# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?<=\s|^)([a-z0-9-.])+@+([a-z0-9-]*)\.([a-z]*)\s"
test_str = ("this regex is intended to find emails with tld level 1 from a text test@domain12.com this a text after email to check detection\n"
"test@domain12.com this is another text to test regex for that i had to write down some email something-new@gmail.com to another.email@gmail.com test123@domain-12.com test@domain.co\n"
"sample@organization.org test.abc@domain.ac.nz test@abc.co\n"
"example@testdomain.net\n")
matches = re.finditer(regex, test_str, re.MULTILINE)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# 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