# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
^(?:(?<!\/\/|\/\*|<!--).)* #check if commented out
<[a-z][a-z0-9]*?\b #find start of a tag
(?:.(?![^?]>))+ #Must not find > between start and class unless ?>
class=(["']) #Find class and opening quotes
(?:(?!\1).)* \bmatch\b (?:(?!\1).)* #see if our tag is in between the quotes
\1 #closing quotes
.*(?<!\?)> #find first > without ? in front of it
"""
test_str = ("<h1 class=\"match\">Match list</h1>\n\n"
"<p class=\"match\">Simple class element.</p>\n\n"
" <p></p> <h6 class='more match classes'> more classes different comma</h6>\n\n"
" <fdf <?php echo 'data=\"extra data test to disturb the page.\"'; ?> class='incluEdit match classes' > dffd\n\n"
" <div class='hoppa match more classes' <?=$zooi ?> > nested elements </div></div>\n\n"
"// <h1 class='match more classes'> no Match list</h1>\n"
"/* <h1 class='match more classes'> no Match list</h1>\n"
"<!-- <h1 class='match more classes'> no Match list</h1>\n\n\n"
"<p class='nomatch more classes'>shouldn't match</p>")
matches = re.finditer(regex, test_str, re.MULTILINE | re.IGNORECASE | 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