Yuki Arimo yukiarimo

🖥️

Coding

Software Developer, AI Engineer, and Artist

yukiarimo / novel_scraper.py

Created November 20, 2025 23:11

Light Novel Web Scraper (from ncode.syosetu.com)

	import requests
	from bs4 import BeautifulSoup
	import time
	import os

	def sanitize_filename(filename):
	"""Removes characters that are invalid for filenames."""
	return "".join(c for c in filename if c.isalnum() or c in (' ', '-', '_')).rstrip()

	def scrape_novel(novel_code):

yukiarimo / apple_dict_extract.py

Created November 20, 2025 22:58

Apple Dictionary Extractor

	import json
	import re
	import sys
	from tqdm import tqdm
	from html import unescape
	from bs4 import BeautifulSoup

	def strip_html_tags(html: str) -> str:
	"""Remove HTML tags for plain text extraction."""
	soup = BeautifulSoup(html, "html.parser")

yukiarimo / character-ai-dwnl-2-0.js

Created May 3, 2024 22:53

Character AI Downloader 2.0

	let htmlString = document.body.innerHTML
	const parser = new DOMParser();
	const doc = parser.parseFromString(htmlString, 'text/html');

	const messages = [];

	const divs = doc.querySelectorAll('.group.relative.max-w-3xl.min-max-w-3xl.m-auto.w-full.p-2');
	divs.forEach(div => {
	const nameElement = div.querySelector('.text-small');
	if (nameElement) {

yukiarimo / webnovel-downloader.js

Created March 14, 2024 20:52

Web novel Downloader

	function extractAndDownloadAllChapters() {
	// Find all containers that hold chapter text
	const chapterContainers = document.querySelectorAll('.cha-words');

	// Initialize an array to hold all chapter texts
	let allChaptersText = [];

	// Iterate over each chapter container
	chapterContainers.forEach(container => {
	// Get all paragraph elements within the container

yukiarimo / bert_train.py

Last active November 20, 2025 23:00

Bert Large CNN Trainer

	import pandas as pd
	import torch
	from torch.utils.data import Dataset, DataLoader
	from transformers import BartForConditionalGeneration, BartTokenizer
	from torch.optim import AdamW
	import os

	os.environ["PYTORCH_MPS_HIGH_WATERMARK_RATIO"] = "0.0"

	# Define your dataset class

yukiarimo / character-ai-wrapper.py

Last active December 24, 2023 08:07

Character AI Dialog Extractor

	import json
	from bs4 import BeautifulSoup

	with open("Main - Rushia Uruha.html") as fp:
	soup = BeautifulSoup(fp, "html.parser")
	items = []
	main_text = None
	target_text = None
	for tag in soup.find_all("span", class_="s1"):
	text = tag.get_text().strip()

yukiarimo / time.js

Created December 2, 2022 21:30

Unix time converter

	function timeConverter(UNIX_timestamp){
	var a = new Date(UNIX_timestamp * 1000);
	var months = ['Jan','Feb','Mar','Apr','May','Jun','Jul','Aug','Sep','Oct','Nov','Dec'];
	var year = a.getFullYear();
	var month = months[a.getMonth()];
	var date = a.getDate();
	var hour = a.getHours();
	var time = date + ' ' + month + ' ' + year + ' ' + hour + ':' + '00' ;
	return time;
	}