Download IPA transcriptions from Wiktionary

download-ipa.py

import requests
from bs4 import BeautifulSoup
from tqdm import tqdm


def get_ipa(html):
    soup = BeautifulSoup(html, 'html5lib')
    ipa_spans = soup.findAll('span', {'class': 'IPA'})
    return [span.text[1:-1] for span in ipa_spans]

def get_html(word):
    r = requests.get(f'https://en.wiktionary.org/wiki/{word}')
    return r.text

def scrape(target_words):
    words = {}
    for word in tqdm(target_words):
        html = get_html(word)
        try:
            ipa = get_ipa(html)
        except:
            ipa = None
        words[word] = ipa
    return words

words = ['баба', 'дядо', 'внуче']  # put words here
transcriptions = scrape(words)

# {
#    'баба': ['ˈbabə', 'ˈbaba', 'ˈbabə', 'bâba'],
#    'внуче': ['ˈvnut͡ʃɛ'],
#    'дядо': ['ˈdʲado']
#}