species_binomial_wiki

import wikipedia
import pandas as pd 
import tempfile
import zipfile
import os 
import json

from owid import walden

raw_dataset = walden.Catalog().find_one("living_planet")

tmp_dir = tempfile.mkdtemp(prefix="etl-")

zipfile.ZipFile(raw_dataset.local_path).extractall(tmp_dir)

df = pd.read_csv(
    os.path.join(tmp_dir, "Public data set/LPR2020data_public.csv"), encoding="latin-1"
)

binom = df['Binomial'].drop_duplicates().str.replace(r'_', ' ')

binom_dict = {}
for b in binom:
    bw = wikipedia.search(b, results = 1)
    binom_dict[b] =  ''.join(bw)



with open('species_binomial_wiki.json', 'w') as fp:
    json.dump(binom_dict, fp, indent = 2)