# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(.*)@user_(\S{8})([:| ])(.*)"
test_str = ("USER_79321756 2010-03-03T04:15:26 ÜT: 47.528139,-122.197916 47.528139 -122.197916 RT @USER_2ff4faca: IF SHE DO IT 1 MORE TIME......IMA KNOCK HER DAMN KOOFIE OFF.....ON MY MOMMA>>haha. #cutthatout\n"
"USER_79321756 2010-03-03T04:55:32 ÜT: 47.528139,-122.197916 47.528139 -122.197916 @USER_77a4822d @USER_2ff4faca okay:) lol. Saying ok to both of yall about to different things!:*\n"
"USER_79321756 2010-03-03T05:13:34 ÜT: 47.528139,-122.197916 47.528139 -122.197916 RT @USER_5d4d777a: YOURE A FOR GETTING IN THE MIDDLE OF THIS @USER_ab059bdc WHO THE FUCK ARE YOU ? A FUCKING NOBODY !!!!>>Lol! Dayum! Aye!\n"
"USER_79321756 2010-03-03T05:28:02 ÜT: 47.528139,-122.197916 47.528139 -122.197916 @USER_77a4822d yea ok..well answer that cheap as Sweden phone you came up on when I call.\n"
"USER_79321756 2010-03-03T05:56:13 ÜT: 47.528139,-122.197916 47.528139 -122.197916 A sprite can disappear in her mouth - lil kim hmmmmm the can not the bottle right?")
matches = re.finditer(regex, test_str, re.MULTILINE | re.IGNORECASE)
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