llm-scraper

Turn any webpage into structured data using LLMs

Runs with mockssource: GitHubTypeScriptMITcommit 2b43d999a17e

TypeScript, MIT licensed. The project labels itself: ai, artificial intelligence, browser, browser automation, gpt, gpt 4, langchain and llama.

llm-scraper runs, with stand-ins for the services it depends on. An Argusic agent installed it in 47.6 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

The llm-scraper repo installs (npm ci), builds with tsc, and its full vitest suite of 8 tests passes against a local schema-correct mock OpenAI server, with real Playwright-driven fetches of news.ycombinator.com and example.com.

What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$1.35 (measured)
recorded runs
2
last tested
stars
6,956
forks
451
open issues
10
watchers
34
size
0 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Time lost to each failure while testing llm-scraper, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • All 8 tests failed with AI_LoadAPIKeyError: OpenAI API key missing/connection refused - tests need an OpenAI-compatible endpoint25 minutes
  • System Node 18.19.1 lacks node:util.styleText required by vitest 4.1.8 (engines ^20.19.0||>=22.12.0); npm ci succeeded but vitest crashed at startup8 minutes
  • @rolldown/binding-linux-x64-gnu missing after npm ci (rolldown native binding absent from node_modules, vitest startup failed MODULE_NOT_FOUND)5 minutes
  • Playwright browsers not installed - chromium.launch threw: Executable does not exist at ~/.cache/ms-playwright/chromium_headless_shell-12083 minutes
Install time
48 minutes
Cold machine to finish
49 minutes
Errors hit and fixed
4 hit, 4 fixed with no human help
How the result was proved
npm run build exited 0 (tsc); npx vitest run tests/scraper.test.ts with OPENAI_BASE_URL=http://127.0.0.1:18100/v1 OPENAI_API_KEY=mock-key-123 (Node 20.19.4 on PATH) exited 0: Test Files 1 passed (1), Tests 8 passed (8)
Model tokens used
6,513,630
Exact commit tested
2b43d999a17e
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Behaviour against real services
this run was verified against stand-in services only

Watch the session

The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.

A recording of attempt 1, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

 succeeded in 0ms:
---dist ignored?---
dist
dist ignored
0
The working tree is clean (only ignored artifacts changed). Let me write the final result line now.
exec
/bin/sh -lc "node -e \"const o={install_succeeded:true,launch_succeeded:true,install_minutes:47.6,e…
 succeeded in 0ms:
{"install_succeeded":true,"launch_succeeded":true,"install_minutes":47.6,"errors":[{"msg":"System N…
tokens used
6,513,630

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

  • Recovered from all 4 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Took 47.6 minutes to install, slower than the median of the 234 comparable projects Argusic has measured.

Of the 235 ai projects Argusic has installed and timed, llm-scraper was the 230th fastest to reach a running state, and 166 of 235 reached one at all.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs with mocks92.001.35
Argusic Runner1/3Runs with mocks92.000.11

Topics (from GitHub)

aiartificial-intelligencebrowserbrowser-automationgptgpt-4langchainllamallmopenaiplaywrightpuppeteerscraper

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/llm-scraper.svg)](https://argusic.com/subject/llm-scraper)

Questions

Does llm-scraper run?
llm-scraper runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 48 minutes, hitting 4 errors on the way, and recorded the session.
How did Argusic test llm-scraper?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 2b43d999a17e. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test llm-scraper?
The run that produced this verdict cost $1.35: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does llm-scraper take to install?
47.6 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does llm-scraper need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing llm-scraper?
4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does llm-scraper compare with the alternatives?
Of the 235 ai projects Argusic has installed and timed, llm-scraper was the 230th fastest to reach a running state, and 166 of 235 reached one at all.
Where is the evidence for llm-scraper?
All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion