# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"([-\.\w]+:\/{2,3})(?!.*[.]{2})(?![-.*\.])((?!.*@\.)[-_\w@^=%&:;~+\.]+(?<![-\.]))(\/[-_\w@^=%&:;/~+\.]+(?<!\.))?\??([-_\w=&@$!|~+]+)*#?([-_\w=&@$!|~+]+)*"
test_str = ("DB_URL=postgresql://postgres:postgres@localhost/postgres?timeout=0\n"
"# Damn, Daniel!\n\n"
"Bob: have you checked https://www.facebook.com?\n"
"lorem https://github.com/justsml?tab=activity#top ipsum\n"
"smb:///winbox/dfs/ - ipp://printer\n"
"leading text chrome-extension://flags??#\n"
"s3://buckets/for/all?true=true\n"
"s3:///////buckets-o-fun\n"
"pkcs11://because-pkcs7-is-weak#only=hash\n"
"\\||@@https://www.google.com <- should match when extracting\n"
"https://we - this is valid\n"
"s3://buckets-o-fun/!hi/raw=val&#keep=hashin'?\n"
"http://aaa.com.co.com:8080/test?dan=dev#den\n"
"hi. pkcs11://because-pkcs7-is-weak\n"
"hi. a://b/c?d=e#f=g && a://b/c?d]\n"
"hi. chrome-extension://flags hi. \n"
"hi. ms-help://good-luck/index.html hi. \n"
"hi. .iris.beep://really/dots. hi. \n"
"hi. iris.beep://really/dots?test=qs hi. \n"
"---\n"
"a://b]/c - Should match `a://b` - it's smallest match.\n"
"http://www.c:ool.com.au - this one's tricky, should match auth URIs: proto://user:pass@host. Including cases where the password could be omitted (`proto://user@host`.)\n"
"boop://really-/ -- technically domains shouldn't end in dashes or other 'special' chars, but this is technically a valid URI.\n"
"---\n"
"a://b./c?d. -- bad dns, trailing dot: tricky w/o look-arounds. (Adding an OR pattern would muddle the returned data indexes.) -- should match `a://b`\n\n\n"
"Invalid Examples:\n"
"https://www...google...com\n"
"https://we@.com\n"
"https://asdas-.com\n"
"http://-apple-.com\n"
"a://(b/c\n"
"chrome-extension)://flags\n"
"ms-help://|good-luck.html\n"
". , ; : ) ] } \n")
matches = re.finditer(regex, test_str, re.IGNORECASE | re.UNICODE | re.MULTILINE)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# 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