HushSearchDocs

Content Extraction

Extract clean markdown from any URL.

Scrape & extractFree demo, no key

POST/v1/extract/3 credits

Request
curl -X POST https://api.hushsearch.io/v1/extract/ \
  -H "X-API-Key: hs_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "url": "https://docs.python.org/3/library/asyncio.html",
  "include_links": true
}'

Fetches any URL and returns clean, LLM-ready markdown. Strips ads, navigation, scripts, and noise. Perfect for building RAG context from web pages.

Request

curl -X POST https://api.hushsearch.io/v1/extract/ \
  -H "X-API-Key: hs_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://arxiv.org/abs/2401.00001"
  }'

Parameters

ParameterTypeRequiredDescription
urlstring (URL)✅The URL to extract content from

Response

{
  "url": "https://arxiv.org/abs/2401.00001",
  "title": "RAG vs Fine-tuning: A Comprehensive Study",
  "markdown_content": "# RAG vs Fine-tuning\n\nThis paper presents...",
  "credits_used": 3,
  "credits_remaining": 497,
  "response_time_ms": 1240
}

Python Example

import requests

response = requests.post(
    "https://api.hushsearch.io/v1/extract/",
    headers={"X-API-Key": "hs_live_..."},
    json={"url": "https://docs.anthropic.com/en/docs/overview"}
)

data = response.json()
print(data["title"])
print(data["markdown_content"][:500])