# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
(?: ([^";\r\n]*) #1 value without quotes or
| \x20* ("(?:[^"]+|"")*") \x20* #2 value inside quotes
)
(?: (;) #3 values delimiter or
| [\r\n]+ # rows delimiter
)
"""
test_str = ("501 ; 8300000000000 ; \";Автономный ;\"\";округ\"\"\n"
" \"\"Ненецкий\"\";\";test1\n"
" 751;8600800000000; \" Автономный округ \"\"Ханты-Мансийский\"\", Район Советский\" ;\n"
" 1755;8700300000000;Автономный округ Чукотский, Район Билибинский\n"
" 1725;7501900000000;Край Забайкальский, Район Петровск-Забайкальский\n\n"
" ;;\n"
" 711;2302100000000;Край Краснодарский, Район Лабинский\n"
" 729;2401600000000;Край Красноярский, Район Иланский\n"
" 765;2700700000000;Край Хабаровский, Район Вяземский")
subst = "\\1\\2\\x01\\3\\x02"
# You can manually specify the number of replacements by changing the 4th argument
result = re.sub(regex, subst, test_str, 0, re.DOTALL | re.VERBOSE)
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