helve.web_extractFetch and extract clean markdown, summaries, or query-focused excerpts from up to 10 URLs across 9 extraction providers.
Tool ID: olostep.scrape
Scrape JS-rendered or bot-protected webpages into clean markdown, HTML, or structured JSON via Olostep.
| Parameter | Type | Required | Description |
|---|---|---|---|
url_to_scrape | string | Required | Public webpage URL to scrape with JS rendering and anti-bot handling |
formats | array | Required | Output formats (default: ['markdown']) |
country | string | Optional | Optional ISO country code for geo-routed scraping (e.g. 'US', 'GB') |
llm_extract | object | Optional | Optional structured LLM extraction schema object |
curl -X POST https://helve.dev/v1/tools/call \
-H "Authorization: Bearer sk_live_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"tool_id": "olostep.scrape",
"arguments": {
"url_to_scrape": "https://example.com",
"formats": [
"markdown"
]
}
}'
call_tool){
"name": "call_tool",
"arguments": {
"tool_id": "olostep.scrape",
"arguments": {
"url_to_scrape": "https://example.com",
"formats": [
"markdown"
]
}
}
}
helve.web_extractFetch and extract clean markdown, summaries, or query-focused excerpts from up to 10 URLs across 9 extraction providers.
browserless.contentRender any JavaScript-heavy web page in headless Chrome via Browserless.io and return the full rendered HTML.
browserless.scrapeExtract structured text, HTML, and attributes for CSS selectors from a JS-rendered page via Browserless.io.
supadata.web_scrapeExtract clean markdown/text content and outbound URLs from a webpage via Supadata.
llamaparse.parse_urlParse a PDF or document URL into clean page-by-page Markdown and text using LlamaParse v2 (polls up to 25s). Requires your own LlamaCloud API key via X-Provider-Key (0% Helve fee).
llamaparse.get_jobFetch the status, page-by-page Markdown, and plain text for an existing LlamaParse v2 job by job_id. Requires your own LlamaCloud API key via X-Provider-Key (0% Helve fee).