# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(GET|POST)\s(?<url>[^ ]*)\s(?<user>[^ ]*)\s([^ ]*\s){4}(?<domain>[^ ]*)"
test_str = (" 1489714117.601 56 27.1.11.11 TCP_REFRESH_HIT/200 54491 GET http://www.flatbed-scanner-review.org/inter-banner_flatbed.jpg bhussain@buttercupgames.com DIRECT/www.flatbed-scanner-review.org image/jpeg DEFAULT_CASE-DefaultGroup-Demo_Clients-NONE-NONE-DefaultRouting <nc,ns,0,-,-,-,-,0,-,-,-,-,-,-,-,nc,-> - http://www.flatbed-scanner-review.org/\n"
"1489713615.376 809 211.166.11.101 TCP_MISS/200 147639 GET http://www.vindy.com/ myuan@buttercupgames.com DIRECT/www.vindy.com text/html DEFAULT_CASE-DefaultGroup-Demo_Clients-NONE-NONE-DefaultRouting <IW_news,3.4,0,-,-,-,-,0,-,-,-,-,-,-,-,IW_news,-> - -")
matches = re.finditer(regex, test_str)
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