导出到数据仓库

import json
from datetime import datetime, timedelta, timezone

LISTS = {"cards": "/v1/cards", "collections": "/v1/collections", "users": "/v1/users", "groups": "/v1/groups"}


def read_list(path, since):
    """Every object of a list, changed since `since` (or all of them). The next page keeps the filters of the first."""
    params = {"limit": 200}
    if since:
        params["updated_since"] = (since - timedelta(minutes=1)).isoformat()
    while params:
        response = session.get(BASE + path, params=params, timeout=120)
        response.raise_for_status()
        body = response.json()
        items = body["data"] if isinstance(body, dict) and "data" in body else body
        yield from items
        if isinstance(body, dict) and "data" in body:
            params = {**params, "cursor": body["next_cursor"]} if body.get("has_more") else None
        else:
            cursor = response.headers.get("X-Next-Cursor")
            params = {**params, "cursor": cursor} if cursor else None


def read_events(cursor):
    """New events of the feed after `cursor` (or from the start of the 30 days), and the cursor to save."""
    events = []
    params = {"limit": 200, **({"cursor": cursor} if cursor else {})}
    while True:
        page = api("GET", "/v1/webhook-events?" + requests.compat.urlencode(params))
        events += page["data"]
        params["cursor"] = page["next_cursor"]
        if not page["has_more"]:
            return events, page["next_cursor"]


def run(state, warehouse):
    started_at = datetime.now(timezone.utc)
    since = state.get("since")
    for table, path in LISTS.items():
        for obj in read_list(path, since if table == "cards" else None):
            warehouse.upsert(f"sursa_{table}", obj["id"], json.dumps(obj))

    events, feed_cursor = read_events(state.get("feed_cursor"))
    for event in events:
        warehouse.insert_once("sursa_events", event["id"], json.dumps(event))
        if event["type"] == "card.deleted":
            warehouse.delete("sursa_cards", event["object"]["id"])

    warehouse.save_state({"since": started_at, "feed_cursor": feed_cursor})