Web Search Rerank

Search the web from a natural-language request and return relevance-ranked webpage results with content and source metadata

データ収集 Finance & Investment Multi-platform Other

概要

Web research often starts with a question rather than a known page. This Data App turns a natural-language request into a relevance-ranked set of webpages, preserving the page text, concise summaries, source identity, and publication context needed for analysis.

It is useful for quickly building a research set around a company, product, topic, or event. Freshness and domain filters help focus the search, while account, organization, and search-role filters can narrow the results when those source attributes are available.

Data notes

Each row represents one webpage returned for the submitted search question. Page URL is used to identify a result and remove duplicates. The result set covers webpage records only; a separate image collection returned by the source is not included here.

Page content may be empty even when a title, snippet, or summary is available. Account name, organization name, site icon, cached URL, language, and family-friendly or navigational flags may also be unavailable for individual pages. Publication and crawl timestamps are preserved as source text without inferring a timezone.

What the results look like

Each row is one relevance-ranked webpage result.

Page URL	Page title	Site name	Published at	Snippet
https://www.example.com/article/123	Xiaomi car delivery momentum continues to rise	Example Site	2026-08-05 14:23:10	Xiaomi car deliveries have continued to grow.

Additional values include the full page content, summary, display and cached URLs, account and organization names, language, source identifiers, and crawl time.

Use cases

Build a research set for a company, product, market, or event by combining Page title, Page content, Snippet, and Summary.
Monitor recent coverage by pairing a Freshness filter with Published at and Last crawled at.
Compare source visibility by grouping results by Site name, Account name, or Organization name.
Preserve traceable source links by using Page URL and Display URL when reviewing or exporting results.

適用範囲と境界

Each run accepts one natural-language search request and returns up to 200 relevance-ranked webpage records in one response. Separate image results are not included.

適している用途
When you need relevance-ranked webpage results for a natural-language research question
When you need webpage titles, summaries, content, source metadata, and publication timestamps in a structured result set
When you want to narrow web search by freshness, domains, account, organization, or search role

適さない用途
When you need image-only results or a dedicated image search dataset
When you need private, login-only, or non-public webpage content

失敗時の処理

作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。

1If no useful webpages are returned, broaden the query or remove restrictive domain and freshness filters
2Retry later after rate limiting, temporary service unavailability, or a timeout
3If authentication fails, verify the API Key configured for the execution environment

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。

フィールド	業務名称	型	必須	デフォルト	列挙値／制約	例	説明
query	Search question	string	はい	—	—	Xiaomi car delivery and sales performance	The natural-language topic or question to search. Provide at least one character; clearer wording produces more focused results.
count	Result count	integer	いいえ	10	1–200	—	The number of webpage results to request. The default is 10 and the allowed range is 1 to 200; fewer results may be available for a narrow query.
freshness	Freshness filter	string	いいえ	noLimit	—	—	Limits results by recency. Use noLimit, oneDay, oneWeek, oneMonth, oneYear, a date such as 2026-08-05, or a date range such as 2026-08-01..2026-08-31. The default is noLimit.
include	Included domains	string	いいえ	—	—	—	Search only the listed domains. Separate up to 100 domain values with \| or commas, using domain values supplied by the Data Hub domain list.
exclude	Excluded domains	string	いいえ	—	—	—	Exclude the listed domains from the search. Separate up to 100 domain values with \| or commas, using domain values supplied by the Data Hub domain list.
account_name	Account name	string	いいえ	—	—	—	Filters results to an exact account name when the source identifies one. Leave empty to search without an account filter.
office_name	Organization name	string	いいえ	—	—	—	Filters results to an exact organization name when the source identifies one. Leave empty to search without an organization filter.
role_code	Search role	string	いいえ	—	—	—	Uses a configured Data Hub search role, such as WEB_SEARCH. Leave empty to use the system default role.

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。

フィールド	業務名称	型	例	説明
account_name	Account name	string	China News Network	The account name associated with the webpage when available.
cached_page_url	Cached page URL	string	—	The cached webpage URL when available.
content	Page content	string	Xiaomi car deliveries have continued to grow, with stronger showroom traffic and steady delivery scheduling.	The webpage body content when available. It is independent from the snippet and summary and may be empty.
date_last_crawled	Last crawled at	string	2026-08-05 15:00:00	The source timestamp of the latest crawl, preserved as returned without timezone conversion.
date_published	Published at	string	2026-08-05 14:23:10	The webpage publication timestamp when available, preserved as returned without timezone conversion.
display_url	Display URL	string	https://www.example.com/article/123	The URL formatted for displaying the webpage result when available.
id	Result ID	string	0	The source sorting identifier for this webpage result.
is_family_friendly	Family-friendly	boolean	false	Whether the source marks the webpage as suitable for family browsing. Empty source values are represented as false.
is_navigational	Navigational result	boolean	false	Whether the source marks the result as navigational. Empty source values are represented as false.
language	Content language	string	en	The language code reported for the webpage when available.
name	Page title	string	Xiaomi car delivery momentum continues to rise	The title of the webpage result.
office_name	Organization name	string	—	The organization associated with the webpage when available.
site_icon	Site icon URL	string	—	The site icon URL when available.
site_name	Site name	string	Example Site	The name of the site hosting the webpage when available.
snippet	Snippet	string	Xiaomi car deliveries have continued to grow.	A short source-provided excerpt for the webpage when available.
summary	Summary	string	Xiaomi car deliveries have continued to grow, with stronger showroom traffic and steady delivery scheduling.	A more complete source-provided summary of the webpage when available.
url	Page URL	string	https://www.example.com/article/123	The original webpage URL. This value identifies and de-duplicates a result record.

レコード Schema

出力はレコード単位で 1 件ずつ返されます。 detail.output.idFieldHint

output.schema

{
  "type": "object",
  "properties": {
    "account_name": {
      "type": "string",
      "title": "Account name",
      "description": "The account name associated with the webpage when available.",
      "prefill": "China News Network"
    },
    "cached_page_url": {
      "type": "string",
      "title": "Cached page URL",
      "description": "The cached webpage URL when available."
    },
    "content": {
      "type": "string",
      "title": "Page content",
      "description": "The webpage body content when available. It is independent from the snippet and summary and may be empty.",
      "prefill": "Xiaomi car deliveries have continued to grow, with stronger showroom traffic and steady delivery scheduling."
    },
    "date_last_crawled": {
      "type": "string",
      "title": "Last crawled at",
      "description": "The source timestamp of the latest crawl, preserved as returned without timezone conversion.",
      "prefill": "2026-08-05 15:00:00"
    },
    "date_published": {
      "type": "string",
      "title": "Published at",
      "description": "The webpage publication timestamp when available, preserved as returned without timezone conversion.",
      "prefill": "2026-08-05 14:23:10"
    },
    "display_url": {
      "type": "string",
      "title": "Display URL",
      "description": "The URL formatted for displaying the webpage result when available.",
      "prefill": "https://www.example.com/article/123"
    },
    "id": {
      "type": "string",
      "title": "Result ID",
      "description": "The source sorting identifier for this webpage result.",
      "prefill": "0"
    },
    "is_family_friendly": {
      "type": "boolean",
      "title": "Family-friendly",
      "description": "Whether the source marks the webpage as suitable for family browsing. Empty source values are represented as false.",
      "prefill": false
    },
    "is_navigational": {
      "type": "boolean",
      "title": "Navigational result",
      "description": "Whether the source marks the result as navigational. Empty source values are represented as false.",
      "prefill": false
    },
    "language": {
      "type": "string",
      "title": "Content language",
      "description": "The language code reported for the webpage when available.",
      "prefill": "en"
    },
    "name": {
      "type": "string",
      "title": "Page title",
      "description": "The title of the webpage result.",
      "prefill": "Xiaomi car delivery momentum continues to rise"
    },
    "office_name": {
      "type": "string",
      "title": "Organization name",
      "description": "The organization associated with the webpage when available."
    },
    "site_icon": {
      "type": "string",
      "title": "Site icon URL",
      "description": "The site icon URL when available."
    },
    "site_name": {
      "type": "string",
      "title": "Site name",
      "description": "The name of the site hosting the webpage when available.",
      "prefill": "Example Site"
    },
    "snippet": {
      "type": "string",
      "title": "Snippet",
      "description": "A short source-provided excerpt for the webpage when available.",
      "prefill": "Xiaomi car deliveries have continued to grow."
    },
    "summary": {
      "type": "string",
      "title": "Summary",
      "description": "A more complete source-provided summary of the webpage when available.",
      "prefill": "Xiaomi car deliveries have continued to grow, with stronger showroom traffic and steady delivery scheduling."
    },
    "url": {
      "type": "string",
      "title": "Page URL",
      "description": "The original webpage URL. This value identifies and de-duplicates a result record.",
      "prefill": "https://www.example.com/article/123"
    }
  },
  "required": [],
  "additionalProperties": false
}

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。

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": {
    "meme_today__data-hub-web-search-rerank": {
      "type": "http",
      "url": "https://mcp-v2.octoparse.com?pin=meme_today/data-hub-web-search-rerank",
      "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

50 returned records

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。 50 件を 1 つの課金単位とし、端数は 50 件に切り上げて課金されます。

$0.008/ 50 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

Search questionquery*The natural-language topic or question to search. Provide at least one character; clearer wording produces more focused results.

Result countcount（任意）The number of webpage results to request. The default is 10 and the allowed range is 1 to 200; fewer results may be available for a narrow query.

Freshness filterfreshness（任意）Limits results by recency. Use noLimit, oneDay, oneWeek, oneMonth, oneYear, a date such as 2026-08-05, or a date range such as 2026-08-01..2026-08-31. The default is noLimit.

Included domainsinclude（任意）Search only the listed domains. Separate up to 100 domain values with | or commas, using domain values supplied by the Data Hub domain list.

Excluded domainsexclude（任意）Exclude the listed domains from the search. Separate up to 100 domain values with | or commas, using domain values supplied by the Data Hub domain list.

Account nameaccount_name（任意）Filters results to an exact account name when the source identifies one. Leave empty to search without an account filter.

Organization nameoffice_name（任意）Filters results to an exact organization name when the source identifies one. Leave empty to search without an organization filter.

Search rolerole_code（任意）Uses a configured Data Hub search role, such as WEB_SEARCH. Leave empty to use the system default role.

まず必須パラメータを入力してください

$0.008 / 50 件