# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^(?P<symbol>[^,]{1,8})(?:,[A-Z.]*)*\s+-\s+(?P<title>(?:(?!Q\d).)*?)\s*(?P<period>Q\d)?\s?(?P<year>(?:19|20)\d{2})?$"
test_str = ("AXP - Earnings call Q2 2021\n"
"AXP - Conference call 2021\n"
"BAC,BAC.PE,BAC.PL,BACRP,BML.PL,BML.PJ,BML.PH,BML.PG,BAC.PB,BAC.PK,BAC.PM,BAC.PN - Earnings call Q2 2021\n"
"GM - General Motors Company (GM) Presents at Deutsche Bank AutoTech Conference\n"
"AXP - American Express Company (AXP) Management Presents at Barclays 2020 Global Financial Services Conference")
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