Last active
December 15, 2025 05:58
-
-
Save gtaylor/bdccbd2143c445819222c4ed243e04ee to your computer and use it in GitHub Desktop.
squarespace-to-astro.py
This file contains hidden or 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
| # /// script | |
| # requires-python = ">=3.12" | |
| # dependencies = [ | |
| # "feedparser", | |
| # "dateparser", | |
| # "markdownify", | |
| # ] | |
| # /// | |
| """ | |
| Horrible, janky script to migrate posts from Squarespace to Astro. | |
| I hope that this is useful to someone as prior art! | |
| 1. Update SQUARESPACE_EXPORT_PATH, OUTPUT_PATH, and TAG_MAP | |
| 2. Run: uv run squarespace-to-astro.py | |
| """ | |
| import json | |
| import markdownify | |
| import dateparser | |
| import feedparser | |
| # Replace with your own path or add logic for a command line arg. | |
| SQUARESPACE_EXPORT_PATH = "/Users/gregtaylor/Downloads/Squarespace-Wordpress-Export-12-15-2025.xml" | |
| # The path to write the resulting markdown files to. | |
| OUTPUT_PATH = "src/data/blog/" | |
| # I wanted to clean my tags up as I was moving over. This is the old vs new map. | |
| TAG_MAP = { | |
| "Drone CI": "CI", | |
| "Quay.io": "CI", | |
| "Minecraft": "Gaming", | |
| } | |
| def map_tags(tags): | |
| """Map tags from Squarespace to our new tag taxonomy.""" | |
| new_tags = [] | |
| for tag in tags: | |
| new_tags.append(TAG_MAP.get(tag, tag)) | |
| return new_tags | |
| def main(): | |
| data = feedparser.parse(SQUARESPACE_EXPORT_PATH) | |
| for entry in data['entries']: | |
| # Squarespace pages are included in the XML but are not blog posts. | |
| content = entry.content[0].value | |
| if not content: | |
| continue | |
| # Old (XML) values | |
| tags = getattr(entry, 'tags', []) | |
| slug = entry.link.split('/')[-1] | |
| # New (to be written) values | |
| new_filename = f"{OUTPUT_PATH}{slug}.md" | |
| new_tags = [] | |
| for tag in tags: | |
| new_tags.append(tag['term']) | |
| new_tags = list(set(map_tags(new_tags))) | |
| new_tags_json = json.dumps(new_tags) | |
| new_pub_datetime = dateparser.parse(entry.published) | |
| new_pub_datetime_iso = new_pub_datetime.isoformat() | |
| markdown_content = markdownify.markdownify(content, strip=['CDATA', 'caption']) | |
| print("=" * 80) | |
| print(f"Post title: {entry.title}") | |
| print(f"Post content: {content}") | |
| print(f"Post date: {entry.published}") | |
| print(f"Post link: {entry.link}") | |
| print(f"Post tags: {getattr(entry, 'tags', [])}") | |
| print("-" * 80) | |
| print(f"New filename: {new_filename}") | |
| print("-" * 80) | |
| new_contents = f"""--- | |
| author: Greg Taylor | |
| pubDatetime: {new_pub_datetime_iso} | |
| modDatetime: | |
| title: {entry.title} | |
| slug: {slug} | |
| featured: false | |
| draft: false | |
| tags: {new_tags_json} | |
| description: "" | |
| --- | |
| {markdown_content} | |
| """ | |
| print(new_contents) | |
| print("=" * 80) | |
| print("\r\n") | |
| with open(new_filename, 'w') as f: | |
| f.write(new_contents) | |
| if __name__ == "__main__": | |
| main() |
Comments are disabled for this gist.