# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^\S+\h+(\S+)\R\K(?:\S+\h+\1(?:\R|\Z))+"
test_str = ("lineA 12345\n"
"lineB 12345\n"
"lineC 12345\n"
"lineD 788878\n"
"lineE 110881\n"
"lineF 110881\n"
"lineG 110881\n"
"lineH 287778\n"
"lineJ 251287\n"
"lineK 242424\n"
"lineL 242424\n"
"lineM 242424")
subst = ""
# You can manually specify the number of replacements by changing the 4th argument
result = re.sub(regex, subst, test_str, 0, re.MULTILINE)
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