# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?>\G(?!^)|^(?:.*?[^\p{P}\h\d\n])?[\p{P}\h]*+1?(?=(?1){10}(?!(?1))))((\d)[\p{P}\h]*+)(?:[^\d\n].*)?"
test_str = (" +18005551212\n"
" 8005551213\n"
" 18005551214\n"
" (800)555-1215\n"
" 800.555.1216\n"
" (800) 555-1217\n"
" 800 555 12 18\n"
" \n"
" stuff before +18005551221 stuff after\n"
" stuff before 8005551222 stuff after\n"
" stuff before 18005551223 stuff after\n"
" stuff before (800)555-1224 stuff after\n"
" stuff before 800.555.1225 stuff after\n"
" stuff before (800) 555-1226 stuff after\n"
" stuff before 800 555 12 27 stuff after\n"
" \n"
" 5551212")
subst = "$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