feat(pineapple): add gget pineapple module (#161)

docs/src/SUMMARY.md

@@ -28,6 +28,7 @@
 * [gget mutate](en/mutate.md)
 * [gget opentargets](en/opentargets.md)
 * [gget pdb](en/pdb.md)  
+* [gget pineapple](en/pineapple.md)  
 * [gget ref](en/ref.md)  
 * [gget search](en/search.md)  
 * [gget setup](en/setup.md)  
@@ -71,6 +72,7 @@
 * [gget mutate](es/mutate.md)  
 * [gget opentargets](es/opentargets.md)  
 * [gget pdb](es/pdb.md)  
+* [gget pineapple](es/pineapple.md)  
 * [gget ref](es/ref.md)  
 * [gget search](es/search.md)  
 * [gget setup](es/setup.md)  

docs/src/en/pineapple.md

@@ -0,0 +1,83 @@
+[<kbd> View page source on GitHub </kbd>](https://github.com/scverse/gget/blob/main/docs/src/en/pineapple.md)
+
+> Python arguments are equivalent to long-option arguments (`--arg`), unless otherwise specified. Flags are True/False arguments in Python.  The manual for any gget tool can be called from the command-line using the `-h` `--help` flag.  
+# gget pineapple 🍍
+List and download curated bio-imaging datasets and pre-trained model weights from [Pineapple](https://github.com/tomouellette/pineapple).  
+[Pineapple](https://github.com/tomouellette/pineapple) (by Tom Ouellette) is a tool for image-based cell profiling that also curates and standardizes a collection of annotated bio-imaging datasets (segmentation and benchmark) and self-supervised model weights, hosted on Google Drive. `gget pineapple` lets you browse this catalog and download the resources directly — no Rust binary required.  
+Return format: JSON (command-line) or data frame/CSV (Python).
+
+> **Scope:** `gget pineapple` wraps only Pineapple's data download. It does not reimplement Pineapple's image-processing features (`process`, `profile`, `neural`, `measure`) — use the [Pineapple](https://github.com/tomouellette/pineapple) tool directly for those.
+
+> ⚠️ Please check each dataset's original reference and license (shown in the catalog) before use. Some datasets are non-commercial only.
+
+**Positional argument**  
+`name`  
+Name of the dataset/weights to fetch, e.g. `vicar_2021` or `dino_vit_small`. Omit to list the full catalog for the chosen category.
+
+**Optional arguments**  
+`-c` `--category`  
+Resource category: `segmentation`, `benchmark`, or `weights`. Default: `segmentation`.  
+
+`-od` `--out_dir`  
+Directory to download the resource into (used with `--download`). Default: current directory.  
+
+`-o` `--out`  
+Path to the file the catalog table will be saved in, e.g. path/to/directory/results.csv (or .json). Default: Standard out.  
+Python: `save=True` will save the output in the current working directory.
+
+**Flags**  
+`-d` `--download`  
+Download the resource (requires a specific `name`) into `--out_dir`. Datasets are large (up to several GB); see the `size_gb` column.  
+
+`-csv` `--csv`  
+Command-line only. Returns results in CSV format.  
+Python: Use `json=True` to return output in JSON format.
+
+`-q` `--quiet`  
+Command-line only. Prevents progress information from being displayed.  
+Python: Use `verbose=False` to prevent progress information from being displayed.  
+
+### Examples
+**List the available segmentation datasets:**
+```bash
+gget pineapple --category segmentation
+```
+```python
+# Python
+gget.pineapple(category="segmentation")
+```
+&rarr; Returns the catalog of curated segmentation datasets.
+
+| name | category | data_authors | size_gb | license | filename | google_drive_id |
+| --- | --- | --- | --- | --- | --- | --- |
+| vicar_2021 | segmentation | Vicar et al. 2021 | 0.113 | CC BY 4.0 | vicar-2021.tar.gz | 12tJOlIHZPFqp8GLek_jV__Uhhgsa530_ |
+| . . . | . . . | . . . | . . . | . . . | . . . | . . . |
+
+<br/><br/>
+**Download a specific dataset:**
+```bash
+gget pineapple vicar_2021 --download --out_dir ./pineapple_data
+```
+```python
+# Python
+gget.pineapple("vicar_2021", download=True, out_dir="./pineapple_data")
+```
+&rarr; Downloads `vicar-2021.tar.gz` into `./pineapple_data` and returns the catalog entry.
+
+<br/><br/>
+**List the pre-trained model weights:**
+```bash
+gget pineapple --category weights
+```
+```python
+# Python
+gget.pineapple(category="weights")
+```
+&rarr; Returns the catalog of pre-trained self-supervised model weights (e.g. `dino_vit_small`, `subcell_vit_base`).
+
+# References
+If you use `gget pineapple` in a publication, please cite the following article and the original dataset references (listed in the catalog `data_authors` column):  
+
+- Pineapple: scalable processing for image-based cell profiling. [https://github.com/tomouellette/pineapple](https://github.com/tomouellette/pineapple)
+
+- Luebbert, L., & Pachter, L. (2023). Efficient querying of genomic reference databases with gget. Bioinformatics. [https://doi.org/10.1093/bioinformatics/btac836](https://doi.org/10.1093/bioinformatics/btac836)

docs/src/en/updates.md

@@ -5,6 +5,7 @@
 #### *gget* officially became part of [*scverse*](https://scverse.org/) on June 9, 2026. 🥳🥳🥳
 
 **Version ≥ 0.30.9** (XXX XX, 2026):  
+- [`gget pineapple`](pineapple.md): **New module** to list and download curated bio-imaging datasets and pre-trained model weights from [Pineapple](https://github.com/tomouellette/pineapple) (by Tom Ouellette). Browse the segmentation/benchmark dataset and model-weights catalog (names, authors, sizes, licenses) and download a resource by name directly from its Google Drive host — no Rust binary required. Available in the Python API and on the command line. Resolves [issue 161](https://github.com/scverse/gget/issues/161).
 
 **Version ≥ 0.30.8** (Jun 28, 2026):  
 - [`gget g2p`](g2p.md): Either `gene` or `--uniprot_id` is now sufficient — whichever is missing is resolved via UniProt and cached. Gene→UniProt picks the canonical reviewed human Swiss-Prot entry; the resolution and its limitations are logged. The canonical pair is **always** prepended to the result as `gene_name` / `uniprot_id` columns (and stored on `df.attrs`), so the output schema is invariant regardless of input mode. Existing call sites continue to work.

docs/src/es/pineapple.md

@@ -0,0 +1,83 @@
+[<kbd> Ver el codigo fuente de la pagina en GitHub </kbd>](https://github.com/scverse/gget/blob/main/docs/src/es/pineapple.md)
+
+> Parámetros de Python són iguales a los parámetros largos (`--parámetro`) de Terminal, si no especificado de otra manera. Banderas son parámetros de verdadero o falso (True/False) en Python. El manuál para cualquier modulo de gget se puede llamar desde la Terminal con la bandera `-h` `--help`.  
+# gget pineapple 🍍
+Lista y descarga conjuntos de datos de bioimagen curados y pesos de modelos preentrenados desde [Pineapple](https://github.com/tomouellette/pineapple).  
+[Pineapple](https://github.com/tomouellette/pineapple) (por Tom Ouellette) es una herramienta para el perfilado celular basado en imágenes que además cura y estandariza una colección de conjuntos de datos de bioimagen anotados (segmentación y benchmark) y pesos de modelos autosupervisados, alojados en Google Drive. `gget pineapple` te permite explorar este catálogo y descargar los recursos directamente — sin necesidad del binario de Rust.  
+Regresa: JSON (línea de comandos) o Dataframe/CSV (Python).
+
+> **Alcance:** `gget pineapple` solo envuelve la descarga de datos de Pineapple. No reimplementa las funciones de procesamiento de imágenes de Pineapple (`process`, `profile`, `neural`, `measure`) — para eso, usa directamente la herramienta [Pineapple](https://github.com/tomouellette/pineapple).
+
+> ⚠️ Por favor revisa la referencia original y la licencia de cada conjunto de datos (mostradas en el catálogo) antes de usarlo. Algunos conjuntos de datos son solo para uso no comercial.
+
+**Parámetro posicional**  
+`name`  
+Nombre del conjunto de datos/pesos a obtener, p. ej. `vicar_2021` o `dino_vit_small`. Omítelo para listar el catálogo completo de la categoría elegida.
+
+**Parámetros optionales**  
+`-c` `--category`  
+Categoría del recurso: `segmentation`, `benchmark`, o `weights`. Por defecto: `segmentation`.  
+
+`-od` `--out_dir`  
+Directorio en el que se descargará el recurso (se usa con `--download`). Por defecto: directorio actual.  
+
+`-o` `--out`  
+Ruta del archivo en el que se guardará la tabla del catálogo, p. ej. ruta/al/directorio/results.csv (o .json). Por defecto: salida estándar.  
+Python: `save=True` guardará la salida en el directorio de trabajo actual.
+
+**Banderas**  
+`-d` `--download`  
+Descarga el recurso (requiere un `name` específico) en `--out_dir`. Los conjuntos de datos son grandes (hasta varios GB); consulta la columna `size_gb`.  
+
+`-csv` `--csv`  
+Solo para Terminal. Produce los resultados en formato CSV.  
+Para Python, usa `json=True` para producir la salida en formato JSON.
+
+`-q` `--quiet`  
+Solo para Terminal. Impide que la información de progreso sea exhibida.  
+Para Python, usa `verbose=False` para impedir que la información de progreso sea exhibida.  
+
+### Ejemplos
+**Listar los conjuntos de datos de segmentación disponibles:**
+```bash
+gget pineapple --category segmentation
+```
+```python
+# Python
+gget.pineapple(category="segmentation")
+```
+&rarr; Produce el catálogo de conjuntos de datos de segmentación curados.
+
+| name | category | data_authors | size_gb | license | filename | google_drive_id |
+| --- | --- | --- | --- | --- | --- | --- |
+| vicar_2021 | segmentation | Vicar et al. 2021 | 0.113 | CC BY 4.0 | vicar-2021.tar.gz | 12tJOlIHZPFqp8GLek_jV__Uhhgsa530_ |
+| . . . | . . . | . . . | . . . | . . . | . . . | . . . |
+
+<br/><br/>
+**Descargar un conjunto de datos específico:**
+```bash
+gget pineapple vicar_2021 --download --out_dir ./pineapple_data
+```
+```python
+# Python
+gget.pineapple("vicar_2021", download=True, out_dir="./pineapple_data")
+```
+&rarr; Descarga `vicar-2021.tar.gz` en `./pineapple_data` y produce la entrada del catálogo.
+
+<br/><br/>
+**Listar los pesos de modelos preentrenados:**
+```bash
+gget pineapple --category weights
+```
+```python
+# Python
+gget.pineapple(category="weights")
+```
+&rarr; Produce el catálogo de pesos de modelos autosupervisados preentrenados (p. ej. `dino_vit_small`, `subcell_vit_base`).
+
+# Citar
+Si utiliza `gget pineapple` en una publicación, favor de citar el siguiente recurso y las referencias originales de los conjuntos de datos (listadas en la columna `data_authors` del catálogo):  
+
+- Pineapple: scalable processing for image-based cell profiling. [https://github.com/tomouellette/pineapple](https://github.com/tomouellette/pineapple)
+
+- Luebbert, L., & Pachter, L. (2023). Efficient querying of genomic reference databases with gget. Bioinformatics. [https://doi.org/10.1093/bioinformatics/btac836](https://doi.org/10.1093/bioinformatics/btac836)

gget/__init__.py

@@ -22,6 +22,7 @@
 from .gget_mutate import mutate
 from .gget_opentargets import opentargets
 from .gget_pdb import pdb
+from .gget_pineapple import pineapple
 from .gget_ref import ref
 from .gget_search import search
 from .gget_seq import seq

gget/constants.py

@@ -7,6 +7,10 @@
 # strategy avoid hanging indefinitely on slow upstreams.
 DEFAULT_REQUESTS_TIMEOUT = (10, 60)
 
+# Google Drive download endpoint used by gget pineapple
+# (the Pineapple bio-imaging datasets/weights are hosted on Google Drive)
+PINEAPPLE_GDRIVE_URL = "https://drive.google.com/uc?export=download"
+
 # Ensembl REST API server for gget seq and info
 ENSEMBL_REST_API = "http://rest.ensembl.org/"
 ENSEMBL_FTP_URL = "http://ftp.ensembl.org/pub/"