import re
regex = re.compile(r"(<script\b[^><]*>)(.*?)(<\/script>)|\bon\w+\s*=\s*\K(?|(\")([^\"]+)\"|(')([^']+)')", flags=re.IGNORECASE | re.DOTALL)
test_str = ("<div id='content' onClick='abc()'>Lorem On='abc' ipsum on to</div>\n"
"<input id='a' type='range'>\n"
"<input id='b' type='range'>\n"
"<script>abc();</script>\n\n\n\n"
"Jan23: The following is an addition set of tests including escaping quotes and .replace(/'/ situations that can cause problems.\n\n\n"
" <div id='content'\n"
" onClick='yyy(\"ere\\'xyz\\'\").value=\\'ewew\\'; yyy(\"jhrhej\")'\n"
" >Lorem On='abc' ipsum on to</div>\n\n\n"
" <input id='a' type='range'\n"
" onPress=\"xxx(document.getElementById(\\\"abc\\\"))\"\n"
" onSomething=\"yyy(\\'fehrje\\')\"\n"
" onSomethingElse=\"document.getElementById('content').innerHTML.replace(/\"/g, \\\"dq\\\")\">\n"
" <input id='b' type='range'>\n\n"
" <script>\n"
" function abc() {console.log('abc()');};\n"
" function xxx(elem) {console.log('xxx:'+elem.className);};\n"
" function yyy(str) {console.log('yyy:'+str);};\n\n"
" yyy(\"ere\\'xyz\\'\");\n"
" yyy(\"jhrhej\");\n\n"
" var aaa=document.getElementById('content').innerHTML;\n"
" var bbb=document.getElementById('content').innerHTML;\n"
" abc();\n"
" aaa.replace(/'/g, \"single-quotes\");\n"
" bbb.replace(/'/g, 'single-quotes');\n"
" aaa.replace(/\"/g, \"quotes\");\n"
" bbb.replace(/\"/g, 'quotes');\n"
" </script>\n\n"
"</body>\n"
"</html>")
matches = regex.finditer(test_str)
for match_num, match in enumerate(matches, start=1):
print(f"Match {match_num} was found at {match.start()}-{match.end()}: {match.group()}")
for group_num, group in enumerate(match.groups(), start=1):
print(f"Group {group_num} found at {match.start(group_num)}-{match.end(group_num)}: {group}")
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