import re
regex = re.compile(r"(?<url>(?:(?<scheme>[a-zA-Z]+:\/\/)?(?<hostname>(?:[-a-zA-Z0-9À-ÖØ-öø-ÿ@%_\+~#=]{1,256}\.){1,256}(?:[-a-zA-Z0-9À-ÖØ-öø-ÿ@%_\+~#=]{1,256})))(?::(?<port>[[:digit:]]+))?(?<path>(?:\/[-a-zA-Z0-9!$&'()*+,\\\/:;=@\[\]._~%]*)*)(?<query>(?:(?:\#|\?)[-a-zA-Z0-9!$&'()*+,\\\/:;=@\[\]._~]*)*))", flags=re.IGNORECASE)
test_str = ("example.com\n"
"www.example.com\n"
"www.example.com:81\n"
"example.com/file.txt?version=2.1&download=true\n"
"https://www.example.com/file.txt\n"
"https://www.example.com\n"
"https://www.example.com:8443\n"
"stfp://example.com:21\n"
"http://www.example.com/file.txt?version=2.1&download=true")
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