# CLI
servo-fetch "https://example.com"                          # clean Markdown
servo-fetch "https://example.com" --format png -o page.png # PNG screenshot

// Rust
let md = servo_fetch::markdown("https://example.com").await?;

# Python
page = servo_fetch.fetch("https://example.com")
print(page.markdown)

servo-fetch "https://example.com"                          # Markdown (default)
servo-fetch "https://example.com" --format json            # Structured JSON
servo-fetch "https://example.com" --format png -o page.png # PNG screenshot
servo-fetch "https://example.com" --js "document.title"    # Run JavaScript
servo-fetch "https://example.com" --schema schema.json     # Schema-driven JSON
servo-fetch "https://example.com" --cookies cookies.txt    # Send session cookies
servo-fetch "https://example.com" -H "X-Api-Key: KEY"      # Custom request header
servo-fetch URL1 URL2 URL3                                 # Parallel batch
servo-fetch "https://example.com" --output page.md         # Save to a single file
servo-fetch URL1 URL2 --output-dir ./out/                  # Save each URL to its own file
servo-fetch crawl "https://docs.example.com" --limit 20    # Crawl a site
servo-fetch crawl URL --output-dir ./pages/                # Save each crawled page to its own file
servo-fetch map "https://example.com"                      # Discover URLs via sitemap
servo-fetch mcp                                            # MCP server (stdio)
servo-fetch serve                                          # HTTP API server

cargo add servo-fetch

// URL → Markdown in one line (async by default; use `blocking::*` for sync)
let md = servo_fetch::markdown("https://example.com").await?;

// Fetch with options
use servo_fetch::{fetch, FetchOptions};
use std::time::Duration;

let page = fetch(&FetchOptions::new("https://example.com").timeout(Duration::from_secs(60))).await?;
println!("{}", page.html);
let md = page.markdown()?;

// Crawl a site
servo_fetch::crawl_each(
    &servo_fetch::CrawlOptions::new("https://docs.example.com")
        .limit(100)
        .user_agent("MyBot/1.0"),
    |result| match &result.outcome {
        Ok(page) => println!("{}: {} chars", result.url, page.content.len()),
        Err(e) => eprintln!("{}: {e}", result.url),
    },
).await?;

// Discover URLs via sitemap (no rendering)
let urls = servo_fetch::map(
    &servo_fetch::MapOptions::new("https://example.com").limit(1000),
).await?;
for u in &urls {
    println!("{}", u.url);
}

pip install servo-fetch

import servo_fetch

page = servo_fetch.fetch("https://example.com")
print(page.markdown)

# Schema extraction
from servo_fetch import Schema, Field
schema = Schema(
    base_selector=".product",
    fields=[
        Field(name="title", selector="h2", type="text"),
        Field(name="price", selector=".price", type="text"),
    ],
)
page = servo_fetch.fetch("https://shop.example.com", schema=schema)
print(page.extracted)

npm install servo-fetch

import { fetch, crawl } from "servo-fetch";

const md = await fetch("https://example.com");

for await (const page of crawl("https://docs.example.com", { limit: 50 })) {
  if (page.ok) console.log(page.url, page.title);
}

{
  "mcpServers": {
    "servo-fetch": {
      "command": "servo-fetch",
      "args": ["mcp"]
    }
  }
}

servo-fetch serve                            # 127.0.0.1:3000
servo-fetch serve --host 0.0.0.0 --port 80   # expose to network

curl -X POST http://127.0.0.1:3000/v1/fetch \
  -H 'content-type: application/json' \
  -d '{"url":"https://example.com"}'

docker run --rm -p 3000:3000 ghcr.io/konippi/servo-fetch:latest
curl -X POST http://127.0.0.1:3000/v1/fetch \
  -H 'content-type: application/json' \
  -d '{"url":"https://example.com"}'

npx skills add https://github.com/konippi/servo-fetch/tree/main/skills/servo-fetch