Is there a tool / code snippet that allows downloading of taxonomy data from the site?

Curators
7

I cleaned it up a bit, let me know if you have questions or it doesn’t work. The output is a csv.

import urllib.request
import urllib.error
import json
import csv
import time

# see https://api.inaturalist.org/v1/docs/#!/Taxa/get_taxa for more details on parameters
# in particular, if there are more than 10,000 results, you'll need to pare it down via parameters to get everything
taxon = 45933		# specify the taxon number here
rank  = 'species'	# use '' (empty quotes) if you don't want to specify a rank

# by default calls only for active taxa, doesn't return all the names for each taxon, and 200 results per page
apiurl = 'https://api.inaturalist.org/v1/taxa?is_active=true&all_names=false&per_page=200'
	
def call_api(sofar=0, page=1):
	"""Call the api repeatedly until all pages have been processed."""
	try:
		response = urllib.request.urlopen(apiurl + '&page=' + str(page) + '&taxon_id=' + str(taxon) + '&rank=' + rank)
	except urllib.error.URLError as e:
		print(e)
	else:
		responsejson = json.loads(response.read().decode())
		for species in responsejson['results']:
			# lots of possible data to keep, here it's name, taxon id, and observations count
			csvwriter.writerow([species['name'], species['id'], species['observations_count']])
		if (sofar + 200 < responsejson['total_results']):  # keep calling the API until we've gotten all the results
			time.sleep(1)  # stay under the suggested API calls/min, not strictly necessary
			call_api(sofar + 200, page + 1)

try:
	with open(str(taxon) +'.csv', encoding='utf-8', mode='w+', newline='') as w:  # open a csv named for the taxon
		csvwriter = csv.writer(w, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
		call_api()
except Exception as e:
	print(e)
3 Likes