Generating shitposts from tumblr/Gutenberg corpora

generate_post.py

import markovify
import tumblr_client
import settings
import re
import nltk

class NltkText(markovify.Text):
    def word_split(self, sentence):
        words = re.split(self.word_split_pattern, sentence)
        if words[0] != "":
            words = [ "::".join(tag) for tag in nltk.pos_tag(words) ]
        else:
            words = list("",)
        return words

    def word_join(self, words):
        return " ".join(word.split("::")[0] for word in words)

print('loading gutenberg corpora...')
gutenberg_texts = " ".join([ " ".join(nltk.corpus.gutenberg.words(f)) for f in nltk.corpus.gutenberg.fileids() ])
gutenberg_model = NltkText(gutenberg_texts)
with open('text_source.txt', 'r', encoding='utf8') as f:
    print('loading tumblr corpora...')
    tumblr_text_model = NltkText(f)

text_model = markovify.combine([tumblr_text_model, gutenberg_model ], [ 2, 1 ])
post = text_model.make_sentence()

tumblr_client.create_post('screaming-bot', post, settings.tags_to_post)