From language name to ISO code

language_to_iso_code.py

import pycountry

def get_code(language):
    lang = pycountry.languages.get(name=language)
    # print(lang)
    if lang is None:
        return language+ " doesn't exist"
    try:
        return lang.alpha_2
    except:
        pass
    try:
        return lang.alpha_3
    except:
        pass
    return language + "has no alpha_2 or alpha_3"
    
    
    
bert_languages = ["Afrikaans","Albanian","Arabic","Aragonese","Armenian","Asturian","Azerbaijani","Bashkir","Basque","Bavarian","Belarusian","Bengali","Bishnupriya","Bosnian","Breton","Bulgarian","Burmese","Catalan","Cebuano","Chechen","Chinese (Simplified)","Chinese (Traditional)","Chuvash","Croatian","Czech","Danish","Dutch","English","Estonian","Finnish","French","Galician","Georgian","German","Modern Greek (1453-)","Gujarati","Haitian","Hebrew","Hindi","Hungarian","Icelandic","Ido","Indonesian","Irish","Italian","Japanese","Javanese","Kannada","Kazakh","Kirghiz","Korean","Latin","Latvian","Lithuanian","Lombard","Low German","Luxembourgish","Macedonian","Malagasy","Malay (macrolanguage)","Malayalam","Marathi","Minangkabau","Nepali (macrolanguage)","Newari","Norwegian Bokmål","Norwegian Nynorsk","Occitan (post 1500)","Persian","Piemontese","Polish","Portuguese","Panjabi","Romanian","Russian","Scots","Serbian","Serbo-Croatian","Sicilian","Slovak","Slovenian","South Azerbaijani","Spanish","Sundanese","Swahili (macrolanguage)","Swedish","Tagalog","Tajik","Tamil","Tatar","Telugu","Turkish","Ukrainian","Urdu","Uzbek","Vietnamese","Volapük","Waray (Philippines)","Welsh","Western Frisian","Western Panjabi","Yoruba"]
result = [get_code(l) for l in bert_languages]
for r,lang in zip(result,bert_languages):
    print(r," --- ",lang)

print(result)