# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?s)PROC DATE:\s*(?P<date>\w+)(?:(?!RID:\s+RSS-\d).)*T PUR\s+(?P<num>\d[.,\d]*)\s+(?P<val>\d[\d,]*)"
test_str = ("RID: RSS-130 SERVICE PAGE: 2 \n"
"REPORTING FOR: 100019912 SSSE INTSERVICE PROC DATE: 15SEP21 \n"
"ROLLUP FOR: 100076212 SSSE REPORT REPORT DATE: 15SEP21 \n"
"ENTITY: 1000208212 SSSE \n"
" \n"
" \n"
" \n"
" \n"
" ACQT \n"
" \n"
" \n"
" PUR \n"
" SAME 10SEP21 120 12,263,518 19,48.5 \n"
" \n"
" T PUR 120 12,263,518 19,48.5")
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