geonode-scraper-sdk 0.1.0__tar.gz

geonode_scraper_sdk-0.1.0/CHANGELOG.md

@@ -0,0 +1,9 @@
+# Changelog
+
+All notable changes to the Python SDK will be documented in this file.
+
+The format is inspired by Keep a Changelog.
+
+## [0.1.0] - 2026-04-09
+
+- Initial public packaging, licensing, and release automation for the Python SDK.

geonode_scraper_sdk-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Geonode Team
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

geonode_scraper_sdk-0.1.0/MANIFEST.in

@@ -0,0 +1,22 @@
+include LICENSE
+include CHANGELOG.md
+include README.md
+include pyproject.toml
+include setup.py
+
+graft geonode_scraper_sdk
+
+prune .github
+prune .openapi-generator
+prune docs
+prune geonode_scraper_sdk.egg-info
+prune scripts
+prune test
+prune tests
+
+exclude .gitignore
+exclude .gitlab-ci.yml
+exclude .openapi-generator-ignore
+
+global-exclude __pycache__
+global-exclude *.py[cod]

geonode_scraper_sdk-0.1.0/PKG-INFO

@@ -0,0 +1,192 @@
+Metadata-Version: 2.4
+Name: geonode-scraper-sdk
+Version: 0.1.0
+Summary: Python SDK for the Geonode Scraper API
+Author: Geonode Team
+License-Expression: MIT
+Keywords: OpenAPI,OpenAPI-Generator,Scraper API
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: urllib3<3.0.0,>=2.1.0
+Requires-Dist: python-dateutil>=2.8.2
+Requires-Dist: pydantic>=2.11
+Requires-Dist: typing-extensions>=4.7.1
+Provides-Extra: dev
+Requires-Dist: pytest>=7.2.1; extra == "dev"
+Requires-Dist: pytest-cov>=2.8.1; extra == "dev"
+Requires-Dist: mypy>=1.5; extra == "dev"
+Requires-Dist: types-python-dateutil>=2.8.19.14; extra == "dev"
+Requires-Dist: ruff>=0.12.11; extra == "dev"
+Dynamic: license-file
+
+# Geonode Scraper SDK
+
+Python SDK for the Geonode Scraper API. It supports synchronous and asynchronous
+content extraction, job polling, usage statistics, and service health checks.
+
+## Requirements
+
+- Python 3.10+
+
+## Installation
+
+```sh
+pip install geonode-scraper-sdk
+```
+
+## Configuration And Authentication
+
+Create a client configuration with your API base URL and API key.
+
+```python
+from geonode_scraper_sdk import Configuration
+
+configuration = Configuration(
+    host="https://api.example.com",
+    api_key={"APIKeyHeader": "your-api-key"},
+)
+```
+
+If you do not set `host`, the generated client defaults to `http://localhost`.
+You normally do not need `api_key_prefix` for this API.
+
+## Quick Start
+
+This example performs a synchronous extraction and prints the markdown result.
+
+```python
+from geonode_scraper_sdk import (
+    ApiClient,
+    ApiException,
+    Configuration,
+    ExtractRequest,
+    ExtractionApi,
+    OutputFormat,
+    ProcessingMode,
+)
+
+configuration = Configuration(
+    host="https://api.example.com",
+    api_key={"APIKeyHeader": "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 Workflow
+
+When `processing_mode=ProcessingMode.ASYNC`, the extract call returns an async
+job response with a job ID and status URL.
+
+```python
+from geonode_scraper_sdk import ApiClient, Configuration, ExtractRequest, ExtractionApi, ProcessingMode
+
+configuration = Configuration(
+    host="https://api.example.com",
+    api_key={"APIKeyHeader": "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.
+
+## 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`.
+
+```python
+from geonode_scraper_sdk import ApiClient, ApiException, Configuration, ExtractionApi, ExtractRequest
+
+configuration = Configuration(
+    host="https://api.example.com",
+    api_key={"APIKeyHeader": "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 main extraction controls:
+
+- `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
+
+Example with additional options:
+
+```python
+from geonode_scraper_sdk import ExtractRequest, OutputFormat, ProcessingMode, ProxySettings, ProxyType
+
+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"},
+)
+```
+
+## API Reference
+
+- `ExtractionApi.extract_v1_extract_post(extract_request)`
+- `ExtractionApi.get_job_result_v1_extract_job_id_get(job_id)`
+- `ExtractionApi.list_jobs_v1_extract_jobs_get(job_id=None, url=None, status=None, output=None, start_date=None, end_date=None, page=None, page_size=None)`
+- `StatisticsApi.get_statistics_v1_statistics_get(start_date=None, end_date=None)`
+- `SystemApi.health_check_health_get()`
+
+## 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

geonode_scraper_sdk-0.1.0/README.md

@@ -0,0 +1,165 @@
+# Geonode Scraper SDK
+
+Python SDK for the Geonode Scraper API. It supports synchronous and asynchronous
+content extraction, job polling, usage statistics, and service health checks.
+
+## Requirements
+
+- Python 3.10+
+
+## Installation
+
+```sh
+pip install geonode-scraper-sdk
+```
+
+## Configuration And Authentication
+
+Create a client configuration with your API base URL and API key.
+
+```python
+from geonode_scraper_sdk import Configuration
+
+configuration = Configuration(
+    host="https://api.example.com",
+    api_key={"APIKeyHeader": "your-api-key"},
+)
+```
+
+If you do not set `host`, the generated client defaults to `http://localhost`.
+You normally do not need `api_key_prefix` for this API.
+
+## Quick Start
+
+This example performs a synchronous extraction and prints the markdown result.
+
+```python
+from geonode_scraper_sdk import (
+    ApiClient,
+    ApiException,
+    Configuration,
+    ExtractRequest,
+    ExtractionApi,
+    OutputFormat,
+    ProcessingMode,
+)
+
+configuration = Configuration(
+    host="https://api.example.com",
+    api_key={"APIKeyHeader": "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 Workflow
+
+When `processing_mode=ProcessingMode.ASYNC`, the extract call returns an async
+job response with a job ID and status URL.
+
+```python
+from geonode_scraper_sdk import ApiClient, Configuration, ExtractRequest, ExtractionApi, ProcessingMode
+
+configuration = Configuration(
+    host="https://api.example.com",
+    api_key={"APIKeyHeader": "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.
+
+## 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`.
+
+```python
+from geonode_scraper_sdk import ApiClient, ApiException, Configuration, ExtractionApi, ExtractRequest
+
+configuration = Configuration(
+    host="https://api.example.com",
+    api_key={"APIKeyHeader": "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 main extraction controls:
+
+- `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
+
+Example with additional options:
+
+```python
+from geonode_scraper_sdk import ExtractRequest, OutputFormat, ProcessingMode, ProxySettings, ProxyType
+
+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"},
+)
+```
+
+## API Reference
+
+- `ExtractionApi.extract_v1_extract_post(extract_request)`
+- `ExtractionApi.get_job_result_v1_extract_job_id_get(job_id)`
+- `ExtractionApi.list_jobs_v1_extract_jobs_get(job_id=None, url=None, status=None, output=None, start_date=None, end_date=None, page=None, page_size=None)`
+- `StatisticsApi.get_statistics_v1_statistics_get(start_date=None, end_date=None)`
+- `SystemApi.health_check_health_get()`
+
+## 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

geonode_scraper_sdk-0.1.0/geonode_scraper_sdk/__init__.py

@@ -0,0 +1,101 @@
+# coding: utf-8
+
+# flake8: noqa
+
+"""
+    Scraper API
+
+    No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator)
+
+    The version of the OpenAPI document: 0.1.0
+    Generated by OpenAPI Generator (https://openapi-generator.tech)
+
+    Do not edit the class manually.
+"""  # noqa: E501
+
+
+__version__ = "0.1.0"
+
+# Define package exports
+__all__ = [
+    "ExtractionApi",
+    "StatisticsApi",
+    "SystemApi",
+    "ApiResponse",
+    "ApiClient",
+    "Configuration",
+    "OpenApiException",
+    "ApiTypeError",
+    "ApiValueError",
+    "ApiKeyError",
+    "ApiAttributeError",
+    "ApiException",
+    "ErrorResponse",
+    "ExtractAsyncResponse",
+    "ExtractRequest",
+    "ExtractSyncResponse",
+    "ExtractionData",
+    "ExtractionError",
+    "ExtractionErrorCode",
+    "ExtractionErrorResponse",
+    "ExtractionMetadata",
+    "HTTPValidationError",
+    "HealthResponse",
+    "HealthStatus",
+    "JobCollectionResponse",
+    "JobListItemResponse",
+    "JobStatus",
+    "JobStatusResponse",
+    "LocationInner",
+    "OutputFormat",
+    "ProcessingMode",
+    "ProxySettings",
+    "ProxyType",
+    "RequestCountResponse",
+    "StatisticsResponse",
+    "TokensUsageResponse",
+    "ValidationError",
+]
+
+# import apis into sdk package
+from geonode_scraper_sdk.api.extraction_api import ExtractionApi as ExtractionApi
+from geonode_scraper_sdk.api.statistics_api import StatisticsApi as StatisticsApi
+from geonode_scraper_sdk.api.system_api import SystemApi as SystemApi
+
+# import ApiClient
+from geonode_scraper_sdk.api_response import ApiResponse as ApiResponse
+from geonode_scraper_sdk.api_client import ApiClient as ApiClient
+from geonode_scraper_sdk.configuration import Configuration as Configuration
+from geonode_scraper_sdk.exceptions import OpenApiException as OpenApiException
+from geonode_scraper_sdk.exceptions import ApiTypeError as ApiTypeError
+from geonode_scraper_sdk.exceptions import ApiValueError as ApiValueError
+from geonode_scraper_sdk.exceptions import ApiKeyError as ApiKeyError
+from geonode_scraper_sdk.exceptions import ApiAttributeError as ApiAttributeError
+from geonode_scraper_sdk.exceptions import ApiException as ApiException
+
+# import models into sdk package
+from geonode_scraper_sdk.models.error_response import ErrorResponse as ErrorResponse
+from geonode_scraper_sdk.models.extract_async_response import ExtractAsyncResponse as ExtractAsyncResponse
+from geonode_scraper_sdk.models.extract_request import ExtractRequest as ExtractRequest
+from geonode_scraper_sdk.models.extract_sync_response import ExtractSyncResponse as ExtractSyncResponse
+from geonode_scraper_sdk.models.extraction_data import ExtractionData as ExtractionData
+from geonode_scraper_sdk.models.extraction_error import ExtractionError as ExtractionError
+from geonode_scraper_sdk.models.extraction_error_code import ExtractionErrorCode as ExtractionErrorCode
+from geonode_scraper_sdk.models.extraction_error_response import ExtractionErrorResponse as ExtractionErrorResponse
+from geonode_scraper_sdk.models.extraction_metadata import ExtractionMetadata as ExtractionMetadata
+from geonode_scraper_sdk.models.http_validation_error import HTTPValidationError as HTTPValidationError
+from geonode_scraper_sdk.models.health_response import HealthResponse as HealthResponse
+from geonode_scraper_sdk.models.health_status import HealthStatus as HealthStatus
+from geonode_scraper_sdk.models.job_collection_response import JobCollectionResponse as JobCollectionResponse
+from geonode_scraper_sdk.models.job_list_item_response import JobListItemResponse as JobListItemResponse
+from geonode_scraper_sdk.models.job_status import JobStatus as JobStatus
+from geonode_scraper_sdk.models.job_status_response import JobStatusResponse as JobStatusResponse
+from geonode_scraper_sdk.models.location_inner import LocationInner as LocationInner
+from geonode_scraper_sdk.models.output_format import OutputFormat as OutputFormat
+from geonode_scraper_sdk.models.processing_mode import ProcessingMode as ProcessingMode
+from geonode_scraper_sdk.models.proxy_settings import ProxySettings as ProxySettings
+from geonode_scraper_sdk.models.proxy_type import ProxyType as ProxyType
+from geonode_scraper_sdk.models.request_count_response import RequestCountResponse as RequestCountResponse
+from geonode_scraper_sdk.models.statistics_response import StatisticsResponse as StatisticsResponse
+from geonode_scraper_sdk.models.tokens_usage_response import TokensUsageResponse as TokensUsageResponse
+from geonode_scraper_sdk.models.validation_error import ValidationError as ValidationError

geonode_scraper_sdk-0.1.0/geonode_scraper_sdk/api/__init__.py

@@ -0,0 +1,7 @@
+# flake8: noqa
+
+# import apis into api package
+from geonode_scraper_sdk.api.extraction_api import ExtractionApi
+from geonode_scraper_sdk.api.statistics_api import StatisticsApi
+from geonode_scraper_sdk.api.system_api import SystemApi
+