sjtu-crawler

Crawl SJTU university announcements and store structured data in SQLite.

69|6|Updated Mar 31, 2026
One-click install
npx skills add https://github.com/xhh678876/openclaw-sjtu --skill sjtu-crawler
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sjtu-crawler
Source: https://github.com/xhh678876/openclaw-sjtu/tree/main/skills/sjtu-crawler
Command: npx skills add https://github.com/xhh678876/openclaw-sjtu --skill sjtu-crawler

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the challenge of manually collecting and understanding scattered Shanghai Jiao Tong University announcements across many campus websites by turning them into structured knowledge.

Core Features & Use Cases

  • Multi-site Announcement Crawling: Collects notices from SJTU portals including academic affairs, graduate school, libraries, IT services, and departments.
  • AI Announcement Distillation: Converts raw announcement content into structured fields such as category, audience, deadline, required actions, summaries, and tags.
  • Use Case: Students and campus assistants can build a local SJTU knowledge base, summarize recent academic notices, compare announcements, or connect results with RAG and reminder systems.

Quick Start

Ask the AI to crawl SJTU announcements and create a structured local knowledge base from the collected notices.

Frequently Asked Questions about sjtu-crawler

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a searchable knowledge base from scattered university announcements?

To build a searchable knowledge base from university announcements, you can crawl multiple campus portals, extract the HTML content, and store it in SQLite. This process structures fragmented notices into a local database ready for retrieval.

What is AI distillation for announcement extraction?

AI distillation for announcement extraction converts raw notice content into structured fields like category, audience, deadline, required actions, summaries, and tags. This transforms unstructured text into searchable data for knowledge base construction.

How do I connect crawled web announcements to a RAG pipeline?

You can connect crawled web announcements to a RAG pipeline by storing the distilled, structured data in SQLite. The structured fields serve as context for retrieval-augmented generation workflows to query campus information.

Does this announcement crawler support configurable site sources for different departments?

Yes, this announcement crawler supports configurable site sources. It applies to SJTU academic portals, administrative notices, graduate school, libraries, and IT services to collect notices across various departments.

What's the best way to extract deadlines and required actions from academic notices?

The best way to extract deadlines and required actions from academic notices is using AI-based content distillation. It automatically identifies and structures critical dates and necessary steps from raw HTML into dedicated fields.

Can I trigger reminder workflows from structured campus announcements?

Yes, you can trigger reminder workflows from structured campus announcements. By extracting deadlines and required actions into structured fields, the stored data can integrate with external reminder systems.