# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^\s*(\d+)\s+(\S+(?: \S+)*)\s+(\S+(?: \S+)*)\s+(\S+(?: \S+)*)\s+(\S+(?: \S+)*)\s+(\S+(?: \S+)*)$"
test_str = (" 8 SIRIO S.P.A. BOMBARDIER INC. BD-100-1A10 I-FORZ STANDARD\n\n"
" 9 ESERCENTE PRIVATO PIAGGIO AERO INDUSTRIES S.P.A. P.180 AVANTI II I-FXRJ SPECIALE/STANDARD\n\n"
"10 MIGNINI & PETRINI S.P.A. ROBINSON HELICOPTER COMPANY R44 II I-HIKE SPECIALE/STANDARD\n\n"
"11 MIGNINI & PETRINI S.P.A. ROBINSON HELICOPTER COMPANY R44 II I-HIKE STANDARD\n\n"
"12 BLUE PANORAMA AIRLINES S.P.A. THE BOEING COMPANY 737-86N I-LCFC STANDARD")
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