def datasets(data="all",
type=None,
uuid=None,
query=None,
id=None,
limit=100,
offset=None,
**kwargs):
"""
Search for datasets and dataset metadata.
:param data: [str] The type of data to get. Default: ``all``
:param type: [str] Type of dataset, options include ``OCCURRENCE``, etc.
:param uuid: [str] UUID of the data node provider. This must be specified if data
is anything other than ``all``.
:param query: [str] Query term(s). Only used when ``data = 'all'``
:param id: [int] A metadata document id.
References http://www.gbif.org/developer/registry#datasets
Usage::
from pygbif import registry
registry.datasets(limit=5)
registry.datasets(type="OCCURRENCE")
registry.datasets(uuid="a6998220-7e3a-485d-9cd6-73076bd85657")
registry.datasets(data='contact', uuid="a6998220-7e3a-485d-9cd6-73076bd85657")
registry.datasets(data='metadata', uuid="a6998220-7e3a-485d-9cd6-73076bd85657")
registry.datasets(data='metadata', uuid="a6998220-7e3a-485d-9cd6-73076bd85657", id=598)
registry.datasets(data=['deleted','duplicate'])
registry.datasets(data=['deleted','duplicate'], limit=1)
"""
args = {"q": query, "type": type, "limit": limit, "offset": offset}
data_choices = [
"all",
"organization",
"contact",
"endpoint",
"identifier",
"tag",
"machinetag",
"comment",
"constituents",
"document",
"metadata",
"deleted",
"duplicate",
"subDataset",
"withNoEndpoint",
]
check_data(data, data_choices)
if len2(data) == 1:
return datasets_fetch(data, uuid, args, **kwargs)
else:
return [datasets_fetch(x, uuid, args, **kwargs) for x in data]
def dataset_metrics(uuid):
"""
Get details on a GBIF dataset.
:param uuid: [str] One or more dataset UUIDs. See examples.
References: http://www.gbif.org/developer/registry#datasetMetrics
Usage::
from pygbif import registry
registry.dataset_metrics(uuid='3f8a1297-3259-4700-91fc-acc4170b27ce')
registry.dataset_metrics(uuid='66dd0960-2d7d-46ee-a491-87b9adcfe7b1')
registry.dataset_metrics(uuid=['3f8a1297-3259-4700-91fc-acc4170b27ce', '66dd0960-2d7d-46ee-a491-87b9adcfe7b1'])
"""
def getdata(x):
url = gbif_baseurl + "dataset/" + x + "/metrics"
return gbif_GET(url, {})
if len2(uuid) == 1:
return getdata(uuid)
else:
return [getdata(x) for x in uuid]
def installations(
data="all",
uuid=None,
q=None,
identifier=None,
identifierType=None,
limit=100,
offset=None,
**kwargs
):
"""
Installations metadata.
:param data: [str] The type of data to get. Default is all data. If not ``all``, then one
or more of ``contact``, ``endpoint``, ``dataset``, ``comment``, ``deleted``, ``nonPublishing``.
:param uuid: [str] UUID of the data node provider. This must be specified if data
is anything other than ``all``.
:param q: [str] Query nodes. Only used when ``data='all'``. Ignored otherwise.
:param identifier: [fixnum] The value for this parameter can be a simple string or integer,
e.g. identifier=120
:param identifierType: [str] Used in combination with the identifier parameter to filter
identifiers by identifier type: ``DOI``, ``FTP``, ``GBIF_NODE``, ``GBIF_PARTICIPANT``,
``GBIF_PORTAL``, ``HANDLER``, ``LSID``, ``UNKNOWN``, ``URI``, ``URL``, ``UUID``
:param limit: [int] Number of results to return. Default: ``100``
:param offset: [int] Record to start at. Default: ``0``
:return: A dictionary
References: http://www.gbif.org/developer/registry#installations
Usage::
from pygbif import registry
registry.installations(limit=5)
registry.installations(q="france")
registry.installations(uuid="b77901f9-d9b0-47fa-94e0-dd96450aa2b4")
registry.installations(data='contact', uuid="b77901f9-d9b0-47fa-94e0-dd96450aa2b4")
registry.installations(data='contact', uuid="2e029a0c-87af-42e6-87d7-f38a50b78201")
registry.installations(data='endpoint', uuid="b77901f9-d9b0-47fa-94e0-dd96450aa2b4")
registry.installations(data='dataset', uuid="b77901f9-d9b0-47fa-94e0-dd96450aa2b4")
registry.installations(data='deleted')
registry.installations(data='deleted', limit=2)
registry.installations(data=['deleted','nonPublishing'], limit=2)
registry.installations(identifierType='DOI', limit=2)
"""
args = {
"q": q,
"limit": limit,
"offset": offset,
"identifier": identifier,
"identifierType": identifierType,
}
data_choices = [
"all",
"contact",
"endpoint",
"dataset",
"identifier",
"tag",
"machineTag",
"comment",
"deleted",
"nonPublishing",
]
check_data(data, data_choices)
def getdata(x, uuid, args, **kwargs):
if x not in ["all", "deleted", "nonPublishing"] and uuid is None:
stop(
"You must specify a uuid if data does not equal all and data does not equal one of deleted or nonPublishing"
)
if uuid is None:
if x == "all":
url = gbif_baseurl + "installation"
else:
url = gbif_baseurl + "installation/" + x
else:
if x == "all":
url = gbif_baseurl + "installation/" + uuid
else:
url = gbif_baseurl + "installation/" + uuid + "/" + x
res = gbif_GET(url, args, **kwargs)
return {"meta": get_meta(res), "data": parse_results(res, uuid)}
if len2(data) == 1:
return getdata(data, uuid, args, **kwargs)
else:
return [getdata(x, uuid, args, **kwargs) for x in data]
def nodes(data="all",
uuid=None,
q=None,
identifier=None,
identifierType=None,
limit=100,
offset=None,
isocode=None,
**kwargs):
"""
Nodes metadata.
:param data: [str] The type of data to get. Default: ``all``
:param uuid: [str] UUID of the data node provider. This must be specified if data
is anything other than ``all``.
:param q: [str] Query nodes. Only used when ``data = 'all'``
:param identifier: [fixnum] The value for this parameter can be a simple string or integer,
e.g. identifier=120
:param identifierType: [str] Used in combination with the identifier parameter to filter
identifiers by identifier type: ``DOI``, ``FTP``, ``GBIF_NODE``, ``GBIF_PARTICIPANT``,
``GBIF_PORTAL``, ``HANDLER``, ``LSID``, ``UNKNOWN``, ``URI``, ``URL``, ``UUID``
:param limit: [int] Number of results to return. Default: ``100``
:param offset: [int] Record to start at. Default: ``0``
:param isocode: [str] A 2 letter country code. Only used if ``data = 'country'``.
:return: A dictionary
References http://www.gbif.org/developer/registry#nodes
Usage::
from pygbif import registry
registry.nodes(limit=5)
registry.nodes(identifier=120)
registry.nodes(uuid="1193638d-32d1-43f0-a855-8727c94299d8")
registry.nodes(data='identifier', uuid="03e816b3-8f58-49ae-bc12-4e18b358d6d9")
registry.nodes(data=['identifier','organization','comment'], uuid="03e816b3-8f58-49ae-bc12-4e18b358d6d9")
uuids = ["8cb55387-7802-40e8-86d6-d357a583c596","02c40d2a-1cba-4633-90b7-e36e5e97aba8",
"7a17efec-0a6a-424c-b743-f715852c3c1f","b797ce0f-47e6-4231-b048-6b62ca3b0f55",
"1193638d-32d1-43f0-a855-8727c94299d8","d3499f89-5bc0-4454-8cdb-60bead228a6d",
"cdc9736d-5ff7-4ece-9959-3c744360cdb3","a8b16421-d80b-4ef3-8f22-098b01a89255",
"8df8d012-8e64-4c8a-886e-521a3bdfa623","b35cf8f1-748d-467a-adca-4f9170f20a4e",
"03e816b3-8f58-49ae-bc12-4e18b358d6d9","073d1223-70b1-4433-bb21-dd70afe3053b",
"07dfe2f9-5116-4922-9a8a-3e0912276a72","086f5148-c0a8-469b-84cc-cce5342f9242",
"0909d601-bda2-42df-9e63-a6d51847ebce","0e0181bf-9c78-4676-bdc3-54765e661bb8",
"109aea14-c252-4a85-96e2-f5f4d5d088f4","169eb292-376b-4cc6-8e31-9c2c432de0ad",
"1e789bc9-79fc-4e60-a49e-89dfc45a7188","1f94b3ca-9345-4d65-afe2-4bace93aa0fe"]
[ registry.nodes(data='identifier', uuid=x) for x in uuids ]
"""
args = {
"q": q,
"limit": limit,
"offset": offset,
"identifier": identifier,
"identifierType": identifierType,
}
data_choices = [
"all",
"organization",
"endpoint",
"identifier",
"tag",
"machineTag",
"comment",
"pendingEndorsement",
"country",
"dataset",
"installation",
]
check_data(data, data_choices)
def getdata(x, uuid, args, **kwargs):
if x != "all" and uuid is None:
stop('You must specify a uuid if data does not equal "all"')
if uuid is None:
if x == "all":
url = gbif_baseurl + "node"
else:
if isocode is not None and x == "country":
url = gbif_baseurl + "node/country/" + isocode
else:
url = gbif_baseurl + "node/" + x
else:
if x == "all":
url = gbif_baseurl + "node/" + uuid
else:
url = gbif_baseurl + "node/" + uuid + "/" + x
res = gbif_GET(url, args, **kwargs)
return {"meta": get_meta(res), "data": parse_results(res, uuid)}
# Get data
if len2(data) == 1:
return getdata(data, uuid, args, **kwargs)
else:
return [getdata(x, uuid, args, **kwargs) for x in data]
def name_usage(key=None,
name=None,
data="all",
language=None,
datasetKey=None,
uuid=None,
sourceId=None,
rank=None,
shortname=None,
limit=100,
offset=None,
**kwargs):
"""
Lookup details for specific names in all taxonomies in GBIF.
:param key: [fixnum] A GBIF key for a taxon
:param name: [str] Filters by a case insensitive, canonical namestring,
e.g. 'Puma concolor'
:param data: [str] The type of data to get. Default: ``all``. Options: ``all``,
``verbatim``, ``name``, ``parents``, ``children``,
``related``, ``synonyms``, ``descriptions``, ``distributions``, ``media``,
``references``, ``speciesProfiles``, ``vernacularNames``, ``typeSpecimens``,
``root``
:param language: [str] Language, default is english
:param datasetKey: [str] Filters by the dataset's key (a uuid)
:param uuid: [str] A uuid for a dataset. Should give exact same results as datasetKey.
:param sourceId: [fixnum] Filters by the source identifier.
:param rank: [str] Taxonomic rank. Filters by taxonomic rank as one of:
``CLASS``, ``CULTIVAR``, ``CULTIVAR_GROUP``, ``DOMAIN``, ``FAMILY``, ``FORM``, ``GENUS``, ``INFORMAL``,
``INFRAGENERIC_NAME``, ``INFRAORDER``, ``INFRASPECIFIC_NAME``, ``INFRASUBSPECIFIC_NAME``,
``KINGDOM``, ``ORDER``, ``PHYLUM``, ``SECTION``, ``SERIES``, ``SPECIES``, ``STRAIN``, ``SUBCLASS``, ``SUBFAMILY``,
``SUBFORM``, ``SUBGENUS``, ``SUBKINGDOM``, ``SUBORDER``, ``SUBPHYLUM``, ``SUBSECTION``, ``SUBSERIES``,
``SUBSPECIES``, ``SUBTRIBE``, ``SUBVARIETY``, ``SUPERCLASS``, ``SUPERFAMILY``, ``SUPERORDER``,
``SUPERPHYLUM``, ``SUPRAGENERIC_NAME``, ``TRIBE``, ``UNRANKED``, ``VARIETY``
:param shortname: [str] A short name..need more info on this?
:param limit: [fixnum] Number of records to return. Default: ``100``. Maximum: ``1000``. (optional)
:param offset: [fixnum] Record number to start at. (optional)
References: http://www.gbif.org/developer/species#nameUsages
Usage::
from pygbif import species
species.name_usage(key=1)
# Name usage for a taxonomic name
species.name_usage(name='Puma', rank="GENUS")
# All name usages
species.name_usage()
# References for a name usage
species.name_usage(key=2435099, data='references')
# Species profiles, descriptions
species.name_usage(key=3119195, data='speciesProfiles')
species.name_usage(key=3119195, data='descriptions')
species.name_usage(key=2435099, data='children')
# Vernacular names for a name usage
species.name_usage(key=3119195, data='vernacularNames')
# Limit number of results returned
species.name_usage(key=3119195, data='vernacularNames', limit=3)
# Search for names by dataset with datasetKey parameter
species.name_usage(datasetKey="d7dddbf4-2cf0-4f39-9b2a-bb099caae36c")
# Search for a particular language
species.name_usage(key=3119195, language="FRENCH", data='vernacularNames')
"""
args = {
"language": language,
"name": name,
"datasetKey": datasetKey,
"rank": rank,
"sourceId": sourceId,
"limit": limit,
"offset": offset,
}
data_choices = [
"all",
"verbatim",
"name",
"parents",
"children",
"related",
"synonyms",
"descriptions",
"distributions",
"media",
"references",
"speciesProfiles",
"vernacularNames",
"typeSpecimens",
"root",
]
check_data(data, data_choices)
if len2(data) == 1:
return name_usage_fetch(data, key, shortname, uuid, args, **kwargs)
else:
return [
name_usage_fetch(x, key, shortname, uuid, args, **kwargs)
for x in data
]
def networks(data="all",
uuid=None,
q=None,
identifier=None,
identifierType=None,
limit=100,
offset=None,
**kwargs):
"""
Networks metadata.
Note: there's only 1 network now, so there's not a lot you can do with this method.
:param data: [str] The type of data to get. Default: ``all``
:param uuid: [str] UUID of the data network provider. This must be specified if data
is anything other than ``all``.
:param q: [str] Query networks. Only used when ``data = 'all'``. Ignored otherwise.
:param identifier: [fixnum] The value for this parameter can be a simple string or integer,
e.g. identifier=120
:param identifierType: [str] Used in combination with the identifier parameter to filter
identifiers by identifier type: ``DOI``, ``FTP``, ``GBIF_NODE``, ``GBIF_PARTICIPANT``,
``GBIF_PORTAL``, ``HANDLER``, ``LSID``, ``UNKNOWN``, ``URI``, ``URL``, ``UUID``
:param limit: [int] Number of results to return. Default: ``100``
:param offset: [int] Record to start at. Default: ``0``
:return: A dictionary
References: http://www.gbif.org/developer/registry#networks
Usage::
from pygbif import registry
registry.networks(limit=1)
registry.networks(uuid='2b7c7b4f-4d4f-40d3-94de-c28b6fa054a6')
"""
args = {
"q": q,
"limit": limit,
"offset": offset,
"identifier": identifier,
"identifierType": identifierType,
}
data_choices = [
"all",
"contact",
"endpoint",
"identifier",
"tag",
"machineTag",
"comment",
"constituents",
]
check_data(data, data_choices)
def getdata(x, uuid, args, **kwargs):
if x != "all" and uuid is None:
stop('You must specify a uuid if data does not equal "all"')
if uuid is None:
url = gbif_baseurl + "network"
else:
if x == "all":
url = gbif_baseurl + "network/" + uuid
else:
url = gbif_baseurl + "network/" + uuid + "/" + x
res = gbif_GET(url, args, **kwargs)
return {"meta": get_meta(res), "data": parse_results(res, uuid)}
if len2(data) == 1:
return getdata(data, uuid, args, **kwargs)
else:
return [getdata(x, uuid, args, **kwargs) for x in data]