Files
Brancheneinstufung2/import_competitive_radar.py
Floke d8665697b2 feat(Notion): Refactor product DBs for GTM strategy
- Implements a 3-tier database architecture (Canonical Products, Portfolio, Companies) to separate product master data from company-specific portfolio information.

- Upgrades import_competitive_radar.py to an intelligent "upsert" script that prevents duplicates by checking for existing entries before importing.

- This enables detailed GTM strategy tracking for RoboPlanet products while monitoring competitor portfolios.

- Updates documentation to reflect the new architecture and import process.
2026-01-22 20:33:55 +00:00

179 lines
6.9 KiB
Python

import json
import requests
import sys
# --- CONFIGURATION ---
JSON_FILE = 'analysis_robo-planet.de-4.json'
NOTION_TOKEN = "" # Will be loaded from file
HEADERS = {
"Authorization": f"Bearer {NOTION_TOKEN}",
"Content-Type": "application/json",
"Notion-Version": "2022-06-28",
}
# --- DATABASE IDs ---
COMPANIES_DB_ID = "2e688f42-8544-8158-8673-d8b1e3eca5b5"
CANONICAL_PRODUCTS_DB_ID = "2f088f42-8544-81d5-bec7-d9189f3bacd4"
PORTFOLIO_DB_ID = "2e688f42-8544-81df-8fcc-f1d7f8745e00"
LANDMINES_DB_ID = "" # Optional: Add if you want to re-import landmines
REFERENCES_DB_ID = "" # Optional: Add if you want to re-import references
# --- API HELPERS ---
def query_db(db_id, filter_payload=None):
"""Retrieves all pages from a Notion database, with optional filter."""
url = f"https://api.notion.com/v1/databases/{db_id}/query"
all_pages = []
start_cursor = None
while True:
payload = {}
if start_cursor:
payload["start_cursor"] = start_cursor
if filter_payload:
payload["filter"] = filter_payload
response = requests.post(url, headers=HEADERS, json=payload)
if response.status_code != 200:
print(f"Error querying DB {db_id}: {response.status_code}")
print(response.json())
return None
data = response.json()
all_pages.extend(data["results"])
if data.get("has_more"):
start_cursor = data["next_cursor"]
else:
break
return all_pages
def create_page(db_id, properties):
"""Creates a new page in a Notion database."""
url = "https://api.notion.com/v1/pages"
payload = {"parent": {"database_id": db_id}, "properties": properties}
response = requests.post(url, headers=HEADERS, data=json.dumps(payload))
if response.status_code == 200:
return response.json()
else:
print(f"Error creating page in DB {db_id}: {response.status_code}")
print(response.json())
return None
# --- STATE AWARENESS HELPERS ---
def get_existing_items_map(db_id, name_property="Name"):
"""Fetches all items from a DB and returns a map of {name: id}."""
print(f"Fetching existing items from DB {db_id} to build cache...")
pages = query_db(db_id)
if pages is None:
sys.exit(f"Could not fetch items from DB {db_id}. Aborting.")
item_map = {}
for page in pages:
try:
item_name = page["properties"][name_property]["title"][0]["text"]["content"]
item_map[item_name] = page["id"]
except (KeyError, IndexError):
continue
print(f" - Found {len(item_map)} existing items.")
return item_map
def get_existing_portfolio_links(db_id):
"""Fetches all portfolio links and returns a set of (company_id, product_id) tuples."""
print(f"Fetching existing portfolio links from DB {db_id}...")
pages = query_db(db_id)
if pages is None:
sys.exit(f"Could not fetch portfolio links from DB {db_id}. Aborting.")
link_set = set()
for page in pages:
try:
company_id = page["properties"]["Related Competitor"]["relation"][0]["id"]
product_id = page["properties"]["Canonical Product"]["relation"][0]["id"]
link_set.add((company_id, product_id))
except (KeyError, IndexError):
continue
print(f" - Found {len(link_set)} existing portfolio links.")
return link_set
# --- MAIN LOGIC ---
def main():
global NOTION_TOKEN, HEADERS
try:
with open("notion_token.txt", "r") as f:
NOTION_TOKEN = f.read().strip()
HEADERS["Authorization"] = f"Bearer {NOTION_TOKEN}"
except FileNotFoundError:
print("Error: `notion_token.txt` not found.")
return
# --- Phase 1: State Awareness ---
print("\n--- Phase 1: Reading current state from Notion ---")
companies_map = get_existing_items_map(COMPANIES_DB_ID)
products_map = get_existing_items_map(CANONICAL_PRODUCTS_DB_ID)
portfolio_links = get_existing_portfolio_links(PORTFOLIO_DB_ID)
# --- Phase 2: Processing JSON ---
print("\n--- Phase 2: Processing local JSON file ---")
try:
with open(JSON_FILE, 'r') as f:
data = json.load(f)
except FileNotFoundError:
print(f"Error: `{JSON_FILE}` not found.")
return
for analysis in data.get('analyses', []):
competitor = analysis['competitor']
competitor_name = competitor['name']
print(f"\nProcessing competitor: {competitor_name}")
# --- Phase 3: "Upsert" Company ---
if competitor_name not in companies_map:
print(f" - Company '{competitor_name}' not found. Creating...")
props = {"Name": {"title": [{"text": {"content": competitor_name}}]}}
new_company = create_page(COMPANIES_DB_ID, props)
if new_company:
companies_map[competitor_name] = new_company["id"]
else:
print(f" - Failed to create company '{competitor_name}'. Skipping.")
continue
company_id = companies_map[competitor_name]
# --- Phase 4: "Upsert" Products and Portfolio Links ---
for product in analysis.get('portfolio', []):
product_name = product['product']
# Upsert Canonical Product
if product_name not in products_map:
print(f" - Product '{product_name}' not found. Creating canonical product...")
props = {"Name": {"title": [{"text": {"content": product_name}}]}}
new_product = create_page(CANONICAL_PRODUCTS_DB_ID, props)
if new_product:
products_map[product_name] = new_product["id"]
else:
print(f" - Failed to create canonical product '{product_name}'. Skipping.")
continue
product_id = products_map[product_name]
# Check and create Portfolio Link
if (company_id, product_id) not in portfolio_links:
print(f" - Portfolio link for '{competitor_name}' -> '{product_name}' not found. Creating...")
portfolio_props = {
"Product": {"title": [{"text": {"content": f"{competitor_name} - {product_name}"}}]},
"Related Competitor": {"relation": [{"id": company_id}]},
"Canonical Product": {"relation": [{"id": product_id}]}
}
new_portfolio_entry = create_page(PORTFOLIO_DB_ID, portfolio_props)
if new_portfolio_entry:
portfolio_links.add((company_id, product_id)) # Add to cache to prevent re-creation in same run
else:
print(f" - Portfolio link for '{competitor_name}' -> '{product_name}' already exists. Skipping.")
print("\n--- ✅ Import script finished ---")
if __name__ == "__main__":
main()