evanmiltenburg

import xlsxwriter

# Create workbook with a new worksheet.
workbook = xlsxwriter.Workbook('hello.xlsx')
worksheet = workbook.add_worksheet()

# Write the tokens.
worksheet.write('A1', 'Hello')
worksheet.write('B1', 'world')
worksheet.write('C1', '!')

evanmiltenburg

import spacy

nlp = spacy.load('nl_core_news_sm')

with open('bordewijk.txt') as f:
    doc = nlp(f.read())

people = [ent.orth_ for ent in doc.ents if ent.label_ == 'PERSON']

print(people)

evanmiltenburg

import requests
import re
import time

r = requests.get('https://direct.mit.edu/books/book/5244/The-Open-Handbook-of-Linguistic-Data-Management',
                 stream=True, headers={'User-agent': 'Mozilla/5.0'})
                 
urls = re.findall('href="(.*?.pdf)"', r.text)
base = 'https://direct.mit.edu'
urls = [base + path for path in urls if '/book/' in path]