extractor

Use LLMs to robustly extract web data

Runs with mockssource: GitHubhomepageTypeScriptApache-2.0commit c9edd2bf363e

TypeScript, Apache-2.0 licensed. The project labels itself: ai agents, article extractor, crawler, data engineering, data pipeline, ecommerce scraping, etl and google gemini.

extractor runs, with stand-ins for the services it depends on. An Argusic agent installed it in 0.1 minutes and hit 1 error on a clean machine with no GPU, and the whole session was recorded.

npm install builds successfully, 84 unit tests pass, 63 html-to-markdown integration tests pass with real ground-truth data, all LLM extraction integration tests pass with mocked providers, processedContent tests pass; Playwright browser tests fail at import on Node 18

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 72 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
72 / 100
cost of the verifying run
$0.22 (measured)
recorded runs
1
last tested
stars
322
forks
10
open issues
3
watchers
0
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.

What went wrong, in the agent's own words

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

  • Playwright MCP bundle requires Node 20+ ESM VM API (Node 18 present) - browser-extraction tests fail at import
Install time
under a minute
Cold machine to finish
39 minutes
Errors hit and fixed
1 hit, 0 fixed with no human help
How the result was proved
npm test returned 165 passed, 1 failed (the 1 failure is Node 18 ESM incompatibility with Playwright, not a code bug)
Model tokens used
916,435
Exact commit tested
c9edd2bf363e
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

The end of the recording

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

The only unresolved failure is the Playwright browser test which requires Node 20+ for ESM VM API s…
tokens used
916,435
**Test Summary (final)**
- **Unit tests**: 3 suites, **84 passed** (converters, extractors, schemaUtils)
- **Integration tests**:
  - `html-to-markdown`: **63 passed** (real HTML/markdown conversion verified against ground-truth …
  - `extract`: **all passed** (mocked LLM providers via `@langchain/openai` and `@langchain/google-…
  - `processedContent`: **3 passed** (TXT, MARKDOWN, HTML format content verification with mocked L…
  - `browser-extraction`: **2 failed** (Node 18 ESM incompatibility with Playwright's MCP bundle — …
- **Overall**: 165 passed, 1 failed, 7 test suites
The only unresolved failure is the Playwright browser test which requires Node 20+ for ESM VM API s…

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

  • Installed in 0.1 minutes, faster than the median of the 123 comparable projects Argusic has measured.
  • Licensed Apache-2.0, as reported by its host.

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.
  • Hit 1 error during setup, 1 of which were not solved.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 124 ai-agents projects Argusic has installed and timed, extractor was the 6th fastest to reach a running state, and 96 of 124 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 Runner1/3Runs with mocks72.000.22

Topics (from GitHub)

ai-agentsarticle-extractorcrawlerdata-engineeringdata-pipelineecommerce-scrapingetlgoogle-geminihtml-parserhtml-to-markdownllmllm-extractionllm-scrapermarkdownnlpopenairagweb-data-extractionweb-extractionwebscraping

Embed the badge

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

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

Questions

Does extractor run?
extractor runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 0 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test extractor?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit c9edd2bf363e. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test extractor?
The run that produced this verdict cost $0.22: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does extractor take to install?
0.1 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 extractor need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing extractor?
1 thing broke in the recorded run. Each one, and the time it cost, is listed on this page.
How does extractor compare with the alternatives?
Of the 124 ai-agents projects Argusic has installed and timed, extractor was the 6th fastest to reach a running state, and 96 of 124 reached one at all.
Where is the evidence for extractor?
The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion