How-to guide
How to analyze Amazon reviews by issue and sentiment
Send an ASIN, a country code and label=issue to amazon/reviews and it returns the reviews shown on the product page, each with full text, star rating, reviewer and verified flag, plus the issue it raises and its sentiment already judged. A run costs 5 credits.
5 credits per run, in one API call
The calls, in order
Each step is one request to the SocialCrawl API. Copy the curl, add your key and run it.
Get Amazon product reviews
5 credits per callTry this call on its endpoint page: Get Amazon product reviewscurlcurl -H "x-api-key: YOUR_API_KEY" \ "https://www.socialcrawl.dev/v1/amazon/reviews?asin=B0BTYCRJSS&country=US&label=issue"
What comes back
A real response from amazon/reviews, captured from the SocialCrawl API, with long lists cut to two rows.
JSON
{
"success": true,
"platform": "amazon",
"endpoint": "/v1/amazon/reviews",
"data": {
"items": [
{
"review": {
"id": "R2U61BULMR42X2",
"entity_id": "B0DCH8VDXF",
"url": "https://example.com/redacted",
"title": "Sample comment text (redacted).",
"text": "Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted).",
"rating": {
"value": 5,
"max": 5
},
"author": {
"name": "user_921b7b",
"avatar_url": "https://example.com/avatars/user_5cdb67.png",
"url": "https://example.com/user_857265",
"location": null,
"reviews_count": null
},
"helpful_votes": 20,
"verified": true,
"source": null,
"language": null,
"original_language": null,
"translated": null,
"images": [
"https://example.com/redacted"
],
"responses": null,
"published_at": "Sample comment text (redacted)."
}
},
{
"review": {
"id": "R15GXKKYVBUR72",
"entity_id": "B0DCH8VDXF",
"url": "https://example.com/redacted",
"title": "Sample comment text (redacted).",
"text": "Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted). Sample comment text (redacted).",
"rating": {
"value": 5,
"max": 5
},
"author": {
"name": "user_7876ab",
"avatar_url": "https://example.com/avatars/user_88388c.png",
"url": "https://example.com/user_11a2bf",
"location": null,
"reviews_count": null
},
"helpful_votes": 5,
"verified": true,
"source": null,
"language": null,
"original_language": null,
"translated": null,
"images": null,
"responses": null,
"published_at": "Sample comment text (redacted)."
}
}
],
"total": null,
"dropped": 0
},
"credits_used": 5,
"credits_remaining": 9999,
"request_id": "req_example000000",
"cached": false,
"pagination": {
"next_cursor": null,
"has_more": false,
"page_size": 13
},
"redacted": true
}Hand this job to your coding agent
Paste this prompt into Claude Code, Cursor or any agent that can make HTTP requests. It names every endpoint and parameter the job needs.
Prompt
Use the SocialCrawl API for this job: Read a product's reviews with the issue each one raises and its sentiment already judged.
Base URL: https://www.socialcrawl.dev. Send the API key in the x-api-key header (an Authorization: Bearer header also works). Values in braces are placeholders to fill.
1. GET /v1/amazon/reviews?asin=B0BTYCRJSS&country=US&label=issue
Every response is JSON with data, credits_used and request_id. The full endpoint reference is at https://www.socialcrawl.dev/llms.txt.FAQ
Have a question? We got answers
Find answers to frequently asked questions about SocialCrawl's API, pricing, and capabilities.
Contact usHow many reviews does one call return?
About 8 per ASIN. The registry is explicit that this is one page of on-page reviews and not a full review crawl, so plan around a sample of the page rather than every review.
What does each review contain?
Each review has its title, full text, star rating, reviewer, helpful votes, a verified purchase flag and any photos. The label=issue option adds the issue and sentiment judgement to each one.
How do I choose the marketplace?
Set country to the store you want, such as US in the example. The ASIN belongs to a marketplace, so pair the two correctly and run the call again per country.
What if I need a comparison or a genuineness check?
The registry points to prism/product-reviews for a rating comparison across shops with themed pros and cons, and prism/review-integrity for whether the ratings look genuine.
Can I repeat the check for many products?
Yes. Loop over your ASIN list with one call each. Each call is priced separately, so multiply the per-run price by the number of products before you start a large list.
How much does one run cost?
One run of the example above costs 5 credits across one API call. Every new account gets 100 free credits, credits for failed or empty calls are refunded automatically, and there is no subscription.
Ask AI about SocialCrawl