# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
(?(DEFINE)
(?<groupStart> <g )
(?<groupAttrs> >|[^>]+> )
(?<groupStartContainer> (?:(?&groupStart)(?&groupAttrs)(?&space)){1,} )
(?<groupEnd> (?:<\/g>(?&space)){1,} )
(?<group> (?:(?&groupStartContainer)(?&tags)){1,}(?&groupEnd)(?:(?&space)(?&tags)(?&groupEnd))? )
(?<tags> (?:<[^>]+\/>(?&space)){1,} )
(?<space> (?:\s+)? )
)
(?<groupeSimples> (?&group) )
"""
test_str = ("<g id=\"Tie2\"> <path fill=\"#402A23\" d=\"M21,2.307c0,1.809,0,3.016,0,3.016s0.057,1.809-1.752,1.809l0.178,0.682l-5.027,5.042l1.342-5.723 c0,0-1.741,0-1.741-1.809c0-1.809,0-3.016,0-3.016S13.876,1,15.686,1s3.618,0,3.618,0S21,0.498,21,2.307z\"/> <polygon fill=\"#402A23\" points=\"20.993,14.717 12.001,23.709 13.684,16.14 19.919,9.905 \"/> <polygon fill=\"#402A23\" points=\"22.855,23.106 14.305,31.657 10.861,28.841 11.271,26.996 21.457,16.81 \"/> <polygon fill=\"#402A23\" points=\"24.128,28.841 17.495,34.269 15.709,32.809 23.32,25.198 \"/> </g> <path id=\"TV\" fill=\"#402A23\" d=\"M32.154,8.083H17.152l4.972-5.813l-1.649-1.406l-5.688,6.633L9.098,0.863L7.447,2.27l4.972,5.813 c-5.297,0-9.574,0-9.574,0s-2.171,0-2.171,2.171v19.541c0,0,0,2.17,2.171,2.17h3.257v2.172h3.257v-2.172h16.283v2.172h3.257v-2.172 c1.997,0,3.256,0,3.256,0s2.172,0,2.172-2.17V10.254C34.326,10.254,34.326,8.083,32.154,8.083z M23.47,26.538 c0,0,0,2.171-2.171,2.171s-15.197,0-15.197,0s-2.171,0-2.171-2.171c0-2.172,0-13.027,0-13.027s0-2.171,2.171-2.171 s15.197,0,15.197,0s2.171,0,2.171,2.171C23.47,15.682,23.47,26.538,23.47,26.538z M28.355,25.452c-0.901,0-1.629-0.728-1.629-1.629 c0-0.9,0.728-1.628,1.629-1.628s1.628,0.728,1.628,1.628C29.983,24.725,29.257,25.452,28.355,25.452z M31.069,20.023h-5.428v-2.17 h5.428V20.023z M31.069,15.682h-5.428v-2.171h5.428V15.682z\"/> <g id=\"Typewriter\"> <g> <path fill=\"#402A23\" d=\"M26.328,12.455v3.783H8.672v-3.783H4.888v16.396h25.223V12.455H26.328z M18.762,17.5h2.521v2.522h-2.521 V17.5z M18.762,21.283h2.521v2.522h-2.521V21.283z M13.717,17.5h2.522v2.522h-2.522V17.5z M13.717,21.283h2.522v2.522h-2.522 V21.283z M8.672,17.5h2.522v2.522H8.672V17.5z M8.672,21.283h2.522v2.522H8.672V21.283z M23.807,27.169H11.194v-2.102h12.612 V27.169z M26.328,23.806h-2.521v-2.522h2.521V23.806z M26.328,20.022h-2.521V17.5h2.521V20.022z\"/> </g> <rect x=\"9.933\" y=\"6.149\" fill=\"#402A23\" width=\"15.133\" height=\"8.828\"/> <rect x=\"1.105\" y=\"11.194\" fill=\"#402A23\" width=\"2.522\" height=\"5.044\"/> <rect x=\"31.373\" y=\"11.194\" fill=\"#402A23\" width=\"2.521\" height=\"5.044\"/> </g> <g id=\"capa\"> <path fill=\"#402A23\" d=\"M27.873,10.156L6.395,9.743c-3.322-0.064-4.033,2.12-4.077,4.438L2.117,24.654l2.607,0.003l0.202-10.474 C4.938,13.469,5.531,12.986,6.247,13l5.218,0.1l-0.226,11.73l1.304,0.025l0.225-11.729l3.91,0.075l-0.225,11.73l1.303,0.024 l0.226-11.729l9.123,0.175L26.88,25.13l1.303,0.025l0.226-11.713c1.101,0.351,1.275,1.467,1.255,2.52l-0.177,9.218l3.258,0.062 l0.178-9.217C32.982,12.886,30.478,10.205,27.873,10.156z\"/> <rect x=\"6.138\" y=\"13.012\" transform=\"matrix(-0.9998 -0.018 0.018 -0.9998 13.2402 37.8739)\" fill=\"#402A23\" width=\"1.304\" height=\"11.732\"/> <rect x=\"8.745\" y=\"13.06\" transform=\"matrix(-0.9998 -0.0195 0.0195 -0.9998 18.424 38.033)\" fill=\"#402A23\" width=\"1.303\" height=\"11.733\"/> <rect x=\"13.959\" y=\"13.161\" transform=\"matrix(-0.9998 -0.0195 0.0195 -0.9998 28.8478 38.3347)\" fill=\"#402A23\" width=\"1.303\" height=\"11.732\"/> <rect x=\"19.172\" y=\"13.262\" transform=\"matrix(-0.9998 -0.0187 0.0187 -0.9998 39.2856 38.623)\" fill=\"#402A23\" width=\"1.303\" height=\"11.731\"/> <rect x=\"24.385\" y=\"13.361\" transform=\"matrix(-0.9998 -0.0195 0.0195 -0.9998 49.6941 38.9389)\" fill=\"#402A23\" width=\"1.304\" height=\"11.733\"/> <rect x=\"21.778\" y=\"13.311\" transform=\"matrix(-0.9998 -0.0195 0.0195 -0.9998 44.4827 38.7881)\" fill=\"#402A23\" width=\"1.304\" height=\"11.733\"/> </g> <g id=\"Typewriter2\"> <rect x=\"9.933\" y=\"6.149\" fill=\"#402A23\" width=\"15.133\" height=\"8.828\"/> <rect x=\"1.105\" y=\"11.194\" fill=\"#402A23\" width=\"2.522\" height=\"5.044\"/> <rect x=\"31.373\" y=\"11.194\" fill=\"#402A23\" width=\"2.521\" height=\"5.044\"/> <g> <path fill=\"#402A23\" d=\"M26.328,12.455v3.783H8.672v-3.783H4.888v16.396h25.223V12.455H26.328z M18.762,17.5h2.521v2.522h-2.521 V17.5z M18.762,21.283h2.521v2.522h-2.521V21.283z M13.717,17.5h2.522v2.522h-2.522V17.5z M13.717,21.283h2.522v2.522h-2.522 V21.283z M8.672,17.5h2.522v2.522H8.672V17.5z M8.672,21.283h2.522v2.522H8.672V21.283z M23.807,27.169H11.194v-2.102h12.612 V27.169z M26.328,23.806h-2.521v-2.522h2.521V23.806z M26.328,20.022h-2.521V17.5h2.521V20.022z\"/> </g> </g>\n")
matches = re.finditer(regex, test_str, re.VERBOSE)
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