logo
JP

JD Product Reviews

Collect public JD.com reviews for one product SKU and return the original review payload, publish times, and shop context

原文 · en-US訳文に戻す

データ収集E-commerce & RetailJD.comReviews & Ratings
開発者
super_ig
料金
$0.08 / 10 件から
最終更新
2026-10-14

概要

Public JD.com product reviews capture how buyers describe quality, delivery, and the SKU they actually purchased. This Data App turns the public review area of one JD product SKU into a consistent set of records covering the original review payload, publish times, shop context, and collection timestamps.

The result is built for repeatable reputation analysis instead of scrolling a product page. Each review keeps its source wording inside Comment data and stays linked to the Source SKU, SKU ID, and shop, so praise and complaints can be compared across collection runs with the same fields.

Data notes

The data covers publicly visible JD.com product reviews for the supplied JD product SKU at collection time, taking the newest public reviews. Returned records keep the order of Collected at from earliest to latest. Each normal record is identified by its Comment ID, which removes duplicate reviews in the same run. Private, deleted, and non-public reviews are outside the coverage.

Comment data keeps the original review payload as source text, including buyer nicknames, ratings, photos, videos, and body text when the source supplies them that way. Comment type, Parent ID, Shop type, and SKU ID are source codes, not rewritten labels. Comment time, Published at, and Collected at preserve the source timestamps without inferring a timezone. Source SKU and No data retain the collection outcome when a product has no public review result.

What the results look like

Each normal record represents one publicly visible review of the selected JD product.

Comment IDBusiness IDComment typePublished atCollected atShop name
10648261023489188010034208826812026-10-12T12:49:472026-10-13T18:37:16小米京东自营旗舰店
10618467021453271610034208826812026-10-12T12:17:422026-10-13T18:37:16小米京东自营旗舰店

Additional values include Comment data, Shop type, SKU ID, and No data.

Use cases

  • Read Comment data to locate quality complaints, then group by Comment type.
  • Compare Published at with Collected at to see how recently the review was captured.
  • Split records by Shop name and Shop type when comparing self-operated and marketplace listings.
  • Use No data with Source SKU to distinguish an empty listing from a failed collection.

適用範囲と境界

Each run accepts one JD product SKU and an expected review count of 1 to 2000. Results are returned in complete batches and may round up. Only publicly visible JD reviews are covered. Pull protection capacity is 150 pages / 3,000 records.

  • 適している用途
  • When you need public JD.com review payloads, publish times, and shop context for one product SKU
  • When you need original review text plus collection timestamps for JD reputation analysis
  • 適さない用途
  • When you need reviews from a marketplace other than JD.com
  • When you need real-time monitoring of newly posted reviews instead of one collection snapshot
  • When you need private, deleted, or otherwise non-public reviews

失敗時の処理

開発者が宣言した失敗時と再試行の動作です。連携時にはシステムプロンプトに含めることをおすすめします。

  1. 1If no reviews are returned, verify the JD product SKU and use No data to distinguish an empty listing from a failed job
  2. 2A partial success still returns the reviews that were completed; submit a new collection after failure or expiry
  3. 3If authentication fails, a task context does not match, or the job times out, check the credential in the execution environment and submit a new collection instead of reusing the old job
  4. 4When the submission outcome is unknown, avoid immediate repeated submissions that could create duplicate tasks

入力

この App の呼び出しに必要なパラメータで、manifest.json の input.schema から生成されています。

  • JD product SKUproduct_sku必須string
    The JD.com product SKU whose public reviews will be collected. Enter one identifier, 1 to 512 characters.
    例100342088268
  • Expected review countcomment_count必須integer
    The expected number of public reviews to collect, from 1 to 2000. Results are returned in complete batches, so the actual count may round up. If the product has fewer public reviews, the result may still be lower.
    範囲1–200

出力

1 件のレコードのフィールド構造で、manifest.json の output.schema から生成されています。

  • Business IDbiz_idstring
    The business identifier linking the review record to the collected product
    例100342088268
  • Comment datacomment_datastring
    The original review payload retained as source text, including rating, body text, photos, and buyer nickname when supplied
    例{"afterUserComment": {}, "avatar": "storage.360buyimg.com/i.imageUpload/6a645f3562616533316234626665623831373638333636333633333131_sma.jpg", "content": "好用好看", "creationTime": "2026-10-12 12:49:47", "guid": "T6NYPc91jp0tdhmCU6-ZyHeB", "id": "106482610234891880", "images": [{"imgUrl": "//img30.360buyimg.com/shaidan/s128x96_jfs/t1/536818/26/12014/1878056/6acc66eaF385886de/00a98dcfc0d5070d.jpg"}], "likeCount": "0", "nickname": "eatt94", "plusAvailable": "0", "productColor": "脂白", "productSize": "", "referenceName": "小米（MI）REDMI Buds 8 真无线蓝牙耳机主动降噪适用于安卓苹果手机 脂白", "score": "5", "videos": null}
  • Comment IDcomment_idstring
    The stable unique identifier of the JD review
    例106482610234891880
  • Comment timecomment_timestring
    The source timestamp of the review without an inferred timezone
    例2026-10-12T12:49:47

サンプルデータ

output.schema から生成したサンプルです。サンプル値のないフィールドには構造上のプレースホルダーを使用しています。

output.example
{
  "biz_id": "100342088268",
  "comment_data": "{\"afterUserComment\": {}, \"avatar\": \"storage.360buyimg.com/i.imageUpload/6a645f3562616533316234626665623831373638333636333633333131_sma.jpg\", \"content\": \"好用好看\", \"creationTime\": \"2026-10-12 12:49:47\", \"guid\": \"T6NYPc91jp0tdhmCU6-ZyHeB\", \"id\": \"106482610234891880\", \"images\": [{\"imgUrl\": \"//img30.360buyimg.com/shaidan/s128x96_jfs/t1/536818/26/12014/1878056/6acc66eaF385886de/00a98dcfc0d5070d.jpg\"}], \"likeCount\": \"0\", \"nickname\": \"eatt94\", \"plusAvailable\": \"0\", \"productColor\": \"脂白\", \"productSize\": \"\", \"referenceName\": \"小米（MI）REDMI Buds 8 真无线蓝牙耳机主动降噪适用于安卓苹果手机 脂白\", \"score\": \"5\", \"videos\": null}",
  "comment_id": "106482610234891880",
  "comment_time": "2026-10-12T12:49:47",
  "comment_type": "1",
  "crawl_time": "2026-10-13T18:37:16",
  "customer": "yunfan",
  "no_data": false,
  "origin_comment_id": "106482610234891880",
  "pid": "0",
  "publish_time": "2026-10-12T12:49:47",
  "shop_id": "1000004123",
  "shop_name": "小米京东自营旗舰店",
  "shop_type": "京东自营店",
  "sku_id": "100342088268",
  "source_sku": "100342088268"
}

連携方法

この App は MCP、API、SDK、ファイルエクスポートのいずれでも連携でき、どのチャネルも同じ能力と料金を共有します。すべてのリクエストは Authorization: Bearer ヘッダーで認証し、認証情報には API Key（長期有効。Data Hub コンソールで作成）を使用します。MCP クライアントは OAuth によるキー不要のログインにも対応しています。CLI や Skill など、さらに多くの連携方法も準備中です。 この App は非同期で実行され、途中でキャンセルできます：キャンセル後、実行は停止します。納品済みのレコードは保持され、課金対象になります。

MCP（Model Context Protocol）を使うと、Claude や Cursor などの AI クライアントからこの App を直接呼び出せます。クライアントと認証方式を選び、下の設定をコピーしてください。

クライアント設定

Bearer の後の値を長期有効な API Key に置き換えてください。あらゆるクライアント、CI、ヘッドレス環境で利用できます。

mcpServers config
{
  "mcpServers": {
    "octoparse_datahub": {
      "type": "http",
      "url": "https://mcp-v2.octoparse.com?pin=super_ig/jd-comment",
      "headers": { "Authorization": "Bearer <YOUR_API_KEY>" }
    }
  }
}
自分の API Keys を表示 →

AI に設定を任せる

設定を手作業で編集したくない場合は、インストールプロンプトをコピーして任意の AI クライアントに貼り付けてください。AI が自分のやり方でセットアップを完了します（プロンプトは AI があなたに API Key を尋ねる形になっているため、認証情報がチャット履歴や共有設定に残りません）。

detail.access.mcp.composeHint

料金

Submit one review collection

返される件数にかかわらず、実行の送信 1 回ごとに課金されます。

$0.0001/ 回
10 returned reviews

正常に返されたレコードの件数に応じて課金されます。失敗した実行には課金されません。 10 件を 1 つの課金単位とし、端数は 10 件に切り上げて課金されます。

$0.08/ 10 件

複数の課金イベントはそれぞれ独立して累計されます。詳細は各項目をご覧ください。失敗した実行には課金されません。

Credits を確認

今すぐ試す

パラメータを入力して実行してください。結果は実際の呼び出しによるものです。

サンプル
パラメータは送信前に input.schema で検証されます
$0.08 / 10 件から