# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?<=TITLE)(?!\s*Direct Submission)[\S\s]*?(?=JOURNAL)"
test_str = (" TITLE The Identification of Novel Diagnostic Marker Genes for the\n"
" Detection of Beer Spoiling Pediococcus damnosus Strains Using the\n"
" BlAst Diagnostic Gene findEr\n"
" JOURNAL PLoS One 11 (3), e0152747 (2016)\n"
" PUBMED 27028007\n"
" REMARK Publication Status: Online-Only\n"
"REFERENCE 2 (bases 1 to 462)\n"
" AUTHORS Behr,J., Geissler,A.J. and Vogel,R.F.\n"
" TITLE Direct Submission\n"
" JOURNAL Submitted (04-AUG-2015) Technische Mikrobiologie, Technische\n"
" TITLE OtherDirect Submission\n"
" JOURNAL Submitted (04-AUG-2015) Technische Mikrobiologie, Technische")
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