# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"([0-9]{5})\s{2,}([^\d\s]+(?:\s+[^\d\s]+)*(?:\s+[a-zA-Z]{1,2}\d{1,2})?)\s+(\d+)\s+(\d+)"
test_str = ("19848 Example School W8 50 14\n"
"10394 ABC School 50 34\n\n"
"18747 ABC School 50 14 //(18747)(ABC School)(50)(14)\n"
"17646 EFG School W11 190 44 //(17646)(EFG School W11)(190)(44)")
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