Clean up WordPress-exported Markdown for Hugo (strip leftover HTML, fix images / code blocks / LaTeX)

wordpress_to_hugo_cleanup.py

import logging
import re
import sys

UPLOADS_URLS = (
    "https://static.infinitescript.com/wordpress/wp-content/uploads",
    "https://infinitescript.com/wordpress/wp-content/uploads",
)

with open(sys.argv[1]) as fp:
    markdown = fp.read()

for url in UPLOADS_URLS:
    markdown = markdown.replace(url, "")
markdown = markdown.replace(" {}", "")
markdown = markdown.replace(" ", " ")
markdown = markdown.replace("&lt;", "<")

# url -> slug
attr_url = re.search(r"url: \/[0-9]{4}\/[0-9]{2}\/[A-Za-z0-9\-]+", markdown)
assert attr_url is not None, "post URL not found in front matter"
attr_url = attr_url.group()
attr_slug = attr_url[attr_url.rfind("/") + 1 :]
markdown = markdown.replace(f"{attr_url}/", f"slug: {attr_slug}")

# Tailing comments after heading
markdown = re.sub(r" \{[#A-Za-z0-9\-]*\.wp-block-heading\}", "", markdown)

# <a>
hyperlinks = re.findall(
    r"<a [A-Za-z0-9= :#&_\"\/\.\-\?]+>[A-Za-z0-9@:_ \-\.\(\)\+]+</a>", markdown
)
for hl in hyperlinks:
    href = re.search(r"href=\"[A-Za-z0-9= :#&_\/\.\-\?]+\"", hl).group()
    text = re.search(r">[A-Za-z0-9@:_ \-\.\(\)\+]+</a>", hl).group()
    markdown = markdown.replace(hl, f"[{text[1:-4]}]({href[6:-1]})")

# <figure>
figures = re.findall(r"<figure [A-Za-z0-9= :#&_\"\/\.\-\?]+>", markdown)
markdown = markdown.replace("</figure>", "")
for f in figures:
    markdown = markdown.replace(f, "")

# Partial converted image
md_images = re.findall(r"\[<img [A-Za-z0-9= ,:#&_\(\)\"\/\.\-\?]+>\]", markdown)
for mi in md_images:
    img_src = re.search(r"src=\"[A-Za-z0-9_\/\-\.]+\"", mi).group()
    img_alt = img_src[img_src.rfind("/") + 1 : img_src.rfind(".")]
    markdown = markdown.replace(mi, f"![{img_alt}]")

# <img>
images = re.findall(r"<img [A-Za-z0-9= ,:#&_\(\)\"\/\.\-\?]+>", markdown)
for i in images:
    img_src = re.search(r"src=\"[A-Za-z0-9\/\-\.]+\"", i).group()
    img_alt = img_src[img_src.rfind("/") + 1 : img_src.rfind(".")]
    markdown = markdown.replace(i, f"![{img_alt}]({img_src[5:-1]})")

# <pre>
codes = re.findall(r"<pre [A-Za-z0-9:;= \"\-]+>", markdown)
markdown = markdown.replace("</pre>", "\n```")
for c in codes:
    language = re.search(r"language=\"[A-Za-z]+\"", c)
    if language is None:
        language = "plain"
        logging.warning(f"Unknown language: {c}")
    else:
        language = language.group()[10:-1]
        language = "plain" if language in ["generic", "raw"] else language

    markdown = markdown.replace(c, f"```{language}\n")

# LaTeX
markdown = markdown.replace(r"\displaystyle", "")
latex = re.findall(
    r"<span class='MathJax_Preview'>[A-Za-z0-9&!_^=,;<> \[\]\|\\\(\)\{\}\+\-\*\/\.]+</span>",
    markdown,
)
for l in latex:
    equation = l[32:-9]
    markdown = markdown.replace(l, f"${equation.strip()}$")

# Dump
with open(sys.argv[1], "w") as fp:
    fp.write(markdown)