# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^ *(\d*) *(\d*) *(\d+\.\d+)(.*)(\(\d+\))$"
test_str = (" 0000000125 1478759 9.2 The Shawshank Redemption (1994)\n"
" 0000000125 1014575 9.2 The Godfather (1972)\n"
" 0000000124 683611 9.0 The Godfather: Part II (1974)\n"
" 0000000124 1451861 8.9 The Dark Knight (2008)\n"
" 0000000124 1150611 8.9 Pulp Fiction (1994)\n"
" 0000000133 750978 8.9 Schindler's List (1993)")
subst = "$1 $2 $3 $4 $5"
# 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