# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?ms)\A(?:\d{2}/\d{2}/\d{2}(?:\d{2})?|−−DATE−−)\s.*\s\p{Lu}{3}$"
test_str = ("08/03/2020 NOVUS HOME Mortgage Company TRU\n"
" MORTGAGE\n"
" 07/08/2020 FACTUAL DATA Mortgage Reporter XPN\n"
" 07/08/2020 FCTUALDATA EFX\n"
" 07/08/2020 NOVUS HOME Mortgage Company TRU\n"
" MORTGAGE\n"
" 07/07/2020 CROSSCOUNTRY Mortgage Loan TRU\n"
" MORTGAG\n"
" 07/07/2020 FACTUAL DATA Mortgage Reporter XPN\n"
" 07/07/2020 FCTUALDATA EFX\n"
" 05/21/2020 CAP ONE NA Bank Credit Card XPN\n"
" 05/21/2020 CAPITAL ONE Credit Card TRU\n"
" 05/21/2020 CAPITALONE Bank EFX\n"
" 05/20/2020 CROSSCOUNTRY Mortgage Loan TRU\n"
" MORTGAG\n"
" 05/20/2020 FACTUAL DATA Mortgage Reporter XPN\n"
" 05/20/2020 FCTUALDATA EFX\n"
" 05/20/2020 FINGERHUT/WEBBANK Finance Company XPN\n"
" 05/07/2020 EMS EFX\n"
" 05/07/2020 GROW FINANCIAL CREDI Credit Bureau/Mortgage TRU\n"
" Processing\n"
" Co-Applicant\n"
" No inquiry records found.")
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