url_match.py

# url_match.py
#     Find out if a string is, or contains, a common URL.
# 
# Copyright (c) 2009 Jannis Andrija Schnitzer
# 
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
# 
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
# 
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
# THE SOFTWARE.


import re

ipv6_regex_str = r"""((([0-9a-fA-F]{1,4}:){1,1}(:[0-9a-fA-F]{1,4}){1,6})|(([0-9a-fA-F]{1,4}:){1,2}(:[0-9a-fA-F]{1,4}){1,5})|(([0-9a-fA-F]{1,4}:){1,3}(:[0-9a-fA-F]{1,4}){1,4})|(([0-9a-fA-F]{1,4}:){1,4}(:[0-9a-fA-F]{1,4}){1,3})|(([0-9a-fA-F]{1,4}:){1,5}(:[0-9a-fA-F]{1,4}){1,2})|(([0-9a-fA-F]{1,4}:){1,6}(:[0-9a-fA-F]{1,4}){1,1})|((([0-9a-fA-F]{1,4}:){1,7}|:):)|(:(:[0-9a-fA-F]{1,4}){1,7})|(((([0-9a-fA-F]{1,4}:){6})(25[0-5]|2[0-4]\d|[0-1]?\d?\d)(\.(25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}))|((([0-9a-fA-F]{1,4}:){5}[0-9a-fA-F]{1,4}:(25[0-5]|2[0-4]\d|[0-1]?\d?\d)(\.(25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}))|(([0-9a-fA-F]{1,4}:){5}:[0-9a-fA-F]{1,4}:(25[0-5]|2[0-4]\d|[0-1]?\d?\d)(\.(25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3})|(([0-9a-fA-F]{1,4}:){1,1}(:[0-9a-fA-F]{1,4}){1,4}:(25[0-5]|2[0-4]\d|[0-1]?\d?\d)(\.(25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3})|(([0-9a-fA-F]{1,4}:){1,2}(:[0-9a-fA-F]{1,4}){1,3}:(25[0-5]|2[0-4]\d|[0-1]?\d?\d)(\.(25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3})|(([0-9a-fA-F]{1,4}:){1,3}(:[0-9a-fA-F]{1,4}){1,2}:(25[0-5]|2[0-4]\d|[0-1]?\d?\d)(\.(25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3})|(([0-9a-fA-F]{1,4}:){1,4}(:[0-9a-fA-F]{1,4}){1,1}:(25[0-5]|2[0-4]\d|[0-1]?\d?\d)(\.(25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3})|((([0-9a-fA-F]{1,4}:){1,5}|:):(25[0-5]|2[0-4]\d|[0-1]?\d?\d)(\.(25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3})|(:(:[0-9a-fA-F]{1,4}){1,5}:(25[0-5]|2[0-4]\d|[0-1]?\d?\d)(\.(25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}))"""

url_regex_str = ipv6_regex_str.join([r"""(((news|telnet|nttp|file|http|ftp|https)://)(([-A-Za-z0-9\.]+)|(\[""", r"""\])))(:[0-9]*)?(?:/[-A-Za-z0-9_\$\.\+\!\*\(\),;:@&=\?/~\#\%]*[^]'\.}>\),\"])?"""])

url_regex = re.compile(url_regex_str)

def is_url(string):
    """Check if the given string *is* an URL.
    
    Checks for common web URLs with a hierarchic part starting with //."""
    return url_regex.match(string) != None

def contains_url(string):
    """Check if one word of the given string (splitted with string.split())
    is a common URL.
    
    Uses is_url()."""
    return any(is_url(splice) for splice in string.split())