# 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, DOTALL, multi-line\n"
r"(?=.*?blue) # if blue isn't there, fail without delay\n\n"
r"########### LINE SKIPPER / COUNTER ############\n"
r"(?: # start non-capture group\n"
r" # the aim is to skip lines that don't contain blue\n"
r" # and capture a corresponding digit sequence\n"
r" (?: # skip one line that doesn't contain blue\n"
r" ^ # beginning of line\n"
r" (?:(?!blue)[^\r\n])* # zero or more chars\n"
r" # that do not start blue\n"
r" (?:\r?\n) # newline chars\n"
r" ) \n"
r"# With each line skipped, let Group 1 capture\n"
r"# an ever-growing portion of the string of numbers\n"
r" (?= # lookahead\n"
r" .* # Go to the end of the file\n"
r" ( # start Group 1\n"
r" ~\d+ # match a tilde and 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" # the possessive + forbids backtracking\n\n\n"
r".*? # lazily match any chars up to...\n"
r"blue # match blue\n"
r".* # Get to the end of the data\n"
r"~ # match a tilde\n"
r"\K # drop what we matched so far\n"
r"\d+ # match digits. This is the match! \n"
r"(?=(?(1)\1)) # if Group 1 has been set, match it\n")
test_str = ("Paint it white\n"
"Paint it black\n"
"Why not blue?\n"
"Or red or brown?\n\n"
"~10~9~8~7~6~5~4~3~2~1")
subst = ""
# 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