Skip to main content
AI Studio  add-on for Spider.
AI & Developer
ollama.com Verified

Ollama Scraper

Extract local LLM model listings, download counts, parameter sizes, and quantization details from the Ollama library. Built on spider-browser .

Get started Docs
target
ollama.com
success rate
99.9%
latency
~4ms
POST /fetch/ollama.com/
return_format
curl -X POST https://api.spider.cloud/fetch/ollama.com/ \
  -H "Authorization: Bearer $SPIDER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"return_format": "json"}'
200 OK · cache hit · response shape
{
  "url": "https://ollama.com/",
  "status": 200,
  "data": {
    "model_name": "string",
    "parameter_size": "string",
    "downloads": "string",
    "tags": "string",
    "quantization": "string",
    "description": "string",
    "last_updated": "string",
    "capabilities": "string"
  }
}
Quick start

Extract data in minutes.

Structured JSON from ollama.com with a single POST. AI-resolved selectors, cached on the first call.

ollama-scraper.ts
import { SpiderBrowser } from "spider-browser";

const spider = new SpiderBrowser({
  apiKey: process.env.SPIDER_API_KEY!,
  stealth: 2,
});

await spider.connect();
const page = spider.page!;
await page.goto("https://ollama.com/library");
await page.content(10000);

const data = await page.evaluate(`(() => {
  const models = [];
  document.querySelectorAll("[class*='model'], li a[href*='/library/']").forEach(el => {
    const name = el.querySelector("h2, [class*='name'], span:first-child")?.textContent?.trim();
    const desc = el.querySelector("p, [class*='description']")?.textContent?.trim();
    const pulls = el.querySelector("[class*='pulls'], [class*='download']")?.textContent?.trim();
    const tags = el.querySelector("[class*='tags'], [class*='size']")?.textContent?.trim();
    if (name) models.push({ name, desc, pulls, tags });
  });
  return JSON.stringify({ total: models.length, models: models.slice(0, 20) });
})()`);

console.log(JSON.parse(data));
await spider.close();
ready to run · spider-browser · TypeScript
Extraction

Fields you can pull.

Model nameParameter sizeDownloadsTagsQuantizationDescriptionLast updatedCapabilities
Rendering

React SPA handling

Full browser rendering for streaming content and dynamic React UI.

Content

Structured parsing

Extract code blocks, documentation, repository data, and metadata.

Waiting

Load completion

Smart network idle detection waits for dynamically loaded content to finish.

Related

More AI & Developer scrapers.

Start

Start scraping ollama.com.

Grab an API key and call the endpoint above. The first request resolves the config; every request after hits cache.