Created
November 9, 2023 01:21
-
-
Save lordjabez/cc72fa8f4e11ef4f39f1ddefa486ae5f to your computer and use it in GitHub Desktop.
Extract all posts from a Wordpress blog using the API
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
#!/usr/bin/env python3 | |
import datetime | |
import sys | |
import cachier | |
import requests | |
blog_domain = sys.argv[1] | |
@cachier.cachier(stale_after=datetime.timedelta(days=1)) | |
def get_posts(blog_domain, page): | |
print(blog_domain, page) | |
api_url = f'https://{blog_domain}/wp-json/wp/v2/posts' | |
params = {'per_page': 10, 'page': page} | |
response = requests.get(api_url, params=params) | |
response.raise_for_status() | |
return response.json() | |
def download_all_posts(blog_domain): | |
all_posts = [] | |
page = 1 | |
while True: | |
posts = get_posts(blog_domain, page) | |
if not posts: | |
break | |
all_posts.extend(posts) | |
page += 1 | |
return all_posts | |
posts = download_all_posts(blog_domain) | |
for post in posts: | |
print(post['title']['rendered']) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment