import re
regex = re.compile(r"(?:[^<]+|<a\b[^>]*>.*?</a>)*((ftp|http|https):\/\/(\w+:{0,1}\w*@)?(\S+)(:[0-9]+)?(\/|\/([\w#!:.?+=&%@!\-\/]))?)[^< ,\"'>]", flags=re.MULTILINE)
test_str = ("I was surfing http://www.google.com, where I found my tweet, check it out <a href=\"http://tinyurl.com/blah\">http://tinyurl.com/blah</a>\n\n"
"<span>http://www.google.com</span>")
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