# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^[\t ]*host[\t ]+(.+?)[\t ]*\n(?:(?!(?:^[\t ]*#.*\n)*[\t ]*host\b)[\t ]*(?:(\w+)\b(?:[\t ]*=[\t ]*|[\t ]+)(.*)|#.*)?(?:\n|\Z))+"
test_str = ("Host test \n"
" Hostname test.domain.com\n"
" User james\n"
" Port 22\n"
" # Comment\n"
" IdentityFile ~/.ssh/key.pub\n\n"
"# With 2 aliases\n"
"Host test2 test-2\n"
" Hostname test2.domain.com\n"
" User = james\n"
" Port=22\n"
" # Port 23\n"
" IdentityFile = ~/.ssh/key2.pub\n\n"
"# For all hosts except test2, activate compression and set log level:\n"
"Host * !test2\n"
" Compression yes\n"
" LogLevel INFO\n\n"
" IdentityFile ~/.ssh/id_rsa\n\n"
"Host *.sweet.home\n"
" Hostname 192.168.2.17\n"
" User tom\n"
" IdentityFile \"~/.ssh/id tom.pub\" # If has spaces, then quote it.\n\n"
"# With a lot of spaces between lines\n"
"Host localhost\n\n"
" Hostname 127.0.0.*\n\n"
" IdentityFile ~/.ssh/id_rsa\n\n"
"# Without empty lines between Host definitions:\n"
"Host dummy\n"
" Hostname ssh.dummy.com\n"
" User user\n"
"Host dummy2\n"
" Hostname ssh.dummy2.com\n"
" User user")
matches = re.finditer(regex, test_str, re.IGNORECASE | 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