myreadingmanga-unofficial/robots/text.js

MyReadingManga WebCrawler. Find By Languages, Genres and Tags.

const readline = require('readline-sync')
const state = require('./state.js')
const axios = require('axios')
const JSSoup = require('jssoup').default

async function robot() {
    const { data } = await axios.get('https://myreadingmanga.info')
    const soup = new JSSoup(data)
    soup.prettify()
    
    const languages = await getLanguages()
    const genres = await getGenres()
    const tags = await getTags()
    const content = { languages, genres, tags }
    state.save(content)

    async function getLanguages() {
        const languagesContainer = soup.findAll('section')
        const a_html = languagesContainer[4].findAll('a')
        const languages = a_html.map(language => {
            const title = language.text;
            const url = language.attrs.href
            return { title, url }
        })
        return languages
    }

    async function getGenres() {
        const genresContainer = soup.findAll('section')
        const a_html = genresContainer[5].findAll('a')
        const genres = a_html.map(genre => {
            const title = genre.text;
            const url = genre.attrs.href
            return { title, url }
        })
        return genres
    }

    async function getTags() {
        const tagsContainer = soup.findAll('section')
        const a_html = tagsContainer[6].findAll('a')
        const tags = a_html.map(tag => {
            const title = tag.text;
            const url = tag.attrs.href
            return { title, url }
        })
        return tags
    }
}

module.exports = robot