AliExpress Reviews Scraper — AI sentiment, no login

For dropshippers, sourcing teams and sellers who want the reviews of any AliExpress product — text, English translation, star rating, date, buyer country, the option bought (SKU) and photos — from a product URL or ID, for $1.50 per 1,000 reviews, and who want to know why buyers complain: with AI classification on, every review gets complaint types, sentiment and purchase motive, and each run saves a summary per product. No login, no cookies.

Independent tool — not affiliated with, endorsed by or sponsored by AliExpress or Alibaba Group. The name is used only to describe the data source.

• Reviews — original text + AliExpress' English translation, stars (1–5), date, country, option (color/size), photos, aspect ratings (e.g. "Sound quality: Good"), helpful votes, follow-up reviews
• Product stats — total review count, average rating and the star distribution (in the summary)
• AI classification (optional) — complaint types (quality/defect, size/fit, delivery, packaging, price/value, customer service, no effect, skin/body reaction, other), sentiment and purchase motive, with probabilities
• Star-only reviews skipped by default — AliExpress has many reviews with stars but no text; they are not collected or charged unless you ask for them

Use it to: check a product's real complaints before you source or dropship it · compare competitors' weak points · monitor your own listings' reviews on a schedule · feed review data and labels to your AI agent or dashboard.

Output sample

Real rows (one per review) from run e0PZVblM8YcK4BhbH (2026-10-05, 1,000 reviews of one earbuds listing, classification on). The original text and AliExpress' English translation are both returned.

rating	date	country	text (original)	textEnglish (AliExpress translation)	complaint (probability)	sentiment	motive
1	2026-05-08	US	прийшло повністю пошкрябане і наче…	It arrived completely scratched and as if it had already bee…	quality_defect (0.98)	negative (1.00)	unknown
5	2026-04-04	MX	Son cómodos y con un volumen bastan…	They are comfortable and have a fairly high volume. Physical…	quality_defect (0.86), other (0.56)	positive (1.00)	unknown
5	2025-11-15	US	Все прийшло.Подарунок виграв на Али…	Everything has arrived. The gift was won on Aliexpress.	none (0.98)	positive (0.98)	gift
5	2026-03-11	US	conseguido con el juego. muy bien	achieved with the game. very good	none (0.98)	positive (1.00)	unknown

Every row also has reviewId, productId, productUrl, option, images[], aspects[], helpfulVotes, additionalReview, logistics, language and classifiedFrom — see Output below.

Input example

The form default — one product, its 20 most recent text reviews, classified (about $0.04, 10 seconds):

{
  "productUrls": ["https://www.aliexpress.com/item/1005008549911526.html"],
  "reviewsPerProduct": 20
}

For competitor research:

{
  "productUrls": ["https://www.aliexpress.com/item/1005008549911526.html", "1005010748356463"],
  "reviewsPerProduct": 200,
  "reviewFilter": "all",
  "classifyReviews": true
}

Pricing

Pay only for what you collect — no subscription.

Event	Price	When
review	$0.0015	One AliExpress review collected (text, English translation, rating, date, country, option, photos).
review-judged	$0.0005	Complaint types, sentiment and purchase motive for one review (only when classification is on).

That is $1.50 per 1,000 reviews plus $0.50 per 1,000 classifications — $2 per 1,000 classified reviews. First run with the form defaults: about $0.04 (20 reviews classified, 10 seconds).

Cost examples

Run	Cost
20 reviews of one product, classified	$0.04
1,000 reviews, classified	$2.00
1,000 reviews, not classified	$1.50
10 competitor products × 200 reviews, classified	$4.00

With the free $5 monthly Apify credit you can collect about 2,500 classified reviews or 3,333 reviews without classification.

Failed products are reported with an error row and not charged. Star-only reviews are skipped and not charged (turn on Include star-only reviews to collect them). If you set a maximum cost per run, the Actor stops cleanly when it is reached (classification is switched off first when the budget only covers collection).

Works with

• Apify API, JavaScript and Python clients — start a run and read the dataset like any Actor (leoworks/aliexpress-reviews-classifier).
• Apify Schedules — a weekly schedule keeps watching the reviews of your own and competitors' listings; our own monitoring runs this Actor every morning.
• Claude, Cursor and Claude Code through the Apify MCP server — see the next section (verified 2026-10-06).
• AliExpress Search Scraper — find the products first with leoworks/aliexpress-search-scraper and pass their productUrl here. Korean Review Classifier — the same labels for any other review dataset: leoworks/korean-review-classifier.

Use with Claude, Cursor or Claude Code (MCP)

Add the Apify MCP server with this Actor as a tool and ask your agent in plain language — for example "Get the latest 50 reviews of https://www.aliexpress.com/item/1005008549911526.html and tell me the main complaints." The agent calls the tool leoworks--aliexpress-reviews-classifier and reads the rows and the per-product summary with get-dataset-items and get-key-value-store-record.

Claude Desktop or Cursor (mcp.json):

{
  "mcpServers": {
    "apify": {
      "url": "https://mcp.apify.com?tools=leoworks/aliexpress-reviews-classifier",
      "headers": { "Authorization": "Bearer YOUR_APIFY_TOKEN" }
    }
  }
}

Claude Code: claude mcp add --transport http apify "https://mcp.apify.com?tools=leoworks/aliexpress-reviews-classifier" --header "Authorization: Bearer YOUR_APIFY_TOKEN". Leave out the header to sign in with OAuth in the browser instead. Your Apify token is in Console → Settings → API & Integrations. We verified this setup with the Apify MCP server (v0.17.2) on 2026-10-06.

How to use

1. Paste AliExpress product URLs (any site — aliexpress.com, aliexpress.us, ko.aliexpress.com …) or product IDs.
2. Set Reviews per product (the form starts at 20 for a quick first run).
3. Optional: Which reviews (all / with photos / with a follow-up review), Classify reviews with AI (on by default).
4. Run it, or schedule it to track new reviews.

Output (one row per review)

{
  "type": "review",
  "productId": "1005008549911526",
  "reviewId": "60093737103906642",
  "rating": 5,
  "date": "2025-11-15",
  "country": "US",
  "text": "Все прийшло.Подарунок виграв на Алиєкспрес",
  "textEnglish": "Everything has arrived. The gift was won on Aliexpress.",
  "language": "other",
  "option": "Color:black",
  "images": ["https://ae-pic-a1.aliexpress-media.com/kf/A4d5c8b0dedb6489ebd7b6d2cfa37a710f.jpg", "…"],
  "aspects": [{ "aspect": "Quality of sound", "value": "Fast" }, { "aspect": "Durability", "value": "Fast" }, { "aspect": "User Friendly", "value": "Good" }],
  "helpfulVotes": 0,
  "labels": {
    "complaint": [{ "label": "none", "labelKo": "불만 없음", "probability": 0.97 }],
    "sentiment": { "label": "positive", "probability": 0.97, "confidence": 0.96 },
    "motive": { "label": "gift", "probability": 0.87, "confidence": 0.84 }
  },
  "classifiedFrom": "english_translation",
  "productUrl": "https://www.aliexpress.com/item/1005008549911526.html"
}

Reviews written in other languages are classified from AliExpress' own English translation (classifiedFrom). Reviewer names and avatars are not collected.

Summary by product (REPORT)

Each run also saves a REPORT record (Output tab → Summary by product) at no extra charge: per product, the AliExpress totals (productReviewTotal, productAverageRating, productStars 5→1) and, for the reviews collected, the complaint rate and mix, sentiment shares, purchase motives and the 3 strongest complaint reviews.

Classification accuracy

Measured on hand-labelled AliExpress reviews (earbuds, phone cases, dresses, kitchen tools, LED strips, car holders; about half with 1–3 stars): complaint type 93% and sentiment 87% on 30 reviews it had not seen before. Labels were set by us; automated labels can be wrong, so check samples before making big decisions.

Limits

Item	Limit
Reviews per product	Up to 5,000 per run
Order	AliExpress' default order (the source does not offer sorting by date or stars)
Filters	All · with photos · with a follow-up review
Classification	English, Korean, Japanese text; other languages via AliExpress' English translation
Product details	Not included — this Actor collects reviews only
Speed	1,000 reviews (893 classified) in about 8 min on the default 256 MB (measured 2026-10-05)

FAQ

Which AI makes the judgments? Jev, TypeSafe's decision model (version jev-1.13.0, pinned). Jev answers each label with a calibrated probability instead of generated text, so the same input gets the same answer from run to run. Only the review text (or its English translation) and the star rating are sent to Jev.

Why are some reviews missing labels? Reviews with photos but no text, or in a language without an English translation, are returned without labels and charged only as review.

Do you classify reviews from other sources? Yes — our Korean Review Classifier classifies any review dataset, and OliveYoung Global & Amore Mall covers K-beauty reviews.

Is it legal? It reads publicly visible review pages without logging in. You are responsible for how you use the data; follow AliExpress' terms and local laws, and do not use personal data.

Reviews and support

If this Actor saved you time, a short review on Apify Store helps others find it. Questions or a product that does not work? Open an issue in the Issues tab — we answer within a day.

Changelog

See the Changelog tab.