# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?:\s|\\n\\n)*(?<subject>\S+(?:\s[IVX]+\.?)?)(?:\s|\\n\\n)+(?<teacher>\S+)(?:\s|\\n\\n)+(?<room>\S+)(?:\s|\\n\\n)*"
test_str = ("TSG MUM \\n\\nBS06-312\n"
"RQWE. FKB \\n\\nBS06-204\n"
"NM. JAK \\n\\nBS06-E05\n"
"DB. FKB \\n\\nBS06-312\n"
"IGT. resetk \\n\\nWender.\n"
"ENG I. \\n\\nWEHN BS06-E06 \\n\\nENG II \\n\\nFLEM BS06-203\n"
"ITSI. MUM \\n\\nBS06-E02\n"
"PQT. RIE \\n\\nBS11-QCR PQT \\n\\nMARK BS11-QCR \\n\\nPQT FIS \\n\\nBS11-QCR\n"
"INC FEY \\n\\nBS06-309\n"
"ABS. DOE \\n\\nBS06 ABS \\n\\nVOG BS06 \\n\\nABS HEI \\n\\nBS06 ABS \\n\\nMOR BS06 \\n\\nABS REM \\n\\nBS06 ABS \\n\\nDEI BS06 \\n\\nABS THA \\n\\nBS06\n"
"ENG III. \\n\\nGLIT BS06-209 \\n\\nENG II \\n\\nWANN BS06-208")
matches = re.finditer(regex, test_str)
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