Lewati ke konten
TakoAPI
Kembali ke skill

finviz-crawler

oleh camopel

DevOps & Cloud
398Unduhan dilaporkan oleh clawskills.sh
0Tayangan
0 sukaMasuk untuk menyukai skill ini
—Belum ada penilaian
Penilaian Anda

Ringkasan

Continuous financial news crawler for finviz.com with SQLite storage, article extraction, and query tool.

Deskripsi

Apa yang Dilakukan Skill Ini

A background daemon that crawls finviz.com every 5 minutes, storing headlines and full article content in a local SQLite database. Includes a query tool to filter by time window, ticker, or content type, with output formatted for LLM summarization pipelines.

Unlike one-shot finance APIs, it accumulates a local historical archive so you can query any past window without rate limits or subscription fees.

Kapan Menggunakannya

  • Tracking NVDA or TSLA headlines without refreshing a browser
  • Generating a daily 6 AM market briefing via cron
  • Searching three weeks of financial news without an internet connection
  • Building a local archive before paywalled articles disappear
  • Feeding yesterday's headlines into an LLM for a portfolio summary

Contoh Alur Kerja

INPUT

User asks: Summarize NVDA news from the last 24 hours

AGENT
  1. 1

    Runs finviz_query.py with --hours 24 filtered to the NVDA ticker

  2. 2

    Retrieves matching article titles and content from local SQLite

  3. 3

    Formats output as clean text for LLM input

  4. 4

    Passes formatted articles to the LLM for summarization

  5. 5

    Returns a concise summary of NVDA headlines and key themes

OUTPUT

A paragraph summarizing NVDA-related news from the past 24 hours, drawn from Bloomberg, Reuters, and Yahoo Finance articles

Instalasi

clawhub install camopel/finviz-crawler

Jalankan perintah CLI-nya, atau tempel prompt ke Claude Code, Cursor, Codex, atau coding agent apa pun yang Anda pakai.

Tautan