Skip to content

Instantly share code, notes, and snippets.

@winzig

winzig/Liberal Regex Pattern for URLs

Forked from gruber/Liberal Regex Pattern for Web URLs
Last active July 30, 2024 22:09
Show Gist options
  • Save winzig/8894715 to your computer and use it in GitHub Desktop.
Save winzig/8894715 to your computer and use it in GitHub Desktop.
Download ZIP

Revisions

  1. winzig revised this gist Jul 31, 2018. No changes.
  2. winzig revised this gist Jul 31, 2018. 1 changed file with 20 additions and 19 deletions.
    39 changes: 20 additions & 19 deletions Liberal Regex Pattern for URLs
    View file
    Original file line number Diff line number Diff line change
    @@ -1,23 +1,21 @@
    # Single-line version:
    (?i)\b((?:https?:(?:\/{1,3}|[a-z0-9%])|[a-z0-9.\-]+\.(?:[a-z0-9]{2,13})\/)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:[.\-][a-z0-9]+)*[.](?:[a-z0-9]{2,13})\b\/?(?!@)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’])))

    (?i)\b(https?:\/{1,3})?((?:(?:[\w.\-]+\.(?:[a-z]{2,13})|(?<=http:\/\/|https:\/\/)[\w.\-]+)\/)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’])|(?:(?<!@)(?:\w+(?:[.\-]+\w+)*\.(?:[a-z]{2,13})|(?:(?:[0-9](?!\d)|[1-9][0-9](?!\d)|1[0-9]{2}(?!\d)|2[0-4][0-9](?!\d)|25[0-5](?!\d))[.]?){4})\b\/?(?!@)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))*(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’])?))

    # Commented multi-line version:

    (?xi)
    \b
    ( # Capture 1: entire matched URL
    (?:
    https?: # URL protocol and colon
    (https?:\/{1,3})? # Capture $1: (optional) URL scheme, colon, and slashes
    ( # Capture $2: Entire matched URL (other than optional protocol://)
    (?:
    (?:
    \/{1,3} # 1-3 slashes
    | # or
    [a-z0-9%] # Single letter or digit or '%'
    # (Trying not to match e.g. "URI::Escape")
    [\w.\-]+\. # looks like domain name
    (?:[a-z]{2,13}) # ending in common popular gTLDs
    | #
    (?<=http:\/\/|https:\/\/)[\w.\-]+ # hostname preceded by http:// or https://
    )
    | # or
    [a-z0-9.\-]+\. # looks like domain name
    (?:[a-z0-9]{2,13}) # ending in common popular gTLDs (or final octet of IPv4 IP)
    \/ # followed by a slash
    \/ # followed by a slash
    )
    (?: # One or more:
    [^\s()<>{}\[\]]+ # Run of non-space, non-()<>{}[]
    @@ -36,11 +34,14 @@
    | # OR, the following to match naked domains:
    (?:
    (?<!@) # not preceded by a @, avoid matching foo@_gmail.com_(?<![@.])
    [a-z0-9]+
    (?:[.\-][a-z0-9]+)*
    \. # avoid matching the last two parts of an email domain
    # like co.uk in [email protected]
    (?:[a-z0-9]{2,13}) # ending in common popular gTLDs (or final octet of IPv4 IP)
    (?:
    \w+
    (?:[.\-]+\w+)*
    \. # avoid matching the last two parts of an email domain like co.uk in [email protected]
    (?:[a-z]{2,13}) # ending in common popular gTLDs
    | # or
    (?:(?:[0-9](?!\d)|[1-9][0-9](?!\d)|1[0-9]{2}(?!\d)|2[0-4][0-9](?!\d)|25[0-5](?!\d))[.]?){4} # IPv4 address, as seen in https://stackoverflow.com/a/13166657/650558
    )
    \b
    \/?
    (?!@) # not succeeded by a @, avoid matching "foo.na" in "[email protected]"
    @@ -50,13 +51,13 @@
    \([^\s()]*?\([^\s()]+\)[^\s()]*?\) # balanced parens, one level deep: (…(…)…)
    |
    \([^\s]+?\) # balanced parens, non-recursive: (…)
    )+
    )*
    (?: # End with:
    \([^\s()]*?\([^\s()]+\)[^\s()]*?\) # balanced parens, one level deep: (…(…)…)
    |
    \([^\s]+?\) # balanced parens, non-recursive: (…)
    | # or
    [^\s`!()\[\]{};:'\".,<>?«»“”‘’] # not a space or one of these punct chars
    )
    )?
    )
    )
  3. winzig revised this gist May 16, 2018. 1 changed file with 3 additions and 3 deletions.
    6 changes: 3 additions & 3 deletions Liberal Regex Pattern for URLs
    View file
    Original file line number Diff line number Diff line change
    @@ -1,5 +1,5 @@
    # Single-line version:
    (?i)\b((?:https?:(?:\/{1,3}|[a-z0-9%])|[a-z0-9.\-]+\.(?:[a-z]{2,13})\/)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:[.\-][a-z0-9]+)*[.](?:[a-z]{2,13})\b\/?(?!@)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’])))
    (?i)\b((?:https?:(?:\/{1,3}|[a-z0-9%])|[a-z0-9.\-]+\.(?:[a-z0-9]{2,13})\/)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:[.\-][a-z0-9]+)*[.](?:[a-z0-9]{2,13})\b\/?(?!@)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’])))

    # Commented multi-line version:

    @@ -16,7 +16,7 @@
    )
    | # or
    [a-z0-9.\-]+\. # looks like domain name
    (?:[a-z]{2,13}) # ending in common popular gTLDs
    (?:[a-z0-9]{2,13}) # ending in common popular gTLDs (or final octet of IPv4 IP)
    \/ # followed by a slash
    )
    (?: # One or more:
    @@ -40,7 +40,7 @@
    (?:[.\-][a-z0-9]+)*
    \. # avoid matching the last two parts of an email domain
    # like co.uk in [email protected]
    (?:[a-z]{2,13})
    (?:[a-z0-9]{2,13}) # ending in common popular gTLDs (or final octet of IPv4 IP)
    \b
    \/?
    (?!@) # not succeeded by a @, avoid matching "foo.na" in "[email protected]"
  4. winzig revised this gist May 16, 2018. 1 changed file with 4 additions and 4 deletions.
    8 changes: 4 additions & 4 deletions Liberal Regex Pattern for URLs
    View file
    Original file line number Diff line number Diff line change
    @@ -1,5 +1,5 @@
    # Single-line version:
    (?i)\b((?:https?:(?:\/{1,3}|[a-z0-9%])|[a-z0-9.\-]+\.\/)(?:[a-z]{2,13})(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:[.\-][a-z0-9]+)*[.](?:[a-z]{2,13})\b\/?(?!@)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’])))
    (?i)\b((?:https?:(?:\/{1,3}|[a-z0-9%])|[a-z0-9.\-]+\.(?:[a-z]{2,13})\/)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:[.\-][a-z0-9]+)*[.](?:[a-z]{2,13})\b\/?(?!@)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’])))

    # Commented multi-line version:

    @@ -15,10 +15,10 @@
    # (Trying not to match e.g. "URI::Escape")
    )
    | # or
    [a-z0-9.\-]+\. # looks like domain name followed by a slash:
    \/
    [a-z0-9.\-]+\. # looks like domain name
    (?:[a-z]{2,13}) # ending in common popular gTLDs
    \/ # followed by a slash
    )
    (?:[a-z]{2,13}) # Covers common popular gTLDs
    (?: # One or more:
    [^\s()<>{}\[\]]+ # Run of non-space, non-()<>{}[]
    | # or
  5. winzig revised this gist May 16, 2018. 1 changed file with 3 additions and 3 deletions.
    6 changes: 3 additions & 3 deletions Liberal Regex Pattern for URLs
    View file
    Original file line number Diff line number Diff line change
    @@ -1,5 +1,5 @@
    # Single-line version:
    (?i)\b((?:https?:(?:\/{1,3}|[a-z0-9%])|[a-z0-9.\-]+\.\/)(?:[a-z]{2,13})(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:[.\-][a-z0-9]+)*[.](?:[a-z]{2,13})\b\/?(?!@)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'".,<>?«»“”‘’])))
    (?i)\b((?:https?:(?:\/{1,3}|[a-z0-9%])|[a-z0-9.\-]+\.\/)(?:[a-z]{2,13})(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:[.\-][a-z0-9]+)*[.](?:[a-z]{2,13})\b\/?(?!@)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’])))

    # Commented multi-line version:

    @@ -31,7 +31,7 @@
    |
    \([^\s]+?\) # balanced parens, non-recursive: (…)
    | # or
    [^\s`!()\[\]{};:'".,<>?«»“”‘’] # not a space or one of these punct chars
    [^\s`!()\[\]{};:'\".,<>?«»“”‘’] # not a space or one of these punct chars
    )
    | # OR, the following to match naked domains:
    (?:
    @@ -56,7 +56,7 @@
    |
    \([^\s]+?\) # balanced parens, non-recursive: (…)
    | # or
    [^\s`!()\[\]{};:'".,<>?«»“”‘’] # not a space or one of these punct chars
    [^\s`!()\[\]{};:'\".,<>?«»“”‘’] # not a space or one of these punct chars
    )
    )
    )
  6. winzig revised this gist May 16, 2018. 1 changed file with 1 addition and 1 deletion.
    2 changes: 1 addition & 1 deletion Liberal Regex Pattern for URLs
    View file
    Original file line number Diff line number Diff line change
    @@ -35,7 +35,7 @@
    )
    | # OR, the following to match naked domains:
    (?:
    (?<!@) # not preceded by a @, avoid matching foo@_gmail.com_(?<![@.])
    (?<!@) # not preceded by a @, avoid matching foo@_gmail.com_(?<![@.])
    [a-z0-9]+
    (?:[.\-][a-z0-9]+)*
    \. # avoid matching the last two parts of an email domain
  7. winzig revised this gist May 16, 2018. No changes.
  8. winzig revised this gist May 16, 2018. 1 changed file with 41 additions and 27 deletions.
    68 changes: 41 additions & 27 deletions Liberal Regex Pattern for URLs
    View file
    Original file line number Diff line number Diff line change
    @@ -1,48 +1,62 @@
    # Single-line version:
    (?i)\b((?:https?:(?:/{1,3}|[a-z0-9%])|[a-z0-9.\-]+[.]/)(?:[a-z]{2,13})(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:[.\-][a-z0-9]+)*[.](?:[a-z]{2,13})\b/?(?!@)))
    (?i)\b((?:https?:(?:\/{1,3}|[a-z0-9%])|[a-z0-9.\-]+\.\/)(?:[a-z]{2,13})(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:[.\-][a-z0-9]+)*[.](?:[a-z]{2,13})\b\/?(?!@)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'".,<>?«»“”‘’])))

    # Commented multi-line version:

    (?xi)
    \b
    ( # Capture 1: entire matched URL
    ( # Capture 1: entire matched URL
    (?:
    https?: # URL protocol and colon
    https?: # URL protocol and colon
    (?:
    /{1,3} # 1-3 slashes
    | # or
    [a-z0-9%] # Single letter or digit or '%'
    # (Trying not to match e.g. "URI::Escape")
    \/{1,3} # 1-3 slashes
    | # or
    [a-z0-9%] # Single letter or digit or '%'
    # (Trying not to match e.g. "URI::Escape")
    )
    | # or
    [a-z0-9.\-]+[.] # looks like domain name followed by a slash:
    /
    | # or
    [a-z0-9.\-]+\. # looks like domain name followed by a slash:
    \/
    )
    (?:[a-z]{2,13}) # Covers common popular gTLDs
    (?: # One or more:
    [^\s()<>{}\[\]]+ # Run of non-space, non-()<>{}[]
    | # or
    \([^\s()]*?\([^\s()]+\)[^\s()]*?\) # balanced parens, one level deep: (…(…)…)
    (?:[a-z]{2,13}) # Covers common popular gTLDs
    (?: # One or more:
    [^\s()<>{}\[\]]+ # Run of non-space, non-()<>{}[]
    | # or
    \([^\s()]*?\([^\s()]+\)[^\s()]*?\) # balanced parens, one level deep: (…(…)…)
    |
    \([^\s]+?\) # balanced parens, non-recursive: (…)
    \([^\s]+?\) # balanced parens, non-recursive: (…)
    )+
    (?: # End with:
    \([^\s()]*?\([^\s()]+\)[^\s()]*?\) # balanced parens, one level deep: (…(…)…)
    (?: # End with:
    \([^\s()]*?\([^\s()]+\)[^\s()]*?\) # balanced parens, one level deep: (…(…)…)
    |
    \([^\s]+?\) # balanced parens, non-recursive: (…)
    | # or
    [^\s`!()\[\]{};:'".,<>?«»“”‘’] # not a space or one of these punct chars
    \([^\s]+?\) # balanced parens, non-recursive: (…)
    | # or
    [^\s`!()\[\]{};:'".,<>?«»“”‘’] # not a space or one of these punct chars
    )
    | # OR, the following to match naked domains:
    | # OR, the following to match naked domains:
    (?:
    (?<!@) # not preceded by a @, avoid matching foo@_gmail.com_(?<![@.])
    (?<!@) # not preceded by a @, avoid matching foo@_gmail.com_(?<![@.])
    [a-z0-9]+
    (?:[.\-][a-z0-9]+)*
    [.] # avoid matching the last two parts of an email domain
    # like co.uk in [email protected]
    \. # avoid matching the last two parts of an email domain
    # like co.uk in [email protected]
    (?:[a-z]{2,13})
    \b
    /?
    (?!@) # not succeeded by a @, avoid matching "foo.na" in "[email protected]"
    \/?
    (?!@) # not succeeded by a @, avoid matching "foo.na" in "[email protected]"
    (?: # One or more:
    [^\s()<>{}\[\]]+ # Run of non-space, non-()<>{}[]
    | # or
    \([^\s()]*?\([^\s()]+\)[^\s()]*?\) # balanced parens, one level deep: (…(…)…)
    |
    \([^\s]+?\) # balanced parens, non-recursive: (…)
    )+
    (?: # End with:
    \([^\s()]*?\([^\s()]+\)[^\s()]*?\) # balanced parens, one level deep: (…(…)…)
    |
    \([^\s]+?\) # balanced parens, non-recursive: (…)
    | # or
    [^\s`!()\[\]{};:'".,<>?«»“”‘’] # not a space or one of these punct chars
    )
    )
    )
  9. winzig revised this gist May 3, 2018. 1 changed file with 2 additions and 2 deletions.
    4 changes: 2 additions & 2 deletions Liberal Regex Pattern for URLs
    View file
    Original file line number Diff line number Diff line change
    @@ -37,8 +37,8 @@
    (?:
    (?<!@) # not preceded by a @, avoid matching foo@_gmail.com_(?<![@.])
    [a-z0-9]+
    (?:\b[.\-][a-z0-9]+)*
    (?<![@.]) # avoid matching the last two parts of an email domain
    (?:[.\-][a-z0-9]+)*
    [.] # avoid matching the last two parts of an email domain
    # like co.uk in [email protected]
    (?:[a-z]{2,13})
    \b
  10. winzig revised this gist May 3, 2018. 1 changed file with 1 addition and 1 deletion.
    2 changes: 1 addition & 1 deletion Liberal Regex Pattern for URLs
    View file
    Original file line number Diff line number Diff line change
    @@ -1,5 +1,5 @@
    # Single-line version:
    (?i)\b((?:https?:(?:/{1,3}|[a-z0-9%])|[a-z0-9.\-]+[.]/)(?:[a-z]{2,13})(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:\b[.\-][a-z0-9]+)*(?<![@.])(?:[a-z]{2,13})\b/?(?!@)))
    (?i)\b((?:https?:(?:/{1,3}|[a-z0-9%])|[a-z0-9.\-]+[.]/)(?:[a-z]{2,13})(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:[.\-][a-z0-9]+)*[.](?:[a-z]{2,13})\b/?(?!@)))

    # Commented multi-line version:

  11. winzig revised this gist May 3, 2018. 1 changed file with 1 addition and 1 deletion.
    2 changes: 1 addition & 1 deletion Liberal Regex Pattern for URLs
    View file
    Original file line number Diff line number Diff line change
    @@ -1,5 +1,5 @@
    # Single-line version:
    (?i)\b((?:https?:(?:/{1,3}|[a-z0-9%])|[a-z0-9.\-]+[.]/)(?:[a-z]{2,13})(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:[.\-][a-z0-9]+)*[.](?:[a-z]{2,13})\b/?(?!@)))
    (?i)\b((?:https?:(?:/{1,3}|[a-z0-9%])|[a-z0-9.\-]+[.]/)(?:[a-z]{2,13})(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:\b[.\-][a-z0-9]+)*(?<![@.])(?:[a-z]{2,13})\b/?(?!@)))

    # Commented multi-line version:

  12. winzig revised this gist May 3, 2018. 1 changed file with 22 additions and 22 deletions.
    44 changes: 22 additions & 22 deletions Liberal Regex Pattern for URLs
    View file
    Original file line number Diff line number Diff line change
    @@ -5,41 +5,41 @@

    (?xi)
    \b
    ( # Capture 1: entire matched URL
    ( # Capture 1: entire matched URL
    (?:
    https?: # URL protocol and colon
    https?: # URL protocol and colon
    (?:
    /{1,3} # 1-3 slashes
    | # or
    [a-z0-9%] # Single letter or digit or '%'
    # (Trying not to match e.g. "URI::Escape")
    /{1,3} # 1-3 slashes
    | # or
    [a-z0-9%] # Single letter or digit or '%'
    # (Trying not to match e.g. "URI::Escape")
    )
    | # or
    # looks like domain name followed by a slash:
    [a-z0-9.\-]+[.]
    | # or
    [a-z0-9.\-]+[.] # looks like domain name followed by a slash:
    /
    )
    (?:[a-z]{2,13})
    (?: # One or more:
    [^\s()<>{}\[\]]+ # Run of non-space, non-()<>{}[]
    | # or
    (?:[a-z]{2,13}) # Covers common popular gTLDs
    (?: # One or more:
    [^\s()<>{}\[\]]+ # Run of non-space, non-()<>{}[]
    | # or
    \([^\s()]*?\([^\s()]+\)[^\s()]*?\) # balanced parens, one level deep: (…(…)…)
    |
    \([^\s]+?\) # balanced parens, non-recursive: (…)
    \([^\s]+?\) # balanced parens, non-recursive: (…)
    )+
    (?: # End with:
    (?: # End with:
    \([^\s()]*?\([^\s()]+\)[^\s()]*?\) # balanced parens, one level deep: (…(…)…)
    |
    \([^\s]+?\) # balanced parens, non-recursive: (…)
    | # or
    [^\s`!()\[\]{};:'".,<>?«»“”‘’] # not a space or one of these punct chars
    \([^\s]+?\) # balanced parens, non-recursive: (…)
    | # or
    [^\s`!()\[\]{};:'".,<>?«»“”‘’] # not a space or one of these punct chars
    )
    | # OR, the following to match naked domains:
    | # OR, the following to match naked domains:
    (?:
    (?<!@) # not preceded by a @, avoid matching foo@_gmail.com_
    (?<!@) # not preceded by a @, avoid matching foo@_gmail.com_(?<![@.])
    [a-z0-9]+
    (?:\b[.\-][a-z0-9]+)*
    [.]
    (?:\b[.\-][a-z0-9]+)*
    (?<![@.]) # avoid matching the last two parts of an email domain
    # like co.uk in [email protected]
    (?:[a-z]{2,13})
    \b
    /?
  13. winzig revised this gist May 3, 2018. 1 changed file with 1 addition and 1 deletion.
    2 changes: 1 addition & 1 deletion Liberal Regex Pattern for URLs
    View file
    Original file line number Diff line number Diff line change
    @@ -38,7 +38,7 @@
    (?:
    (?<!@) # not preceded by a @, avoid matching foo@_gmail.com_
    [a-z0-9]+
    (?:[.\-][a-z0-9]+)*
    (?:\b[.\-][a-z0-9]+)*
    [.]
    (?:[a-z]{2,13})
    \b
  14. winzig revised this gist May 3, 2018. 1 changed file with 2 additions and 2 deletions.
    4 changes: 2 additions & 2 deletions Liberal Regex Pattern for URLs
    View file
    Original file line number Diff line number Diff line change
    @@ -17,9 +17,9 @@
    | # or
    # looks like domain name followed by a slash:
    [a-z0-9.\-]+[.]
    (?:[a-z]{2,13})
    /
    /
    )
    (?:[a-z]{2,13})
    (?: # One or more:
    [^\s()<>{}\[\]]+ # Run of non-space, non-()<>{}[]
    | # or
  15. winzig revised this gist May 3, 2018. 1 changed file with 1 addition and 2 deletions.
    3 changes: 1 addition & 2 deletions Liberal Regex Pattern for URLs
    View file
    Original file line number Diff line number Diff line change
    @@ -1,6 +1,5 @@
    # Single-line version:
    (?i)\b((?:https?:(?:/{1,3}|[a-z0-9%])|[a-z0-9.\-]+[.](?:[a-z]{2,13})(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:[.\-][a-z0-9]+)*[.](?:[a-z]{2,13})\b/?(?!@)))

    (?i)\b((?:https?:(?:/{1,3}|[a-z0-9%])|[a-z0-9.\-]+[.]/)(?:[a-z]{2,13})(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:[.\-][a-z0-9]+)*[.](?:[a-z]{2,13})\b/?(?!@)))

    # Commented multi-line version:

  16. winzig revised this gist Feb 9, 2014. 1 changed file with 3 additions and 3 deletions.
    6 changes: 3 additions & 3 deletions Liberal Regex Pattern for URLs
    View file
    Original file line number Diff line number Diff line change
    @@ -1,5 +1,5 @@
    # Single-line version:
    (?i)\b((?:https?:(?:/{1,3}|[a-z0-9%])|[a-z0-9.\-]+[.](?:com|net|org|edu|gov|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|yu|za|zm|zw)/)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:[.\-][a-z0-9]+)*[.](?:com|net|org|edu|gov|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|yu|za|zm|zw)\b/?(?!@)))
    (?i)\b((?:https?:(?:/{1,3}|[a-z0-9%])|[a-z0-9.\-]+[.](?:[a-z]{2,13})(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:[.\-][a-z0-9]+)*[.](?:[a-z]{2,13})\b/?(?!@)))


    # Commented multi-line version:
    @@ -18,7 +18,7 @@
    | # or
    # looks like domain name followed by a slash:
    [a-z0-9.\-]+[.]
    (?:com|net|org|edu|gov|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj| Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|yu|za|zm|zw)
    (?:[a-z]{2,13})
    /
    )
    (?: # One or more:
    @@ -41,7 +41,7 @@
    [a-z0-9]+
    (?:[.\-][a-z0-9]+)*
    [.]
    (?:com|net|org|edu|gov|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj| Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|yu|za|zm|zw)
    (?:[a-z]{2,13})
    \b
    /?
    (?!@) # not succeeded by a @, avoid matching "foo.na" in "[email protected]"
  17. @gruber gruber renamed this gist Feb 8, 2014. 1 changed file with 0 additions and 0 deletions.
    0 gistfile1.txt → Liberal Regex Pattern for URLs
    View file
    File renamed without changes.
  18. @gruber gruber created this gist Feb 8, 2014.
    49 changes: 49 additions & 0 deletions gistfile1.txt
    View file
    Original file line number Diff line number Diff line change
    @@ -0,0 +1,49 @@
    # Single-line version:
    (?i)\b((?:https?:(?:/{1,3}|[a-z0-9%])|[a-z0-9.\-]+[.](?:com|net|org|edu|gov|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|yu|za|zm|zw)/)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:[.\-][a-z0-9]+)*[.](?:com|net|org|edu|gov|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|yu|za|zm|zw)\b/?(?!@)))


    # Commented multi-line version:

    (?xi)
    \b
    ( # Capture 1: entire matched URL
    (?:
    https?: # URL protocol and colon
    (?:
    /{1,3} # 1-3 slashes
    | # or
    [a-z0-9%] # Single letter or digit or '%'
    # (Trying not to match e.g. "URI::Escape")
    )
    | # or
    # looks like domain name followed by a slash:
    [a-z0-9.\-]+[.]
    (?:com|net|org|edu|gov|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj| Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|yu|za|zm|zw)
    /
    )
    (?: # One or more:
    [^\s()<>{}\[\]]+ # Run of non-space, non-()<>{}[]
    | # or
    \([^\s()]*?\([^\s()]+\)[^\s()]*?\) # balanced parens, one level deep: (…(…)…)
    |
    \([^\s]+?\) # balanced parens, non-recursive: (…)
    )+
    (?: # End with:
    \([^\s()]*?\([^\s()]+\)[^\s()]*?\) # balanced parens, one level deep: (…(…)…)
    |
    \([^\s]+?\) # balanced parens, non-recursive: (…)
    | # or
    [^\s`!()\[\]{};:'".,<>?«»“”‘’] # not a space or one of these punct chars
    )
    | # OR, the following to match naked domains:
    (?:
    (?<!@) # not preceded by a @, avoid matching foo@_gmail.com_
    [a-z0-9]+
    (?:[.\-][a-z0-9]+)*
    [.]
    (?:com|net|org|edu|gov|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj| Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|yu|za|zm|zw)
    \b
    /?
    (?!@) # not succeeded by a @, avoid matching "foo.na" in "[email protected]"
    )
    )