Retail Review Export & Product Feedback Analyzer avatar

Retail Review Export & Product Feedback Analyzer

Pricing

from $1.00 / 1,000 review extracteds

Go to Apify Store
Retail Review Export & Product Feedback Analyzer

Retail Review Export & Product Feedback Analyzer

Analyze supplied retail review JSON or Apify datasets with product summaries, rating coverage, local signals and optional OpenRouter analysis.

Pricing

from $1.00 / 1,000 review extracteds

Rating

0.0

(0)

Developer

Inus Grobler

Inus Grobler

Maintained by Community

Actor stats

0

Bookmarked

5

Total users

1

Monthly active users

24 days ago

Last modified

Features

Limited permissions

Share

Turn your retail review exports into clean review rows, product summaries and feedback signals. Paste JSON reviews or provide an Apify dataset ID. The Actor uses evidence you supply; live retailer API collection is unavailable.

Quick start

Illustrative input; replace source values with your own authorized evidence.

{
"providedRecords": [
{
"productUrl": "https://example.com/owned-product/1",
"productTitle": "Owned example product",
"reviewTitle": "Clear instructions",
"reviewText": "This owned demonstration review describes clear instructions and a useful product.",
"reviewRating": 4
}
],
"providedRecordLimit": 1,
"maxReviewsPerProduct": 3,
"outputMode": "summary_only",
"includeOpenRouterAnalysis": false
}

Replace the demonstration records with productUrl, productTitle and meaningful reviewText. Include reviewRating on a 0–5 scale only when known. Set providedRecordLimit to bound the total scan and maxReviewsPerProduct to bound each product. For a dataset, clear providedRecords to [] and set providedDatasetId.

Result types

Illustrative output; replace source values with your own authorized evidence.

{
"productUrl": "https://example.com/owned-product/1",
"productTitle": "Owned example product",
"reviewTitle": "Clear instructions",
"reviewText": "This owned demonstration review describes clear instructions and a useful product.",
"reviewRating": 4,
"itemType": "review",
"dataInputSource": "provided",
"sourceVerified": false
}
  • raw_reviews returns your validated review rows.
  • summary_only returns one product review summary per product.
  • review_signals_and_summary returns review-level feedback signals and product summaries.
  • raw_reviews_and_summary returns reviews and product summaries.

Unknown ratings stay unknown. REVIEW_SUMMARY in the key-value store reports delivered-review counts, rated-review coverage and average supplied ratings. These are sample statistics, separate from a retailer’s published totals. No review-removal or market-wide inference is made. Every output row is marked dataInputSource=provided and sourceVerified=false.

Optional analysis

Local feedback signals are labelled local_fallback. Set includeOpenRouterAnalysis=true with your OpenRouter key and a small maxReviewsToAnalyzeWithOpenRouter to request model analysis. Model output remains an interpretation of the supplied text. Without a key or sufficient budget, analysis is explicitly local. No other external API or child Actor is used.

Limits and billing

Read the Pricing tab before running. The existing product_processed event applies to each processed product group; review_extracted applies to accepted review values after the requested output is written. ai_review_analyzed applies only to newly model-analyzed reviews. Summaries do not add another review-result charge. Empty, invalid or unsupported source requests do not create paid review rows; start fees and platform usage may still apply.

PROVIDED_DATA_SUMMARY records scan limits, rejected and duplicate records, confirmed review delivery, output mode and event counts. Start with one product and three reviews. Historical monitoring is not updated by supplied-data processing.

Python API example

from apify_client import ApifyClient
client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("thescrapelab/warehouse-grocery-review-intelligence-scraper").call(run_input={"providedDatasetId": "YOUR_DATASET_ID", "providedRecordLimit": 3, "maxReviewsPerProduct": 3, "outputMode": "summary_only", "includeOpenRouterAnalysis": False})
if run is None:
raise RuntimeError("No run metadata returned")
dataset_id = run["defaultDatasetId"] if isinstance(run, dict) else run.default_dataset_id
for row in client.dataset(dataset_id).iterate_items():
print(row)

For no valid output, check rejection codes and required product context. Supply a dataset you can access and a small processing limit. Open Issues with a run ID and sanitized sample for support.