Geonode Scraper SDK

Python SDK for the Geonode Scraper API. Supports single-URL extraction, batch extraction, site crawling, URL mapping, web search, job polling, and usage statistics.

Requirements

• Python 3.10+

Installation

pip install geonode-scraper-sdk

Configuration And Authentication

Create a client configuration with your API base URL and API key.

from geonode_scraper_sdk import Configuration

configuration = Configuration(
    host="https://api.example.com",
    api_key={"ApiKeyAuth": "your-api-key"},
)

If you do not set host, the generated client defaults to http://localhost.

Quick Start

Synchronous extraction — blocks until the result is ready.

from geonode_scraper_sdk import (
    ApiClient,
    ApiException,
    Configuration,
    ExtractRequest,
    ExtractionApi,
    OutputFormat,
    ProcessingMode,
)

configuration = Configuration(
    host="https://api.example.com",
    api_key={"ApiKeyAuth": "your-api-key"},
)

with ApiClient(configuration) as api_client:
    api = ExtractionApi(api_client)

    try:
        response = api.extract_v1_extract_post(
            ExtractRequest(
                url="https://example.com",
                formats=[OutputFormat.MARKDOWN],
                processing_mode=ProcessingMode.SYNC,
            )
        )
        print(response.data.markdown)
        print(response.tokens_charged)
    except ApiException as exc:
        print(exc.status)
        print(exc.body)

Async Extraction Workflow

When processing_mode=ProcessingMode.ASYNC, the extract call returns an async job response with a job ID and status URL.

from geonode_scraper_sdk import ApiClient, Configuration, ExtractRequest, ExtractionApi, ProcessingMode

configuration = Configuration(
    host="https://api.example.com",
    api_key={"ApiKeyAuth": "your-api-key"},
)

with ApiClient(configuration) as api_client:
    api = ExtractionApi(api_client)

    submit = api.extract_v1_extract_post(
        ExtractRequest(
            url="https://example.com",
            processing_mode=ProcessingMode.ASYNC,
        )
    )

    job = api.get_job_result_v1_extract_job_id_get(submit.job_id)
    print(job.status)
    if job.data and job.data.markdown:
        print(job.data.markdown)

Use get_job_result_v1_extract_job_id_get(job_id) to poll a single job, or list_jobs_v1_extract_jobs_get(...) to inspect and filter job history.

Batch Extraction

Submit multiple URLs in one request and poll for results.

from geonode_scraper_sdk import ApiClient, BatchApi, BatchRequest, Configuration, OutputFormat

configuration = Configuration(
    host="https://api.example.com",
    api_key={"ApiKeyAuth": "your-api-key"},
)

with ApiClient(configuration) as api_client:
    api = BatchApi(api_client)

    accepted = api.create_batch_v1_batch_post(
        BatchRequest(
            urls=["https://example.com", "https://example.org"],
            formats=[OutputFormat.MARKDOWN],
        )
    )
    print(accepted.job_id, accepted.accepted_urls)

    status = api.get_batch_status_v1_batch_job_id_get(
        job_id=accepted.job_id, page=1, page_size=10
    )
    print(status.status, status.completed_urls, status.total_urls)

Site Crawling

Crawl a website from a seed URL up to a configurable depth and page limit.

from geonode_scraper_sdk import ApiClient, Configuration, CrawlApi, CrawlRequest, OutputFormat

configuration = Configuration(
    host="https://api.example.com",
    api_key={"ApiKeyAuth": "your-api-key"},
)

with ApiClient(configuration) as api_client:
    api = CrawlApi(api_client)

    accepted = api.create_crawl_v1_crawl_post(
        CrawlRequest(
            url="https://example.com",
            depth=2,
            limit=50,
            formats=[OutputFormat.MARKDOWN],
        )
    )
    print(accepted.job_id, accepted.estimated_pages)

    status = api.get_crawl_status_v1_crawl_job_id_get(
        job_id=accepted.job_id, page=1, page_size=10
    )
    print(status.status, status.completed_pages, status.total_pages)

URL Mapping

Discover all URLs under a base URL by combining sitemap parsing with HTML link extraction. Returns synchronously.

from geonode_scraper_sdk import ApiClient, Configuration, MapApi, MapRequest

configuration = Configuration(
    host="https://api.example.com",
    api_key={"ApiKeyAuth": "your-api-key"},
)

with ApiClient(configuration) as api_client:
    api = MapApi(api_client)

    result = api.map_urls_v1_map_post(MapRequest(url="https://example.com"))
    for link in result.links:
        print(link.url, link.source)

Web Search

Run a search query and get back ranked results. Returns synchronously.

from geonode_scraper_sdk import ApiClient, Configuration, SearchApi, SearchRequest

configuration = Configuration(
    host="https://api.example.com",
    api_key={"ApiKeyAuth": "your-api-key"},
)

with ApiClient(configuration) as api_client:
    api = SearchApi(api_client)

    result = api.search_v1_search_post(SearchRequest(query="geonode scraper api"))
    for hit in result.results:
        print(hit.position, hit.title, hit.url)

Use list_search_jobs_v1_search_jobs_get(...) to inspect search job history and get_search_job_v1_search_job_id_get(job_id) to fetch a single search job by ID.

Usage

Check the caller's live work-concurrency slot usage against their plan limit.

from geonode_scraper_sdk import ApiClient, Configuration, UsageApi

configuration = Configuration(
    host="https://api.example.com",
    api_key={"ApiKeyAuth": "your-api-key"},
)

with ApiClient(configuration) as api_client:
    api = UsageApi(api_client)

    usage = api.get_concurrency_usage_v1_usage_concurrency_get()
    print(usage.work_concurrency_in_use, usage.work_concurrency_limit)

Error Handling

Non-2xx responses raise ApiException or one of its subclasses. The exception includes the HTTP status, response body, and any deserialized error model in exc.data.

from geonode_scraper_sdk import ApiClient, ApiException, Configuration, ExtractionApi, ExtractRequest

configuration = Configuration(
    host="https://api.example.com",
    api_key={"ApiKeyAuth": "your-api-key"},
)

with ApiClient(configuration) as api_client:
    api = ExtractionApi(api_client)

    try:
        api.extract_v1_extract_post(ExtractRequest(url="https://example.com"))
    except ApiException as exc:
        print(exc.status)
        print(exc.body)
        print(exc.data)

Request Options

ExtractRequest supports the following fields:

• formats: output formats to return; defaults to [OutputFormat.HTML]
• render_js: use a headless browser for JavaScript-rendered pages; defaults to False
• processing_mode: ProcessingMode.SYNC or ProcessingMode.ASYNC; defaults to sync
• proxy: optional ProxySettings for country and proxy type selection
• headers: optional request headers dictionary
• wait_config: optional WaitConfig for explicit browser wait policy (wait_until, wait_for, wait_timeout)

Example with additional options:

from geonode_scraper_sdk import ExtractRequest, OutputFormat, ProcessingMode, ProxySettings, ProxyType, WaitConfig, WaitUntil

request = ExtractRequest(
    url="https://example.com",
    formats=[OutputFormat.HTML, OutputFormat.MARKDOWN],
    render_js=True,
    processing_mode=ProcessingMode.SYNC,
    proxy=ProxySettings(country="US", type=ProxyType.RESIDENTIAL),
    headers={"User-Agent": "geonode-scraper-sdk-demo"},
    wait_config=WaitConfig(
        wait_until=WaitUntil.NETWORKIDLE,
        wait_for="#content",
        wait_timeout=2000,
    ),
)

API Reference

ExtractionApi (/v1/extract)

• extract_v1_extract_post(extract_request)
• get_job_result_v1_extract_job_id_get(job_id)
• list_jobs_v1_extract_jobs_get(job_id, url, status, output, start_date, end_date, page, page_size)

BatchApi (/v1/batch)

• create_batch_v1_batch_post(batch_request)
• get_batch_status_v1_batch_job_id_get(job_id, page, page_size)
• cancel_batch_v1_batch_job_id_delete(job_id)
• list_batch_jobs_v1_batch_jobs_get(status, start_date, end_date, page, page_size)

CrawlApi (/v1/crawl)

• create_crawl_v1_crawl_post(crawl_request)
• get_crawl_status_v1_crawl_job_id_get(job_id, page, page_size)
• cancel_crawl_v1_crawl_job_id_delete(job_id)
• list_crawl_jobs_v1_crawl_jobs_get(url, status, start_date, end_date, page, page_size)

MapApi (/v1/map)

• map_urls_v1_map_post(map_request)
• list_map_jobs_v1_map_jobs_get(url, status, start_date, end_date, page, page_size)
• get_map_job_v1_map_job_id_get(job_id)

SearchApi (/v1/search)

• search_v1_search_post(search_request)
• list_search_jobs_v1_search_jobs_get(query, status, start_date, end_date, page, page_size)
• get_search_job_v1_search_job_id_get(job_id)

StatisticsApi (/v1/statistics)

• get_statistics_v1_statistics_get(start_date, end_date)

SystemApi (/health)

• health_check_health_get()

UsageApi (/v1/usage)

• get_concurrency_usage_v1_usage_concurrency_get()

WebhooksApi (/v1/webhooks)

• list_webhooks_v1_webhooks_get(page, page_size)
• create_webhook_v1_webhooks_post(webhook_create)
• get_webhook_v1_webhooks_webhook_id_get(webhook_id)
• update_webhook_v1_webhooks_webhook_id_patch(webhook_id, webhook_update)
• delete_webhook_v1_webhooks_webhook_id_delete(webhook_id)
• list_deliveries_v1_webhooks_webhook_id_deliveries_get(webhook_id, page, page_size, status)
• rotate_secret_v1_webhooks_webhook_id_rotate_secret_post(webhook_id)

Advanced Usage

Each generated API method also exposes:

• *_with_http_info() to get the deserialized payload together with status and headers
• *_without_preload_content() to work with the raw HTTP response directly