import re
regex = re.compile(r"""
(?:<(?:(?:[a-z]+\s(?:[^>=]|='[^']*'|="[^"]*"|=[^'"\s]*)*"\s?\/?|\/[a-z]+)>)|(?:(?!<)(?:[^.?!]|[.?!](?=\S)))*)+[.?!]
""", flags=re.DOTALL | re.IGNORECASE | re.VERBOSE)
test_str = ("I am was trying to split paragraph to sentences. The paragraph can have a word like F.C.B also it includes some html tag like anchor and other tags. I was trying to use like below but it was not perfect separating my paragraph to the specific sentence by living the html tag as it is.\n\n"
"In 2004, he <a href=\"http://test.pic.org/jpeg.\"> received </a> national attention during his Party primary, his keynote address July, <a onmouseover=\" fnRotator('I like droids. '); \"> and </a> his election to the Senate in November. He began his presidential campaign in he won sufficient delegates in the Democratic Party primaries to receive the presidential nomination.")
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