myreadingmanga-unofficial/robots/image.js

MyReadingManga WebCrawler. Find By Languages, Genres and Tags.

const state = require('./state.js')
const axios = require('axios')
const JSSoup = require('jssoup').default
const imageDownloader = require('image-downloader')
const fs = require('fs');
async function robot(manga) {
    const content = state.load()
    await getPages(manga, content)

    async function getPages(manga, content) {
        const { data } = await axios.get(manga.url)
        const soup = new JSSoup(data)
        soup.prettify()
        const prePages = soup.findAll('img')
        const pages = prePages
            .filter(prePage => !prePage.attrs.src.endsWith("gif"))
            .filter(prePage => !prePage.attrs.src.includes("wp-content"))
        pages.map(page => console.log(page.attrs.src))
        downloadAll(pages, manga.title)
    }

    async function downloadAll(pages, title) {
        pages.map(async page => {
            const pos = page.attrs.src.lastIndexOf('/')+1
            const fileName = page.attrs.src.substr(pos)
            const url = page.attrs.src
            await downloadAndSave(title, fileName, url)
        })
    }

    async function downloadAndSave(title, fileName, url) {
        if(!fs.existsSync('./content')) fs.mkdirSync('./content')
        if(!fs.existsSync(`./content/${title}`)) fs.mkdirSync(`./content/${title}`)
        return imageDownloader.image({ url, dest: `./content/${title}/${fileName}` })
    }
}

module.exports = robot