Crawl - Olostep Docs

Through the Olostep /v1/crawls endpoint you can crawl a website and get the content from all the pages.

Crawl a website and get the content from all subpages (or limit the depth of the crawl)
Use special patterns to crawl specific pages (e.g. /blog/**)
Pass a webhook_url to get notified when the crawl is completed
Search query to only find specific pages and sort by relevance

For API details see the Crawl Endpoint API Reference.

Installation

pip install olostep

npm install olostep

# curl is available by default on macOS, Linux, and Windows

npm install node-fetch

pip install requests

Start a crawl

Provide the starting URL, include/exclude URL globs, and max_pages. Optional: max_depth, include_external, include_subdomain, search_query, top_n, webhook_url, timeout.

from olostep import Olostep

client = Olostep(api_key="YOUR_REAL_KEY")

crawl = client.crawls.create(
    start_url="https://olostep.com",
    max_pages=100,
    include_urls=["/**"],
    exclude_urls=["/collections/**"],
    include_external=False,
)

print(crawl.id, crawl.status)

import Olostep from 'olostep'

const client = new Olostep({ apiKey: 'YOUR_REAL_KEY' })

const crawl = await client.crawls.create({
  url: 'https://olostep.com',
  maxPages: 100,
  includeUrls: ['/**'],
  excludeUrls: ['/collections/**'],
  includeExternal: false,
})

console.log(crawl.id, crawl.status)

curl -s -X POST "https://api.olostep.com/v1/crawls" \
  -H "Authorization: Bearer $OLOSTEP_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "start_url": "https://olostep.com",
    "max_pages": 100,
    "include_urls": ["/**"],
    "exclude_urls": ["/collections/**"]
  }'

olostep crawl "https://olostep.com" \
  --max-pages 100 \
  --include-url "/**" \
  --exclude-url "/collections/**" \
  --formats markdown,html

const API_URL = 'https://api.olostep.com'
const res = await fetch(`${API_URL}/v1/crawls`, {
  method: 'POST',
  headers: { 'Authorization': 'Bearer <YOUR_API_KEY>', 'Content-Type': 'application/json' },
  body: JSON.stringify({
    start_url: 'https://olostep.com',
    max_pages: 100,
    include_urls: ['/**'],
    exclude_urls: ['/collections/**']
  })
})
console.log(await res.json())

import time, json

API_URL = 'https://api.olostep.com'
API_KEY = '<YOUR_API_KEY>'
HEADERS = { 
    'Content-Type': 'application/json',
    'Authorization': f'Bearer {API_KEY}' 
}

data = {
  "start_url": "https://olostep.com",
  "max_pages": 100,
  "include_urls": ["/**"],
  "exclude_urls": ["/collections/**"],
  "include_external": False
}

res = requests.post(f"{API_URL}/v1/crawls", headers=HEADERS, json=data)
crawl = res.json()
print(json.dumps(crawl, indent=2))

Since everything in Olostep is an object, you will receive a crawl object in response. The crawl object has a few properties like id and status, which you can use to track the crawl.

Check crawl status

Poll the crawl to track progress until status is completed.

# Using the crawl object from the previous step
info = crawl.info()
print(info.status, info.pages_count)

# Or wait until completed
crawl.wait_till_done(check_every_n_secs=5)

// Using the crawl object from the previous step
const info = await crawl.info()
console.log(info.status, info.pages_count)

// Or wait until completed
await crawl.waitTillDone({ checkEveryNSecs: 5 })

curl -s -X GET "https://api.olostep.com/v1/crawls/<CRAWL_ID>" \
  -H "Authorization: Bearer $OLOSTEP_API_KEY"

const crawlId = '<CRAWL_ID>'
const status = await fetch(`${API_URL}/v1/crawls/${crawlId}`, {
  headers: { 'Authorization': 'Bearer <YOUR_API_KEY>' }
}).then(r => r.json())
console.log(status)

import time

def get_crawl_info(crawl_id):
    return requests.get(f'{API_URL}/v1/crawls/{crawl_id}', headers=HEADERS).json()

crawl_id = crawl['id']
while True:
    info = get_crawl_info(crawl_id)
    print(info['status'], info.get('pages_count'))
    if info['status'] == 'completed':
        break
    time.sleep(5)

Alternatively, you can pass a webhook_url when starting the crawl to be notified when the crawl is completed.

List pages (paginate/stream with cursor)

Fetch pages and iterate using cursor and limit. Works while the crawl is in_progress or completed.

# Iterate all pages (auto-waits for crawl completion, handles pagination)
for page in crawl.pages():
    print(page.url, page.retrieve_id)

// Iterate all pages (auto-waits for crawl completion, handles pagination)
for await (const page of crawl.pages()) {
  console.log(page.url, page.retrieve_id)
}

curl -s -G "https://api.olostep.com/v1/crawls/<CRAWL_ID>/pages" \
  -H "Authorization: Bearer $OLOSTEP_API_KEY" \
  --data-urlencode "cursor=0" \
  --data-urlencode "limit=10"

let cursor = 0
while (true) {
  const pages = await fetch(`${API_URL}/v1/crawls/${crawlId}/pages?cursor=${cursor}&limit=10`, {
    headers: { 'Authorization': 'Bearer <YOUR_API_KEY>' }
  }).then(r => r.json())
  pages.pages.forEach(p => console.log(p.url, p.retrieve_id))
  if (pages.cursor === undefined) break
  cursor = pages.cursor
}

def get_pages(crawl_id, cursor=None, limit=10, search_query=None):
    params = { 
        'cursor': cursor, 
        'limit': limit
    }
    return requests.get(f'{API_URL}/v1/crawls/{crawl_id}/pages', headers=HEADERS, params=params).json()

cursor = 0
while True:
    page_batch = get_pages(crawl_id, cursor=cursor, limit=10)
    for page in page_batch['pages']:
        print(page['url'], page['retrieve_id'])
    if 'cursor' not in page_batch:
        break
    cursor = page_batch['cursor']
    time.sleep(5)

Search query (limit to top N relevant)

Use search_query at start, and optionally filter listing with search_query. Limit per-page exploration with top_n.

from olostep import Olostep

client = Olostep(api_key="YOUR_REAL_KEY")

crawl = client.crawls.create(
    start_url="https://olostep.com",
    max_pages=100,
    include_urls=["/**"],
    search_query="contact us",
    top_n=5,
)

for page in crawl.pages(search_query="contact us"):
    print(page.url)

import Olostep from 'olostep'

const client = new Olostep({ apiKey: 'YOUR_REAL_KEY' })

const crawl = await client.crawls.create({
  url: 'https://olostep.com',
  maxPages: 100,
  includeUrls: ['/**'],
  searchQuery: 'contact us',
  topN: 5,
})

for await (const page of crawl.pages()) {
  console.log(page.url)
}

curl -s -X POST "https://api.olostep.com/v1/crawls" \
  -H "Authorization: Bearer $OLOSTEP_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "start_url": "https://olostep.com",
    "max_pages": 100,
    "include_urls": ["/**"],
    "search_query": "contact us",
    "top_n": 5
  }'

olostep crawl "https://olostep.com" \
  --max-pages 100 \
  --include-url "/**" \
  --search-query "contact us" \
  --top-n 5

await fetch(`${API_URL}/v1/crawls`, { method: 'POST', headers: { 'Authorization': 'Bearer <YOUR_API_KEY>', 'Content-Type': 'application/json' }, body: JSON.stringify({ start_url: 'https://olostep.com', max_pages: 100, include_urls: ['/**'], search_query: 'contact us', top_n: 5 }) })

data = {
  "start_url": "https://olostep.com",
  "max_pages": 100,
  "include_urls": ["/**"],
  "search_query": "contact us",
  "top_n": 5
}
crawl = requests.post(f'{API_URL}/v1/crawls', headers=HEADERS, json=data).json()
pages = requests.get(f"{API_URL}/v1/crawls/{crawl['id']}/pages", headers=HEADERS, params={'search_query': 'contact us'}).json()
print(len(pages['pages']))

Retrieve content

Use each page’s retrieve_id with /v1/retrieve to fetch html_content and/or markdown_content.

# Retrieve content for each crawled page
for page in crawl.pages():
    content = page.retrieve(["markdown"])
    print(content.markdown_content)

// Retrieve content for each crawled page
for await (const page of crawl.pages()) {
  const content = await client.retrieve.get(page.retrieve_id, ['markdown'])
  console.log(content.markdown_content)
}

curl -s -G "https://api.olostep.com/v1/retrieve" \
  -H "Authorization: Bearer $OLOSTEP_API_KEY" \
  --data-urlencode "retrieve_id=<RETRIEVE_ID>"

# `olostep crawl` retrieves content automatically. To fetch a single
# page by its retrieve_id later:
olostep scrape-get <RETRIEVE_ID>

const retrieved = await fetch(`${API_URL}/v1/retrieve?retrieve_id=<RETRIEVE_ID>`, { headers: { 'Authorization': 'Bearer <YOUR_API_KEY>' } }).then(r => r.json())
console.log(retrieved.markdown_content)

def retrieve_content(retrieve_id):
    return requests.get(f"{API_URL}/v1/retrieve", headers=HEADERS, params={"retrieve_id": retrieve_id}).json()

for page in get_pages(crawl['id'], limit=5)['pages']:
    retrieved = retrieve_content(page['retrieve_id'])
    print(retrieved.get('markdown_content'))

Notes

Pagination is cursor-based; repeat requests until cursor is absent.
Content fields on /v1/crawls/{crawl_id}/pages are deprecated; prefer /v1/retrieve.
Webhooks: set webhook_url to receive a POST when the crawl completes.

Pricing

Crawl costs 1 credit per page crawled.

​Installation

​Start a crawl

​Check crawl status

​List pages (paginate/stream with cursor)

​Search query (limit to top N relevant)

​Retrieve content

​Notes

​Pricing