# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"[A-Za-zА-Яа-я0-9]+|[^A-Za-zА-Яа-я0-9]+"
test_str = ("Популярные теги дня\n\n"
" javascript\n"
" JavaScript\n"
" 32k подписчиков 28k вопросов \n"
" php\n"
" PHP\n"
" 24k подписчиков 32k вопросов \n"
" html\n"
" HTML\n"
" 28k подписчиков 24k вопросов \n"
" css\n"
" CSS\n"
" 24k подписчиков 20k вопросов \n"
" веб-разработка\n"
" Веб-разработка\n"
" 24k подписчиков 8k вопросов \n"
" mysql\n"
" MySQL\n"
" 18k подписчиков 8k вопросов \n"
" jquery\n"
" jQuery\n"
" 23k подписчиков 12k вопросов \n"
" python\n"
" Python\n"
" 17k подписчиков 7k вопросов \n"
" wordpress\n"
" WordPress\n"
" 4k подписчиков 7k вопросов \n"
" программирование\n"
" Программирование\n"
" 25k подписчиков 8k вопросов \n\n")
subst = ""
# You can manually specify the number of replacements by changing the 4th argument
result = re.sub(regex, subst, test_str, 0)
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