feat: added opensearch harvesting

.github/workflows/docs.yml

@@ -60,7 +60,7 @@ jobs:
       - name: Install project dependencies
         run: poetry install
       - name: Build the documentation
-        run: poetry run mkdocs build --strict --site-dir _site
+        run: poetry run mkdocs build --site-dir _site
       - name: Upload artifact
         uses: actions/upload-pages-artifact@v3
 

CONTRIBUTING.md

@@ -331,6 +331,9 @@ git push && git push --tags
 - [EURAC STAC](https://stac.eurac.edu/)
 - [EOEPCA develop STAC](https://eoapi.develop.eoepca.org/stac/)
 - [EOX hub-int STAC](https://stac.hub-int.eox.at/)
+- [Creodias OpenSearch](https://finder.creodias.eu/resto/api/collections/describe.xml)
+  - [Creodias Sentinel1](https://finder.creodias.eu/resto/api/collections/Sentinel1/describe.xml)
+  - [Creodias Sentinel2](https://finder.creodias.eu/resto/api/collections/Sentinel2/describe.xml)
 
 ### Inspiration
 

docs/api.md

@@ -2,7 +2,28 @@
 
 The section shows information about the API relevant for the developers.
 
-::: eodm.extract
-::: eodm.load
+## Extractors
+
+::: eodm.extract.extract_stac_api_items
+::: eodm.extract.extract_stac_api_collections
+::: eodm.extract.extract_opensearch_features
+
+## Loaders
+
+::: eodm.load.load_stac_api_items
+::: eodm.load.load_stac_api_collections
+
+## Opensearch
+
+::: eodm.opensearch.OpenSearchClient
+::: eodm.opensearch.OpenSearchFeature
+::: eodm.opensearch.OpenSearchUrl
+
+## Serializers
+
 ::: eodm.serializers
+
+
+## STAC Contributions
+
 ::: eodm.stac_contrib

docs/cli.md

@@ -36,6 +36,7 @@ $ eodm extract [OPTIONS] COMMAND [ARGS]...
 **Commands**:
 
 * `openeo`: Extract data from openEO results
+* `opensearch`: Extract features from a OpenSearch API
 * `stac-api`: Extract data from a STAC API
 * `stac-catalog`: Extract data from a STAC Catalog
 
@@ -74,6 +75,45 @@ $ eodm extract openeo results [OPTIONS] ASSET_NAME [RESULTS]
 
 * `--help`: Show this message and exit.
 
+### `eodm extract opensearch`
+
+Extract features from a OpenSearch API
+
+**Usage**:
+
+```console
+$ eodm extract opensearch [OPTIONS] COMMAND [ARGS]...
+```
+
+**Options**:
+
+* `--help`: Show this message and exit.
+
+**Commands**:
+
+* `features`: Extract features found in an OpenSearch...
+
+#### `eodm extract opensearch features`
+
+Extract features found in an OpenSearch API given a product type
+
+**Usage**:
+
+```console
+$ eodm extract opensearch features [OPTIONS] URL PRODUCT_TYPE
+```
+
+**Arguments**:
+
+* `URL`: [required]
+* `PRODUCT_TYPE`: [required]
+
+**Options**:
+
+* `-l, --limit INT`: Limit number of results  [default: 0]
+* `-o, --output [default|json]`: Output format. Default to STDOUT multiline  [default: default]
+* `--help`: Show this message and exit.
+
 ### `eodm extract stac-api`
 
 Extract data from a STAC API

pyproject.toml

@@ -20,6 +20,8 @@ rioxarray = "^0.15.5"
 rio-cogeo = "^5.3.0"
 rio-stac = "^0.9.0"
 python-dateutil = "^2.9.0.post0"
+lxml = "^5.3.0"
+geojson-pydantic = "^1.1.2"
 
 
 [tool.poetry.group.dev.dependencies]
@@ -38,6 +40,7 @@ mkdocs-material-extensions = "^1.3.1"
 pytest-cov = "^6.0.0"
 pytest-mock = "^3.14.0"
 respx = "^0.21.1"
+types-lxml = "^2024.12.13"
 
 
 [tool.commitizen]

src/eodm/cli/extract/apps/opensearch.py

@@ -0,0 +1,46 @@
+from typing import Annotated
+
+import typer
+
+from eodm.cli._serialization import serialize
+from eodm.cli._types import (
+    Output,
+    OutputType,
+)
+from eodm.extract import extract_opensearch_features
+
+app = typer.Typer(no_args_is_help=True)
+
+
+@app.callback()
+def main():
+    """
+    Extract features from a OpenSearch API
+    """
+
+
+@app.command(no_args_is_help=True)
+def features(
+    url: str,
+    product_type: str,
+    limit: Annotated[
+        int,
+        typer.Option(
+            "--limit",
+            "-l",
+            metavar="INT",
+            help="Limit number of results",
+        ),
+    ] = 0,
+    output: OutputType = Output.default,
+):
+    """
+    Extract features found in an OpenSearch API given a product type
+    """
+
+    features = extract_opensearch_features(
+        url=url,
+        product_types=[product_type],
+        limit=limit,
+    )
+    serialize(features, output_type=output)

src/eodm/cli/extract/main.py

@@ -1,6 +1,7 @@
 import typer
 
 from .apps.openeo import app as openeo
+from .apps.opensearch import app as opensearch
 from .apps.stac_api import app as stac_api
 from .apps.stac_catalog import app as stac_catalog
 
@@ -12,3 +13,4 @@
 app.add_typer(stac_api, name="stac-api")
 app.add_typer(stac_catalog, name="stac-catalog")
 app.add_typer(openeo, name="openeo")
+app.add_typer(opensearch, name="opensearch")

src/eodm/extract.py

@@ -3,6 +3,8 @@
 import pystac_client
 from pystac import Collection, Item
 
+from .opensearch import OpenSearchClient, OpenSearchFeature
+
 
 def extract_stac_api_items(
     url: str,
@@ -13,7 +15,7 @@ def extract_stac_api_items(
     query: dict | None = None,
     filter: dict | None = None,
 ) -> Iterator[Item]:
-    """Extracts items from a STAC API
+    """Extracts STAC Items from a STAC API
 
     Args:
         url (str): Link to STAC API endpoint
@@ -43,7 +45,7 @@ def extract_stac_api_items(
 
 
 def extract_stac_api_collections(url: str) -> Iterator[Collection]:
-    """Extracts collections from a STAC API
+    """Extracts STAC Collections from a STAC API
 
     Args:
         url (str): Link to STAC API endpoint
@@ -54,3 +56,30 @@ def extract_stac_api_collections(url: str) -> Iterator[Collection]:
 
     client = pystac_client.Client.open(url)
     yield from client.get_collections()
+
+
+def extract_opensearch_features(
+    url: str,
+    product_types: list[str],
+    limit: int = 0,
+) -> Iterator[OpenSearchFeature]:
+    """Extracts OpenSearch Features from an OpenSearch API
+
+    Args:
+        url (str): Link to OpenSearch API endpoint
+        productTypes (list[str]): List of productTypes to search for
+
+    Yields:
+        Iterator[OpenSearchFeature]: OpenSearch Features
+    """
+    client = OpenSearchClient(url)
+
+    query = {}
+
+    # TODO: create mapper to map to STAC items
+    for product_type in product_types:
+        query["{eo:productType}"] = product_type
+        for i, feature in enumerate(client.search(query), start=1):
+            if limit and i >= limit:
+                break
+            yield feature