# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^.*\d/\h*\d.*(?:\R(?!END OF REPORT).*)*\REND OF REPORT\b"
test_str = ("TRAFFIC MEASUREMENT REPORT PART 1/ 6 VLR MEASUREMENT VLRMEAS \n\n"
"SAMPLE DATE: FROM 2020-10-22 14:00:00:09\n"
" TO 2020-10-22 15:00:00:13\n\n"
"REGISTERED SUBSCRIBERS:\n\n\n"
"LOCATION AREA CODE CURRENT AVERAGE TMS1 TMS2 TMS3\n"
" UNKNOWN LAC 2 2 0 0 0\n"
" 113 75868 75749 0 0 0\n"
" 115 40627 40732 0 0 0\n"
" 1102 70422 70489 0 0 0\n"
" 1105 87075 87067 0 0 0\n"
" 1117 56150 56180 0 0 0\n"
" 1118 67175 67444 0 0 0\n"
" 1120 74385 74381 0 0 0\n"
" 1121 65034 65060 0 0 0\n"
" 1122 21636 21407 0 0 0\n"
" 1217 22944 22856 0 0 0\n"
" 1218 49054 48993 0 0 0\n"
" 1318 24283 24066 0 0 0\n"
" 1418 16366 16350 0 0 0\n"
" 2118 17812 17674 0 0 0\n"
" 2120 79644 79489 0 0 0\n"
"TOTAL 768477 767939 0 0 0\n\n"
"PART 1/ 6\n"
"END OF REPORT\n\n"
"testing some data\n"
"here\n\n"
"TRAFFIC MEASUREMENT REPORT PART 2/ 6 VLR MEASUREMENT VLRMEAS \n\n"
"SAMPLE DATE: FROM 2020-10-22 14:00:00:09\n"
" TO 2020-10-22 15:00:00:13\n\n"
"REGISTERED SUBSCRIBERS:\n\n\n"
"LOCATION AREA CODE CURRENT AVERAGE TMS1 TMS2 TMS3\n"
" UNKNOWN LAC 2 2 0 0 0\n"
" 113 75868 75749 0 0 0\n"
" 115 40627 40732 0 0 0\n"
" 1102 70422 70489 0 0 0\n"
" 1105 87075 87067 0 0 0\n"
" 1117 56150 56180 0 0 0\n"
" 1118 67175 67444 0 0 0\n"
" 1120 74385 74381 0 0 0\n"
" 1121 65034 65060 0 0 0\n"
" 1122 21636 21407 0 0 0\n"
" 1217 22944 22856 0 0 0\n"
" 1218 49054 48993 0 0 0\n"
" 1318 24283 24066 0 0 0\n"
" 1418 16366 16350 0 0 0\n"
" 2118 17812 17674 0 0 0\n"
" 2120 79644 79489 0 0 0\n"
"TOTAL 768477 767939 0 0 0\n\n"
"PART 2/ 6\n"
"END OF REPORT")
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