dousha/wp2md-python
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

preserve syntax highlighter language settings

Browse Source
This commit is contained in:
dousha 2025-01-06 00:19:45 +08:00
parent 1f2dde537c
commit b7a5a8dce2
3 changed files with 81 additions and 51 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
.DS_Store vendored Normal file
View File

Binary file not shown.

3
.idea/misc.xml generated
View File

@ -1,4 +1,7 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="Black">
<option name="sdkName" value="wp-migrator" />
</component>
<component name="ProjectRootManager" version="2" project-jdk-name="wp-migrator" project-jdk-type="Python SDK" />
</project>

43
main.py
View File

@ -6,9 +6,11 @@ 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']
@ -32,6 +34,10 @@ def md(html, **options):
return IframeConverter(**options).convert(html)
def code_parser(el):
return el['data-language'][0] if el.has_attr('data-language') else 'text'
mkdirp('output')
with open(in_file, 'r', encoding='utf-8') as f:
@ -56,16 +62,36 @@ for item in items:
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 = 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)))
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:.+?\s*-->', '', content)
content = re.sub(r'<!-- /?wp:((?!syntaxhighlighter).)*\s*-->', '', content)
content = re.sub(r'<!--more-->', '<p class="more">:::more:::</p>', content)
content = '\n'.join([s.strip() for s in content.splitlines() if s.strip()])
content = md(content).strip() + '\n'
frontmatter = f"---\nlayout: {post_type}\nid: {post_id}\ntitle: \"{title}\"\ncreator: \"{creator}\"\ndate: {date}\ncategories:\n{categories}\ntags:\n{tags}\ndraft: {'yes' if status == 'draft' else 'no'}\npublished: {'yes' if status == 'publish' else 'no'}\n---\n\n"
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:
@ -77,7 +103,8 @@ for item in items:
filename_disambiguation = 1
while os.path.exists(filename_candidate):
filename_candidate = "output/" + title_slug + "_(" + str(filename_disambiguation) + ").md"
filename_candidate = "output/" + title_slug + "_(" + str(
filename_disambiguation) + ").md"
filename_disambiguation = filename_disambiguation + 1
with open(filename_candidate, 'w', encoding='utf-8') as f: