549 - Create script for exporting Doc as HTML

.gitignore

@@ -2,10 +2,12 @@
 _site
 *.DS_Store
 node_modules
-tools/__pycache__
+*__pycache__
 tools/venv
 tools/files/meetup.ics
 bin/
 lib/
 .venv
-pyvenv.cfg
+pyvenv.cfg
+tools/blog_automation/service_account_key.json
+tools/blog_automation/venv

tools/blog_automation/README.md

@@ -0,0 +1,82 @@
+# Goals of this Automation
+
+# Setup
+## 🔑 Setting up Google Service Account Credentials
+
+To allow our scripts to access Google Drive and export documents, you need to create a **Google Cloud Project**, a **service account**, and download its credentials as a JSON key file.
+
+*Alternatively, you can ask Silke for the service_account_key.json (in which case, you can skip steps 0-3).*
+
+### 0. Create a Google Cloud Project
+1. Go to [Google Cloud Console](https://console.cloud.google.com/).
+2. Open the project selector (top bar) and click **New Project**.
+3. Name the project **`blog-automation`**.
+4. Click **Create**.
+5. Make sure the new project is selected in the top bar.
+
+👉 **Note:** You need the **Project Editor** or **Owner** role on this project to create service accounts and keys.  
+If you’re the one who created the project, you already have these permissions.
+
+### 1. Enable the Drive API
+1. In the left menu, go to **APIs & Services → Library**.
+2. Search for **Google Drive API**.
+3. Click **Enable**.
+
+### 2. Create a Service Account
+1. In the left menu, go to **IAM & Admin → Service Accounts**.
+2. Click **Create Service Account**.
+3. Name it **`blog-exporter`** and add a short description (e.g. *Exports blog content from Google Docs*).
+4. Click **Create and Continue**.  
+   - You do **not** need to assign project-wide roles to this service account.
+   - Just click **Done** once the account is created.
+
+### 3. Generate and Download the JSON Key
+1. Click on the service account you just created.
+2. Go to the **Keys** tab.
+3. Click **Add Key → Create new key**.
+4. Choose **JSON** and click **Create**.
+5. A file will be downloaded (e.g. `blog-exporter-123abc.json`).  
+   - Rename it to **`service_account_key.json`**.  
+   - Move this file into the **`blog_automation`** folder of this repo (the same folder where this README lives).  
+   - **Do not commit this file to Git!** It should already be listed in `.gitignore`.
+
+### 4. Share the Google Drive Folder or Document
+1. In Google Drive, right-click the folder (e.g. `blog_automation`) or a specific Google Doc.
+2. Click **Share**.
+3. Enter the service account’s email (looks like `blog-exporter@blog-automation.iam.gserviceaccount.com`).
+4. Give it at least **Viewer** access.
+5. Save changes.  
+   - Now the service account can read/export files in that folder or doc.
+
+---
+
+✅ At this point you should have:
+- A **Google Cloud Project** called `blog-automation` with the **Drive API enabled**.
+- A **service account** called `blog-exporter`.
+- A local **`service_account_key.json`** file inside your `blog_automation` folder (same place as this README, ignored by git).
+- The service account email added as a **Viewer** to your Google Drive folder or doc.
+
+
+## Set up Virtual Environment & Install Required Package
+- Set up venv `python -m venv venv`
+- `source venv/bin/activate`
+- `pip install -r requirements.txt`
+
+# Automation Script
+
+## Find Document ID
+Each Google Doc has a unique ID in its URL.  
+For example, if the URL is:
+https://docs.google.com/document/d/1ABCDEFghijklmnopQRS_tUVWXyz1234567890/edit
+
+Then the **Document ID** is:
+
+1ABCDEFghijklmnopQRS_tUVWXyz1234567890
+
+Use this ID in your scripts when exporting the document.
+
+## Run Automation
+1. Activate virtual environment: `source venv/bin/activate`
+2. Run the script: `python export_blog.py <DOC_ID>`
+
+

tools/blog_automation/doc_to_html_conversion.py

@@ -0,0 +1,109 @@
+from google.oauth2 import service_account
+from googleapiclient.discovery import build
+import os
+import markdown
+import argparse
+from pathlib import Path
+from googleapiclient.errors import HttpError
+import datetime as dt
+
+# --- Configuration ---
+SERVICE_ACCOUNT_FILE = 'service_account_key.json'
+YAML_HEADER = '''
+---
+layout: post
+title: [TITLE]
+date: [DATE]
+author_name: [AUTHOR]
+author_role: [AUTHOR ROLE]
+blurb_img: [IMG PATH]
+blurb_img_source: [IMG SOURCE (optional)]
+description: [BLOG DESCRIPTION]
+category: [CATEGORY]
+---
+'''
+
+def _current_directory():
+    return Path(__file__).resolve().parent
+
+def _posts_directory():
+    # Path to the directory where the script itself is located
+    script_dir = _current_directory()
+
+    # Construct the path relative to the script’s location
+    posts_dir = (script_dir / "../../_posts").resolve()
+
+    return posts_dir
+
+def _today_date_str():
+    return dt.date.today().isoformat()
+
+def _create_blog_filename_with_date(doc_name, date_str):
+    formatted_blog_title = doc_name.lower().replace(' ', '-').strip()
+    filename = f"{date_str}-{formatted_blog_title}.html"
+    return filename
+
+def export_blog_as_html(document_id, date=None):
+    if date is None:
+        date = _today_date_str()
+    service_account_path = os.path.join(_current_directory(), SERVICE_ACCOUNT_FILE)
+    if not os.path.exists(service_account_path):
+        print(f"ERROR: Service account key file '{service_account_path}' not found.\n"
+              "Please obtain your own Google service account key and place it at this path.\n"
+              "(Never commit this file to version control.)")
+        exit(1)
+    creds = service_account.Credentials.from_service_account_file(
+        service_account_path, 
+        scopes=['https://www.googleapis.com/auth/drive.readonly']
+    )
+    drive = build('drive', 'v3', credentials=creds)
+
+    try:
+        # 1. Get document name from Drive
+        doc_metadata = drive.files().get(fileId=document_id, fields='name').execute()
+        doc_name = doc_metadata.get('name', 'exported_blog')
+        blog_filename = _create_blog_filename_with_date(doc_name, date)
+
+        # 2. Export as Markdown
+        request = drive.files().export_media(
+            fileId=document_id,
+            mimeType='text/markdown'
+        )
+        md_bytes = request.execute()
+    except HttpError as error:
+        if error.resp.status == 404:
+            raise FileNotFoundError(f"Document ID '{document_id}' not found.") from error
+        else:
+            raise
+
+    # 3. Convert Markdown to HTML and save to local file
+    import re
+    html = markdown.markdown(md_bytes.decode('utf-8'))
+    # Remove <strong> tags from inside heading tags (e.g. <h2><strong>Heading</strong></h2> -> <h2>Heading</h2>)
+    html = re.sub(r'<h(\d)><strong>(.+?)</strong></h\1>', r'<h\1>\2</h\1>', html)
+
+    # Remove the first heading if present (e.g. <h1>...</h1> or <h2>...</h2> at the start)
+    html = re.sub(r'^<h[1-6]>.*?</h[1-6]>\s*', '', html, flags=re.DOTALL)
+
+    # Wrap the body in <div class="text-justify">
+    html_body = f'<div class="text-justify">\n{html}\n</div>'
+
+    # YAML front matter
+    yaml_header = YAML_HEADER.replace('[TITLE]', doc_name.title()).replace('[DATE]', date)
+
+    final_html = yaml_header + '\n' + html_body
+
+    posts_dir = _posts_directory()
+    filename = f"{posts_dir}/{blog_filename}.html"
+    with open(filename, 'w', encoding='utf-8') as f:
+        f.write(final_html)
+
+    print(f"Saved HTML to: {filename}")
+
+if __name__ == "__main__":
+    # To run script: `python export_blog.py <DOC_ID> --date <DATE>`
+    parser = argparse.ArgumentParser(description="Export a Google Doc as HTML with custom formatting.")
+    parser.add_argument("doc_id", help="The Google Doc ID to export.")
+    parser.add_argument("--date", help="Date for the blog post (YYYY-MM-DD). If not provided, uses today.", default=None)
+    args = parser.parse_args()
+    export_blog_as_html(args.doc_id, args.date)

tools/blog_automation/requirements.txt

@@ -0,0 +1,23 @@
+cachetools==5.5.2
+certifi==2025.8.3
+charset-normalizer==3.4.2
+google-api-core==2.25.1
+google-api-python-client==2.177.0
+google-auth==2.40.3
+google-auth-httplib2==0.2.0
+google-auth-oauthlib==1.2.2
+googleapis-common-protos==1.70.0
+httplib2==0.22.0
+idna==3.10
+Markdown==3.8.2
+oauthlib==3.3.1
+proto-plus==1.26.1
+protobuf==6.31.1
+pyasn1==0.6.1
+pyasn1_modules==0.4.2
+pyparsing==3.2.3
+requests==2.32.4
+requests-oauthlib==2.0.0
+rsa==4.9.1
+uritemplate==4.2.0
+urllib3==2.5.0