# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^(?P<Username>[-\w\.]+)(?:\s+\W*at\W*\s+|\s*[^\@\s]*?@[^\@\s]*?\s*)(?P<Domain>([\w\-]+)(?:(?:\.|\s+\W*?dot\W*?\s+)([\w\-]+))+?(?:(?:\.|\s+\W*?dot\W*?\s+)([\w\-]+))??$)"
test_str = ("Parse email, also distorted ones, and convert them back to the real ones.\n"
"Inspirated by dislick's work: https://regex101.com/r/wB7xJ7/1\n\n"
"frenci98@gmail.com\n"
"st11389@copernico.bo.it\n"
"gigilafontana .at. gmail [dot] com\n"
"d98.copernico@gmail.com\n"
"domenico-tosello at dotcom-sas dot com\n"
"my.e-M4il [at] w3-spAce.org\n"
"email@sub-sub.sub dot domain dot info\n"
"email@foo dot foo dot foo dot foo")
subst = "\\1@\\3.\\4"
# You can manually specify the number of replacements by changing the 4th argument
result = re.sub(regex, subst, test_str, 0, re.MULTILINE)
if result:
print (result)
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html