web-research

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Web Research with x402 APIs

使用x402 API进行网页研究

Access Exa (neural search) and Firecrawl (web scraping) through x402-protected endpoints.

通过x402保护的端点访问Exa（神经网络搜索）和Firecrawl（网页爬取）工具。

Setup

设置

See rules/getting-started.md for installation and wallet setup.

请查看rules/getting-started.md了解安装和钱包设置方法。

Quick Reference

快速参考

Task	Endpoint	Price	Best For
Neural search	`https://stableenrich.dev/api/exa/search`	$0.01	Semantic web search
Find similar	`https://stableenrich.dev/api/exa/find-similar`	$0.01	Pages similar to a URL
Extract text	`https://stableenrich.dev/api/exa/contents`	$0.002	Clean text from URLs
Direct answers	`https://stableenrich.dev/api/exa/answer`	$0.01	Factual Q&A
Scrape page	`https://stableenrich.dev/api/firecrawl/scrape`	$0.0126	Single page to markdown
Web search	`https://stableenrich.dev/api/firecrawl/search`	$0.0252	Search with scraping

任务	端点	价格	最佳适用场景
神经网络搜索	`https://stableenrich.dev/api/exa/search`	$0.01	语义网页搜索
查找相似页面	`https://stableenrich.dev/api/exa/find-similar`	$0.01	与指定URL相似的页面
提取文本	`https://stableenrich.dev/api/exa/contents`	$0.002	从URL提取干净文本
直接获取答案	`https://stableenrich.dev/api/exa/answer`	$0.01	事实性问答
爬取页面	`https://stableenrich.dev/api/firecrawl/scrape`	$0.0126	将单页面转换为markdown
网页搜索	`https://stableenrich.dev/api/firecrawl/search`	$0.0252	搜索并爬取结果

When to Use What

工具选择指南

Scenario	Tool
General web search	WebSearch (free) or Exa ($0.01)
Semantic/conceptual search	Exa search
Find pages like X	Exa find-similar
Get clean text from URL	Exa contents
Scrape blocked/JS-heavy site	Firecrawl scrape
Search + scrape results	Firecrawl search
Quick fact lookup	Exa answer

See rules/when-to-use.md for detailed guidance.

场景	工具
通用网页搜索	WebSearch（免费）或Exa（$0.01）
语义/概念搜索	Exa search
查找与X相似的页面	Exa find-similar
从URL获取干净文本	Exa contents
爬取被封锁/JS密集型网站	Firecrawl scrape
搜索并爬取结果	Firecrawl search
快速事实查询	Exa answer
请查看rules/when-to-use.md获取详细指导。

Exa Neural Search

Exa神经网络搜索

Semantic search that understands meaning, not just keywords:

bash

npx agentcash fetch https://stableenrich.dev/api/exa/search -m POST -b '{
  "query": "startups building AI agents for customer support",
  "numResults": 10,
  "type": "neural"
}'

Options:

```
query
```
- Search query (required)
```
numResults
```
- Number of results (default: 10, max: 25)
```
type
```
- "neural" (semantic) or "keyword" (traditional)
```
includeDomains
```
- Only search these domains
```
excludeDomains
```
- Skip these domains
```
startPublishedDate
```
/
```
endPublishedDate
```
- Date range filter

Returns: List of URLs with titles, snippets, and relevance scores.

理解语义而非仅匹配关键词的语义搜索：

bash

npx agentcash fetch https://stableenrich.dev/api/exa/search -m POST -b '{
  "query": "startups building AI agents for customer support",
  "numResults": 10,
  "type": "neural"
}'

选项：

```
query
```
- 搜索查询（必填）
```
numResults
```
- 结果数量（默认：10，最大值：25）
```
type
```
- "neural"（语义）或"keyword"（传统）
```
includeDomains
```
- 仅在这些域名中搜索
```
excludeDomains
```
- 排除这些域名
```
startPublishedDate
```
/
```
endPublishedDate
```
- 日期范围筛选 返回结果：包含URL、标题、摘要和相关度评分的列表。

Find Similar Pages

查找相似页面

Find pages semantically similar to a reference URL:

bash

npx agentcash fetch https://stableenrich.dev/api/exa/find-similar -m POST -b '{
  "url": "https://example.com/article-i-like",
  "numResults": 10
}'

Great for:

Finding competitor products
Discovering related content
Expanding research sources

查找与参考URL语义相似的页面：

bash

npx agentcash fetch https://stableenrich.dev/api/exa/find-similar -m POST -b '{
  "url": "https://example.com/article-i-like",
  "numResults": 10
}'

适用场景：

查找竞品产品
发现相关内容
拓展研究来源

Extract Text Content

提取文本内容

Get clean, structured text from URLs:

bash

npx agentcash fetch https://stableenrich.dev/api/exa/contents -m POST -b '{
  "urls": [
    "https://example.com/article1",
    "https://example.com/article2"
  ]
}'

Options:

```
urls
```
- Array of URLs to extract
```
text
```
- Include full text (default: true)
```
highlights
```
- Include key highlights

Cheapest option ($0.002) when you already have URLs and just need the content.

从URL获取干净、结构化的文本：

bash

npx agentcash fetch https://stableenrich.dev/api/exa/contents -m POST -b '{
  "urls": [
    "https://example.com/article1",
    "https://example.com/article2"
  ]
}'

选项：

```
urls
```
- 待提取的URL数组
```
text
```
- 是否包含完整文本（默认：true）
```
highlights
```
- 是否包含关键要点这是成本最低的选项（$0.002），适用于已获取URL仅需提取内容的场景。

Direct Answers

直接获取答案

Get factual answers to questions:

bash

npx agentcash fetch https://stableenrich.dev/api/exa/answer -m POST -b '{"query": "What is the population of Tokyo?"}'

Returns a direct answer with source citations. Best for:

Factual questions
Quick lookups
Verification of claims

获取事实性问题的答案：

bash

npx agentcash fetch https://stableenrich.dev/api/exa/answer -m POST -b '{"query": "What is the population of Tokyo?"}'

返回带来源引用的直接答案。最佳适用场景：

事实性问题
快速查询
验证主张

Firecrawl Scrape

Firecrawl页面爬取

Scrape a single page to clean markdown:

bash

npx agentcash fetch https://stableenrich.dev/api/firecrawl/scrape -m POST -b '{"url": "https://example.com/page-to-scrape"}'

Options:

```
url
```
- Page to scrape (required)
```
formats
```
- Output formats: ["markdown", "html", "links"]
```
onlyMainContent
```
- Skip nav/footer/ads (default: true)
```
waitFor
```
- Wait ms for JS to render

Advantages over WebFetch:

Handles JavaScript-rendered content
Bypasses common blocking
Extracts main content only
LLM-optimized markdown output

将单页面爬取为干净的markdown格式：

bash

npx agentcash fetch https://stableenrich.dev/api/firecrawl/scrape -m POST -b '{"url": "https://example.com/page-to-scrape"}'

选项：

```
url
```
- 待爬取的页面（必填）
```
formats
```
- 输出格式：["markdown", "html", "links"]
```
onlyMainContent
```
- 是否跳过导航/页脚/广告（默认：true）
```
waitFor
```
- 等待JS渲染的毫秒数 相比WebFetch的优势：
支持JS渲染的内容
绕过常见的访问封锁
仅提取主要内容
生成适合LLM的markdown输出

Firecrawl Search

Firecrawl搜索

Web search with automatic scraping of results:

bash

npx agentcash fetch https://stableenrich.dev/api/firecrawl/search -m POST -b '{
  "query": "best practices for react server components",
  "limit": 5
}'

Options:

```
query
```
- Search query (required)
```
limit
```
- Number of results (default: 5)
```
scrapeOptions
```
- Options passed to scraper

Returns search results with full scraped content for each.

自动爬取搜索结果的网页搜索：

bash

npx agentcash fetch https://stableenrich.dev/api/firecrawl/search -m POST -b '{
  "query": "best practices for react server components",
  "limit": 5
}'

选项：

```
query
```
- 搜索查询（必填）
```
limit
```
- 结果数量（默认：5）
```
scrapeOptions
```
- 传递给爬取工具的选项返回包含每个结果完整爬取内容的搜索结果列表。

Workflows

工作流

Deep Research

深度研究

(Optional) Check balance:
```
npx agentcash wallet info
```
Search broadly with Exa
Find related sources with find-similar
Extract content from top sources
Synthesize findings

bash

npx agentcash fetch https://stableenrich.dev/api/exa/search -m POST -b '{"query": "AI agents in healthcare 2024", "numResults": 15}'

bash

npx agentcash fetch https://stableenrich.dev/api/exa/find-similar -m POST -b '{"url": "https://best-article-found.com"}'

bash

npx agentcash fetch https://stableenrich.dev/api/exa/contents -m POST -b '{"urls": ["url1", "url2", "url3"]}'

（可选）查看余额：
```
npx agentcash wallet info
```
使用Exa进行广泛搜索
使用find-similar查找相关来源
从优质来源提取内容
整合研究结果

bash

npx agentcash fetch https://stableenrich.dev/api/exa/search -m POST -b '{"query": "AI agents in healthcare 2024", "numResults": 15}'

bash

npx agentcash fetch https://stableenrich.dev/api/exa/find-similar -m POST -b '{"url": "https://best-article-found.com"}'

bash

npx agentcash fetch https://stableenrich.dev/api/exa/contents -m POST -b '{"urls": ["url1", "url2", "url3"]}'

Blocked Site Scraping

被封锁网站爬取

Try WebFetch first (free)
If blocked/empty, use Firecrawl with
```
waitFor
```
for JS-heavy sites

bash

npx agentcash fetch https://stableenrich.dev/api/firecrawl/scrape -m POST -b '{"url": "https://blocked-site.com/article", "waitFor": 3000}'

先尝试WebFetch（免费）
如果被封锁/返回空内容，使用Firecrawl并设置
```
waitFor
```
以处理JS密集型网站

bash

npx agentcash fetch https://stableenrich.dev/api/firecrawl/scrape -m POST -b '{"url": "https://blocked-site.com/article", "waitFor": 3000}'

Cost Optimization

成本优化

Use Exa contents ($0.002) when you already have URLs
Use WebSearch/WebFetch first (free) and fall back to x402 endpoints
Batch URL extraction - pass multiple URLs to Exa contents
Limit results - request only as many as needed

使用Exa contents（$0.002）：当你已拥有URL时
优先使用WebSearch/WebFetch（免费），必要时再使用x402端点
批量提取URL - 向Exa contents传递多个URL
限制结果数量 - 仅请求所需数量的结果