MinerU-HTML tested by Argusic Runner

Attempt 1 of 3 · Runs with mocks · Argusic Score 92.0 of 100

all runs of MinerU-HTMLarticle-extractorcorpus-toolsnlpragscrapingtext-extraction

Session recording

Loading recording...

Download the original recording · fingerprint ca28a441b05bbcb1...

What the test found

MinerU-HTML v1.1.2 package installs and imports correctly in a Python 3.12 venv; the full extraction pipeline runs to completion with a mock LLM backend, correctly filtering navigation/auxiliary elements from main content HTML; all 20 internal modules import cleanly; config validation, fallback handlers (trafilatura/bypass/empty), batch processing, and error handling all work.

No unit tests exist in the repository. Verification used a custom mock InferenceBackend to exercise the full simplify→prompt→parse→map→convert pipeline end-to-end. All external dependencies (vLLM 0.11.1, transformers 4.57.6, openai 3.37.0, mineru-webkit 0.1.6) import successfully.

Argusic installed MinerU-HTML in 12 minutes and launched it; verification reached Verified with mock services. 2 of 2 recorded errors were worked through (see the timeline below).

Runs with mocksall runs of MinerU-HTML

This summary is drawn from the agent's recorded report for this run. Every figure traces to the log and recording above; nothing here is authored.

Error and fix timeline

No errors were recorded for this run.

Discussion