Evidence · first-party tested/Best AI Tools to Scrape Web Pages Into Clean Markdown or Structured Data
It did not wait for the client-side size selector to hydrate; the response shows the product title and $115 price but no concrete size inventory values.
What was measured
Interaction Stability
How reliably the tool executes through dynamic loading and interaction steps without losing sync or failing at runtime.
decisive for this rankingcapability
Reliably completing dynamic loading and interaction steps is part of successfully scraping pages, not just convenience. (3 of 3 judges)
What was given, what came back
Test input: Nike Air Force 1 '07 size options extraction · mixed
Input — what we sent
Input, verbatim
https://www.nike.com/t/air-force-1-07-mens-shoes-jBrhbr/CW2288-111 — Wait for the size selection options to fully render. Extract the product name, price, and a list of all available shoe sizes.
A Nike product page with client-side JavaScript hydration used to test whether a headless scraper waits for dynamic DOM content before extracting product details and all available shoe sizes.
Output — unretouched
Jina Reader extracting a Nike product page
Also checked on this input — same tool, 5 other criteria
JS DOM Hydration✗ FailedIt fails to wait for client-side hydration on the size-selector grid: the response leaves the selector as empty layout nodes and instead spills the site-wide international menu and regional index into the output.JS DOM Hydration◐ MixedThe engine can recover static product metadata from a JavaScript-heavy product page, including the title "Nike Air Force 1 '07 Men's Shoes" and the $115 price, but it does not needlessly enrich the dynamic state beyond those static markers.JS DOM Hydration✗ FailedIt did not capture the client-rendered size selector; after 7.0 s the extract still lacked the live size grid and showed only static page content.Output Quality◐ MixedIt recovered the product title and the $115 price, but the result was padded with image/link markup and navigation artifacts rather than a clean product-only extract.Schema Extraction Integrity◐ MixedCan still extract some static fields correctly on a dynamic product page, including the SEO header and price markers, but it corrupts the requested product-specific output by substituting broad site-directory text for the size data.
Provenance
- Observation
- 813f348c-4de5-462c-b815-5c06a67402cc
- Evidence run
- 06e1dbd6-5518-4af8-aa1a-735259a75b4f
- Study
- Scrape Web Pages Into Clean Markdown or Structured Data Using AI
- Research task
- 86b9jm3a3
- Tested at
- Jun 23, 2026
- Source
- first-party
- Evidence state
- verified
- Proof shown
- input + output shown
- Cost / latency
- not captured
- Repeat run
- not captured
- Tester
- not captured
The last three rows are honest blanks, not placeholders — our capture has no field for them yet.
Query this
get_evidence({
tool: "jina-ai-reader"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 2 other tools
measured on Interaction Stability
Firecrawl✓ WorkedReliably waited for client-side hydration and captured the complete size set, from M 5 / W 6.5 through M 18 / W 19.5.Skyvern⚠ StruggledHandles the page extraction itself, but the run’s live recording pipeline can fall out of sync during hydration: the report states the screen capture froze on the initial page view, making the recording unwatchable and hard to debug.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com