import re
regex = re.compile(r"(?:((?<!previously measured\s)\d+.\d+\s*mm)(?:[^.?!\n]*?)?nodule|nodule(?:[^.?!\n]*?((?<!previously measured\s)\d+.\d+\s*mm))?)", flags=re.IGNORECASE)
test_str = ("For example, the largest nodule which is located in the right lower lobe and currently measures 4.4 mm (image #82, series 3) previously measured 3.6 mm on 09/01/2011.\"\n\n"
"In this case, I would like the regex to hit on 4.4 mm not 3.6 mm. Furthermore, if multiple hits are found I would like to only keep the largest size found. For example,\n\n"
" \"For example, the largest nodule which is located in the right lower lobe and currently measures 4.4 mm (image #82, series 3) previously measured 3.6 mm on 09/01/2011. Another nodule was found measuring 2.2 mm. the 2.4 mm had another nodule. The last nodule, previously measured 4.6 mm, now is 4.5 mm")
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