nsmargolies

import wikipediaapi  # pip install wikipedia-api
import pandas as pd
import concurrent.futures
from tqdm import tqdm

def wiki_scrape(topic_name, verbose=True):
    def wiki_link(link):
        try:
            page = wiki_api.page(link)
            if page.exists():

nsmargolies

def wiki_page(page_name):
    wiki_api = wikipediaapi.Wikipedia(language='en',
            extract_format=wikipediaapi.ExtractFormat.WIKI)
    page_name = wiki_api.page(page_name)
    if not page_name.exists():
        print('Page {} does not exist.'.format(page_name))
        return

    page_data = pd.DataFrame({
        'page': page_name,

nsmargolies

import pandas as pd
import re
import spacy
import neuralcoref

nlp = spacy.load('en_core_web_lg')
neuralcoref.add_to_pipe(nlp)


def get_entity_pairs(text, coref=True):