151 lines
5.2 KiB
JavaScript
151 lines
5.2 KiB
JavaScript
/**
|
||
* 零依赖搜索核心:Parallel(默认,匿名免 key)与 Exa(备用)两个免费后端的统一封装。
|
||
*
|
||
* 只用 Node 内置 fetch,不依赖任何 npm 包。两个后端都是公开的免费 MCP 端点,
|
||
* 本模块以 JSON-RPC `tools/call` 的方式直接调用它们,并归一化成统一的结果结构:
|
||
* `{ url, title?, snippet?, publishedAt? }[]`。
|
||
*
|
||
* 上游实现参考:@sheep233_/dsh-web-search-free(github.com/sheep-programmer/dsh-web-search-free)。
|
||
*/
|
||
|
||
/** Parallel Web Search 免费 MCP 端点(匿名可用,OpenCode 默认后端之一)。 */
|
||
export const PARALLEL_MCP_URL = 'https://search.parallel.ai/mcp';
|
||
/** Exa 免费 MCP 端点(匿名可用;EXA_API_KEY 可提升限额)。 */
|
||
export const EXA_MCP_URL = 'https://mcp.exa.ai/mcp';
|
||
|
||
const USER_AGENT = 'web-search-free/1.0.0';
|
||
/** 单次上游搜索请求的超时,避免远端挂起拖死 MCP 请求。 */
|
||
const REQUEST_TIMEOUT_MS = Number(process.env.SEARCH_TIMEOUT_MS ?? 30_000);
|
||
|
||
/**
|
||
* 向免费 MCP 端点发一次 `tools/call`,返回工具结果里的 text 载荷。
|
||
* 响应可能是裸 JSON,也可能是 SSE(`data: {...}`)分帧,两种都兼容。
|
||
*/
|
||
async function callMcpTool(endpoint, toolName, toolArgs, signal) {
|
||
const response = await fetch(endpoint, {
|
||
method: 'POST',
|
||
redirect: 'error',
|
||
headers: {
|
||
'content-type': 'application/json',
|
||
'accept': 'application/json, text/event-stream',
|
||
'user-agent': USER_AGENT,
|
||
},
|
||
body: JSON.stringify({
|
||
jsonrpc: '2.0',
|
||
id: 1,
|
||
method: 'tools/call',
|
||
params: { name: toolName, arguments: toolArgs },
|
||
}),
|
||
...(signal !== undefined ? { signal } : {}),
|
||
});
|
||
if (!response.ok) {
|
||
throw new Error(`${toolName} API error (HTTP ${response.status})`);
|
||
}
|
||
const text = extractToolText(await response.text());
|
||
if (text === undefined) {
|
||
throw new Error(`${toolName} returned no tool result`);
|
||
}
|
||
return text;
|
||
}
|
||
|
||
/** 从裸 JSON 或 SSE 文本中提取 MCP `tools/call` 的 result.content[].text。 */
|
||
export function extractToolText(body) {
|
||
const parsePayload = (raw) => {
|
||
try {
|
||
const data = JSON.parse(raw);
|
||
const item = data.result?.content?.find((c) => c.type === 'text' && typeof c.text === 'string');
|
||
return item?.text || undefined;
|
||
} catch {
|
||
return undefined; // 不是 JSON 载荷,交给 SSE 行解析
|
||
}
|
||
};
|
||
|
||
const trimmed = body.trim();
|
||
if (trimmed.length > 0) {
|
||
const direct = parsePayload(trimmed);
|
||
if (direct !== undefined) return direct;
|
||
}
|
||
for (const line of body.split('\n')) {
|
||
if (!line.startsWith('data: ')) continue;
|
||
const data = parsePayload(line.slice(6));
|
||
if (data !== undefined) return data;
|
||
}
|
||
return undefined;
|
||
}
|
||
|
||
/** Parallel 响应解析:text 是内嵌 JSON `{ results: [...] }`。 */
|
||
export function mapParallelResponse(text) {
|
||
let payload;
|
||
try {
|
||
payload = JSON.parse(text);
|
||
} catch (error) {
|
||
throw new Error(`Parallel search returned an unprocessable payload: ${String(error)}`);
|
||
}
|
||
const sources = [];
|
||
for (const item of payload.results ?? []) {
|
||
if (!item.url) continue;
|
||
sources.push({
|
||
url: item.url,
|
||
...(item.title ? { title: item.title } : {}),
|
||
...(item.excerpts?.length > 0 ? { snippet: item.excerpts.join(' ') } : {}),
|
||
...(item.publish_date ? { publishedAt: item.publish_date } : {}),
|
||
});
|
||
}
|
||
return sources;
|
||
}
|
||
|
||
/**
|
||
* Exa 响应解析:text 是纯文本块,每条结果以 `Title: ` 开头:
|
||
* ```
|
||
* Title: <标题>
|
||
* URL: <链接>
|
||
* Published: <日期 | N/A>
|
||
* Author: <作者 | N/A>
|
||
* Highlights:
|
||
* <正文摘要>
|
||
* ```
|
||
*/
|
||
export function parseExaText(text) {
|
||
const blocks = text.split(/(?=^Title: )/m).filter((block) => block.trim().length > 0);
|
||
const sources = [];
|
||
for (const block of blocks) {
|
||
const url = block.match(/^URL: (\S+)$/m)?.[1];
|
||
if (url === undefined) continue;
|
||
const title = block.match(/^Title: (.+)$/m)?.[1]?.trim();
|
||
const published = block.match(/^Published: (.+)$/m)?.[1]?.trim();
|
||
const highlights = block.split(/^Highlights:\s*$/m)[1]?.trim();
|
||
sources.push({
|
||
url,
|
||
...(title ? { title } : {}),
|
||
...(highlights ? { snippet: highlights.slice(0, 500) } : {}),
|
||
...(published && published !== 'N/A' ? { publishedAt: published } : {}),
|
||
});
|
||
}
|
||
return sources;
|
||
}
|
||
|
||
/** Parallel 搜索(默认免费后端)。 */
|
||
export async function parallelSearch(query, maxResults) {
|
||
const text = await callMcpTool(PARALLEL_MCP_URL, 'web_search', {
|
||
objective: query,
|
||
search_queries: [query],
|
||
}, AbortSignal.timeout(REQUEST_TIMEOUT_MS));
|
||
const sources = mapParallelResponse(text);
|
||
return maxResults !== undefined ? sources.slice(0, maxResults) : sources;
|
||
}
|
||
|
||
/** Exa 搜索(备用免费后端;apiKey 可选,用于提升匿名限额)。 */
|
||
export async function exaSearch(query, maxResults, apiKey) {
|
||
const endpoint = apiKey
|
||
? `${EXA_MCP_URL}?exaApiKey=${encodeURIComponent(apiKey)}`
|
||
: EXA_MCP_URL;
|
||
const text = await callMcpTool(endpoint, 'web_search_exa', {
|
||
query,
|
||
type: 'auto',
|
||
numResults: maxResults ?? 8,
|
||
livecrawl: 'fallback',
|
||
}, AbortSignal.timeout(REQUEST_TIMEOUT_MS));
|
||
const sources = parseExaText(text);
|
||
return maxResults !== undefined ? sources.slice(0, maxResults) : sources;
|
||
}
|