Created
September 27, 2017 13:02
-
-
Save filipsPL/91eab98b8ba9f7454a49661f1cce71ba to your computer and use it in GitHub Desktop.
Super simple TOC generator from a ready HTML file.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# -*- coding: utf-8 -*- | |
from re import sub | |
fname = "FAQ.html" | |
header="<h4>" | |
outfile = "FAQ+TOC.html" | |
#-----------------------------------------# | |
with open(fname) as f: | |
content = f.readlines() | |
content = [x.strip() for x in content] | |
body = "" | |
toc = "<ul>\n" | |
for line in content: | |
if line.startswith(header): | |
plainText = sub('<[^<]+?>', '', line) | |
kotwica = sub(' |,|\.|\+|\?|\!|/', '', plainText) | |
#print kotwica | |
body += "<a name='%s'></a>%s\n" % (kotwica, line) | |
toc += " <li><a href='#%s'>%s</a></li>\n" % (kotwica, plainText) | |
else: | |
body += line + "\n" | |
toc += "</ul>\n\n" | |
#print "---------------------" | |
#print toc | |
# replace <body> with <body> + TOC | |
content = body.replace("<body>", "<body>\n\n" + toc) | |
f = open( outfile, 'w' ) | |
f.write(content) | |
f.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment