# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?:^|\ |\n)(((?:(?:http(?:s)?\:)?(?:\/\/))|(?:\/\/))?(?:(?=[a-z0-9\-\.]{1,255}(?=\/|\ |$|\:|\n|\?|\,|\!))(?:(?:(?:[a-z0-9]{1}(?:[a-z0-9\-]{1,62})?\.){1,127})[a-z]{2,}(?:\.[a-z]{2})?))(?:[a-z0-9\/\-\_\%\?\&\!\$\'\,\(\)\*\.\+\=\;])*?)(?=$|\.(?=\ |$)|\:|\n|\ |\?(?=\ |$)|\,|\!)"
test_str = ("I really like to go to google.com and google stuff.\n"
" <br>\n"
" I also like http://hercdev.io, both are pretty cool!\n"
"http://google.com\n"
" <br>\n"
" This is the url to an image: https://objects.dreamhost.com/herc-scripts/chicken_sombrero.gif\n"
" <br>\n"
" But this is the actual image: <img src=\"https://objects.dreamhost.com/herc-scripts/chicken_sombrero.gif\" style=\"max-width: 100px;\" />\n"
" <br>\n"
" Note that the url to the image in the <img> tag is unaffected. This is true for things that are already links also, like <a href=\"http://google.com\" target=\"_blank\">this.</a>")
subst = "<a href=\"$1\">$1</a>"
# You can manually specify the number of replacements by changing the 4th argument
result = re.sub(regex, subst, test_str, 0, re.IGNORECASE)
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