# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
@font-face\s* # Match @font-face and some spaces
( # Start group 1
\{ # Match {
(?: # A non-capturing group
[^{}]+ # Match anything except {} one or more times
| # Or
(?1) # Recurse/rerun the expression of group 1
)* # Repeat 0 or more times
\} # Match }
) # End group 1
(*SKIP)(*FAIL) # Skip it
| # Or
url\s*\( # Match url, optionally some whitespaces and then (
\s* # Match optionally some whitespaces
("|'|) # It seems that the quotes are optional according to http://www.w3.org/TR/CSS2/syndata.html#uri
(?!["']?(?:https?://|ftp://)) # Put your negative-rules here (do not match url's with http, https or ftp)
(?:[^\\]|\\.)*? # Match anything except a backslash or backslash and a character zero or more times ungreedy
\2 # Match what was matched in group 2
\s* # Match optionally some whitespaces
\) # Match )
"""
test_str = (".someclass0 {\n"
" background: url('http://images/someimage.png') no-repeat;\n"
"}\n\n"
"@font-face {\n"
" font-family: 'FontAwesome';\n"
" src: url(\"fonts/fontawesome-webfont.eot?v=4.0.3\");\n"
" src: url(\"fonts/fontawesome-webfont.eot?#iefix&v=4.0.3\") format(\"embedded-opentype\"), url(\"fonts/fontawesome-webfont.woff?v=4.0.3\") format(\"woff\"), url(\"fonts/fontawesome-webfont.ttf?v=4.0.3\") format(\"truetype\"), url(\"fonts/fontawesome-webfont.svg?v=4.0.3#fontawesomeregular\") format(\"svg\");\n"
" font-weight: normal;\n"
" font-style: normal;\n"
"}\n\n"
".someclass1 {\n"
" background: url('images/someimage.png') no-repeat;\n"
"}\n\n"
".someclass2 {\n"
" background: url(\"images/someimage.png\") no-repeat;\n"
"}\n\n"
".someclass3 {\n"
" background: url(images/someimage.png) no-repeat;\n"
"}")
matches = re.finditer(regex, test_str, re.VERBOSE | re.DOTALL)
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