@rexxhayanasi/nhentai/dist/Parser/doujin.js

A scraper for NHentai with types

"use strict";
var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
    function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
    return new (P || (P = Promise))(function (resolve, reject) {
        function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
        function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
        function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
        step((generator = generator.apply(thisArg, _arguments || [])).next());
    });
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.parseDoujinInfo = void 0;
const lib_1 = require("../lib");
const parseDoujinInfo = ($, site, api_pages) => __awaiter(void 0, void 0, void 0, function* () {
    const pages = [];
    const gallery_id = ($('.thumb-container').first().find('a > img').attr('data-src') ||
        '/galleries/')
        .split('/galleries/')[1]
        .split('/')[0];
    if (site === 'net' && api_pages)
        api_pages.forEach((page, i) => pages.push(`https://i.nhentai.net/galleries/${gallery_id}/${i + 1}.${(0, lib_1.getExtension)(page.t)}`));
    else
        for (const el of $('.thumb-container')) {
            const url = ($(el).find('a > img').attr('data-src') || '').replace(/t(?=\.)/, '');
            if (url) {
                const page = url.replace(lib_1.imageSites[site], 'i.nhentai.net');
                const status = yield (0, lib_1.getPageStatus)(page);
                pages.push(status === 200 ? page : url);
            }
        }
    const cover = $('#cover').find('a > img').attr('data-src') ||
        $('#cover').find('a > img').attr('src');
    const id = ($('#cover').find('a').attr('href') || 'g/')
        .split('g/')[1]
        .split('/')[0];
    const titles = {
        english: $('#info').find('h1').text().trim(),
        original: $('#info').find('h2').text().trim()
    };
    const baseURL = lib_1.baseURLS[site];
    const parodies = [];
    const characters = [];
    const tags = [];
    const artists = [];
    const groups = [];
    const languages = [];
    const categories = [];
    $('.tag-container.field-name').each((i, el) => {
        const type = $(el).text().trim().toLowerCase();
        const contents = [];
        const push = (field) => contents
            .filter((content) => content !== '')
            .forEach((content) => field.push(content));
        $(el)
            .find('.tags')
            .find('a')
            .each((i, el) => {
            contents.push($(el).text().trim().split('\n')[0]);
        });
        type.startsWith('parodies')
            ? push(parodies)
            : type.startsWith('characters')
                ? push(characters)
                : type.startsWith('tags')
                    ? push(tags)
                    : type.startsWith('artists')
                        ? push(artists)
                        : type.startsWith('groups')
                            ? push(groups)
                            : type.startsWith('languages')
                                ? push(languages)
                                : push(categories);
    });
    const url = `${baseURL}/g/${id}`;
    const images = new lib_1.Pages(pages, titles.english);
    return {
        id,
        title: titles.english,
        originalTitle: titles.original,
        parodies: (0, lib_1.clean)(parodies),
        characters: (0, lib_1.clean)(characters),
        tags: (0, lib_1.clean)(tags),
        artists: (0, lib_1.clean)(artists),
        groups: (0, lib_1.clean)(groups),
        languages: (0, lib_1.clean)(languages),
        categories: (0, lib_1.clean)(categories),
        cover: !pages.some(url => url.includes('cdn.dogehls.xyz'))
            ? cover.replace('cdn.dogehls.xyz', 't3.nhentai.net')
            : null,
        images,
        url
    };
});
exports.parseDoujinInfo = parseDoujinInfo;