Evidence · first-party tested/Best AI Tools to Scrape Web Pages Into Clean Markdown or Structured Data
It 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.
What was measured
Output Quality
Conceptually matches the prompt and is visually usable.
decisive for this rankingtransformation
Whether the result matches the page and is actually usable is the main outcome the ranking is trying to measure. (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
Interaction Stability✗ FailedIt 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.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.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
- 92e7286e-bc9b-43d1-ac1a-fb62c00e6053
- 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 — 3 other tools
measured on Output Quality
Firecrawl◐ MixedCaptures the title, pricing, and inventory layout, but the output still includes raw backend code artifacts, media-matrix noise, and uncleaned global link trees.Skyvern✓ WorkedReturns accurate product data for the hydrated page, including the correct product name Nike Air Force 1 '07 and a long size list; the visible output shows 14 fully readable size pairs from M 7 / W 8.5 through M 14 / W 15.5.Spider⚠ StruggledPreserved the product title and $115 price, but omitted the dynamic size-selection and inventory section, leaving the result incomplete.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com