A collection of useful regular expressions, in PCRE and Python syntax

useful_regexes.pl

# Garbage matcher
# matches any string consisting of only |, <, >, +, *, ^, #, =, and hyphen chains.
# this is to identify patterns like ++<===> ######## <---->^^ which serve no purpose but to decorate the text
/(\||(--+)|(__+)|<|>|\+|\*|\^|#|=|~)+|(\\|_|\/){2,}/

# Garbage matcher 2
# matches anything that isn't a letter, space or basic punctuation.
# this is typically useful for cleaning up emojis
/.(?<!([a-zA-Z0-9]|,|\.|'| |\?|\!))/

# layout hyphenation matcher, typically matches hyphens used as bullet points
/(^\ *-\ )/

# e-mail address matcher
# the theoretical character limit for top-level domains is 63 characters
/([a-z]|[0-9]|\.|\+|-)+@([a-z]|[0-9]|\.|-)+\.[a-z]{2,63}/

# phone number matcher
# see this stackoverflow post explaining how mant digits to account for in a phone number
# https://stackoverflow.com/a/4729239/2980717
/\(?\+?(\(?[0-9]\)?(-|\ |\.)?){6,30}[0-9]/

# URL matcher
/https?\:\/\/(www\.)?([A-z]|[0-9]|\.|-|%)+\.[A-z]{2,63}(\/([A-z]|[0-9]|-|\.|_|#)+)*\/?(\?([A-z]|[0-9]|\.|-|%|=|&|_|#|\:|\+)+)?/
# https?\:\/\/(www\.)?                          # pretty self explanatory
# ([A-z]|[0-9]|\.|-|%)+                         # adress
# +\.[A-z]{2,63}                                # domain name
# (\/([A-z]|[0-9]|-|\.|_|#)+)*\/?               # /stuff/between/slashes/
# (\?([A-z]|[0-9]|\.|-|%|=|&|_|#|\:|\+)+)?      # request details after ?

useful_regexes.py

# PAT at the beginning of each regex name stands for Pattern
PAT_GARBAGE = r"((\||(--+)|(__+)|<|>|\+|\*|\^|#|=|~)+|(\\|_|/){2,})"
PAT_GARBAGE_2 = r".(?<!([a-zA-Z0-9]|,|\.|'| |\?|\!))"
PAT_BULLET_HYPHENS = r"(^\s*-\ )"
PAT_EMAIL = r"(([A-z]|[0-9]|\.|\+)+@([A-z]|[0-9]|\.|-)+\.[A-z]{2,63})"
PAT_PHONE = r"(\(?\+?(\(?[0-9]\)?(-|\ |\.)?){6,30}[0-9])"
PAT_URL = r"(https?\://(www\.)?([A-z]|[0-9]|\.|-|%)+\.[A-z]{2,63}(/([A-z]|[0-9]|-|\.|_|#)+)*/?(\?([A-z]|[0-9]|\.|-|%|=|&|_|#|\:|\+)+)?)"

This code is released under the .