# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"</h1>\s*(<div>)?(.*?)\s*(</div>)?</header>"
test_str = ("<header><h1>A Suspenseful Movie Title</h1><div>The narrative traces the journey of three youngsters from a seaside community who inadvertently capture a homicide on camera. As they unwittingly become enmeshed with the perpetrator, it unravels a convoluted case that entangles numerous families, culminating in an unpredictable outcome.</div></header>\n\n"
"<header>\n"
"<h1>Movie Title</h1>\n"
"A group of extraordinary individuals, each with unconventional occupations, emerged as champions for the common people on the streets by pursuing justice. Suddenly, they gained access to supernatural abilities.\n"
"</header>\n\n"
"<header>\n"
" <h1>Funny Comedy Movie Title</h1>The following is a comical tale of a husband and wife's pursuit of their ambition to obtain a flat.</header>")
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