Scrapegraph-ai
Python scraper based on AI
Runs with mockssource: GitHubhomepagePythonMITcommit c75c8084fae2
Python, MIT licensed. The project labels itself: ai crawler, ai scraping, ai search, crawler, data extraction, firecrawl alternative, large language model and llm.
Scrapegraph-ai runs, with stand-ins for the services it depends on. An Argusic agent installed it in 2 minutes and hit 13 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
191 unit tests pass after fixing 13 categories of test failures covering models_tokens assertions, cleanup_html behaviors, logger capture, file paths, missing dependencies, mock patterns, and mock class completeness
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 56 of 100 (the mean of this project's run scores).
At a glance
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.
- robot_node_test: mock patched on wrong attribute (instance attr vs import path)3 minutes
- search_internet_node_test and search_link_node_test: require real ChatOllama server3 minutes
- test_llm_missing_tokens: logger.warning writes to stderr, test checked capsys.out2 minutes
- test_token_limits_range: gemini-2.0-pro-exp has 2M tokens exceeding 1.1M upper bound1 minute
- test_specific_models_additional: deepseek-chat token limit changed from 28672 to 1280001 minute
- test_groq_specific: model key 'claude-3-haiku-20240307"' has spurious trailing apostrophe1 minute
- Install time
- 2 minutes
- Cold machine to finish
- 46 minutes
- Errors hit and fixed
- 13 hit, 13 fixed with no human help
- How the result was proved
- python -m pytest 21 test files (191 passing, 0 failing) in 10 seconds with model-provider and network calls mocked
- Model tokens used
- 2,179,933
- Exact commit tested
- c75c8084fae2
- 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.
=============================== warnings summary =============================== ======================= 191 passed, 2 warnings in 10.00s ======================= 191 tests pass, 0 failures across the core unit test suite. Let me generate the final report. exec /bin/sh -lc 'cd /work/repo && . .venv/bin/activate && python -m pytest tests/test_telemetry_flag.py… succeeded in 11041ms: -- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html 191 passed, 2 warnings in 9.97s 191 tests pass with zero failures across the core unit test suite. Here's the final ARGUSIC_RESULT: tokens used 2,179,933 191 tests pass with zero failures across the core unit test suite. Here's the final ARGUSIC_RESULT:
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 2 minutes.
- Recovered from all 13 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.
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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.35 | |
| Argusic Runner | 1/3 | Did not run | 20.00 | 0.04 |
Topics (from GitHub)
ai-crawlerai-scrapingai-searchcrawlerdata-extractionfirecrawl-alternativelarge-language-modelllmmarkdownragscrapingscraping-pythonweb-crawlerweb-crawlersweb-dataweb-data-extractionweb-scraperweb-scrapingweb-searchwebscraping
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/scrapegraph-ai)Questions
- Does Scrapegraph-ai run?
- Scrapegraph-ai runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 2 minutes, hitting 13 errors on the way, and recorded the session.
- How did Argusic test Scrapegraph-ai?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit c75c8084fae2. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test Scrapegraph-ai?
- The run that produced this verdict cost $0.35: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Scrapegraph-ai take to install?
- 2 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 Scrapegraph-ai need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Scrapegraph-ai?
- 13 things broke in the recorded run, and 13 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for Scrapegraph-ai?
- 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.