# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^NODE_([0-9]+)_.*_([0-9]+)"
test_str = ("NODE_1_length_59711_cov_84.026979_g0_i0_1 12.8\n"
"NODE_1_length_59711_cov_84.026979_g0_i0_2 18.9\n"
"NODE_2_length_59711_cov_84.026979_g0_i0_1 14.3\n"
"NODE_2_length_59711_cov_84.026979_g0_i0_2 16.1\n"
"NODE_165433_length_59711_cov_84.026979_g0_i0_1 29")
subst = "$1_$2"
# 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