A python port for regex-weburl.js by @dperini

regex-weburl.py

import re
URL_REGEX = re.compile(
    u"^"
    # protocol identifier
    u"(?:(?:(?:https?|ftp):)?//)"
    # user:pass authentication
    u"(?:\S+(?::\S*)?@)?"
    u"(?:"
    # IP address exclusion
    # private & local networks
    u"(?!(?:10|127)(?:\.\d{1,3}){3})"
    u"(?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})"
    u"(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})"
    # IP address dotted notation octets
    # excludes loopback network 0.0.0.0
    # excludes reserved space >= 224.0.0.0
    # excludes network & broadcast addresses
    # (first & last IP address of each class)
    u"(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])"
    u"(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}"
    u"(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))"
    u"|"
    # host & domain names, may end with dot
    # can be replaced by a shortest alternative
    # u"(?![-_])(?:[-\w\u00a1-\uffff]{0,63}[^-_]\.)+"
    # u"(?:(?:[a-z\u00a1-\uffff0-9]-?)*[a-z\u00a1-\uffff0-9]+)"
    # # domain name
    # u"(?:\.(?:[a-z\u00a1-\uffff0-9]-?)*[a-z\u00a1-\uffff0-9]+)*"
    u"(?:"
    u"(?:"
    u"[a-z0-9\u00a1-\uffff]"
    u"[a-z0-9\u00a1-\uffff_-]{0,62}"
    u")?"
    u"[a-z0-9\u00a1-\uffff]\."
    u")+"
    # TLD identifier name, may end with dot
    u"(?:[a-z\u00a1-\uffff]{2,}\.?)"
    u")"
    # port number (optional)
    u"(?::\d{2,5})?"
    # resource path (optional)
    u"(?:[/?#]\S*)?"
    u"$"
    , re.UNICODE | re.I
)

@doronhorwitz quoting this stack overflow answer:

The fact that you're seeing the u means you're on Python 2 - strings are Unicode by default on Python 3
So u can be safely removed in Python 3

Here is version with r instead of u:

import re

URL_REGEX = re.compile(
    r"^"
    # protocol identifier
    r"(?:(?:(?:https?|ftp):)?//)"
    # user:pass authentication
    r"(?:\S+(?::\S*)?@)?"
    r"(?:"
    # IP address exclusion
    # private & local networks
    r"(?!(?:10|127)(?:\.\d{1,3}){3})"
    r"(?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})"
    r"(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})"
    # IP address dotted notation octets
    # excludes loopback network 0.0.0.0
    # excludes reserved space >= 224.0.0.0
    # excludes network & broadcast addresses
    # (first & last IP address of each class)
    r"(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])"
    r"(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}"
    r"(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))"
    r"|"
    # host & domain names, may end with dot
    # can be replaced by a shortest alternative
    # r"(?![-_])(?:[-\w\u00a1-\uffff]{0,63}[^-_]\.)+"
    # r"(?:(?:[a-z\u00a1-\uffff0-9]-?)*[a-z\u00a1-\uffff0-9]+)"
    # # domain name
    # r"(?:\.(?:[a-z\u00a1-\uffff0-9]-?)*[a-z\u00a1-\uffff0-9]+)*"
    r"(?:"
    r"(?:"
    r"[a-z0-9\u00a1-\uffff]"
    r"[a-z0-9\u00a1-\uffff_-]{0,62}"
    r")?"
    r"[a-z0-9\u00a1-\uffff]\."
    r")+"
    # TLD identifier name, may end with dot
    r"(?:[a-z\u00a1-\uffff]{2,}\.?)"
    r")"
    # port number (optional)
    r"(?::\d{2,5})?"
    # resource path (optional)
    r"(?:[/?#]\S*)?"
    r"$"
    , re.UNICODE | re.I
)

Got it, so you originally posted a Python 2 solution . So thanks now for the Python 3 version