russellballestrini/russell.ballestrini.net
1
0
Fork 0
Code Issues Pull requests 1 Projects Releases Packages Wiki Activity Actions

Switch blog.json from embedded content to content_url links

Browse source 
Changes blog.json generation to link to hosted markdown files instead of
embedding full content. Each post now includes a content_url field pointing
to {site_url}/{slug}/index.md. This significantly reduces blog.json file
size while maintaining full content access via standard HTTP requests.

Updated README.rst to document the new linking behavior & how blog.json works.
This commit is contained in:
russell@unturf.com 2026-01-20 03:21:19 -05:00
parent 2bda81d294
commit d8cf83e051
2 changed files with 13 additions and 24 deletions
Download patch file Download diff file Expand all files Collapse all files

29
lib/generate_jsonblog.py
View file

@ -1,7 +1,7 @@
#!/usr/bin/env python3
"""
Generate JSON Blog (jsonblog.dev) format - single JSON file with all posts.
Uses Markdown content from index.md files generated by rst2md.py.
Links to Markdown files (index.md) generated by rst2md.py instead of embedding content.
"""
import json
@ -109,20 +109,8 @@ def parse_atom_feed(atom_path):
return feed_info, entries
def load_markdown_content(output_dir, slug):
"""Load markdown content from index.md file."""
md_path = output_dir / slug / 'index.md'
if md_path.exists():
try:
return md_path.read_text(encoding='utf-8')
except Exception as e:
print(f"Warning: Could not read {md_path}: {e}")
return None
return None
def generate_jsonblog(atom_path, output_dir, site_url):
"""Generate JSON Blog format with Markdown content."""
"""Generate JSON Blog format with links to Markdown content."""
feed_info, entries = parse_atom_feed(atom_path)
jsonblog = {
@ -146,15 +134,12 @@ def generate_jsonblog(atom_path, output_dir, site_url):
'createdAt': entry['createdAt'],
}
# Try to load markdown content
md_content = load_markdown_content(output_dir, entry['slug'])
if md_content:
post['content'] = md_content
# Check if markdown file exists, then link to it
md_path = output_dir / entry['slug'] / 'index.md'
if md_path.exists():
post['content_url'] = f"{site_url}/{entry['slug']}/index.md"
post['content_type'] = 'markdown'
markdown_found += 1
else:
# Fallback to plain text from HTML
post['content'] = entry['content']
if entry['updatedAt'] and entry['updatedAt'] != entry['createdAt']:
post['updatedAt'] = entry['updatedAt']
@ -170,7 +155,7 @@ def generate_jsonblog(atom_path, output_dir, site_url):
jsonblog['posts'].append(post)
print(f"Generated {len(jsonblog['posts'])} posts ({markdown_found} with markdown content)")
print(f"Generated {len(jsonblog['posts'])} posts ({markdown_found} with markdown links)")
return jsonblog