Convert WordPress to Dev.to markup

wp_to_devto_regex.py

import re

INFILE = 'from_wp.txt'
OUTFILE = 'for_devto.txt'

patterns = [
(r"<!--[a-zA-Z0-9:\/\s\-\"\{\}\,]*-->",""),
(r"<li>","- "),
(r"</li>",""),
(r"<strong>","**"),
(r"</strong>","**"),
(r"<em>","_"),
(r"</em>","_"),
(r"<ul>","<u>"),
(r"</ul>","</u>"),
(r"<a href=\"([A-Za-z0-9\:\/\.\-\?\=\#\_]*)\">([A-Za-z0-9\s\'\:\.\-\(\)\/\?\=\#\_]*)</a>","[\\2](\\1)"),
(r"<code>","`"),
(r"</code>","`"),
(r"<p>",""),
(r"</p>",""),
(r"<h1>","##"),
(r"</h1>",""),
(r"<h2>","###"),
(r"</h2>",""),
(r"<h3>","####"),
(r"</h3>",""),
(r"</figure>",""),
]

with open(INFILE,encoding='utf-8') as f:
    text = f.read().replace("\n\n","\n")

for patt, repl in patterns:
    text = re.sub(pattern=patt, repl=repl, string=text)

with open(OUTFILE, 'w', encoding='utf-8') as f:
    f.write(text.replace("\n\n","\n"))

print(f"Results are in {OUTFILE}. Remember to upload images manually to Dev.to (if you don't want WordPress bandwidth to be used), but retain <figcaption>...</figcaption> blocks")