120 lines
3.6 KiB
Python
120 lines
3.6 KiB
Python
#!/usr/bin/env python3
|
|
# encoding: utf-8
|
|
|
|
from bs4 import BeautifulSoup
|
|
from slugify import slugify
|
|
from markdownify import MarkdownConverter
|
|
import os
|
|
import re
|
|
import json
|
|
|
|
in_file = 'wpexport20241219.xml'
|
|
|
|
|
|
class IframeConverter(MarkdownConverter):
|
|
def convert_iframe(self, el, text, convert_as_inline):
|
|
src = el['src']
|
|
if 'youtube' in src:
|
|
code = re.search(r'embed/([^?]+)', src).group(1)
|
|
return f"::: youtube {code}\n:::\n"
|
|
|
|
if 'steam' in src:
|
|
code = re.search(r'\/([0-9]+)', src).group(1)
|
|
return f"::: steam {code}\n:::\n"
|
|
|
|
return f"::: iframe {src}\n:::\n"
|
|
|
|
|
|
def mkdirp(path):
|
|
if not os.path.exists(path):
|
|
os.makedirs(path)
|
|
|
|
|
|
def md(html, **options):
|
|
return IframeConverter(**options).convert(html)
|
|
|
|
|
|
def code_parser(el):
|
|
if not el.has_attr('data-language'):
|
|
return 'text'
|
|
|
|
lang = el['data-language']
|
|
if lang == 'jscript':
|
|
return 'js'
|
|
|
|
return lang
|
|
|
|
|
|
mkdirp('output')
|
|
|
|
with open(in_file, 'r', encoding='utf-8') as f:
|
|
raw_content = f.read()
|
|
|
|
soup = BeautifulSoup(raw_content, 'xml')
|
|
|
|
items = soup.find_all('item')
|
|
print(f"{len(items)} items found")
|
|
|
|
for item in items:
|
|
post_type_raw = item.find('wp:post_type', recursive=False)
|
|
if post_type_raw is None:
|
|
continue
|
|
|
|
post_type = post_type_raw.contents[0]
|
|
if post_type != 'page' and post_type != 'post':
|
|
continue
|
|
|
|
post_id = item.find('wp:post_id', recursive=False).contents[0]
|
|
title = item.find('title', recursive=False).contents[0]
|
|
creator = item.find('dc:creator', recursive=False).contents[0]
|
|
date = item.find('wp:post_date', recursive=False).contents[0]
|
|
status = item.find('wp:status', recursive=False).contents[0]
|
|
tags = item.findAll('category', {'domain': 'post_tag'})
|
|
tags = '\n'.join(list(map(lambda x: ' - ' + x.contents[0], tags)))
|
|
categories = item.findAll('category', {'domain': 'category'})
|
|
categories = '\n'.join(
|
|
list(map(lambda x: ' - ' + x.contents[0], categories)))
|
|
content = item.find('content:encoded', recursive=False).contents[0]
|
|
content = re.sub(r'<!-- /?wp:((?!syntaxhighlighter).)*\s*-->', '', content)
|
|
content = re.sub(r'<!--more-->', '<p class="more">:::more:::</p>', content)
|
|
lines = [s for s in content.splitlines()]
|
|
for i in range(len(lines)):
|
|
line = lines[i]
|
|
if line.startswith('<!-- wp:syntaxhighlighter/code'):
|
|
possibleParams = line[30:-4].strip()
|
|
if possibleParams == '':
|
|
continue
|
|
params = json.loads(possibleParams)
|
|
nextline = lines[i + 1]
|
|
if 'language' in params:
|
|
nextline = nextline[
|
|
:4] + f" data-language={params['language']} " + nextline[
|
|
4:]
|
|
if 'highlightLines' in params:
|
|
nextline = nextline[
|
|
:4] + f" data-highlight={params['highlightLines']} " + nextline[
|
|
4:]
|
|
lines[i + 1] = nextline
|
|
|
|
content = '\n'.join(lines)
|
|
content = md(content, code_language_callback=code_parser).strip() + '\n'
|
|
frontmatter = f"---\nlayout: {post_type}\nid: {post_id}\ntitle: \"{title}\"\ncreator: \"{creator}\"\ndate: {date}\ncategories:\n{categories}\ntags:\n{tags}\ndraft: {'true' if status == 'draft' else 'false'}\npublished: {'true' if status == 'publish' else 'false'}\n---\n\n"
|
|
|
|
title_slug = slugify(title)
|
|
if len(title_slug) < 1:
|
|
title_slug = 'untitled'
|
|
|
|
output_folder = 'output/' + str(date)[:4] + '/' + str(date)[5:7] + '/'
|
|
mkdirp(output_folder)
|
|
filename_candidate = output_folder + title_slug + ".md"
|
|
filename_disambiguation = 1
|
|
|
|
while os.path.exists(filename_candidate):
|
|
filename_candidate = "output/" + title_slug + "_(" + str(
|
|
filename_disambiguation) + ").md"
|
|
filename_disambiguation = filename_disambiguation + 1
|
|
|
|
with open(filename_candidate, 'w', encoding='utf-8') as f:
|
|
f.write(frontmatter)
|
|
f.write(content)
|