#!/usr/bin/env python3 """ Publish 5 SEO articles to dasindonesia.com via WordPress REST API. Upload featured images as WebP 1000x567, set alt text, publish all. """ import requests from requests.auth import HTTPBasicAuth import json import sys import os import re WP_URL = "https://dasindonesia.com/wp-json/wp/v2" USER = "bambangbot" APP_PASSWORD = "u3a1 G2pQ 3SWY f0zI OlGP YAjU" AUTH = HTTPBasicAuth(USER, APP_PASSWORD) IMG_DIR = "/home/mantapman/.hermes/profiles/atun/workspace/artikel-das/featured-images" def get_or_create_category(name): """Get category ID by name, create if not exists.""" r = requests.get(f"{WP_URL}/categories", params={"search": name}, auth=AUTH) r.raise_for_status() cats = r.json() for cat in cats: if cat["name"].lower() == name.lower(): print(f" Found category '{name}' -> ID {cat['id']}") return cat["id"] # Create r = requests.post(f"{WP_URL}/categories", json={"name": name}, auth=AUTH) if r.status_code == 201: print(f" Created category '{name}' -> ID {r.json()['id']}") return r.json()["id"] print(f" WARN: Cannot get/create category '{name}', using default (1)") return 1 def upload_image(filepath, alt_text, filename): """Upload image to WP media library, return media ID.""" with open(filepath, "rb") as f: r = requests.post( f"{WP_URL}/media", auth=AUTH, files={"file": (filename, f, "image/webp")}, data={ "alt_text": alt_text, "caption": alt_text, } ) if r.status_code in (200, 201): media = r.json() print(f" Uploaded image -> ID {media['id']}") return media["id"], media["source_url"] else: print(f" ERROR uploading image: {r.status_code} {r.text[:200]}") return None, None def parse_article(md_path): """Parse markdown file into article data.""" with open(md_path, "r") as f: text = f.read() # Title m = re.search(r'^# Artikel \d+: (.+)', text, re.MULTILINE) title = m.group(1).strip() if m else "Untitled" # SEO fields seo = {} for field in ["SEO Title", "Meta Description", "Slug", "Keyphrase", "Kategori"]: m = re.search(r'\*\*' + field + r':\*\* (.+)', text) seo[field] = m.group(1).strip() if m else "" # Alt text m = re.search(r'\*\*Alt text:\*\* (.+)', text) alt_text = m.group(1).strip() if m else "" # Featured image filename m = re.search(r'\*\*File name:\*\* (.+)', text) fname = m.group(1).strip() if m else "" # Content (between ## Konten and end or next ##) konten_match = re.search(r'## Konten\n\n(.+?)(?=\n---|\n# Artikel|\Z)', text, re.DOTALL) content_raw = konten_match.group(1).strip() if konten_match else "" # Convert to WP Gutenberg HTML content_html = convert_to_wp_html(content_raw) return { "title": title, "seo_title": seo["SEO Title"], "meta_description": seo["Meta Description"], "slug": seo["Slug"], "keyphrase": seo["Keyphrase"], "kategori": seo["Kategori"], "alt_text": alt_text, "fname": fname, "content": content_html, } def convert_to_wp_html(md_text): """Convert markdown-ish content to WP HTML with Gutenberg blocks.""" lines = md_text.split("\n") blocks = [] for line in lines: stripped = line.strip() if not stripped: blocks.append("") continue # Headings if stripped.startswith("### "): blocks.append(f"

{stripped[4:]}

") elif stripped.startswith("## "): blocks.append(f"

{stripped[3:]}

") elif stripped.startswith("# "): blocks.append(f"

{stripped[2:]}

") # Blockquote elif stripped.startswith("> "): blocks.append(f"
{stripped[2:]}
") # Bold/italic list item elif stripped.startswith("- **") or stripped.startswith("* **"): blocks.append(f"
  • {stripped.lstrip('-* ')}
    • ") # Numbered list item elif re.match(r'^\d+[.)]\s', stripped): text = re.sub(r'^\d+[.)]\s', '', stripped) blocks.append(f"
  • {text}
    • ") # Regular bold item elif stripped.startswith("**") and stripped.endswith("**"): blocks.append(f"

    {stripped.strip('*')}

    ") # Regular paragraph else: # Process inline bold, italic, links processed = re.sub(r'\*\*(.+?)\*\*', r'\1', stripped) processed = re.sub(r'\*(.+?)\*', r'\1', processed) processed = re.sub(r'\[(.+?)\]\((.+?)\)', r'\1', processed) blocks.append(f"

    {processed}

    ") # Wrap in Gutenberg blocks html = "" in_list = False for block in blocks: if block.startswith("
  • "): if not in_list: html += "\n" in_list = False if block == "": html += "\n" else: html += f"{block}\n" if in_list: html += "\n" return html def create_post(article, category_id, media_id): """Create WordPress post with Yoast meta.""" post = { "title": article["title"], "content": article["content"], "slug": article["slug"], "status": "publish", "categories": [category_id], "featured_media": media_id, "meta": { "_yoast_wpseo_title": article["seo_title"], "_yoast_wpseo_metadesc": article["meta_description"], "_yoast_wpseo_focuskw": article["keyphrase"], } } r = requests.post(f"{WP_URL}/posts", json=post, auth=AUTH) if r.status_code in (200, 201): data = r.json() print(f" PUBLISHED: {data['link']}") return True else: print(f" ERROR: {r.status_code} - {r.text[:500]}") return False def main(): articles_data = [ { "md": "/home/mantapman/.hermes/profiles/atun/workspace/artikel-das/artikel-1-transmisi-matic.md", "img": os.path.join(IMG_DIR, "artikel-1-transmisi-matic.webp"), "img_filename": "cara-merawat-transmisi-matic-mobil.webp", }, { "md": "/home/mantapman/.hermes/profiles/atun/workspace/artikel-das/artikel-2-ac-mobil.md", "img": os.path.join(IMG_DIR, "artikel-2-ac-mobil.webp"), "img_filename": "penyebab-ac-mobil-tidak-dingin.webp", }, { "md": "/home/mantapman/.hermes/profiles/atun/workspace/artikel-das/artikel-3-balancing-spooring.md", "img": os.path.join(IMG_DIR, "artikel-3-balancing-spooring.webp"), "img_filename": "pentingnya-balancing-dan-spooring-mobil.webp", }, { "md": "/home/mantapman/.hermes/profiles/atun/workspace/artikel-das/artikel-4-biaya-servis-bmw.md", "img": os.path.join(IMG_DIR, "artikel-4-biaya-servis-bmw.webp"), "img_filename": "biaya-servis-mobil-bmw.webp", }, { "md": "/home/mantapman/.hermes/profiles/atun/workspace/artikel-das/artikel-5-memilih-ban-mobil.md", "img": os.path.join(IMG_DIR, "artikel-5-memilih-ban-mobil.webp"), "img_filename": "tips-memilih-ban-mobil-untuk-jalan-indonesia.webp", }, ] success = 0 for i, art in enumerate(articles_data, 1): print(f"\n{'='*60}") print(f"ARTIKEL {i}") print(f"{'='*60}") # Parse article = parse_article(art["md"]) print(f" Title: {article['title']}") print(f" Slug: {article['slug']}") print(f" Keyphrase: {article['keyphrase']}") print(f" Kategori: {article['kategori']}") # Get/create category cat_id = get_or_create_category(article["kategori"]) # Upload image if os.path.exists(art["img"]): media_id, media_url = upload_image(art["img"], article["alt_text"], art["img_filename"]) else: print(f" WARN: Image not found: {art['img']}") media_id = None if media_id: # Create post if create_post(article, cat_id, media_id): success += 1 else: print(f" SKIPPED: No featured image") print(f"\n{'='*60}") print(f"DONE: {success}/{len(articles_data)} articles published") print(f"{'='*60}") if __name__ == "__main__": main()