import re
regex = re.compile(r"(?P<origin>(?P<protocol>http[s]?:)?\/\/(?P<host>[a-z0-9A-Z-_.]+))(?P<port>:\d+)?(?P<path>[\/a-zA-Z0-9-\.]+)?(?P<search>\?[^#\n]+)?(?P<hash>#.*)?", flags=re.MULTILINE)
test_str = ("https://www.geeksforgeeks.org/lru-cache-implementation/#hastest?name=234ksldjfkl&sjkldf=\n"
"https://developer.ibm.com/series/kubernetes-learning-path/\n"
"https://www.google.com/search?q=cannot+find+package+%22context%22+in+any+of%3A&oq=cannot+find+package+%22context%22+in+any+of%3A&aqs=chrome..69i57j0l5.205752j0j4&sourceid=chrome&ie=UTF-8#hello world\n\n"
"https://myaccount.google.com/name?utm_source=google-account&utm_medium=web&pli=1&rapt=AEjHL4PXc8zLqgFQOXxYQRbdKJI8\\nyNq3u&name=rjl@1239015423#Kkn1HwudmOHSj7MpYAguZoOmrznrl0PF7hyLkZ17xFdrXToG5UDkMhO2bM1a6i5xw#path=234&sp=\\n")
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