# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^!*(?P<title>[A-Za-z0-9].+?)(?:\s+(?P<isbn>[0-9]{10}))?\s+by\s+(?P<author>[A-Z0-9][^(]+)(?=\s\()"
test_str = ("!!Mixed Fortunes - An Economic History of China Russia and the West 0198703635 by Vladimir Popov (Jun 17, 2014 4_1).pdf\n"
"!Mixed Fortunes - An Economic History of China Russia and the West 0198703635 by Vladimir Popov (Jun 17, 2014 4_1).pdf\n"
"Mixed Fortunes - An Economic History of China Russia and the West 0198703635 by Vladimir Popov (Jun 17, 2014 4_1).pdf\n"
"!!Mixed Fortunes - An Economic History of China Russia and the West by Vladimir Popov (Jun 17, 2014 4_1).pdf\n"
"!!Mixed Fortunes - An Economic History of China Russia and the West by 1 Vladimir Popov (Jun 17, 2014 4_1).pdf")
subst = "\\3"
# 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