# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"<[^'\">]*((\"[^\"]*\"|'[^']*')[^'\">]*)*>"
test_str = ("some text <tag link=\"fo>o\"> other text\n"
"some text <tag link=\"fo>o\"> other text\n\n"
"<meta name=\"keywords\" content=\"javascript,regex><><><<>,regular expression,debugger,explainer,helper,tester,match,pcre,python,editor\" />\n\n"
"<meta name=\"descrip><>><>tion\" content=\"Online reg>---<ex tester, debugger with highlighting for PHP, PCRE, Python and JavaScript.\" />\n\n"
"<meta name=\"author\" content=\"Firas Dib\" />\n"
"content content content \n"
"content <meta property=\"twitter:ca><<>>><>><>rd\" content=\"summary\" />content content \n"
"content content \n"
"content content content <meta property=\"twitter:site\" content=\"@regex101\" />content content content content \n"
"content content content content \n"
"<meta property=\"twitter:title\" content=\"Regex101 - online regex editor and debugger\" />")
matches = re.finditer(regex, test_str)
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