# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\"(?:GET|POST)\s+([^\s?]*)"
test_str = ("\n\n"
" 83.198.250.175 - - [22/Mar/2009:07:40:06 +0100] \"GET /images/ht1.gif HTTP/1.1\" 200 61 \"http://www.facades.fr/\" \"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Wanadoo 6.7; Orange 8.0)\" \"-\"\n\n"
" 65.33.94.190 - - [05/Apr/2003:17:26:27 -0500] \"POST /samples/dem/tt.php?x=e2323 HTTP/1.0\" 404 276\n\n"
" 151.227.152.48 - - [02/Jul/2014:14:35:55 +0100] \"GET /css/main.css HTTP/1.1\" 200 4658 \"http://stanmore.menczykowski.co.uk/\" \"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36\"\n\n"
" 10.143.2.119 64.103.161.112 - [06/Jan/1970:00:48:01 +0000] \"GET /right_arrow.jpg HTTP/1.1\" 304 0 \"http://64.103.161.112/index_eth_diag.html\" \"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.95 Safari/537.36\"\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