animevibe-cli/scrape.js

const fetch = require('node-fetch');
const cheerio = require('cheerio');

function makeUrlScrape(scrape, defaultUrl) {
    return async (url=defaultUrl) => {
        const res = await fetch(url);
        const $ = cheerio.load(await res.text());
        return { url, ...scrape($, { url }) };
    };
}

const scrapeAnimevibeDownloadPage = makeUrlScrape($ => {
    const entries = $('.alert > p').map((_, p) => {
        const key = $(p).text().split(' ')[0].toLowerCase();
        const href = $(p).next('a').attr('href');
        return [[key, href]];
    }).get();
    return Object.fromEntries(entries);
});

const scrapeVidCDNDownloadPage = makeUrlScrape($ => {
    const downloads = scrapeDownloads($);
    const info = scrapeInfo($);
    return { ...info, downloads };
});

function scrapeDownloads($) {
    return $('div.mirror_link').first()
    .find('.dowload  > a').map((_, a) => {
        const info = parseDownload($(a).text());
        const url = $(a).attr('href');
        return { ...info, url };
    }).get();
}

function scrapeInfo($) {
    const keys = ['filename', 'filesize', 'duration', 'resolution'];
    const entries = $('.sumer_l > ul > li > span').map((i, span) => {
        const key = keys[i];
        const value = $(span).text();
        return [[key, value]];
    }).get();
    return Object.fromEntries(entries);
}

function parseDownload(text) {
    const regex = /Download\s+\((?<quality>[\w\d]+)P\s+-\s+(?<format>[\w\d]+)\)/;
    const { groups } = regex.exec(text);
    return groups;
}

const scrapeAnimevibeSeriesPage = makeUrlScrape(($, { url }) => {
    const seriesId = url.split('/')[4];
    const downloadId = scrapeDownloadId($);
    const currentEpisodeNumber = scrapeEpisodeNumber($);

    const infoDiv = $('#blogShort');
    const englishTitle = infoDiv.find('h5.title-av-search-res').text();
    const thumbnailUrl = infoDiv.find('#thumb-rsz').attr('data-bg');

    const info = scrapeInfoDiv(infoDiv, $);
    const episodeCount = parseInt(info['Number of Episodes'].split(' ', 1));
    const views = parseInt(info['Views'].split(' ', 1));
    const summary = info['Summary'];
    const gernes = info['Genre'].split(', ');
    const otherTitles = parseTitles(info['Alternate Titles']);
    const myAnimeListScore = parseFloat(info['[MyAnimeList] Score']);
    const type = info['Type'];
    const status = info['Status'];
    const dates = parseDates(info['Date']);

    return {
        seriesId,
        downloadId,
        currentEpisodeNumber,
        episodeCount, 
        titles: { english: englishTitle, ...otherTitles },
        thumbnailUrl,
        type,
        ...dates,
        status,
        gernes,
        summary, 
        myAnimeListScore,
        views,
    };
});

function scrapeEpisodeNumber($) {
    const button = $('.current-episode-button');
    return button.length ? parseInt(button.text()) : null;
}

function scrapeDownloadId($) {
    const href = $('.download-av > a:nth-child(1)').attr('href');
    return new URL(href).searchParams.get('id');
}

function parseTitles(text) {
    const regex = /(?<nativeJapanese>[^,]*), (?<japanese>[^,]*), (?<jsonParsableAbbreviations>\[.*\])/;
    const { groups } = regex.exec(text);
    const json = groups.jsonParsableAbbreviations.replace(/'/g, '"');
    return {
        nativeJapanese: groups.nativeJapanese,
        japanese: groups.japanese,
        abbreviations: JSON.parse(json),
    };
}

function parseDates(text) {
    const regex = /(?<releaseDate>\w{3} \d{1,2}, \d{4})( to (\?|(?<finishedDate>\w{3} \d{1,2}, \d{4})))?/;
    const { groups } = regex.exec(text);
    const releaseDate = groups.releaseDate;
    const finishedDate = groups.finishedDate || null;
    return { releaseDate, finishedDate };
}

function scrapeInfoDiv(infoDiv, $) {
    const entries = infoDiv.find('h6.excerpt-anime-info').map((_, h6) => {
        const [key, value] = $(h6).text().split(/(^[^:]+): /).slice(1);
        return [[key, value]];
    }).get();

    return Object.fromEntries(entries);
}

async function scrapeMp4UploadVideoFileUrl(url) {
    const id = url.split('/').pop();
    const res = await fetch(url, {
        method: 'POST',
        body: new URLSearchParams({
            id, op: 'download2'
        }),
        redirect: 'manual',
    });
    return res.headers.get('location');
}

module.exports = {
    scrapeVidCDNDownloadPage, 
    scrapeAnimevibeSeriesPage, 
    scrapeAnimevibeDownloadPage,
    scrapeMp4UploadVideoFileUrl,
};