claudetools/temp/bardach_purge_urls.py

"""
Bardach Contacts - Clear junk businessHomePage values from Microsoft 365.

Targets:
  - All junk contacts with ms-outlook:// URLs
  - Suspicious contact "Facebook" with value "Penfield@1964"
  - Suspicious contact "Megan Billings" with value "John"

Does NOT touch:
  - 10 legitimate websites
  - 1 Facebook page link (DiBella's Restaurant)
"""

import json
import subprocess
import sys
import time

# --- Configuration ---
TENANT_ID = "dd4a82e8-85a3-44ac-8800-07945ab4d95f"
CLIENT_ID = "fabb3421-8b34-484b-bc17-e46de9703418"
CLIENT_SECRET = "~QJ8Q~NyQSs4OcGqHZyPrA2CVnq9KBfKiimntbMO"
SCOPE = "https://graph.microsoft.com/.default"
USER = "barbara@bardach.net"
TOKEN_URL = f"https://login.microsoftonline.com/{TENANT_ID}/oauth2/v2.0/token"
GRAPH_BASE = f"https://graph.microsoft.com/v1.0/users/{USER}/contacts"
ANALYSIS_FILE = "D:/ClaudeTools/temp/bardach_url_analysis.json"
TOKEN_REFRESH_INTERVAL = 200


def get_token():
    """Acquire OAuth2 token via client credentials."""
    result = subprocess.run(
        [
            "curl", "-s", "-X", "POST", TOKEN_URL,
            "-H", "Content-Type: application/x-www-form-urlencoded",
            "-d", f"client_id={CLIENT_ID}&client_secret={CLIENT_SECRET}&scope={SCOPE}&grant_type=client_credentials",
        ],
        capture_output=True, text=True
    )
    data = json.loads(result.stdout)
    if "access_token" not in data:
        print(f"[ERROR] Failed to acquire token: {data}")
        sys.exit(1)
    print("[OK] Token acquired")
    return data["access_token"]


def patch_contact(token, contact_id, display_name, index, total):
    """PATCH a single contact to clear businessHomePage."""
    url = f"{GRAPH_BASE}/{contact_id}"
    result = subprocess.run(
        [
            "curl", "-s", "-o", "/dev/null", "-w", "%{http_code}",
            "-X", "PATCH", url,
            "-H", f"Authorization: Bearer {token}",
            "-H", "Content-Type: application/json",
            "-d", '{"businessHomePage": ""}',
        ],
        capture_output=True, text=True
    )
    http_code = result.stdout.strip()
    success = http_code in ("200", "204")
    if not success:
        print(f"  [FAIL] {index}/{total} - {display_name} - HTTP {http_code}")
    return success


def main():
    # Load analysis data
    with open(ANALYSIS_FILE, "r", encoding="utf-8") as f:
        data = json.load(f)

    # Build target list
    targets = []

    # 1) Junk contacts with ms-outlook:// pattern
    for c in data.get("junk_contacts", []):
        if c.get("url", "").startswith("ms-outlook://"):
            targets.append((c["id"], c["displayName"]))

    # 2) Suspicious contacts: "Facebook" and "Megan Billings"
    for c in data.get("suspicious_contacts", []):
        name = c.get("displayName", "")
        if name == "Facebook" or name == "Megan Billings":
            targets.append((c["id"], c["displayName"]))

    total = len(targets)
    print(f"[INFO] Contacts to patch: {total}")
    if total == 0:
        print("[WARNING] No targets found. Exiting.")
        return

    # Acquire initial token
    token = get_token()

    successes = 0
    failures = 0

    for i, (cid, name) in enumerate(targets, 1):
        # Re-acquire token every TOKEN_REFRESH_INTERVAL operations
        if i > 1 and (i - 1) % TOKEN_REFRESH_INTERVAL == 0:
            print(f"[INFO] Re-acquiring token at operation {i}...")
            token = get_token()

        ok = patch_contact(token, cid, name, i, total)
        if ok:
            successes += 1
        else:
            failures += 1

        # Progress every 50
        if i % 50 == 0 or i == total:
            print(f"[PROGRESS] {i}/{total} done  (success={successes}, fail={failures})")

    print()
    print("=" * 50)
    print(f"[SUMMARY] Total: {total}  Success: {successes}  Failures: {failures}")
    print("=" * 50)


if __name__ == "__main__":
    main()