multithreaded

gistfile1.py

import requests
from bs4 import BeautifulSoup
from concurrent import futures

BASE_URL = "http://ordnet.dk/ddo/ordbog?query={}"

def get_ipa(word):
    soup = BeautifulSoup(requests.get(BASE_URL.format(word)).text)
    try:
        return soup.select(".lydskrift")[0].contents[1]
    except IndexError:
        pass
    return None

def main(path_to_file):
    ans = []

    words = [line.split(" ")[0] for line in open(path_to_file)]
    with futures.ThreadPoolExecutor(max_workers=50) as p:
        ipas = p.map(get_ipa, words)
    ans = [ipa for ipa in futures.as_completed(ipas) if ipa]

    return ans