notmebotz-tools/scrape/search/gimage.js

Sebuah Tools yang berfungsi untuk mendownload Video atau Foto dari media sosial, serta sebagai tools yang berguna untuk aplikasi kamu seperti untuk BOT

"use strict";
const axios = require("axios");
const { load } = require("cheerio");
const { stringify } = require("node:querystring");

const baseURL = "http://images.google.com/search?";
const exts = [".jpg", ".jpeg", ".png", ".gif", ".bmp", ".svg"];
const srcRegex = /\["(http[^"\[\]]+?)",(\d+),(\d+)\]/g;

const defaultOptions = {
    filteredDomains: ["gstatic.com"],
    userAgent:
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:109.0) Gecko/20100101 Firefox/117.0",
    queryString: "",
};

/**
 * Search for images on Google.
 * @param {string} searchTerm - The term to search for.
 * @param {Object} options - Optional search options.
 * @returns {Promise<Object>} - Returns search results in JSON format.
 */
async function search(searchTerm, options = {}) {
    const opts = Object.assign({}, defaultOptions, options);

    let url =
        baseURL +
        stringify({
            tbm: "isch",
            q: searchTerm,
        });

    opts.filteredDomains = defaultOptions.filteredDomains.concat(
        options?.filteredDomains ?? []
    );

    if (!Array.isArray(opts.filteredDomains))
        throw new TypeError("filteredDomains must be of type string[]");

    url += encodeURIComponent(
        opts.filteredDomains.map((s) => ` -site:${s}`).join("")
    );

    if (opts.queryString.length > 0) url += opts.queryString;

    try {
        const res = await axios({ url: url, headers: { "User-Agent": opts.userAgent } });
        const $ = load(res.data);
        const $scripts = $("script");

        let scriptContents = [];

        const isTagElement = (element) => element?.children !== null;

        for (let i = 0; i < $scripts.length; ++i) {
            const $script = $scripts[i];

            if (isTagElement($script) && $script.children.length > 0) {
                const content = $script.children[0]?.data;
                if (content && srcRegex.test(content)) scriptContents.push(content);
            }
        }

        function getSources(content) {
            let srcs = [];

            for (const result of content.matchAll(srcRegex)) {
                if (result[1] && result[2] && result[3]) {
                    let src = {
                        url: decodeURI(result[1]),
                        width: parseInt(result[3]),
                        height: parseInt(result[2]),
                    };

                    if (
                        opts.filteredDomains.every(
                            (domain) => !src.url.includes(domain)
                        ) &&
                        exts.some((ext) => src.url.includes(ext))
                    )
                        srcs.push(src);
                }
            }

            return srcs;
        }

        const finalResults = scriptContents.map(getSources).flat();

        // Return results as a structured JSON response
        return {
            author: "Herza",
            status: 200,
            searchTerm: searchTerm,
            totalResults: finalResults.length,
            images: finalResults,
        };
    } catch (err) {
        return {
            error: "Terjadi kesalahan",
            message: err.message,
        };
    }
}

module.exports = { search };