# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?i)(\d*\.?\d+)\s*(?:tab|cap|grag|past|sob|comp)"
test_str = (" PRODUCTS\n"
"0 PULSAR AT 20 MG ORAL 30 TAB RECUB\n"
"1 LIPITOR 40 MG 1+1 ORAL 15 TAB\n"
"2 LOFTYL 150 MG ORAL 30 TAB\n"
"3 SOMAZINA 500 MG ORAL 10 COMP RECUB\n"
"4 LOFTYL 30 TAB 150 MG ORAL")
matches = re.finditer(regex, test_str, re.MULTILINE)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
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