web-search
brave/brave-search-skills
適用於網頁搜尋。回傳包含摘要、網址及縮圖的排序結果。支援最新內容篩選、安全搜尋、Goggles 自訂排序以及分頁功能。主要搜尋端點。
...展開全部關於web-search
web-search 技能提供對 Brave 搜尋引擎的程式化存取,讓使用者能夠進行線上搜尋並擷取結構化結果。此技能旨在回傳包含摘要、網址、縮圖及元資料的排序搜尋結果,協助開發人員和應用程式將網頁搜尋功能直接整合至其工作流程中。 透過支援「安全搜尋」(SafeSearch)、新鮮度篩選器,以及透過 Goggles 進行的自訂排序等功能,此技能能解決從網路上快速取得相關且經過篩選的資訊,並以適合自動化系統和使用者介面的結構化格式呈現。
此技能同時支援 GET 與 POST HTTP 方法,使其能靈活處理簡單查詢,或包含 Goggles 配置以進行自訂結果排序的複雜、較長查詢。透過參數可精確控制搜尋,包括國家、語言、結果數量、內容過濾、日期範圍,以及文字裝飾、拼字檢查和豐富回調等附加功能。 透過「最新度」與「結果篩選」選項,使用者可將搜尋範圍縮小至特定時間區間,或鎖定特定結果類型,例如新聞、影片、討論等。認證機制透過 API 金鑰管理,確保服務存取的安全性。
Web-search 此服務非常適合開發人員建置搜尋介面、資料擷取工具,或需要高速存取精選搜尋結果的應用程式。目標使用者包括那些需要從網路擷取結構化資料以建立搜尋使用者介面、代理程式或儀表板的開發者,以及利用搜尋功能來強化 AI 處理流程與研究工作流程的系統。 其速度、靈活性與結構化輸出相結合的特點,使其特別適合於快速檢索相關網路資訊至關重要,同時又能控制結果呈現與排序的應用場景。
常見問題
如何對發送至web-search 技能的請求進行驗證?
您必須在請求標頭中包含您的 API 金鑰,格式為 `X-Subscription-Token:
我可以根據最新度或內容類型篩選結果嗎?
可以,此技能支援「過去一天」、「過去一週」、「過去一個月」或「過去一年」等新鮮度篩選條件,以及自訂日期範圍。您可透過 `result_filter` 參數,篩選新聞、影片、討論、常見問題等各類結果。
搜尋支援哪些 HTTP 方法?
同時支援 GET 和 POST 方法。若查詢內容較長或使用複雜的 Goggles 設定時,建議使用 POST 方法。
web-search 是否支援安全搜尋?
是的,您可以將 `safesearch` 參數設定為 `off`、`moderate` 或 `strict`,以控制成人內容的過濾。
什麼是 Goggles,它是如何運作的?
Goggles 是一項用於自訂搜尋結果排序的功能,可透過提供 URL 或內嵌設定來實現。它允許您對結果的評分與顯示方式進行細緻的控制。
Web Search
Requires API Key: Get one at https://api.search.brave.com
Plan: Included in the Search plan. See https://api-dashboard.search.brave.com/app/subscriptions/subscribe
Quick Start (cURL)
Basic Search
curl -s "https://api.search.brave.com/res/v1/web/search?q=python+web+frameworks" \ -H "Accept: application/json" \ -H "X-Subscription-Token: ${BRAVE_SEARCH_API_KEY}"
With Parameters
curl -s "https://api.search.brave.com/res/v1/web/search" \ -H "Accept: application/json" \ -H "X-Subscription-Token: ${BRAVE_SEARCH_API_KEY}" \ -G \ --data-urlencode "q=rust programming tutorials" \ --data-urlencode "country=US" \ --data-urlencode "search_lang=en" \ --data-urlencode "count=10" \ --data-urlencode "safesearch=moderate" \ --data-urlencode "freshness=pm"
Endpoint
GET https://api.search.brave.com/res/v1/web/searchPOST https://api.search.brave.com/res/v1/web/search
Note: Both GET and POST methods are supported. POST is useful for long queries or complex Goggles.
Authentication: X-Subscription-Token: <API_KEY> header
Optional Headers:
Accept-Encoding: gzip— Enable gzip compression
When to Use Web Search
| Feature | Web Search (this) | LLM Context (llm-context) | Answers (answers) |
|---|---|---|---|
| Output | Structured results (links, snippets, metadata) | Pre-extracted page content for LLMs | End-to-end AI answers with citations |
| Result types | Web, news, videos, discussions, FAQ, infobox, locations, rich | Extracted text chunks, tables, code | Synthesized answer + source list |
| Unique features | Goggles, structured data (schemas), rich callbacks | Token budget control, threshold modes | Multi-iteration search, streaming, OpenAI SDK compatible |
| Speed | Fast (~0.5-1s) | Fast (<1s) | Slower (~30-180s) |
| Best for | Search UIs, data extraction, custom ranking | RAG pipelines, AI agents, grounding | Chat interfaces, thorough research |
Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
q | string | Yes | - | Search query (1-400 chars, max 50 words) |
country | string | No | US | Search country (2-letter country code or ALL) |
search_lang | string | No | en | Language preference (2+ char language code) |
ui_lang | string | No | en-US | UI language (e.g., "en-US") |
count | int | No | 20 | Max results per page (1-20) |
offset | int | No | 0 | Page offset for pagination (0-9) |
safesearch | string | No | moderate | Adult content filter (off/moderate/strict) |
freshness | string | No | - | Time filter (pd/pw/pm/py or date range) |
text_decorations | bool | No | true | Include highlight markers |
spellcheck | bool | No | true | Auto-correct query |
result_filter | string | No | - | Filter result types (comma-separated) |
goggles | string | No | - | Custom ranking filter (URL or inline) |
extra_snippets | bool | No | - | Get up to 5 extra snippets per result |
operators | bool | No | true | Apply search operators |
units | string | No | - | Measurement units (metric/imperial) |
enable_rich_callback | bool | No | false | Enable rich 3rd party data callback |
include_fetch_metadata | bool | No | false | Include fetched_content_timestamp on results |
Freshness Values
| Value | Description |
|---|---|
pd | Past day (24 hours) |
pw | Past week (7 days) |
pm | Past month (31 days) |
py | Past year (365 days) |
YYYY-MM-DDtoYYYY-MM-DD | Custom date range |
Result Filter Values
Filter types: discussions, faq, infobox, news, query, videos, web, locations
# Only web and video resultscurl "...&result_filter=web,videos"
Location Headers (Optional)
For location-aware results, add these headers. Lat/Long is sufficient when coordinates are known — the other headers are only needed as a fallback when coordinates are unavailable.
| Header | Type | Description |
|---|---|---|
X-Loc-Lat | float | User latitude (-90.0 to 90.0) |
X-Loc-Long | float | User longitude (-180.0 to 180.0) |
X-Loc-Timezone | string | IANA timezone (e.g., "America/San_Francisco") |
X-Loc-City | string | City name |
X-Loc-State | string | State/region code (ISO 3166-2) |
X-Loc-State-Name | string | State/region full name (e.g., "California") |
X-Loc-Country | string | 2-letter country code |
X-Loc-Postal-Code | string | Postal code (e.g., "94105") |
Priority:
X-Loc-Lat+X-Loc-Longtake precedence. When provided, downstream services resolve the location directly from coordinates and the text-based headers (City, State, Country, Postal-Code) are not used for location resolution. Provide text-based headers only when you don't have coordinates. Sending both won't break anything — lat/long simply wins.
Response Format
Response Fields
| Field | Type | Description |
|---|---|---|
type | string | Always "search" |
query.original | string | The original search query |
query.altered | string? | Spellcheck-corrected query (if changed) |
query.cleaned | string? | Cleaned/normalized query |
query.spellcheck_off | bool? | Whether spellcheck was disabled |
query.more_results_available | bool | Whether more pages exist |
query.show_strict_warning | bool? | True if strict safesearch blocked adult results |
query.search_operators | object? | Applied search operators (applied, cleaned_query, sites) |
web.type | string | Always "search" |
web.results[].title | string | Page title |
web.results[].url | string | Page URL |
web.results[].description | string? | Snippet/description text |
web.results[].age | string? | Human-readable age (e.g., "2 days ago") |
web.results[].language | string? | Content language code |
web.results[].meta_url | object | URL components (scheme, netloc, hostname, path) |
web.results[].thumbnail | object? | Thumbnail (src, original) |
web.results[].thumbnail.original | string? | Original full-size image URL |
web.results[].thumbnail.logo | bool? | Whether the thumbnail is a logo |
web.results[].profile | object? | Publisher identity (name, url, long_name, img) |
web.results[].page_age | string? | ISO datetime of publication (e.g., "2025-04-12T14:22:41") |
web.results[].extra_snippets | list[str]? | Up to 5 additional excerpts |
web.results[].deep_results | object? | Additional links (buttons, links) from the page |
web.results[].schemas | list? | Raw schema.org structured data |
web.results[].product | object? | Product info and reviews |
web.results[].recipe | object? | Recipe details (ingredients, time, ratings) |
web.results[].article | object? | Article metadata (author, publisher, date) |
web.results[].book | object? | Book info (author, ISBN, rating) |
web.results[].software | object? | Software product info |
web.results[].rating | object? | Aggregate ratings |
web.results[].faq | object? | FAQ found on the page |
web.results[].movie | object? | Movie info (directors, actors, genre) |
web.results[].video | object? | Video metadata (duration, views, creator) |
web.results[].location | object? | Location/restaurant details |
web.results[].qa | object? | Question/answer info |
web.results[].creative_work | object? | Creative work data |
web.results[].music_recording | object? | Music/song data |
web.results[].organization | object? | Organization info |
web.results[].review | object? | Review data |
web.results[].content_type | string? | Content type classification |
web.results[].fetched_content_timestamp | int? | Fetch timestamp (with include_fetch_metadata=true) |
web.mutated_by_goggles | bool | Whether results were re-ranked by Goggles |
web.family_friendly | bool | Whether results are family-friendly |
mixed | object? | Preferred display order (see Mixed Response below) |
discussions.results[] | array? | Forum discussion clusters |
discussions.results[].data.forum_name | string? | Forum/community name |
discussions.results[].data.num_answers | int? | Number of answers/replies |
discussions.results[].data.question | string? | Discussion question |
discussions.results[].data.top_comment | string? | Top-voted comment excerpt |
faq.results[] | array? | FAQ entries |
news.results[] | array? | News articles |
videos.results[] | array? | Video results |
infobox.results[] | array? | Knowledge graph entries |
locations.results[] | array? | Local POI results |
rich.hint.vertical | string? | Rich result type |
rich.hint.callback_key | string? | Callback key for rich data |
JSON Example
{ "type": "search", "query": { "original": "python frameworks", "altered": "python web frameworks", "spellcheck_off": false, "more_results_available": true }, "web": { "type": "search", "results": [ { "title": "Top Python Web Frameworks", "url": "https://example.com/python-frameworks", "description": "A comprehensive guide to Python web frameworks...", "age": "2 days ago", "language": "en", "meta_url": { "scheme": "https", "netloc": "example.com", "hostname": "example.com", "path": "/python-frameworks" }, "thumbnail": { "src": "https://...", "original": "https://original-image-url.com/img.jpg" }, "extra_snippets": ["Additional excerpt 1...", "Additional excerpt 2..."] } ], "family_friendly": true }, "mixed": { "type": "mixed", "main": [ {"type": "web", "index": 0, "all": false}, {"type": "web", "index": 1, "all": false}, {"type": "videos", "all": true} ], "top": [], "side": [] }, "videos": { "...": "..." }, "news": { "...": "..." }, "rich": { "type": "rich", "hint": { "vertical": "weather", "callback_key": "<callback_key_hex>" } }}Mixed Response
The mixed object defines the preferred display order of results across types. It contains three arrays:
| Array | Purpose |
|---|---|
main | Primary result list (ordered sequence of results to display) |
top | Results to display above main results |
side | Results to display alongside main results (e.g., infobox) |
Each entry is a ResultReference with type (e.g., "web", "videos"), index (into the corresponding result array), and all (true to include all results of that type at this position).
Search Operators
| Operator | Syntax | Description |
|---|---|---|
| Site | site:example.com | Limit results to a specific domain |
| File extension | ext:pdf | Results with a specific file extension |
| File type | filetype:pdf | Results created in a specific file type |
| In title | intitle:python | Pages with term in the title |
| In body | inbody:tutorial | Pages with term in the body |
| In page | inpage:guide | Pages with term in title or body |
| Language | lang:es | Pages in a specific language (ISO 639-1) |
| Location | loc:us | Pages from a specific country (ISO 3166-1 alpha-2) |
| Include | +term | Force inclusion of a term |
| Exclude | -term | Exclude pages containing the term |
| Exact match | "exact phrase" | Match the exact phrase in order |
| AND | term1 AND term2 | Both terms required (uppercase) |
| OR / NOT | term1 OR term2, NOT term | Logical operators (uppercase) |
Set operators=false to disable operator parsing.
Goggles (Custom Ranking) — Unique to Brave
Goggles let you re-rank search results — boost trusted sources, suppress SEO spam, or build focused search scopes.
| Method | Example |
|---|---|
| Hosted | --data-urlencode "goggles=https://raw.githubusercontent.com/brave/goggles-quickstart/main/goggles/rust_programming.goggle" |
| Inline | --data-urlencode 'goggles=$discard$site=example.com' |
Hosted goggles must be on GitHub/GitLab, include
! name:,! description:,! author:headers, and be registered at https://search.brave.com/goggles/create. Inline rules need no registration.
Syntax: $boost=N / $downrank=N (1–10), $discard, $site=example.com. Combine with commas: $site=example.com,boost=3. Separate rules with (%0A).
Allow list: $discard$site=docs.python.org$site=developer.mozilla.org — Block list: $discard,site=pinterest.com$discard,site=quora.com
Resources: Discover · Syntax · Quickstart
Rich Data Enrichments
For queries about weather, stocks, sports, currency, etc., use the rich callback workflow:
# 1. Search with rich callback enabledcurl -s "https://api.search.brave.com/res/v1/web/search?q=weather+san+francisco&enable_rich_callback=true" \ -H "X-Subscription-Token: ${BRAVE_SEARCH_API_KEY}"# Response includes: "rich": {"hint": {"callback_key": "abc123...", "vertical": "weather"}}# 2. Get rich data with the callback keycurl -s "https://api.search.brave.com/res/v1/web/rich?callback_key=abc123..." \ -H "X-Subscription-Token: ${BRAVE_SEARCH_API_KEY}"
Supported Rich Types: Calculator, Definitions, Unit Conversion, Unix Timestamp, Package Tracker, Stock, Currency, Cryptocurrency, Weather, American Football, Baseball, Basketball, Cricket, Football/Soccer, Ice Hockey, Web3, Translator
Rich Callback Endpoint
GET https://api.search.brave.com/res/v1/web/rich
| Parameter | Type | Required | Description |
|---|---|---|---|
callback_key | string | Yes | Callback key from the web search rich.hint.callback_key field |
Use Cases
- General-purpose search integration: Richest result set (web, news, videos, discussions, FAQ, infobox, locations) in one call. For RAG/LLM grounding, prefer
llm-context. - Structured data extraction: Products, recipes, ratings, articles via
schemasand typed fields on results. - Custom search with Goggles: Unique to Brave. Boost/discard sites with inline rules or hosted Goggles for fully customized ranking.
Notes
- Pagination: Use
offset(0-9) withcountto page through results - Count: Max 20 for web search; actual results may be less than requested





首頁
