Menu

Individual skill

local-scrape

0upvotes

Extract clean article text from web pages for free with Trafilatura — no API credits, no browser needed. Use this skill whenever the user wants page content and the page is static (articles, docs, blogs, news). Always try this BEFORE Firecrawl: it is the default scraping path on the user's limited free tier. Also use when the user says "scrape", "extract article text", or needs bulk text extraction for research or RAG.

skills-imported/local-scrape/SKILL.md

Read pinned source

Source commit faf37c0859ebf627bfcb5225e8057d088691e0ae

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
No
Observed behavior
Not checked yet
Last checked
Nov 8, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
56
Repository last updated
Oct 10, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Local Scrape (free, zero-credit)

Trafilatura-based article extraction running locally in `~/workspace/.venvs/scrape`. Fetches with urllib (proxy-aware on this VM) and strips boilerplate — nav, footers, ads, cookie banners — leaving clean article text. Verified 2026-09-30: 7,415 clean chars from a JS-free news article.

## The scraping decision tree (credit-saving order)

1. **Static page → this skill** (free). Articles, docs, blogs, most news.
1b. **Fetch blocked or page needs light JS → Jina Reader** (free, no key, no install): `curl -sL "https://r.jina.ai/<url>"` returns clean Markdown with title + published time. Verified working from this VM 2026-09-30. Try this before the browser tools for single pages — it's one HTTP call. (Idea salvaged from evaluating Panniantong/agent-reach, which was declined: its other backends duplicate working capabilities or need desktop login-state absent here.)
2. **JavaScript-heavy or interactive → browser tools** (`browser.open`, `browser.spawn_task`). Still free. Do NOT script Playwright/Chromium from exec — the runtime routes browser work through the browser tools.
3. **Anti-bot blocked, or bulk structured extraction where 1+2 fail → Firecrawl** (costs credits, last resort — see the `firecrawl` skill). The user is on a limited free tier.

## Usage

```bash
Back to top