nealcaren

# /// script
# requires-python = ">=3.12"
# dependencies = [
#     "pymupdf",
#     "pillow",
# ]
# ///

import fitz  # PyMuPDF
import os

nealcaren

nealcaren

nealcaren

import requests
import re
import plistlib

# Find the available Chrome Drivers
url = "https://pypi.org/project/chromedriver-binary/#history"
html = requests.get(url).text
available = re.findall("\/project\/chromedriver-binary\/(.*?)\/", html)
available = [i for i in available if i.count(".") > 2]

nealcaren

nealcaren

nealcaren

nealcaren

# http://stackoverflow.com/questions/753052/strip-html-from-strings-in-python

from HTMLParser import HTMLParser

class MLStripper(HTMLParser):
    def __init__(self):
        self.reset()
        self.fed = []
    def handle_data(self, d):
        self.fed.append(d)

nealcaren

nealcaren

# coding: utf-8

from string import punctuation
from nltk.tokenize import sent_tokenize
from collections import Counter

liwc_stem_categories = {"yellow": ["Perceptual processes", "See"], "four": ["Total function words", "Numbers"], "jihad": ["Religion"], "sleep": ["Biological processes", "Body"], "authorit": ["Achievement"], "feeding": ["Biological processes", "Ingestion"], "buddy": ["Social processes", "Friends"], "opport": ["Affective processes", "Positive emotion", "Achievement"], "abilit": ["Achievement"], "bike": ["Leisure"], "buddh": ["Religion"], "daze": ["Affective processes", "Negative emotion"], "lord": ["Religion"], "emphysem": ["Biological processes", "Health"], "hormone": ["Biological processes", "Health"], "risk": ["Affective processes", "Negative emotion", "Anxiety"], "compassion": ["Social processes", "Affective processes", "Positive emotion"], "rise": ["Motion", "Relativity"], "voic": ["Perceptual processes", "Hear"], "arous": ["Biological processes", "Body", "Sexual"], "govern": ["Work"], "