# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = (r"(?xsm) # free-spacing mode, multi-line\n"
r"(?=.*?pig) # lookahead: if pig is not there, fail right away to save the effort\n"
r"(?: # start counter-line-skipper (lines that don't include pig)\n"
r" (?: # skip one line that doesn't have pig\n"
r" ^ # beginning of line\n"
r" (?:(?!pig)[^\r\n])* # zero or more chars not followed by pig\n"
r" (?:\r?\n) # newline chars\n"
r" ) \n"
r" # for each line skipped, let Group 1 match an ever increasing portion of the numbers string at the bottom\n"
r" (?= # lookahead\n"
r" .* # get to the end of the input\n"
r" ( # start Group 1\n"
r" :\d+ # match a colon and some digits\n"
r" (?(1)\1) # if Group 1 is set, match Group 1\n"
r" ) # end Group 1\n"
r" ) # end lookahead\n"
r")*+ # end counter-line-skipper: zero or more times\n"
r".*? # match\n"
r"\K # drop everything we've matched so far\n"
r"pig # match pig (this is the match!)\n"
r"(?=.*(\d+)(?(1)\1)) # capture the next number to Group 2")
test_str = ("my cat pi g\n"
"dog p ig\n"
"my pig\n"
"my cow\n"
"my mouse\n\n"
":7:6:5:4:3:2:1")
subst = "\\2"
# You can manually specify the number of replacements by changing the 4th argument
result = re.sub(regex, subst, test_str, 1)
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