Replace GA tags with Matomo

gistfile1.txt

#!/usr/bin/env python

# SPDX-License-Identifier: Apache-2.0
#
# Algorithm borrowed from https://github.com/merobi-hub/SPDXUpdater

import sys
import os
import re

# OLD_TAG_1:
#
# <script type="application/javascript">
# window.ga=window.ga||function(){(ga.q=ga.q||[]).push(arguments)};ga.l=+new Date;
# ga("create", "UA-XXXXXXXXX-1", "auto");
# ga("send", "pageview");
# </script>
# <script async src="https://www.google-analytics.com/analytics.js"></script>
#

OLD_TAG_1_REGEX = "\s*\<script\s+type=\"application/javascript\"\>\s*window.ga.*\n.*\n.*\n.*\n.*analytics.js\"\>\<\/script\>"

# OLD_TAG_2:
#
# <script type="text/javascript">
#     var _gaq = _gaq || [];
#     _gaq.push(['_setAccount', 'UA-XXXXXXXXX-1']);
#     _gaq.push(['_trackPageview']);
# </script>

OLD_TAG_2_REGEX = "\s*\<script\s+type=\"text\/javascript\"\>\s*var\s*_gaq.*\n.*\n.*_trackPageview\S+\s*\<\/script\>"

# OLD_TAG_3:
#
# <script type="application/javascript">
#     var doNotTrack = false;
#     window.ga=window.ga||function(){(ga.q=ga.q||[]).push(arguments)};ga.l=+new Date;
#     ga('create', 'UA-XXXXXXXXX-1', 'auto');
#     ga('send', 'pageview');
# </script>
# <script async src='https://www.google-analytics.com/analytics.js'></script>

OLD_TAG_3_REGEX = "\s*\<script\s+type=\"application\/javascript\"\>\s*\n.*\n\s+window.ga.*\n.*\n.*\n.*\n.*analytics.js\'\>\<\/script\>"

# OLD_FOOTER:
# 
# <div class="footer">This page uses <a href="https://analytics.google.com/">
# Google Analytics</a> to collect statistics. You can disable it by blocking
# the JavaScript coming from www.google-analytics.com. Check our
# <a href="privacy_notice.html">Privacy Policy</a>
# for more details.
# <script type="text/javascript">
#     (function() {
#     var ga = document.createElement('script');
#     ga.src = ('https:' == document.location.protocol ?
#         'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
#     ga.setAttribute('async', 'true');
#     var nodes = document.documentElement.childNodes;
#     var i = -1;
#     var node;
#     do {
#         i++;
#         node = nodes[i]
#     } while(node.nodeType !== Node.ELEMENT_NODE);
#     node.appendChild(ga);
#     })();
# </script>
# </div>

OLD_FOOTER_REGEX = "\s*\<div\s+class=\"footer\"\>[\w\W\n]*appendChild\(ga\).*\n.*\n.*\s*\<\/div\>"

NEW_TAG = '''
<!-- Matomo -->
[...]
</script>
<!-- End Matomo -->'''


def process_file(contents):

    contents = re.sub(OLD_TAG_1_REGEX, NEW_TAG, contents)
    contents = re.sub(OLD_TAG_2_REGEX, NEW_TAG, contents)
    contents = re.sub(OLD_TAG_3_REGEX, NEW_TAG, contents)
    contents = re.sub(OLD_FOOTER_REGEX, '', contents)
    
    return(contents)


dir = sys.argv[1]

for root, dirs, files in os.walk(dir, topdown=False):
    for f in files: 
        if '.html' in f:
            path = os.path.join(root, f)
            with open(path, 'r') as t:
                str_contents = t.read()
                if 'UA-XXXXXXXXX-1' in str_contents:
                    print("found in: " + path)

                    new_contents = process_file(str_contents)

                    with open(path, 'w') as t:
                        t.write(new_contents)