feat(notion): Add import script for competitor references

import_references_to_notion.py

@@ -0,0 +1,143 @@
+import json
+import os
+import requests
+import sys
+
+# Configuration
+JSON_FILE = 'analysis_robo-planet.de.json'
+TOKEN_FILE = 'notion_token.txt'
+# Root Page ID from notion_integration.md
+PARENT_PAGE_ID = "2e088f42-8544-8024-8289-deb383da3818" 
+DB_TITLE = "Competitive Radar - References"
+
+def load_json_data(filepath):
+    """Loads the analysis JSON data."""
+    try:
+        with open(filepath, 'r') as f:
+            return json.load(f)
+    except FileNotFoundError:
+        print(f"Error: File '{filepath}' not found.")
+        sys.exit(1)
+    except json.JSONDecodeError:
+        print(f"Error: Failed to decode JSON from '{filepath}'.")
+        sys.exit(1)
+
+def load_notion_token(filepath):
+    """Loads the Notion API token."""
+    try:
+        with open(filepath, 'r') as f:
+            return f.read().strip()
+    except FileNotFoundError:
+        print(f"Error: Token file '{filepath}' not found.")
+        sys.exit(1)
+
+def create_database(token, parent_page_id):
+    """Creates the References database in Notion."""
+    url = "https://api.notion.com/v1/databases"
+    headers = {
+        "Authorization": f"Bearer {token}",
+        "Notion-Version": "2022-06-28",
+        "Content-Type": "application/json"
+    }
+    
+    payload = {
+        "parent": {"type": "page_id", "page_id": parent_page_id},
+        "title": [{"type": "text", "text": {"content": DB_TITLE}}],
+        "properties": {
+            "Reference Name": {"title": {}},
+            "Competitor": {"select": {}},
+            "Industry": {"select": {}},
+            "Snippet": {"rich_text": {}},
+            "Case Study URL": {"url": {}}
+        }
+    }
+    
+    print(f"Creating database '{DB_TITLE}'...")
+    response = requests.post(url, headers=headers, json=payload)
+    
+    if response.status_code != 200:
+        print(f"Error creating database: {response.status_code}")
+        print(response.text)
+        sys.exit(1)
+        
+    db_data = response.json()
+    print(f"Database created successfully! ID: {db_data['id']}")
+    return db_data['id']
+
+def add_reference(token, db_id, competitor, reference):
+    """Adds a single reference entry to the database."""
+    url = "https://api.notion.com/v1/pages"
+    headers = {
+        "Authorization": f"Bearer {token}",
+        "Notion-Version": "2022-06-28",
+        "Content-Type": "application/json"
+    }
+    
+    ref_name = reference.get("name", "Unknown Reference")
+    industry = reference.get("industry", "Unknown")
+    snippet = reference.get("testimonial_snippet", "")
+    case_url = reference.get("case_study_url")
+    
+    # Truncate snippet if too long (Notion limit is 2000 chars for text block, but good practice anyway)
+    if len(snippet) > 2000:
+        snippet = snippet[:1997] + "..."
+
+    properties = {
+        "Reference Name": {"title": [{"text": {"content": ref_name}}]},
+        "Competitor": {"select": {"name": competitor}},
+        "Industry": {"select": {"name": industry}},
+        "Snippet": {"rich_text": [{"text": {"content": snippet}}]}
+    }
+    
+    if case_url and case_url.startswith("http"):
+        properties["Case Study URL"] = {"url": case_url}
+        
+    payload = {
+        "parent": {"database_id": db_id},
+        "properties": properties
+    }
+    
+    try:
+        response = requests.post(url, headers=headers, json=payload)
+        response.raise_for_status()
+        print(f"  - Added: {ref_name}")
+    except requests.exceptions.HTTPError as e:
+        print(f"  - Failed to add {ref_name}: {e}")
+        # print(response.text) # Uncomment for debugging
+
+def main():
+    token = load_notion_token(TOKEN_FILE)
+    data = load_json_data(JSON_FILE)
+    
+    # Check if we have reference analysis data
+    ref_analysis = data.get("reference_analysis", [])
+    if not ref_analysis:
+        print("Warning: No reference analysis data found in JSON.")
+        # We proceed anyway to create the DB and show it works, 
+        # but in a real scenario we might want to exit or use dummy data.
+    
+    # 1. Create Database (You could also check if it exists, but for this script we create new)
+    # Ideally, we would search for an existing DB first to avoid duplicates.
+    # For this task, we create it.
+    db_id = create_database(token, PARENT_PAGE_ID)
+    
+    # 2. Iterate and Import
+    print("Importing references...")
+    count = 0
+    for entry in ref_analysis:
+        competitor = entry.get("competitor_name", "Unknown Competitor")
+        refs = entry.get("references", [])
+        
+        if not refs:
+            print(f"Skipping {competitor} (No references found)")
+            continue
+            
+        print(f"Processing {competitor} ({len(refs)} references)...")
+        for ref in refs:
+            add_reference(token, db_id, competitor, ref)
+            count += 1
+            
+    print(f"\nImport complete! {count} references added.")
+
+if __name__ == "__main__":
+    main()