# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^(\d+)\. ?(.+?)(?:value|vlaue|balue|valie): ?(.+?)[\n\r]{2,}"
test_str = ("Some junk data\n"
"More junk data \n\n"
"1. fairly long key, all on one line\n"
"value: some other text with spaces and stuff\n\n"
"Some junk data\n\n"
"More junk data \n\n"
"2. hey look! another long \n"
"and broken key. on two lines\n"
"value: a different value with some different information\n\n"
"Some junk data\n"
"More junk data \n\n"
"3. hey look! another long line. on a line\n"
"value: a different value \n"
"broken, with some different information\n\n"
"Some junk data\n"
"More junk data ")
subst = ""
# You can manually specify the number of replacements by changing the 4th argument
result = re.sub(regex, subst, test_str, 0, re.MULTILINE | re.DOTALL)
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