Runs after a scheduled scrape, creates snapshots, diffs content, classifies changes, and fires webhook/email notifications.
// Source: https://github.com/mperkins0155/AnyCrawl | License: MIT | Copyright 2025 AnyForAI
// Provided via justclaw.it.com; keep this notice with the code.
/**
* MonitorPostProcessor — runs after a scheduled scrape execution completes
* successfully. It snapshots content, diffs against the previous run, and fires
* notifications for meaningful changes.
*
* Called from ExecutionLifecycle.finalizeExecution() on the completed branch.
* Must NEVER throw: wrap all errors and log warnings so the execution lifecycle
* is never disrupted.
*/
import { randomUUID } from "crypto";
import {
getDB,
schemas,
eq,
sql,
getMonitorByScheduledTask,
getLatestSnapshot,
} from "@anycrawl/db";
import { getJobResults } from "@anycrawl/db";
import { log, config } from "@anycrawl/
... (truncated -- full source via MCP)
See the full source, get the GitHub permalink, and search 40K more like it.
Get a free API key