import re
regex = re.compile(r"(?:\.\s+(?=[A-Z]))([^;]+(?:,\s+p\.\s+\d+(?:\-\d+)?))", flags=re.IGNORECASE)
test_str = "\"First there is a sentence or two, then a citation which I'd like to extract. Bookwriter, Johnny J., Book Title, 50th Edition, Publishing Company, United States, 2016, p. 18.\""
match = regex.search(test_str)
if match:
print(f"Match 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