# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
#opening tag
\{(RAW|ACCESS|DWNLINK|MODL|\w+)
#optional attributes
(?>
\{ ([^}]*) }
)?
}
#optional text and closing tag
(?:
( #text:= any char except "{", or a "{" not followed by /commandname
[^{]*+
(?>\{(?!/?\1[{}])[^{]*)*?
)
#closing tag
\{/\1}
)?
"""
test_str = ("<div class=\"blog-list-item blog\"><header class=\"entry-title\">\n"
" <h1>Welcome to our website</h1>\n"
" </header><article id=\"entry-72\" class=\"entry post-72 page et-bg-layout-dark et-white-bg\"><div class=\"jumbotron row\">\n"
"<div class=\"col-md-8\">\n"
"<ul>\n"
"<li>You have a pending job on your neck?…</li>\n"
"<li>Do your company need a website makeover ?…</li>\n"
"<li>Or a competitive web application ? ?…</li>\n"
"<li>Do you need a customized plugin, or a tweak ?…</li>\n"
"<li>Maybe you want a personal website ?…</li>\n"
"<li>Or a graphic for your new project ?…</li>\n"
"</ul>\n"
"<div class=\"bg-primary well\">\n"
"<h4 class=\"text-center text-white shadow\">Track your project as we work it to perfection...</h4>\n"
"</div>\n"
"</div>\n"
"<div class=\"pull-right col-md-4\">\n"
"<h4 class=\"bg-primary text-white well\">Other services we offer</h4>\n"
"{ACCESS{type=500}}\n"
"<ul>\n"
"<li>SEO work for an existing website or new</li>\n"
"<li>Bulk SMS</li>\n"
"<li>E-currency exchange</li>\n"
"<li>Facebook AD</li>\n"
"<li>Google AD</li>\n"
"</ul>\n"
"{/ACCESS}</div>\n"
"{RAW{say=email,access=500}} {RAW} <a class=\"btn button large tall green\" href=\"client-area\">Place new Job now as we deliver at the quickest <em>reasonable time</em></a>{/RAW}</div></article></div>")
matches = re.finditer(regex, test_str, re.IGNORECASE | re.VERBOSE)
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