# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
<div\b # Start of outer DIV start tag.
[^>]*? # Lazily match up to id attrib.
\bclass\s*+=\s*+ # id attribute name and =
([\'"]?+) # $1: Optional quote delimiter.
\basd\b # specific ID to be matched.
(?(1)\1) # If open quote, match same closing quote
[^>]*+> # remaining outer DIV start tag.
( # $2: DIV contents. (may be called recursively!)
(?: # Non-capture group for DIV contents alternatives.
# DIV contents option 1: All non-DIV, non-comment stuff...
[^<]++ # One or more non-tag, non-comment characters.
# DIV contents option 2: Start of a non-DIV tag...
| < # Match a "<", but only if it
(?! # is not the beginning of either
/?div\b # a DIV start or end tag,
| !-- # or an HTML comment.
) # Ok, that < was not a DIV or comment.
# DIV contents Option 3: an HTML comment.
| <!--.*?--> # A non-SGML compliant HTML comment.
# DIV contents Option 4: a nested DIV element!
| <div\b[^>]*+> # Inner DIV element start tag.
(?2) # Recurse group 2 as a nested subroutine.
</div\s*> # Inner DIV element end tag.
)*+ # Zero or more of these contents alternatives.
) # End 2$: DIV contents.
</div\s*>
"""
test_str = ("<div>\n"
" <div class=\"asd\">\n"
" <div>\n"
" <div>\n"
" Hello\n"
" </div>\n"
" </div>\n"
" </div>\n"
"</div>")
matches = re.search(regex, test_str, re.MULTILINE | re.DOTALL | re.IGNORECASE | re.VERBOSE)
if matches:
print ("Match was found at {start}-{end}: {match}".format(start = matches.start(), end = matches.end(), match = matches.group()))
for groupNum in range(0, len(matches.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = matches.start(groupNum), end = matches.end(groupNum), group = matches.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