Regular Expressions 101

Community Patterns

RFC 3987 compliant URL regex

8

Regular Expression
ECMAScript (JavaScript)

/
^[a-z](?:[-a-z0-9\+\.])*:(?:\/\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~!\$&'\(\)\*\+,;=:\xA0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF]|[\uD800-\uD83E\uD840-\uD87E\uD880-\uD8BE\uD8C0-\uD8FE\uD900-\uD93E\uD940-\uD97E\uD980-\uD9BE\uD9C0-\uD9FE\uDA00-\uDA3E\uDA40-\uDA7E\uDA80-\uDABE\uDAC0-\uDAFE\uDB00-\uDB3E\uDB44-\uDB7E][\uDC00-\uDFFF]|[\uD83F\uD87F\uD8BF\uD8FF\uD93F\uD97F\uD9BF\uD9FF\uDA3F\uDA7F\uDABF\uDAFF\uDB3F\uDB7F][\uDC00-\uDFFD])*@)?(?:\[(?:(?:(?:[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}:[0-9a-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\._~!\$&'\(\)\*\+,;=@\xA0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF]|[\uD800-\uD83E\uD840-\uD87E\uD880-\uD8BE\uD8C0-\uD8FE\uD900-\uD93E\uD940-\uD97E\uD980-\uD9BE\uD9C0-\uD9FE\uDA00-\uDA3E\uDA40-\uDA7E\uDA80-\uDABE\uDAC0-\uDAFE\uDB00-\uDB3E\uDB44-\uDB7E][\uDC00-\uDFFF]|[\uD83F\uD87F\uD8BF\uD8FF\uD93F\uD97F\uD9BF\uD9FF\uDA3F\uDA7F\uDABF\uDAFF\uDB3F\uDB7F][\uDC00-\uDFFD])*)(?::[0-9]*)?(?:\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~!\$&'\(\)\*\+,;=:@\xA0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF]|[\uD800-\uD83E\uD840-\uD87E\uD880-\uD8BE\uD8C0-\uD8FE\uD900-\uD93E\uD940-\uD97E\uD980-\uD9BE\uD9C0-\uD9FE\uDA00-\uDA3E\uDA40-\uDA7E\uDA80-\uDABE\uDAC0-\uDAFE\uDB00-\uDB3E\uDB44-\uDB7E][\uDC00-\uDFFF]|[\uD83F\uD87F\uD8BF\uD8FF\uD93F\uD97F\uD9BF\uD9FF\uDA3F\uDA7F\uDABF\uDAFF\uDB3F\uDB7F][\uDC00-\uDFFD]))*)*|\/(?:(?:(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~!\$&'\(\)\*\+,;=:@\xA0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF]|[\uD800-\uD83E\uD840-\uD87E\uD880-\uD8BE\uD8C0-\uD8FE\uD900-\uD93E\uD940-\uD97E\uD980-\uD9BE\uD9C0-\uD9FE\uDA00-\uDA3E\uDA40-\uDA7E\uDA80-\uDABE\uDAC0-\uDAFE\uDB00-\uDB3E\uDB44-\uDB7E][\uDC00-\uDFFF]|[\uD83F\uD87F\uD8BF\uD8FF\uD93F\uD97F\uD9BF\uD9FF\uDA3F\uDA7F\uDABF\uDAFF\uDB3F\uDB7F][\uDC00-\uDFFD]))+)(?:\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~!\$&'\(\)\*\+,;=:@\xA0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF]|[\uD800-\uD83E\uD840-\uD87E\uD880-\uD8BE\uD8C0-\uD8FE\uD900-\uD93E\uD940-\uD97E\uD980-\uD9BE\uD9C0-\uD9FE\uDA00-\uDA3E\uDA40-\uDA7E\uDA80-\uDABE\uDAC0-\uDAFE\uDB00-\uDB3E\uDB44-\uDB7E][\uDC00-\uDFFF]|[\uD83F\uD87F\uD8BF\uD8FF\uD93F\uD97F\uD9BF\uD9FF\uDA3F\uDA7F\uDABF\uDAFF\uDB3F\uDB7F][\uDC00-\uDFFD]))*)*)?|(?:(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~!\$&'\(\)\*\+,;=:@\xA0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF]|[\uD800-\uD83E\uD840-\uD87E\uD880-\uD8BE\uD8C0-\uD8FE\uD900-\uD93E\uD940-\uD97E\uD980-\uD9BE\uD9C0-\uD9FE\uDA00-\uDA3E\uDA40-\uDA7E\uDA80-\uDABE\uDAC0-\uDAFE\uDB00-\uDB3E\uDB44-\uDB7E][\uDC00-\uDFFF]|[\uD83F\uD87F\uD8BF\uD8FF\uD93F\uD97F\uD9BF\uD9FF\uDA3F\uDA7F\uDABF\uDAFF\uDB3F\uDB7F][\uDC00-\uDFFD]))+)(?:\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~!\$&'\(\)\*\+,;=:@\xA0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF]|[\uD800-\uD83E\uD840-\uD87E\uD880-\uD8BE\uD8C0-\uD8FE\uD900-\uD93E\uD940-\uD97E\uD980-\uD9BE\uD9C0-\uD9FE\uDA00-\uDA3E\uDA40-\uDA7E\uDA80-\uDABE\uDAC0-\uDAFE\uDB00-\uDB3E\uDB44-\uDB7E][\uDC00-\uDFFF]|[\uD83F\uD87F\uD8BF\uD8FF\uD93F\uD97F\uD9BF\uD9FF\uDA3F\uDA7F\uDABF\uDAFF\uDB3F\uDB7F][\uDC00-\uDFFD]))*)*|(?!(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~!\$&'\(\)\*\+,;=:@\xA0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF]|[\uD800-\uD83E\uD840-\uD87E\uD880-\uD8BE\uD8C0-\uD8FE\uD900-\uD93E\uD940-\uD97E\uD980-\uD9BE\uD9C0-\uD9FE\uDA00-\uDA3E\uDA40-\uDA7E\uDA80-\uDABE\uDAC0-\uDAFE\uDB00-\uDB3E\uDB44-\uDB7E][\uDC00-\uDFFF]|[\uD83F\uD87F\uD8BF\uD8FF\uD93F\uD97F\uD9BF\uD9FF\uDA3F\uDA7F\uDABF\uDAFF\uDB3F\uDB7F][\uDC00-\uDFFD])))(?:\?(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~!\$&'\(\)\*\+,;=:@\/\?\xA0-\uD7FF\uE000-\uFDCF\uFDF0-\uFFEF]|[\uD800-\uD83E\uD840-\uD87E\uD880-\uD8BE\uD8C0-\uD8FE\uD900-\uD93E\uD940-\uD97E\uD980-\uD9BE\uD9C0-\uD9FE\uDA00-\uDA3E\uDA40-\uDA7E\uDA80-\uDABE\uDAC0-\uDAFE\uDB00-\uDB3E\uDB44-\uDB7E\uDB80-\uDBBE\uDBC0-\uDBFE][\uDC00-\uDFFF]|[\uD83F\uD87F\uD8BF\uD8FF\uD93F\uD97F\uD9BF\uD9FF\uDA3F\uDA7F\uDABF\uDAFF\uDB3F\uDB7F\uDBBF\uDBFF][\uDC00-\uDFFD])*)?(?:\#(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~!\$&'\(\)\*\+,;=:@\/\?\xA0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF]|[\uD800-\uD83E\uD840-\uD87E\uD880-\uD8BE\uD8C0-\uD8FE\uD900-\uD93E\uD940-\uD97E\uD980-\uD9BE\uD9C0-\uD9FE\uDA00-\uDA3E\uDA40-\uDA7E\uDA80-\uDABE\uDAC0-\uDAFE\uDB00-\uDB3E\uDB44-\uDB7E][\uDC00-\uDFFF]|[\uD83F\uD87F\uD8BF\uD8FF\uD93F\uD97F\uD9BF\uD9FF\uDA3F\uDA7F\uDABF\uDAFF\uDB3F\uDB7F][\uDC00-\uDFFD])*)?$
/
i

Description

This is a JavaScript port of the URL regex from http://stackoverflow.com/a/190405/384062 that includes a bug fix and some optimization.

Mathias Bynens's Regenerate was used to convert unicode escapes.

Bug fix: Eliminated stray | falsely allowing querystring to contain |

Optimization: Merged alternated character classes in querystring and fragment identifier portions for better performance.

Submitted by Hans Meyer - 9 years ago