# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
(?<firstcapture> ~Start [^~]* ) #_(3)
(?<randomStuff> .*? ) #_(4)
(?<loop_first> #_(5 start)
(?:
~
(?: LOOP )
\d [^~]
)
( .*? ) # (1)
) #_(5 end)
(?:
(?<loop_middle> #_(6 start)
(?:
(?:
~
(?: LOOP )
\d [^~]
)
.*?
)*
) #_(6 end)
(?<loop_last> #_(7 start)
(?:
~
(?: LOOP )
\d [^~]
)
( .*? ) # (2)
) #_(7 end)
)?
(?<end> ~End [ ] stuff~ ) #_(8)
"""
test_str = (" BlahBlahBlah~Start capture~Yadda~Yadda~Yadda~LOOP1 hello1~LOOP2 hello2~LOOP3 hello3~End stuff~\n\n"
" BlahBlahBlah~Start capture~Yadda~Yadda~Yadda~LOOP1 hello1~LOOP2 hello2~End stuff~\n\n"
" BlahBlahBlah~Start capture~Yadda~Yadda~Yadda~LOOP1 hello1~LOOP3 hello3~End stuff~\n\n"
" BlahBlahBlah~Start capture~Yadda~Yadda~Yadda~LOOP1 hello1~End stuff~\n")
subst = "${firstcapture}${randomStuff}${loop_last}${loop_middle}${loop_first}${end}"
# You can manually specify the number of replacements by changing the 4th argument
result = re.sub(regex, subst, test_str, 0, re.MULTILINE | re.VERBOSE)
if result:
print (result)
# 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