Initial commit - divination content

extract_divination.py

@@ -0,0 +1,79 @@
+import os
+import re
+from datetime import datetime
+
+markdown_dir = r"c:\Users\David\Resilio Sync\CODE\disinfozone\divination\markdown"
+images_dir = r"c:\Users\David\Resilio Sync\CODE\disinfozone\divination\images"
+
+essays = []
+
+def parse_frontmatter(content):
+    # Very basic frontmatter parser for +++ blocks
+    match = re.search(r'^\+\+\+\s*(.*?)\s*\+\+\+', content, re.DOTALL)
+    if not match:
+        return None
+    
+    fm_text = match.group(1)
+    data = {}
+    for line in fm_text.split('\n'):
+        if '=' in line:
+            key, val = line.split('=', 1)
+            key = key.strip()
+            val = val.strip().strip('"').strip("'")
+            if key == 'images':
+                # Parse list like ['/images/wide29.jpg']
+                images = re.findall(r"['\"](.*?)['\"]", val)
+                data[key] = images
+            else:
+                data[key] = val
+    return data
+
+for filename in os.listdir(markdown_dir):
+    if filename.endswith(".md"):
+        path = os.path.join(markdown_dir, filename)
+        with open(path, 'r', encoding='utf-8') as f:
+            content = f.read()
+            data = parse_frontmatter(content)
+            if data:
+                # Add slug
+                data['slug'] = filename.replace('.md', '.html')
+                if data['slug'] == 'the-weight-of-wonder.html':
+                    data['slug'] = 'the-weight-of-wonder-v3.html'
+                
+                # Infer sigil
+                sigil = None
+                if 'images' in data and data['images']:
+                    banner = data['images'][0]
+                    # banner is like '/images/wide54.jpg' or '/images/onlinemadness-wide.jpg'
+                    basename = os.path.basename(banner)
+                    name_part = basename.replace('-wide.jpg', '').replace('wide', '').replace('.jpg', '')
+                    
+                    if basename.startswith('wide'):
+                        sigil_path = f"/images/div{name_part}.png"
+                    else:
+                        sigil_path = f"/images/{name_part}.png"
+                    
+                    # Verify if sigil exists (rough check)
+                    # For now just use the path
+                    data['sigil'] = sigil_path
+                
+                # Parse date for sorting
+                # format can be 2025-02-09T13:13:13-03:33 or 2025-10-20T22:11:33
+                date_str = data.get('date', '1970-01-01')
+                try:
+                    # Strip timezone for simple sorting
+                    clean_date = date_str.split('T')[0]
+                    data['sort_date'] = datetime.strptime(clean_date, "%Y-%m-%d")
+                except:
+                    data['sort_date'] = datetime(1970, 1, 1)
+                
+                essays.append(data)
+
+# Sort by date descending
+essays.sort(key=lambda x: x['sort_date'], reverse=True)
+
+# Output summary
+print(f"Total essays found: {len(essays)}")
+for e in essays[:5]:
+    print(f"[{e.get('date')}] {e.get('title')} -> {e.get('slug')}")
+    print(f"  Image: {e.get('images')} | Sigil: {e.get('sigil')}")