randomgutenberg.py

#!/usr/bin/env python
"download random text file from gutenberg project into current directory; `pip install Gutenberg` first"
import random
from gutenberg.acquire import load_etext
from gutenberg.cleanup import strip_headers

list_generated_random = []

def get_unique_random(lower, upper):
    choice = random.randrange(lower, upper)
    while choice in list_generated_random:
        choice = random.randrange(lower, upper)
    list_generated_random.append(choice)
    return choice

def main():
    while True:
        doc_id = get_unique_random(1, 53000)
        print("downloading doc id: %s" % doc_id)
        text = strip_headers(load_etext(doc_id)).strip()
        with open('%s.txt' % doc_id, 'w+') as f:
            f.write(text)
        print('%s.txt written' % doc_id)

if __name__ == '__main__':
    try:
        main()
    except KeyboardInterrupt:
        print('exiting\ngoodbye :)')