yukiarimo

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

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

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

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