Convert a JSON Export of post data from AnchorCMS to individual markdown files grouped by year for consumption by Eleventy
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import json | |
import os | |
from datetime import datetime | |
from markdownify import markdownify # requires installation: https://pypi.org/project/markdownify/ | |
outputDirBase = 'posts/' | |
# open the file | |
with open('blog_posts.json', 'r') as file: | |
post_data = json.load(file) | |
for post in post_data: | |
filename = post['slug'] | |
postTitle = post['title'] | |
postDescription = post['description'] | |
postTag = post['category'] | |
postCreated = post['created'] | |
postUpdated = post['updated'] | |
postContent = post['markdown'] | |
# determine date-based output path | |
# convert created date to datetime object, so we can get the year | |
created = datetime.strptime(postCreated, '%Y-%m-%d %H:%M:%S') | |
# convert the updated date to a datetime object | |
updated = datetime.strptime(postUpdated, '%Y-%m-%d %H:%M:%S') | |
# some updated timestamps are before created timestamps (possibly a bug from the CMS) | |
# set updated to the same time if that's the case, since it doesn't make sense | |
if updated < created: | |
updated = created | |
outputDirFinal = outputDirBase + str(created.year) + '/' | |
# if output directory doesn't exist, create it | |
# on macOS, this requires sudo permissions | |
if not os.path.exists(outputDirFinal): | |
os.makedirs(outputDirFinal) | |
# we read the data, now write to a md file, formatting with front matter for Eleventy | |
newFileName = outputDirFinal + filename + '.md' | |
newFile = open(newFileName, 'w') | |
# start front matter | |
newFile.write('---\n') | |
newFile.write('title: "' + postTitle.replace('"', '\\"') + '"\n') | |
newFile.write('description: "' + postDescription.replace('"', '\\"') + '"\n') | |
newFile.write('date: \'' + created.strftime('%Y-%m-%d') + '\'\n') | |
newFile.write('updated: \'' + updated.strftime('%Y-%m-%d') + '\'\n') | |
newFile.write('tags: [\'' + postTag + '\']\n') | |
newFile.write('---\n\n') | |
# end front matter | |
# uncomment the next line to inject blog archive notice box | |
# newFile.write('{% include "partials/blog-archive-notice.html" %}\n\n') | |
# write the post content, converting from HTML to markdown | |
newFile.write(markdownify(postContent)) | |
# log output | |
print("Wrote: " + newFileName) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
SELECT | |
posts.title, posts.slug, posts.description, posts.created, posts.updated, posts.markdown, categories.title as 'category' | |
FROM `posts` | |
INNER JOIN `categories` | |
on (posts.category = categories.id); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment