İçeriğe geç
TakoAPI
Becerilere dön

web-pilot

liranudi tarafından

Web & Frontend Development
4.7kİndirme sayıları clawskills.sh tarafından bildirilir
1Yıldızlar
0Görüntülenmeler
0 beğeniBu beceriyi beğenmek için giriş yapın
—Henüz değerlendirilmedi
Puanınız

Özet

Search the web and read page contents without API keys.

Açıklama

Bu Beceri Ne Yapar

Web browsing toolkit built on four Python scripts. Searches via DuckDuckGo, Brave, or Google across multiple pages, reads page text, runs interactive browser sessions with tab management and click support, and downloads files including PDFs. No API keys required.

Works without any API keys or account signups, using Playwright and Chromium directly to access real browser behavior including cookie banner dismissal.

Ne Zaman Kullanılır

  • Scraping search results from DuckDuckGo without an API key
  • Extracting readable text from a paywalled or cookie-gated page
  • Taking a full-page screenshot of a site for visual reference
  • Downloading a PDF and pulling its text content automatically
  • Navigating a multi-tab session to compare content across pages

Örnek İş Akışı

GİRİŞ

User asks: find recent articles about LLM context windows and summarize the top result

AJAN
  1. 1

    Run google_search.py with the query and --pages 2 to get a result list

  2. 2

    Pick the top URL from the returned JSON

  3. 3

    Run read_page.py on that URL with --format markdown

  4. 4

    Parse the markdown output and extract the main article text

  5. 5

    Return a summary to the user

ÇIKIŞ

Markdown text of the article, ready for summarization

Kurulum

clawhub install liranudi/web-pilot

CLI komutunu çalıştırın ya da istemi Claude Code, Cursor, Codex veya kullandığınız kodlama ajanına yapıştırın.

Bağlantılar