Automate blogpost imports with rss (#13472)

* chore: add python script to fetch blog content and create post

* chore: implement scheduled action to run script and create pr

* Apply suggestions from code review

* Update action.yml

---------

Co-authored-by: Julien Genestoux <julien.genestoux@gmail.com>

.github/actions/blog/action.yml

@@ -0,0 +1,36 @@
+name: Fetch and Create Blog Posts
+description: Fetches the latest blog posts from the Unlock Protocol blog and creates new posts in the website repository.
+on:
+  schedule:
+    - cron: '0 0 * * *'  # Run once per day at midnight
+  pull_request:
+
+jobs:
+  fetch_and_create_posts:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.x'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install feedparser requests
+
+      - name: Fetch RSS feed and create posts
+        run: python rss_feed.py
+
+      - name: Create Pull Request
+        uses: peter-evans/create-pull-request@v4
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          commit-message: "Add new blog posts"
+          title: "New blog posts from RSS feed"
+          body: "Automatically generated PR to add new blog posts fetched from the RSS feed."
+          branch: new-blog-posts

.github/actions/blog/rss_feed.py

@@ -0,0 +1,60 @@
+import os
+import re
+import requests
+import feedparser
+from datetime import datetime
+
+# Fetch the RSS feed
+rss_url = 'https://paragraph.xyz/api/blogs/rss/@unlockprotocol'
+feed = feedparser.parse(rss_url)
+
+# Create the base directory for storing blog posts
+blog_dir = '../../../unlock-protocol-com/blog'
+os.makedirs(blog_dir, exist_ok=True)
+
+# Iterate over each post in the feed
+for entry in feed.entries:
+    # Extract post details
+    title = entry.title
+    subtitle = entry.subtitle if 'subtitle' in entry else ''
+    author_name = entry.author
+    publish_date = entry.published
+    description = entry.summary
+    image_url = entry.image.href if 'image' in entry else ''
+
+    # Generate a slug for the blog post
+    slug = re.sub(r'[^\w\-_\. ]', '_', title).lower().replace(' ', '_')
+
+    # Create a directory for the blog post images
+    post_images_dir = f'../../../unlock-protocol-com/public/images/blog/{slug}'
+    os.makedirs(post_images_dir, exist_ok=True)
+
+    # Fetch and save the image locally
+    local_image_path = ''
+    if image_url:
+        image_filename = os.path.basename(image_url)
+        local_image_path = os.path.join(post_images_dir, image_filename)
+        response = requests.get(image_url)
+        with open(local_image_path, 'wb') as f:
+            f.write(response.content)
+
+    # Create the post content
+    post_content = f'''---
+title: "{title}"
+subtitle: "{subtitle}"
+authorName: "{author_name}"
+publishDate: "{publish_date}"
+description: "{description}"
+image: "../../../unlock-protocol-com/public/images/blog/{slug}/{image_filename}"
+---
+
+{entry.content[0].value}
+'''
+
+    # Generate the filename for the blog post
+    post_filename = f'{slug}.md'
+    post_file_path = os.path.join(blog_dir, post_filename)
+
+    # Save the post to a file
+    with open(post_file_path, 'w') as f:
+        f.write(post_content)