# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^.*?(\+?(?:\d{11,14})|(?:\d{5}\s(?:\d{3}\s\d{3}|\d{6}))|(?:\d{3}(?:\s\d{3}){3})|(?:\d{4}\s\d{3}\s\d{3})).*$"
test_str = ("This is sample. 775 657 7576 sample\n"
"Second sample line. 661-525-5366 sample 123\n"
"Third line sample 466.755.7888.\n"
"07123452670\n\n"
"07812 345 931\n\n"
"07412 123466\n\n"
"00447912345188\n\n"
"+971557017442\n\n"
"+971 557 856 832\n\n"
"0414 934 993\n\n"
"So basically, I need a regex for matching 11 digits. (07123456270)\n\n"
"Matching 5 digits, followed by space, followed by 3 digits, followed by space, followed by 3 digits. (07812 345 931)\n\n"
"Matching 5 digits, followed by space, followed by 6 digits (07412 123466)\n\n"
"Matching 14 digits (12345678901234)\n\n"
"Matching a + sign followed after with 12 digits (+971557017442)\n\n"
"Matching + followed with 3 digits, space, followed by 3 digits, space, 3 more digits (+971 557 856 832)\n\n"
"Last one, 4 digits, space, 3 digits, space, 3 digits. (0414 934 993)\n\n"
"Someone please help")
subst = "$1"
# 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