){6}
                  |                                                ::(?:[0-9A-Fa-f]{1,4}:){5}
                  | (?:                          [0-9A-Fa-f]{1,4})?::(?:[0-9A-Fa-f]{1,4}:){4}
                  | (?:(?:[0-9A-Fa-f]{1,4}:){0,1}[0-9A-Fa-f]{1,4})?::(?:[0-9A-Fa-f]{1,4}:){3}
                  | (?:(?:[0-9A-Fa-f]{1,4}:){0,2}[0-9A-Fa-f]{1,4})?::(?:[0-9A-Fa-f]{1,4}:){2}
                  | (?:(?:[0-9A-Fa-f]{1,4}:){0,3}[0-9A-Fa-f]{1,4})?::   [0-9A-Fa-f]{1,4}:
                  | (?:(?:[0-9A-Fa-f]{1,4}:){0,4}[0-9A-Fa-f]{1,4})?::
                  )
                  (?P<ls32>[0-9A-Fa-f]{1,4}:[0-9A-Fa-f]{1,4}
                  | (?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}
                       (?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)
                  )
                |   (?:(?:[0-9A-Fa-f]{1,4}:){0,5}[0-9A-Fa-f]{1,4})?::   [0-9A-Fa-f]{1,4}
                |   (?:(?:[0-9A-Fa-f]{1,4}:){0,6}[0-9A-Fa-f]{1,4})?::
                )
              | (?P<IPvFuture>[Vv][0-9A-Fa-f]+\.[A-Za-z0-9\-._~!$&\'()*+,;=:]+)
              )
              \]
            )
          | (?P<IPv4address>(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}
                               (?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?))
          | (?P<regname>(?:[A-Za-z0-9\-._~!$&\'()*+,;=]|%[0-9A-Fa-f]{2})+)
          )
          (?::(?P<port>[0-9]*))?
        )
        (?P<path_abempty>(?:\/(?:[A-Za-z0-9\-._~!$&\'()*+,;=:@]|%[0-9A-Fa-f]{2})*)*)
        (?:\?(?P<query>       (?:[A-Za-z0-9\-._~!$&\'()*+,;=:@\\/?]|%[0-9A-Fa-f]{2})*))?
        (?:\#(?P<fragment>    (?:[A-Za-z0-9\-._~!$&\'()*+,;=:@\\/?]|%[0-9A-Fa-f]{2})*))?
        $
        /mx', $url, $m)) return FALSE;
    switch ($m['scheme']) {
    case 'https':
    case 'http':
        if ($m['userinfo']) return FALSE; // HTTP scheme does not allow userinfo.
        break;
    case 'ftps':
    case 'ftp':
        break;
    default:
        return FALSE;   // Unrecognized URI scheme. Default to FALSE.
    }
    // Validate host name conforms to DNS "dot-separated-parts".
    if ($m['regname']) { // If host regname specified, check for DNS conformance.
        if (!preg_match('/# HTTP DNS host name.
            ^                      # Anchor to beginning of string.
            (?!.{256})             # Overall host length is less than 256 chars.
            (?:                    # Group dot separated host part alternatives.
              [A-Za-z0-9]\.        # Either a single alphanum followed by dot
            |                      # or... part has more than one char (63 chars max).
              [A-Za-z0-9]          # Part first char is alphanum (no dash).
              [A-Za-z0-9\-]{0,61}  # Internal chars are alphanum plus dash.
              [A-Za-z0-9]          # Part last char is alphanum (no dash).
              \.                   # Each part followed by literal dot.
            )*                     # Zero or more parts before top level domain.
            (?:                    # Explicitly specify top level domains.
              com|edu|gov|int|mil|net|org|biz|
              info|name|pro|aero|coop|museum|
              asia|cat|jobs|mobi|tel|travel|
              [A-Za-z]{2})         # Country codes are exactly two alpha chars.
              \.?                  # Top level domain can end in a dot.
            $                      # Anchor to end of string.
            /ix', $m['host'])) return FALSE;
    }
    $m['url'] = $url;
    for ($i = 0; isset($m[$i]); ++$i) unset($m[$i]);
    return $m; // return TRUE == array of useful named $matches plus the valid $url.
}

This function utilizes two regexes; one to match a subset of valid generic URIs (absolute ones having a non-empty host), and a second to validate the DNS "dot-separated-parts" host name. Although this function currently validates only HTTP and FTP schemes, it is structured such that it can be easily extended to handle other schemes.

Answer 24

For Python, this is the actual URL validating regex used in Django 1.5.1:

import re
regex = re.compile(
        r'^(?:http|ftp)s?://'  # http:// or https://
        r'(?:(?:[A-Z0-9](?:[A-Z0-9-]{0,61}[A-Z0-9])?\.)+(?:[A-Z]{2,6}\.?|[A-Z0-9-]{2,}\.?)|'  # domain...
        r'localhost|'  # localhost...
        r'\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}|'  # ...or ipv4
        r'\[?[A-F0-9]*:[A-F0-9:]+\]?)'  # ...or ipv6
        r'(?::\d+)?'  # optional port
        r'(?:/?|[/?]\S+)$', re.IGNORECASE)

This does both ipv4 and ipv6 addresses as well as ports and GET parameters.

Found in the code here, Line 44.

Answer 25

This one works for me very well. (https?|ftp)://(www\d?|[a-zA-Z0-9]+)?\.[a-zA-Z0-9-]+(\:|\.)([a-zA-Z0-9.]+|(\d+)?)([/?:].*)?

Answer 26

For convenience here's a one-liner regexp for URL's that will also match localhost where you're more likely to have ports than .com or similar.

(http(s)?:\/\/.)?(www\.)?[-a-zA-Z0-9@:%._\+~#=]{2,256}(\.[a-z]{2,6}|:[0-9]{3,4})\b([-a-zA-Z0-9@:%_\+.~#?&\/\/=]*)

Answer 27

I found the following Regex for URLs, tested successfully with 500+ URLs:

/\b(?:(?:https?|ftp):\/\/)(?:\S+(?::\S*)?@)?(?:(?!10(?:\.\d{1,3}){3})(?!127(?:\.\d{1,3}){3})(?!169\.254(?:\.\d{1,3}){2})(?!192\.168(?:\.\d{1,3}){2})(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))|(?:(?:[a-z\x{00a1}-\x{ffff}0-9]+-?)*[a-z\x{00a1}-\x{ffff}0-9]+)(?:\.(?:[a-z\x{00a1}-\x{ffff}0-9]+-?)*[a-z\x{00a1}-\x{ffff}0-9]+)*(?:\.(?:[a-z\x{00a1}-\x{ffff}]{2,})))(?::\d{2,5})?(?:\/[^\s]*)?\b/gi

I know it looks ugly, but the good thing is that it works. :)

Explanation and demo with 581 random URLs on regex101.

Source: In search of the perfect URL validation regex

Answer 28

To Match a URL there are various option and it depend on you requirement. below are few.

_(^|[\s.:;?\-\]<\(])(https?://[-\w;/?:@&=+$\|\_.!~*\|'()\[\]%#,☺]+[\w/#](\(\))?)(?=$|[\s',\|\(\).:;?\-\[\]>\)])_i

#\b(([\w-]+://?|www[.])[^\s()<>]+(?:\([\w\d]+\)|([^[:punct:]\s]|/)))#iS

And there is a link which gives you more than 10 different variations of validation for URL.

https://mathiasbynens.be/demo/url-regex

Answer 29

I tried to formulate my version of url. My requirement was to capture instances in a String where possible url can be cse.uom.ac.mu - noting that it is not preceded by http nor www

String regularExpression = "((((ht{2}ps?://)?)((w{3}\\.)?))?)[^.&&[a-zA-Z0-9]][a-zA-Z0-9.-]+[^.&&[a-zA-Z0-9]](\\.[a-zA-Z]{2,3})";

assertTrue("www.google.com".matches(regularExpression));
assertTrue("www.google.co.uk".matches(regularExpression));
assertTrue("http://www.google.com".matches(regularExpression));
assertTrue("http://www.google.co.uk".matches(regularExpression));
assertTrue("https://www.google.com".matches(regularExpression));
assertTrue("https://www.google.co.uk".matches(regularExpression));
assertTrue("google.com".matches(regularExpression));
assertTrue("google.co.uk".matches(regularExpression));
assertTrue("google.mu".matches(regularExpression));
assertTrue("mes.intnet.mu".matches(regularExpression));
assertTrue("cse.uom.ac.mu".matches(regularExpression));

//cannot contain 2 '.' after www
assertFalse("www..dr.google".matches(regularExpression));

//cannot contain 2 '.' just before com
assertFalse("www.dr.google..com".matches(regularExpression));

// to test case where url www must be followed with a '.'
assertFalse("www:google.com".matches(regularExpression));

// to test case where url www must be followed with a '.'
//assertFalse("http://wwwe.google.com".matches(regularExpression));

// to test case where www must be preceded with a '.'
assertFalse("https://www@.google.com".matches(regularExpression));

Answer 30

The following RegEx will work:

"@((((ht)|(f))tp[s]?://)|(www\.))([a-z][-a-z0-9]+\.)?([a-z][-a-z0-9]+\.)?[a-z][-a-z0-9]+\.[a-z]+[/]?[a-z0-9._\/~#&=;%+?-]*@si"

Answer 31

Use this one its working for me

function validUrl(Url) {
    var myRegExp  =/^(?:(?:https?|ftp):\/\/)(?:\S+(?::\S*)?@)?(?:(?!10(?:\.\d{1,3}){3})(?!127(?:\.\d{1,3}){3})(?!169\.254(?:\.\d{1,3}){2})(?!192\.168(?:\.\d{1,3}){2})(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))|(?:(?:[a-z\u00a1-\uffff0-9]+-?)*[a-z\u00a1-\uffff0-9]+)(?:\.(?:[a-z\u00a1-\uffff0-9]+-?)*[a-z\u00a1-\uffff0-9]+)*(?:\.(?:[a-z\u00a1-\uffff]{2,})))(?::\d{2,5})?(?:\/[^\s]*)?$/i;

    if (!RegExp.test(Url.value)) {
        $("#urlErrorLbl").removeClass('highlightNew');
        return false;
    } 

    $("#urlErrorLbl").addClass('highlightNew'); 
    return true; 
}

Answer 32

You don't specify which language you're using. If PHP is, there is a native function for that:

$url = 'http://www.yoururl.co.uk/sub1/sub2/?param=1&param2/';

if ( ! filter_var( $url, FILTER_VALIDATE_URL ) ) {
    // Wrong
}
else {
    // Valid
}

Returns the filtered data, or FALSE if the filter fails.

Check it here >>

Hope it helps.

Answer 33

https?:\/{2}(?:[\/-\w.]|(?:%[\da-fA-F]{2}))+

You can use this pattern for detecting URLs.

Following is the proof of concept

RegExr: URL Detector

Answer 34

I think some people weren't able to use your php code because of the modifiers implied. I copied your code as is and used as an example:

if(
    preg_match(
        "/^{$IRI_reference}$/iu",
        'http://www.url.com'
    )
){
    echo 'true';
}

Notice the "i" and "u" modifiers. without "u" php throws an exception saying:

Warning: preg_match() [function.preg-match]: Compilation failed: character value in \x{...} sequence is too large at offset XX

Answer 35

whats wrong with plain and simple FILTER_VALIDATE_URL ?

 $url = "http://www.example.com";

if(!filter_var($url, FILTER_VALIDATE_URL))
  {
  echo "URL is not valid";
  }
else
  {
  echo "URL is valid";
  }

I know its not the question exactly but it did the job for me when I needed to validate urls so thought it might be useful to others who come across this post looking for the same thing

Answer 36

To Check URL regex would be:

^http(s{0,1})://[a-zA-Z0-9_/\\-\\.]+\\.([A-Za-z/]{2,5})[a-zA-Z0-9_/\\&\\?\\=\\-\\.\\~\\%]*

Answer 37

This is not a regular expression but accomplishes the same thing (Javascript only):

function isAValidUrl(url) {
  try {
    new URL(url);
    return true;
  } catch(e) {
    return false;
  }
}

Answer 38

How about this:

^(https?:\/\/(?:www\.|(?!www))[a-zA-Z0-9][a-zA-Z0-9-]+[a-zA-Z0-9]\.[^\s]{2,}|www\.[a-zA-Z0-9][a-zA-Z0-9-]+[a-zA-Z0-9]\.[^\s]{2,}|https?:\/\/(?:www\.|(?!www))[a-zA-Z0-9]\.[^\s]{2,}|www\.[a-zA-Z0-9]\.[^\s]{2,})$

These are the test cases:

You can try it out in here : https://regex101.com/r/mS9gD7/41

Answer 39

IMPROVED

Detects Urls like these:

• https://www.example.pl
• http://www.example.com
• www.example.pl
• example.com
• http://blog.example.com
• http://www.example.com/product
• http://www.example.com/products?id=1&page=2
• http://www.example.com#up
• http://255.255.255.255
• 255.255.255.255
• http:// www.site.com:8008

Regex:

/^(?:http(s)?:\/\/)?[\w.-]+(?:\.[\w\.-]+)+[\w\-\._~:/?#[\]@!\$&'\(\)\*\+,;=.]+$/gm

Answer 40

I use this: /((https?:\/\/|ftp:\/\/|www\.)\S+\.[^()\n ]+((?:\([^)]*\))|[^.,;:?!"'\n\)\]<* ])+)/

It's short, but it handles edge cases like certain Wikipedia links (https://en.wikipedia.org/wiki/Sally_(name)) that ends in a bracket, which the most voted answers here don't seem to cover.

Answer 41

Updated, International & Modern Answer for 2023 And Beyond

Covering 99%+ URLs supported by modern browsers, that includes:

• emojis in domain name and path
• enforcing for top level domain: first character should be alpha but can have numbers afterwards, 2 characters minimum, up to the theoretical limit of 63, yet allowing underscores, accented characters and internationalized characters
• world's most common languages alphabets, characters & diacritics in path & domain name. Includes English (duh), French, Spanish, Portuguese, German, Italian, Bengali, Devenagri, Marathi, ~99% Chinese (CJK), Japanese, Korean, Taiwanese, Vietnamese, Urdu, Arabic, Greek, Cyrillic and all others that share their character sets with these
• Added versions with and without support for IPv4 URLs that are also used and seen online & supported by all modern browsers

Use this to include the protocol ("http/https") & IPv4 URLs:

https?:\/\/(\b(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?):\d{1,5}\b|([-a-zA-Z0-9\u1F60-\uFFFF\u1F60-\uFFFF\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u024F@:%._\+~#=]{1,256})\.([a-zA-Z][a-zA-Z0-9\u1F60-\uFFFF\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u024F\u0370-\u03ff\u1f00-\u1fff\u0400-\u04ff()-]{1,62}))\b([\/#][-a-zA-Z0-9\u1F60-\uFFFF\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u024F\u0370-\u03ff\u1f00-\u1fff\u0400-\u04ff\u0900-\u097F\u0600-\u06FF\u0985-\u0994\u0995-\u09a7\u09a8-\u09ce\u0981\u0982\u0983\u09e6-\u09ef\u0750-\u077F\uFB50-\uFDFF\uFE70-\uFEFF\u4E00-\u9FFFẸɓɗẹỊỌịọṢỤṣụ()@:%_\+.~#?&//=\[\]!\$'*+,;]*)?

Use this to include the protocol but not IPv4 addresses:

https?:\/\/([-a-zA-Z0-9\u1F60-\uFFFF\u1F60-\uFFFF\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u024F@:%._\+~#=]{1,256})\.([a-zA-Z][a-zA-Z0-9\u1F60-\uFFFF\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u024F\u0370-\u03ff\u1f00-\u1fff\u0400-\u04ff()-]{1,62})\b([\/#][-a-zA-Z0-9\u1F60-\uFFFF\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u024F\u0370-\u03ff\u1f00-\u1fff\u0400-\u04ff\u0900-\u097F\u0600-\u06FF\u0985-\u0994\u0995-\u09a7\u09a8-\u09ce\u0981\u0982\u0983\u09e6-\u09ef\u0750-\u077F\uFB50-\uFDFF\uFE70-\uFEFF\u4E00-\u9FFFẸɓɗẹỊỌịọṢỤṣụ()@:%_\+.~#?&//=\[\]!\$'*+,;]*)?

To match domain names and paths (no IPv4):

([-a-zA-Z0-9\u1F60-\uFFFF\u1F60-\uFFFF\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u024F@:%._\+~#=]{1,256})\.([a-zA-Z][a-zA-Z0-9\u1F60-\uFFFF\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u024F\u0370-\u03ff\u1f00-\u1fff\u0400-\u04ff()-]{1,62})\b([\/#][-a-zA-Z0-9\u1F60-\uFFFF\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u024F\u0370-\u03ff\u1f00-\u1fff\u0400-\u04ff\u0900-\u097F\u0600-\u06FF\u0985-\u0994\u0995-\u09a7\u09a8-\u09ce\u0981\u0982\u0983\u09e6-\u09ef\u0750-\u077F\uFB50-\uFDFF\uFE70-\uFEFF\u4E00-\u9FFFẸɓɗẹỊỌịọṢỤṣụ()@:%_\+.~#?&//=\[\]!\$'*+,;]*)?

Battle-Tested with all these Real-World & Theoretical Edge Cases:

// Check with a simple copy/paste in console!

const regexURLsAndIPs =
  /^https?:\/\/(\b(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?):\d{1,5}\b|([-a-zA-Z0-9\u1F60-\uFFFF\u1F60-\uFFFF\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u024F@:%._\+~#=]{1,256})\.([a-zA-Z][a-zA-Z0-9\u1F60-\uFFFF\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u024F\u0370-\u03ff\u1f00-\u1fff\u0400-\u04ff()-]{1,62}))\b([\/#][-a-zA-Z0-9\u1F60-\uFFFF\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u024F\u0370-\u03ff\u1f00-\u1fff\u0400-\u04ff\u0900-\u097F\u0600-\u06FF\u0985-\u0994\u0995-\u09a7\u09a8-\u09ce\u0981\u0982\u0983\u09e6-\u09ef\u0750-\u077F\uFB50-\uFDFF\uFE70-\uFEFF\u4E00-\u9FFFẸɓɗẹỊỌịọṢỤṣụ()@:%_\+.~#?&//=\[\]!\$'*+,;]*)?$/

const shouldMatch = [
  'https://base.com/',
  'http://t.co',
  'https://www.google.com.ua/',
  'https://subdomains.as.deep.as.you.want.example.com',
  'https://sub.second_leveldomain_underscore.verylongtoplevedomain/nice',
  'https://domain-name.com/path-common-characters/ABCxyz01789',
  'http://domaîn-with-àccents.ca',
  'http://path-with-accents.com/àèìòùçÇßØøÅåÆæœ',
  'https://en.wikipedia.org/wiki/Möbius_strip',
  'http://www..tld/emojis--in--domain/-and-path-/',
  'https://y.at/',
  'https://hashtag.forpath#lets-go',
  "http://special.com/all-special-characters-._~:/?#[]@!$&'()*+,;=",
  'https://greek_with_diacritics.co/ΑαΒβΣσ/ςΤτϋΰήώΊΪΌΆΈΎΫΉΏᾶἀ',
  'https://el.wikipedia.org/wiki/Ποσειδώνας_(πλανήτης)',
  'http://cyrillic-and-extras.ru/АаБбВвЪъыӸӹЫЯЯяѶѷ',
  'https://ru.wikipedia.org/wiki/Заглавная_страница',
  'https://most-arabic.co/گچپژیلفقهموء-يجريبتج/',
  'https://urdu.co/حروفِ/',
  'https://nigerian.ni/ƁƊƎẸɓɗǝẹỊƘỌịƙọṢỤṣụ',
  'https://bengali.sports.co/স্পর্শঅনুনাসিকলসওষ্ঠ্যপফবভম/',
  'https://devenagri.cc/कखगघङचछजझञटठडढणतथदधनपफबभमयरलवशषस',
  'https://h.org/wiki/Wikipedia:关于中文维基百科/en',
  'https://zh.wikipedia.org/wiki/Wikipedia:关于中文维基百科/en',
  'http://others.kr/korean-안녕ㆅㅇㄹㅿㆍㅡㅣㅗㅑㅠㅕ/japanese-一龠ぁゔａｚＡＺ０９々〆〤ヶ',
  'https://龠.subdomain.com',
  'http://127.0.0.1:22/valid-ip',
  'http://127.00.00.01:22/ugly-but-still-works-with-modern-browsers',
  'http://0.0.0.0:0/is-min',
  'https://255.255.255.255:0/is-max',
  'https://this.tld-is-63-characters-wich-is-the-theoretical-limit-000000000000',
]

const shouldNotMatch = [
  'noprotocol.com',
  ' https://space-in-front.com',
  'https://invalid.0om',
  'https://invalid.-om',
  'https://invalid-single-letter-tld.c',
  'https://invalid-domain&char.com',
  'https://invalid:com',
  'https://not valid.com',
  'https://not,valid.com',
  'https://龠.c龠',
  'https://invalidαΒβΣσ.com',
  'notvalid://www.google.com',
  'http://missing-tld',
  'https://0.0.0.0missing-port',
  '0.0.0.0:0/missing-protocol',
  'https://256.255.255.255:0/is-above-max',
  'https://this.tld-is-64-characters-which-is-too-looooooooooooooooooooooooooong',
]

function checkStringsMatchRegex(regex, array, shouldMatch = true) {
  for (let i = 0; i < array.length; i++) {
    if (regex.test(array[i]) !== shouldMatch) {
      const matchStr = shouldMatch ? 'match' : 'not match'
      console.error('regex.test(array[i])', regex.test(array[i]))
      throw new Error(`String "${array[i]}" should ${matchStr} regex "${regex}"`)
    }
  }
  const successMatchingStr = shouldMatch ? 'matching all strings' : 'not matching a single string'
  console.log(`Success with ${successMatchingStr} in the test array.`)
}

checkStringsMatchRegex(regexURLsAndIPs, shouldMatch, true)
checkStringsMatchRegex(regexURLsAndIPs, shouldNotMatch, false)

Answer 42

This is a rather old thread now and the question asks for a regex based URL validator. I ran into the thread whilst looking for precisely the same thing. While it may well be possible to write a really comprehensive regex to validate URLs. I eventually settled on another way to do things - by using PHP's parse_url function.

It returns boolean false if the url cannot be parsed. Otherwise, it returns the scheme, the host and other information. This may well not be enough for a comprehensive URL check on its own, but can be drilled down into for further analysis. If the intent is to simply catch typos, invalid schemes etc. It is perfectly adequate!

Answer 43

Here is the best and the most matched regex for this situation

^(?:http(?:s)?:\/\/)?(?:www\.)?(?:[\w-]*)\.\w{2,}$

Answer 44

To match the URL up to the domain:

(^(\bhttp)(|s):\/{2})(?=[a-z0-9-_]{1,255})\.\1\.([a-z]{3,7}$)

It can be simplified to:

(^(\bhttp)(|s):\/{2})(?=[a-z0-9-_.]{1,255})\.([a-z]{3,7})

the latter does not check for the end for the end line so that it can be later used create full blown URL with full paths and query strings.

Answer 45

This should work:

function validateUrl(value){
 return /^(http(s)?:\/\/.)?(www\.)?[-a-zA-Z0-9@:%._\+~#=]{2,256}\.[a-z]{2,6}\b([-a-zA-Z0-9@:%_\+.~#?&//=]*)$/gi.test(value);
}

console.log(validateUrl('google.com')); // true
console.log(validateUrl('www.google.com')); // true
console.log(validateUrl('http://www.google.com')); // true
console.log(validateUrl('http:/www.google.com')); // false
console.log(validateUrl('www.google.com/test')); // true

Answer 46

I think I found a more general regexp to validate urls, particularly websites

​(https?:\/\/)?(www\.)[-a-zA-Z0-9@:%._\+~#=]{2,256}\.[a-z]{2,4}\b([-a-zA-Z0-9@:%_\+.~#?&//=]*)|(https?:\/\/)?(www\.)?(?!ww)[-a-zA-Z0-9@:%._\+~#=]{2,256}\.[a-z]{2,4}\b([-a-zA-Z0-9@:%_\+.~#?&//=]*)

it does not allow for instance www.something or http://www or http://www.something

Check it here: http://regexr.com/3e4a2

Answer 47

I created a similar regex (PCRE) to the one @eyelidlessness provided following RFC3987 along with other RFC documents. The major difference between @eyelidlessness and my regex are mainly readability and also URN support.

The regex below is all one piece (instead of being mixed with PHP) so it can be used in different languages very easily (so long as they support PCRE)

The easiest way to test this regex is to use regex101 and copy paste the code and test strings below with the appropriate modifiers (gmx).

To use this regex in PHP, insert the regex below into the following code:

$regex = <<<'EOD'
// Put the regex here
EOD;

---

You can match a link without a scheme by doing the following:
To match a link without a scheme (i.e. john.doe@gmail.com or www.google.com/pathtofile.php?query), replace this section:

  (?:
    (?<scheme>
      (?<urn>urn)|
      (?&d_scheme)
    )
    :
  )?

with this:

  (?:
    (?<scheme>
      (?<urn>urn)|
      (?&d_scheme)
    )
    :
  )?

Note, however, that by replacing this, the regex does not become 100% reliable.

---

Regex (PCRE) with gmx modifiers for the multi-line test string below

(?(DEFINE)
  # Definitions
  (?<ALPHA>[\p{L}])
  (?<DIGIT>[0-9])
  (?<HEX>[0-9a-fA-F])
  (?<NCCHAR>
    (?&UNRESERVED)|
    (?&PCT_ENCODED)|
    (?&SUB_DELIMS)|
    @
  )
  (?<PCHAR>
    (?&UNRESERVED)|
    (?&PCT_ENCODED)|
    (?&SUB_DELIMS)|
    :|
    @|
    \/
  )
  (?<UCHAR>
    (?&UNRESERVED)|
    (?&PCT_ENCODED)|
    (?&SUB_DELIMS)|
    :
  )
  (?<RCHAR>
    (?&UNRESERVED)|
    (?&PCT_ENCODED)|
    (?&SUB_DELIMS)
  )
  (?<PCT_ENCODED>%(?&HEX){2})
  (?<UNRESERVED>
    ((?&ALPHA)|(?&DIGIT)|[-._~])
  )
  (?<RESERVED>(?&GEN_DELIMS)|(?&SUB_DELIMS))
  (?<GEN_DELIMS>[:\/?#\[\]@])
  (?<SUB_DELIMS>[!$&'()*+,;=])
  # URI Parts
  (?<d_scheme>
    (?!urn)
    (?:
      (?&ALPHA)
      ((?&ALPHA)|(?&DIGIT)|[+-.])*
      (?=:)
    )
  )
  (?<d_hier_part_slashes>
    (\/{2})?
  )
  (?<d_authority>(?&d_userinfo)?)
  (?<d_userinfo>(?&UCHAR)*)
  (?<d_ipv6>
    (?![^:]*::[^:]*::[^:]*)
    (
      (
        ((?&HEX){0,4})
        :
      ){1,7}
      ((?&d_ipv4)|:|(?&HEX){1,4})
    )
  )
  (?<d_ipv4>
    ((?&octet)\.){3}
    (?&octet)
  )
  (?<octet>
    (
      25[]0-5]|
      2[0-4](?&DIGIT)|
      1(?&DIGIT){2}|
      [1-9](?&DIGIT)|
      (?&DIGIT)
    )
  )
  (?<d_reg_name>(?&RCHAR)*)
  (?<d_urn_name>(?&UCHAR)*)
  (?<d_port>(?&DIGIT)*)
  (?<d_path>
    (
      \/
      ((?&PCHAR)*)*
      (?=\?|\#|$)
    )
  )
  (?<d_query>
    (
      ((?&PCHAR)|\/|\?)*
    )?
  )
  (?<d_fragment>
    (
      ((?&PCHAR)|\/|\?)*
    )?
  )
)
^
(?<link>
  (?:
    (?<scheme>
      (?<urn>urn)|
      (?&d_scheme)
    )
    :
  )
  (?(urn)
    (?:
      (?<namespace_identifier>[0-9a-zA-Z\-]+)
      :
      (?<namespace_specific_string>(?&d_urn_name)+)
    )
    |
    (?<hier_part>
      (?<slashes>(?&d_hier_part_slashes))
      (?<authority>
        (?:
          (?<userinfo>(?&d_authority))
          @
        )?
        (?<host>
          (?<ipv4>\[?(?&d_ipv4)\]?)|
          (?<ipv6>\[(?&d_ipv6)\])|
          (?<domain>(?&d_reg_name))
        )
        (?:
          :
          (?<port>(?&d_port))
        )?
      )
      (?<path>(?&d_path))?
    )
    (?:
      \?
      (?<query>(?&d_query))
    )?
    (?:
      \#
      (?<fragment>(?&d_fragment))
    )?
  )
)
$

Test Strings

# Valid URIs
ftp://cnn.example.com&story=breaking_news@10.0.0.1/top_story.htm
ftp://ftp.is.co.za/rfc/rfc1808.txt
http://www.ietf.org/rfc/rfc2396.txt
ldap://[2001:db8::7]/c=GB?objectClass?one
mailto:John.Doe@example.com
news:comp.infosystems.www.servers.unix
tel:+1-816-555-1212
telnet://192.0.2.16:80/
urn:isbn:0451450523
urn:oid:2.16.840
urn:isan:0000-0000-9E59-0000-O-0000-0000-2
urn:oasis:names:specification:docbook:dtd:xml:4.1.2
http://localhost/test/somefile.php?query=someval&variable=value#fragment
http://[2001:db8:a0b:12f0::1]/test
ftp://username:password@domain.com/path/to/file/somefile.html?queryVariable=value#fragment
https://subdomain.domain.com/path/to/file.php?query=value#fragment
https://subdomain.example.com/path/to/file.php?query=value#fragment
mailto:john.smith(comment)@example.com
mailto:user@[2001:DB8::1]
mailto:user@[255:192:168:1]
mailto:M.Handley@cs.ucl.ac.uk
http://localhost:4433/path/to/file?query#fragment
# Note that the example below IS a valid as it does follow RFC standards
localhost:4433/path/to/file

# These work with the optional scheme group although I'd suggest making the scheme mandatory as misinterpretations can occur
john.doe@gmail.com
www.google.com/pathtofile.php?query
[192a:123::192.168.1.1]:80/path/to/file.html?query#fragment

Answer 48

As far as I have found, this expression is good for me-

(https?:\/\/(?:www\.|(?!www))[a-zA-Z0-9][a-zA-Z0-9-]+[a-zA-Z0-9]\.[^\s]{2,}|https?:\/\/(?:www\.|(?!www))[a-zA-Z0-9]\.[^\s]{2,}|www\.[a-zA-Z0-9]\.[^\s]{2,})

Working example-

function RegExForUrlMatch()
{
  var expression = /(https?:\/\/(?:www\.|(?!www))[a-zA-Z0-9][a-zA-Z0-9-]+[a-zA-Z0-9]\.[^\s]{2,}|https?:\/\/(?:www\.|(?!www))[a-zA-Z0-9]\.[^\s]{2,}|www\.[a-zA-Z0-9]\.[^\s]{2,})/g;

  var regex = new RegExp(expression);
  var t = document.getElementById("url").value;

  if (t.match(regex)) {
    document.getElementById("demo").innerHTML = "Successful match";
  } else {
    document.getElementById("demo").innerHTML = "No match";
  }
}

<input type="text" id="url" placeholder="url" onkeyup="RegExForUrlMatch()">

<p id="demo">Please enter a URL to test</p>

Answer 49

Below expression will work for all popular domains. It will accept following urls:

• www.yourwebsite.com
• http://www.yourwebsite.com
• www.yourwebsite.com
• yourwebsite.com
• yourwebsite.co.in

In addition it will make message with url as link also
e.g. please visit yourwebsite.com
In above example it will make yourwebsite.com as hyperlink

if (new RegExp("([-a-z0-9]{1,63}\\.)*?[a-z0-9][-a-z0-9]{0,61}[a-z0-9]\\.(com|com/|org|gov|cm|net|online|live|biz|us|uk|co.us|co.uk|in|co.in|int|info|edu|mil|ca|co|co.au|org/|gov/|cm/|net/|online/|live/|biz/|us/|uk/|co.us/|co.uk/|in/|co.in/|int/|info/|edu/|mil/|ca/|co/|co.au/)(/[-\\w@\\+\\.~#\\?*&/=% ]*)?$").test(strMessage) || (new RegExp("^[a-z ]+[\.]?[a-z ]+?[\.]+[a-z ]+?[\.]+[a-z ]+?[-\\w@\\+\\.~#\\?*&/=% ]*").test(strMessage) && new RegExp("([a-zA-Z0-9]+://)?([a-zA-Z0-9_]+:[a-zA-Z0-9_]+@)?([a-zA-Z0-9.-]+\\.[A-Za-z]{2,4})(:[0-9]+)?(/.*)?").test(strMessage)) || (new RegExp("^[a-z ]+[\.]?[a-z ]+?[-\\w@\\+\\.~#\\?*&/=% ]*").test(strMessage) && new RegExp("([a-zA-Z0-9]+://)?([a-zA-Z0-9_]+:[a-zA-Z0-9_]+@)?([a-zA-Z0-9.-]+\\.[A-Za-z]{2,4})(:[0-9]+)?(/.*)?").test(strMessage))) {
  if (new RegExp("^[a-z ]+[\.]?[a-z ]+?[\.]+[a-z ]+?[\.]+[a-z ]+?$").test(strMessage) && new RegExp("([a-zA-Z0-9]+://)?([a-zA-Z0-9_]+:[a-zA-Z0-9_]+@)?([a-zA-Z0-9.-]+\\.[A-Za-z]{2,4})(:[0-9]+)?(/.*)?").test(strMessage)) {
    var url1 = /(^|<|\s)([\w\.]+\.(?:com|org|gov|cm|net|online|live|biz|us|uk|co.us|co.uk|in|co.in|int|info|edu|mil|ca|co|co.au))(\s|>|$)/g;
    var html = $.trim(strMessage);
    if (html) {
      html = html.replace(url1, '$1<a style="color:blue; text-decoration:underline;" target="_blank"  href="http://$2">$2</a>$3');
    }
    returnString = html;
    return returnString;
  } else {
    var url1 = /(^|&lt;|\s)(www\..+?\.(?:com|org|gov|cm|net|online|live|biz|us|uk|co.us|co.uk|in|co.in|int|info|edu|mil|ca|co|co.au)[^,\s]*)(\s|&gt;|$)/g,
      url2 = /(^|&lt;|\s)(((https?|ftp):\/\/|mailto:).+?\.(?:com|org|gov|cm|net|online|live|biz|us|uk|co.us|co.uk|in|co.in|int|info|edu|mil|ca|co|co.au)[^,\s]*)(\s|&gt;|$)/g,
      url3 = /(^|&lt;|\s)([\w\.]+\.(?:com|org|gov|cm|net|online|live|biz|us|uk|co.us|co.uk|in|co.in|int|info|edu|mil|ca|co|co.au)[^,\s]*)(\s|&gt;|$)/g;

    var html = $.trim(strMessage);
    if (html) {
      html = html.replace(url1, '$1<a style="color:blue; text-decoration:underline;" target="_blank"  href="http://$2">$2</a>$3').replace(url2, '$1<a style="color:blue; text-decoration:underline;" target="_blank"  href="$2">$2</a>$5').replace(url3, '$1<a style="color:blue; text-decoration:underline;" target="_blank"  href="http://$2">$2</a>$3');
    }
    returnString = html;

    return returnString;
  }
}

Answer 50

After rigorous searching i finally settled with the following

^[a-zA-Z0-9]+\:\/\/[a-zA-Z0-9]+\.[-a-zA-Z0-9]+\.?[a-zA-Z0-9]+$|^[a-zA-Z0-9]+\.[-a-zA-Z0-9]+\.[a-zA-Z0-9]+$

And this thing work for general in future URLs.

Answer 51

The best regex, i've found is: /(^|\s)((https?:\/\/)?[\w-]+(\.[\w-]+)+\.?(:\d+)?(\/\S*)?)/gi

For ios swift : (^|\\s)((https?:\\/\\/)?[\\w-]+(\\.[\\w-]+)+\\.?(:\\d+)?(\\/\\S*)?)

http://jsfiddle.net/9BYdp/1/

Found here

Answer 52

Interestingly, none of the answers above worked for what I needed, so I figured I would offer my solution. I needed to be able to do the following:

• Match http(s)://www.google.com, http://google.com, www.google.com, and google.com
• Match Github markdown style links like [Google](http://www.google.com)
• Match all possible domain extensions, like .com, or .io, or .guru, etc. Basically anything between 2-6 characters in length
• Split everything into proper groupings so that I could access each part as needed.

Here was the solution:

/^(\[[A-z0-9 _]*\]\()?((?:(http|https):\/\/)?(?:[\w-]+\.)+[a-z]{2,6})(\))?$

This gives me all of the above requirements. You could optionally add the ability for ftp and file if necessary:

/^(\[[A-z0-9 _]*\]\()?((?:(http|https|ftp|file):\/\/)?(?:[\w-]+\.)+[a-z]{2,6})(\))?$

Answer 53

I think it is a very simple way. And it works very good.

var hasURL = (str) =>{
 var url_pattern = new RegExp("(www.|http://|https://|ftp://)\w*");
 if(!url_pattern.test(str)){
  document.getElementById("demo").innerHTML = 'No URL';
 }
 else
  document.getElementById("demo").innerHTML = 'String has a URL';
};

<p>Please enter a string and test it has any url or not</p>
<input type="text" id="url" placeholder="url" onkeyup="hasURL(document.getElementById('url').value)">
<p id="demo"></p>

Answer 54

If you would like to apply a more strict rule, here is what I have developed:

isValidUrl(input) {
    var regex = /^(((H|h)(T|t)(T|t)(P|p)(S|s)?):\/\/)?[-a-zA-Z0-9@:%._\+~#=]{2,100}\.[a-zA-Z]{2,10}(\/([-a-zA-Z0-9@:%_\+.~#?&//=]*))?/
    return regex.test(input)
}

Answer 55

Regardless the broad question asked, I post this for anyone in the future who is looking for something simple... as I think validating a URL has no perfect regular expression that fit all needs, it depends on your requirements, i.e: in my case, I just needed to verify if a URL is in the form of domain.extension and I wanted to allow the www or any other subdomain like blog.domain.extension I don't care about http(s) as in my app I have a field which says "enter the URL" so it's obvious what that entered string is.

so here is the regEx:

/^(www\.|[a-zA-Z0-9](.*[a-zA-Z0-9])?\.)?((?!www)[a-zA-Z0-9][a-zA-Z0-9-]+[a-zA-Z0-9])\.[a-z]{2,5}(:[0-9]{1,5})?$/i

The first block in this regExp is:

(www\.|[a-zA-Z0-9](.*[a-zA-Z0-9])?\.)? ---> we start to check if the URL start with www. or [a-zA-Z0-9](.*[a-zA-Z0-9])? which means a letterOrNumber + (anyCharacter(0 or multiple times) + another letterOrNumber) followed with a dot

Note that the (.*[a-zA-Z0-9])?\.)? we translated by (anyCharacter(0 or multiple times) + another letterOrNumber) is optional (can be or not) that's why we grouped it between parentheses and followed with the question mark ?

the whole block we discussed so far is also put between parentheses and followed by ? which means both www or any other word (that represents a subdomain) is optional.

The second part is: ((?!www)[a-zA-Z0-9][a-zA-Z0-9-]+[a-zA-Z0-9])\. ---> which represents the "domain" part, it can be any word (except www) starting with an alphabet or a number + any other alphabet (including dash "-") repeated one or more time, and ending with any alphabet or number followed with a dot.

The final part is [a-z]{2,} ---> which represent the "extension", it can be any alphabet repeated 2 or more times, so it can be com, net, org, art basically any extension

Answer 56

A simple check for URL is

^(ftp|http|https):\/\/[^ "]+$

Answer 57

The following Regex works for me:

(http(s)?:\/\/.)?(ftp(s)?:\/\/.)?(www\.)?[-a-zA-Z0-9@:%._\+~#=]{0,256}\.[a-z] 
{2,6}\b([-a-zA-Z0-9@:%_\+.~#?&//=]*)

matches:

https://google.com t.me https://t.me ftp://google.com http://sm.tj http://bro.tj t.me/rshss https:google.com www.cool.com.au http://www.cool.com.au http://www.cool.com.au/ersdfs http://www.cool.com.au/ersdfs?dfd=dfgd@s=1 http://www.cool.com:81/index.html

Answer 58

Javascript now has a URL Constructor called new URL(). It allows you to skip REGEX completely.

/**
 * 
 * The URL() constructor returns a newly created URL object representing 
 * the URL defined by the parameters. 
 * 
 * https://developer.mozilla.org/en-US/docs/Web/API/URL/URL
 * 
 */
let requestUrl = new URL('https://username:password@developer.mozilla.org:8080/en-US/docs/search.html?par1=abc&par2=123&par3=true#Recent');

let urlParts = {
  origin: requestUrl.origin,
  href: requestUrl.href,
  protocol: requestUrl.protocol,
  username: requestUrl.username,
  password: requestUrl.password,
  host: requestUrl.host,
  hostname: requestUrl.hostname,
  port: requestUrl.port,
  pathname: requestUrl.pathname,
  search: requestUrl.search,
  searchParams: {
    par1: String(requestUrl.searchParams.get('par1')),
    par2: Number(requestUrl.searchParams.get('par2')),
    par3: Boolean(requestUrl.searchParams.get('par3')),
  },
  hash: requestUrl.hash      
};

console.log(urlParts);

Answer 59

Thank you to @eyelidlessness for the extremely thorough (albeit long) RFC based regular expression.

For those of us using EICMAScript / JavaScript / Apps Script it doesn't work, however. Here is an otherwise exact replica of his answer that will work with these (along with a snippet to run for example - neat new feature!):

regEx_valid_URL = /^[a-z](?:[-a-z0-9\+\.])*:(?:\/\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\uA0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF\u10000-\u1FFFD\u20000-\u2FFFD\u30000-\u3FFFD\u40000-\u4FFFD\u50000-\u5FFFD\u60000-\u6FFFD\u70000-\u7FFFD\u80000-\u8FFFD\u90000-\u9FFFD\uA0000-\uAFFFD\uB0000-\uBFFFD\uC0000-\uCFFFD\uD0000-\uDFFFD\uE1000-\uEFFFD!\$&'\(\)\*\+,;=:])*@)?(?:\[(?:(?:(?:[0-9a-f]{1,4}:){6}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|::(?:[0-9a-f]{1,4}:){5}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:){4}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,1}[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:){3}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,2}[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:){2}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,3}[0-9a-f]{1,4})?::[0-9a-f]{1,4}:(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,4}[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,5}[0-9a-f]{1,4})?::[0-9a-f]{1,4}|(?:(?:[0-9a-f]{1,4}:){0,6}[0-9a-f]{1,4})?::)|v[0-9a-f]+\.[-a-z0-9\._~!\$&'\(\)\*\+,;=:]+)\]|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3}|(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\uA0}-\uD7FF}\uF900-\uFDCF}\uFDF0}-\uFFEF}\u10000-\u1FFFD\u20000-\u2FFFD\u30000-\u3FFFD\u40000-\u4FFFD\u50000-\u5FFFD\u60000-\u6FFFD\u70000-\u7FFFD\u80000-\u8FFFD\u90000-\u9FFFD\uA0000-\uAFFFD\uB0000-\uBFFFD\uC0000-\uCFFFD\uD0000-\uDFFFD\uE1000-\uEFFFD!\$&'\(\)\*\+,;=])*)(?::[0-9]*)?(?:\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\uA0}-\uD7FF}\uF900-\uFDCF}\uFDF0}-\uFFEF}\u10000-\u1FFFD\u20000-\u2FFFD\u30000-\u3FFFD\u40000-\u4FFFD\u50000-\u5FFFD\u60000-\u6FFFD\u70000-\u7FFFD\u80000-\u8FFFD\u90000-\u9FFFD\uA0000-\uAFFFD\uB0000-\uBFFFD\uC0000-\uCFFFD\uD0000-\uDFFFD\uE1000-\uEFFFD!\$&'\(\)\*\+,;=:@]))*)*|\/(?:(?:(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\uA0}-\uD7FF}\uF900-\uFDCF}\uFDF0}-\uFFEF}\u10000-\u1FFFD\u20000-\u2FFFD\u30000-\u3FFFD\u40000-\u4FFFD\u50000-\u5FFFD\u60000-\u6FFFD\u70000-\u7FFFD\u80000-\u8FFFD\u90000-\u9FFFD\uA0000-\uAFFFD\uB0000-\uBFFFD\uC0000-\uCFFFD\uD0000-\uDFFFD\uE1000-\uEFFFD!\$&'\(\)\*\+,;=:@]))+)(?:\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\uA0}-\uD7FF}\uF900-\uFDCF}\uFDF0}-\uFFEF}\u10000-\u1FFFD\u20000-\u2FFFD\u30000-\u3FFFD\u40000-\u4FFFD\u50000-\u5FFFD\u60000-\u6FFFD\u70000-\u7FFFD\u80000-\u8FFFD\u90000-\u9FFFD\uA0000-\uAFFFD\uB0000-\uBFFFD\uC0000-\uCFFFD\uD0000-\uDFFFD\uE1000-\uEFFFD!\$&'\(\)\*\+,;=:@]))*)*)?|(?:(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\uA0}-\uD7FF}\uF900-\uFDCF}\uFDF0}-\uFFEF}\u10000-\u1FFFD\u20000-\u2FFFD\u30000-\u3FFFD\u40000-\u4FFFD\u50000-\u5FFFD\u60000-\u6FFFD\u70000-\u7FFFD\u80000-\u8FFFD\u90000-\u9FFFD\uA0000-\uAFFFD\uB0000-\uBFFFD\uC0000-\uCFFFD\uD0000-\uDFFFD\uE1000-\uEFFFD!\$&'\(\)\*\+,;=:@]))+)(?:\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\uA0}-\uD7FF}\uF900-\uFDCF}\uFDF0}-\uFFEF}\u10000-\u1FFFD\u20000-\u2FFFD\u30000-\u3FFFD\u40000-\u4FFFD\u50000-\u5FFFD\u60000-\u6FFFD\u70000-\u7FFFD\u80000-\u8FFFD\u90000-\u9FFFD\uA0000-\uAFFFD\uB0000-\uBFFFD\uC0000-\uCFFFD\uD0000-\uDFFFD\uE1000-\uEFFFD!\$&'\(\)\*\+,;=:@]))*)*|(?!(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\uA0}-\uD7FF}\uF900-\uFDCF}\uFDF0}-\uFFEF}\u10000-\u1FFFD\u20000-\u2FFFD\u30000-\u3FFFD\u40000-\u4FFFD\u50000-\u5FFFD\u60000-\u6FFFD\u70000-\u7FFFD\u80000-\u8FFFD\u90000-\u9FFFD\uA0000-\uAFFFD\uB0000-\uBFFFD\uC0000-\uCFFFD\uD0000-\uDFFFD\uE1000-\uEFFFD!\$&'\(\)\*\+,;=:@])))(?:\?(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\uA0}-\uD7FF}\uF900-\uFDCF}\uFDF0}-\uFFEF}\u10000-\u1FFFD\u20000-\u2FFFD\u30000-\u3FFFD\u40000-\u4FFFD\u50000-\u5FFFD\u60000-\u6FFFD\u70000-\u7FFFD\u80000-\u8FFFD\u90000-\u9FFFD\uA0000-\uAFFFD\uB0000-\uBFFFD\uC0000-\uCFFFD\uD0000-\uDFFFD\uE1000-\uEFFFD!\$&'\(\)\*\+,;=:@])|[\uE000-\uF8FF}\uF0000-\uFFFFD\u100000-\u10FFFD\/\?])*)?(?:\#(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\uA0}-\uD7FF}\uF900-\uFDCF}\uFDF0}-\uFFEF}\u10000-\u1FFFD\u20000-\u2FFFD\u30000-\u3FFFD\u40000-\u4FFFD\u50000-\u5FFFD\u60000-\u6FFFD\u70000-\u7FFFD\u80000-\u8FFFD\u90000-\u9FFFD\uA0000-\uAFFFD\uB0000-\uBFFFD\uC0000-\uCFFFD\uD0000-\uDFFFD\uE1000-\uEFFFD!\$&'\(\)\*\+,;=:@])|[\/\?])*)?$/i;

checkedURL = RegExp(regEx_valid_URL).exec('gopher://example.somewhere.university/');

if (checkedURL != null) {
 console.log('The URL ' + checkedURL + ' is valid');
}

Answer 60

[(http(s)?):\/\/(www\.)?a-zA-Z0-9@:%._\+~#=]{2,256}\.[a-z]{2,6}\b([-a-zA-Z0-9@:%_\+.~#?&//=]*)

Answer 61

URL regexes from Android Open Source Project

Introduction

The Android Open Source Project (AOSP) contains multiple code blocks with URL regular expressions in Patterns.java. It can be difficult for non-Java users to extract the regex patterns out of it because of unicode, so I wrote some code to do it. Because the regex patterns contain unicode, which literal string syntax can differ per programming language, I've added two formats of each regex pattern. For example, Java uses \uUNICODE_NUMBER format, whereas PHP uses \u{UNICODE_NUMBER}.

Pattern called "WEB_URL"

Description from API doc:

Regular expression pattern to match most part of RFC 3987 Internationalized URLs, aka IRIs.

Regex in unicode \uUNICODE_NUMBER (Java, Python, Ruby) format:

(((?:(?i:http|https|rtsp|ftp)://(?:(?:[a-zA-Z0-9\$\-\_\.\+\!\*\'\(\)\,\;\?\&\=]|(?:\%[a-fA-F0-9]{2})){1,64}(?:\:(?:[a-zA-Z0-9\$\-\_\.\+\!\*\'\(\)\,\;\?\&\=]|(?:\%[a-fA-F0-9]{2})){1,25})?\@)?)?(?:(([a-zA-Z0-9[\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]]](?:[a-zA-Z0-9[\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]]_\-]{0,61}[a-zA-Z0-9[\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]]]){0,1}\.)+(xn\-\-[\w\-]{0,58}\w|[a-zA-Z[\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]]]{2,63})|((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]))))(?:\:\d{1,5})?)([/\?](?:(?:[a-zA-Z0-9[\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]];/\?:@&=#~\-\.\+!\*'\(\),_\$])|(?:%[a-fA-F0-9]{2}))*)?(?:\b|$|^))```

Regex in unicode \u{UNICODE_NUMBER} (PHP) format:

(((?:(?i:http|https|rtsp|ftp)://(?:(?:[a-zA-Z0-9\$\-\_\.\+\!\*\'\(\)\,\;\?\&\=]|(?:\%[a-fA-F0-9]{2})){1,64}(?:\:(?:[a-zA-Z0-9\$\-\_\.\+\!\*\'\(\)\,\;\?\&\=]|(?:\%[a-fA-F0-9]{2})){1,25})?\@)?)?(?:(([a-zA-Z0-9[\u{00a0}-\u{d7ff}\u{f900}-\u{fdcf}\u{fdf0}-\u{ffef}\u{d800}\u{dc00}-\u{d83f}\u{dffd}\u{d840}\u{dc00}-\u{d87f}\u{dffd}\u{d880}\u{dc00}-\u{d8bf}\u{dffd}\u{d8c0}\u{dc00}-\u{d8ff}\u{dffd}\u{d900}\u{dc00}-\u{d93f}\u{dffd}\u{d940}\u{dc00}-\u{d97f}\u{dffd}\u{d980}\u{dc00}-\u{d9bf}\u{dffd}\u{d9c0}\u{dc00}-\u{d9ff}\u{dffd}\u{da00}\u{dc00}-\u{da3f}\u{dffd}\u{da40}\u{dc00}-\u{da7f}\u{dffd}\u{da80}\u{dc00}-\u{dabf}\u{dffd}\u{dac0}\u{dc00}-\u{daff}\u{dffd}\u{db00}\u{dc00}-\u{db3f}\u{dffd}\u{db44}\u{dc00}-\u{db7f}\u{dffd}&&[^\u{00a0}[\u{2000}-\u{200a}]\u{2028}\u{2029}\u{202f}\u{3000}]]](?:[a-zA-Z0-9[\u{00a0}-\u{d7ff}\u{f900}-\u{fdcf}\u{fdf0}-\u{ffef}\u{d800}\u{dc00}-\u{d83f}\u{dffd}\u{d840}\u{dc00}-\u{d87f}\u{dffd}\u{d880}\u{dc00}-\u{d8bf}\u{dffd}\u{d8c0}\u{dc00}-\u{d8ff}\u{dffd}\u{d900}\u{dc00}-\u{d93f}\u{dffd}\u{d940}\u{dc00}-\u{d97f}\u{dffd}\u{d980}\u{dc00}-\u{d9bf}\u{dffd}\u{d9c0}\u{dc00}-\u{d9ff}\u{dffd}\u{da00}\u{dc00}-\u{da3f}\u{dffd}\u{da40}\u{dc00}-\u{da7f}\u{dffd}\u{da80}\u{dc00}-\u{dabf}\u{dffd}\u{dac0}\u{dc00}-\u{daff}\u{dffd}\u{db00}\u{dc00}-\u{db3f}\u{dffd}\u{db44}\u{dc00}-\u{db7f}\u{dffd}&&[^\u{00a0}[\u{2000}-\u{200a}]\u{2028}\u{2029}\u{202f}\u{3000}]]_\-]{0,61}[a-zA-Z0-9[\u{00a0}-\u{d7ff}\u{f900}-\u{fdcf}\u{fdf0}-\u{ffef}\u{d800}\u{dc00}-\u{d83f}\u{dffd}\u{d840}\u{dc00}-\u{d87f}\u{dffd}\u{d880}\u{dc00}-\u{d8bf}\u{dffd}\u{d8c0}\u{dc00}-\u{d8ff}\u{dffd}\u{d900}\u{dc00}-\u{d93f}\u{dffd}\u{d940}\u{dc00}-\u{d97f}\u{dffd}\u{d980}\u{dc00}-\u{d9bf}\u{dffd}\u{d9c0}\u{dc00}-\u{d9ff}\u{dffd}\u{da00}\u{dc00}-\u{da3f}\u{dffd}\u{da40}\u{dc00}-\u{da7f}\u{dffd}\u{da80}\u{dc00}-\u{dabf}\u{dffd}\u{dac0}\u{dc00}-\u{daff}\u{dffd}\u{db00}\u{dc00}-\u{db3f}\u{dffd}\u{db44}\u{dc00}-\u{db7f}\u{dffd}&&[^\u{00a0}[\u{2000}-\u{200a}]\u{2028}\u{2029}\u{202f}\u{3000}]]]){0,1}\.)+(xn\-\-[\w\-]{0,58}\w|[a-zA-Z[\u{00a0}-\u{d7ff}\u{f900}-\u{fdcf}\u{fdf0}-\u{ffef}\u{d800}\u{dc00}-\u{d83f}\u{dffd}\u{d840}\u{dc00}-\u{d87f}\u{dffd}\u{d880}\u{dc00}-\u{d8bf}\u{dffd}\u{d8c0}\u{dc00}-\u{d8ff}\u{dffd}\u{d900}\u{dc00}-\u{d93f}\u{dffd}\u{d940}\u{dc00}-\u{d97f}\u{dffd}\u{d980}\u{dc00}-\u{d9bf}\u{dffd}\u{d9c0}\u{dc00}-\u{d9ff}\u{dffd}\u{da00}\u{dc00}-\u{da3f}\u{dffd}\u{da40}\u{dc00}-\u{da7f}\u{dffd}\u{da80}\u{dc00}-\u{dabf}\u{dffd}\u{dac0}\u{dc00}-\u{daff}\u{dffd}\u{db00}\u{dc00}-\u{db3f}\u{dffd}\u{db44}\u{dc00}-\u{db7f}\u{dffd}&&[^\u{00a0}[\u{2000}-\u{200a}]\u{2028}\u{2029}\u{202f}\u{3000}]]]{2,63})|((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]))))(?:\:\d{1,5})?)([/\?](?:(?:[a-zA-Z0-9[\u{00a0}-\u{d7ff}\u{f900}-\u{fdcf}\u{fdf0}-\u{ffef}\u{d800}\u{dc00}-\u{d83f}\u{dffd}\u{d840}\u{dc00}-\u{d87f}\u{dffd}\u{d880}\u{dc00}-\u{d8bf}\u{dffd}\u{d8c0}\u{dc00}-\u{d8ff}\u{dffd}\u{d900}\u{dc00}-\u{d93f}\u{dffd}\u{d940}\u{dc00}-\u{d97f}\u{dffd}\u{d980}\u{dc00}-\u{d9bf}\u{dffd}\u{d9c0}\u{dc00}-\u{d9ff}\u{dffd}\u{da00}\u{dc00}-\u{da3f}\u{dffd}\u{da40}\u{dc00}-\u{da7f}\u{dffd}\u{da80}\u{dc00}-\u{dabf}\u{dffd}\u{dac0}\u{dc00}-\u{daff}\u{dffd}\u{db00}\u{dc00}-\u{db3f}\u{dffd}\u{db44}\u{dc00}-\u{db7f}\u{dffd}&&[^\u{00a0}[\u{2000}-\u{200a}]\u{2028}\u{2029}\u{202f}\u{3000}]];/\?:@&=#~\-\.\+!\*'\(\),_\$])|(?:%[a-fA-F0-9]{2}))*)?(?:\b|$|^))

Other patterns

Patterns.java contains more patterns, but posting them will hit the Stackoverflow post length limit. But I'll post the API descriptions of them here, so that you know about their existence and purpose. I've also added code below to output these patterns using Kotlin.

Pattern called "WEB_URL_WITHOUT_PROTOCOL"

Description:

Regular expression to match strings that do not start with a supported protocol. The TLDs are expected to be one of the known TLDs.

Definition:

"("
+ WORD_BOUNDARY
+ "(?<!:\\/\\/)"
+ "("
+ "(?:" + STRICT_DOMAIN_NAME + ")"
+ "(?:" + PORT_NUMBER + ")?"
+ ")"
+ "(?:" + PATH_AND_QUERY + ")?"
+ WORD_BOUNDARY
+ ")";

Pattern called "WEB_URL_WITH_PROTOCOL"

Description:

Regular expression to match strings that start with a supported protocol. Rules for domain names and TLDs are more relaxed. TLDs are optional.

Definition:

"("
+ WORD_BOUNDARY
+ "(?:"
+ "(?:" + PROTOCOL + "(?:" + USER_INFO + ")?" + ")"
+ "(?:" + RELAXED_DOMAIN_NAME + ")?"
+ "(?:" + PORT_NUMBER + ")?"
+ ")"
+ "(?:" + PATH_AND_QUERY + ")?"
+ WORD_BOUNDARY
+ ")";

Pattern called "AUTOLINK_WEB_URL"

Description:

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.

Definition:

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

Code to output the patterns from AOSP Patterns.java

This code is written in language Kotlin (a Java JVM based language). If converts the regex patterns from AOSP Patterns.java to a readable format:

import java.util.regex.Pattern

fun createPattern(pattern: Pattern, unicodeStringFormat: String): String =
    pattern.toString().flatMap {
        val charCode = it.code
        if (charCode > 126) {
            unicodeStringFormat.format(charCode).toList()
        } else {
            listOf(it)
        }
    }.joinToString("")

fun main() {
    val unicodeStringFormatJava = "\\u%04x"
    val unicodeStringFormatPHP = "\\u{%04x}"

    // Pattern: WEB_URL
    println(createPattern(Patterns.WEB_URL, unicodeStringFormatJava))
    println(createPattern(Patterns.WEB_URL, unicodeStringFormatPHP))

    // Pattern: AUTOLINK_WEB_URL
    println(createPattern(Patterns.AUTOLINK_WEB_URL, unicodeStringFormatJava))
    println(createPattern(Patterns.AUTOLINK_WEB_URL, unicodeStringFormatPHP))

    // Pattern: WEB_URL_WITH_PROTOCOL (variable modified to public visibility)
    println(createPattern(Patterns.WEB_URL_WITH_PROTOCOL.toPattern(), unicodeStringFormatJava))
    println(createPattern(Patterns.WEB_URL_WITH_PROTOCOL.toPattern(), unicodeStringFormatPHP))

    // Pattern: WEB_URL_WITHOUT_PROTOCOL (variable modified to public visibility)
    println(createPattern(Patterns.WEB_URL_WITHOUT_PROTOCOL.toPattern(), unicodeStringFormatJava))
    println(createPattern(Patterns.WEB_URL_WITHOUT_PROTOCOL.toPattern(), unicodeStringFormatPHP))
}

Answer 62

(http(s|)\:\/\/|)((([a-zA-Z0-9-_]{1,}\.){1,})([a-zA-Z]{1}[a-zA-Z0-9-]{1,}))(:[0-9]{1,}|)(\/[a-zA-Z0-9_~#?\+\&\.\/-=%-]{1,}|)

Answer 63

/^(http|HTTP)+(s|S)?:\/\/[\w.-]+(?:\.[\w\.-]+)+[\w\-\._\$\(\)/]+$/g

check demo with tests:

https://regexr.com/5cedu

Answer 64

The best regex is a combination of the best answers here! hahaha! I have just tested them all, and put the best together! I changed it a little to only have one capture group! I was able to find 637 URLs in the source code of this page! Only a few false positives!

((?:(?:https?|ftp)://)(?:\S+(?::\S*)?@|\d{1,3}(?:\.\d{1,3}){3}|(?:(?:[a-z\d\x{00a1}-\x{ffff}]+-?)*[a-z\d\x{00a1}-\x{ffff}]+)(?:\.(?:[a-z\d\x{00a1}-\x{ffff}]+-?)*[a-z\d\x{00a1}-\x{ffff}]+)*(?:\.[a-z\x{00a1}-\x{ffff}]{2,6}))(?::\d+)?(?:[^\s]*)|(?:(?:(?:[A-Za-z]{3,9}:(?:\/\/)?)(?:[-;:&=\+\$,\w]+@)?[A-Za-z0-9.-]+(?::[0-9]+)?|(?:www.|[-;:&=\+\$,\w]+@)[A-Za-z0-9.-]+)(?:(?:\/[\+~%\/.\w-_]*)?\??(?:[-\+=&;%@.\w_]*)#?(?:[\w]*))?)|(?:(?:(?:(?:[A-Za-z]{3,9}:(?:\/\/)?)(?:[-;:&=\+\$,\w]+@)?[A-Za-z0-9.-]+|(?:www.|[-;:&=\+\$,\w]+@)[A-Za-z0-9.-]+)(?:(?:\/[\+~%\/.\w-_]*)?\??(?:[-\+=&;%@.\w_]*)#?(?:[\w]*))?))|(?:(?:(?:[\\w]+:)?//)?(?:(?:[\\d\\w]|%[a-fA-f\\d]{2,2})+(?::(?:[\\d\\w]|%[a-fA-f\\d]{2,2})+)?@)?(?:[\\d\\w][-\\d\\w]{0,253}[\\d\\w]\\.)+[\\w]{2,4}(?::[\\d]+)?(?:/(?:[-+_~.\\d\\w]|%[a-fA-f\\d]{2,2})*)*(?:\\?(?:&?(?:[-+_~.\\d\\w]|%[a-fA-f\\d]{2,2})=?)*)?(?:#(?:[-+_~.\\d\\w]|%[a-fA-f\\d]{2,2})*)?)|(?:https?:\/\/(?:[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?\.)+[a-z0-9][a-z0-9-]{0,61}[a-z0-9])(?::?\d*)\/?(?:[a-z_\/0-9\-#.]*)\??(?:[a-z_\/0-9\-#=&]*)|(?:(?:(?:https?:)?(?:\/?\/))(?:(?:[\d\w]|%[a-fA-f\d]{2,2})+(?::(?:[\d\w]|%[a-fA-f\d]{2,2})+)?@)?(?:[\d\w][-\d\w]{0,253}[\d\w]\.)+[\w]{2,63}(?::[\d]+)?(?:/(?:[-+_~.\d\w]|%[a-fA-f\d]{2,2})*)*(?:\?(?:&?(?:[-+_~.\d\w]|%[a-fA-f\d]{2,2})=?)*)?(?:#(?:[-+_~.\d\w]|%[a-fA-f\d]{2,2})*)?)|(?:(?:https?|ftp)://(?:www\d?|[a-zA-Z0-9]+)?\.[a-zA-Z0-9-]+(?:\:|\.)(?:[a-zA-Z0-9.]+|(?:\d+)?)(?:[/?:].*)?)|(?:\b(?:(?:https?|ftp):\/\/)(?:\S+(?::\S*)?@)?(?:(?!10(?:\.\d{1,3}){3})(?!127(?:\.\d{1,3}){3})(?!169\.254(?:\.\d{1,3}){2})(?!192\.168(?:\.\d{1,3}){2})(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))|(?:(?:[a-z\x{00a1}-\x{ffff}0-9]+-?)*[a-z\x{00a1}-\x{ffff}0-9]+)(?:\.(?:[a-z\x{00a1}-\x{ffff}0-9]+-?)*[a-z\x{00a1}-\x{ffff}0-9]+)*(?:\.(?:[a-z\x{00a1}-\x{ffff}]{2,})))(?::\d{2,5})?(?:\/[^\s]*)?\b))