Script for generating a glossary from text

glossary.py

import sys
import re
import json
import requests
import nltk
import random
import time

# id and key from https://developer.oxforddictionaries.com/
app_id = ''
app_key = ''
url = 'https://od-api.oxforddictionaries.com:443/api/v1/entries/en/%s'

min_word_length = 7

words_count = 50

# models - https://pythonprogramming.net/natural-language-toolkit-nltk-part-speech-tagging/

def is_valid(pos): return pos[:2] == 'VB' or pos[:2] == 'JJ' or pos[:2] == 'NN'

def get_word_definition(word):
    request_url = (url) % (word)
    r = requests.get(request_url, headers={
                     'app_id': app_id, 'app_key': app_key})
    response = r.json()
    definition = response['results'][0]['lexicalEntries'][0]['entries'][0]['senses'][0]['definitions'][0]
    return definition

def clear_text(text):
    template = '[^A-Za-z ]+'
    clear_text = re.sub(template, '', text)
    return clear_text

def main(argv):
    # uncomment at first time
    # nltk.download()

    with open('input.txt') as f:
        text = f.read()
    text = clear_text(text)

    tokenized = nltk.word_tokenize(text)
    valid_words = [word for (word, pos) in nltk.pos_tag(
        tokenized) if is_valid(pos)]
    valid_words_set = set(
        [x.lower() for x in valid_words if (len(x) > min_word_length)])

    print(('\tFinded %s words...') % (len(valid_words_set)))

    global words_count
    if len(valid_words_set) < words_count:
        print("\tInsufficient number of words..")
        exit(1)

    with open('result.txt', 'w', encoding='utf-8') as f:
        while words_count != 0:
            word = valid_words_set.pop()
            try:
                definition = get_word_definition(word)
                result = '%s - %s' % (word, definition)
                print('\t'+result)
                f.write(result+'\n')
                words_count -= 1
            except:
                pass


if __name__ == "__main__":
    main(sys.argv[1:])