@wabarc/cairn/dist/cli.js

Node package and CLI tool for saving web page as single HTML file

#!/usr/bin/env node
"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 });
const commander_1 = require("commander");
const archiver_1 = require("./archiver");
const utils_1 = require("./utils");
const fs_1 = require("fs");
class Handler {
    constructor() {
        this.urls = [];
        this.opts = {};
    }
    main() {
        return __awaiter(this, void 0, void 0, function* () {
            const program = this.parser();
            const options = program.opts();
            if (this.urls.length < 1) {
                // Output help information and exit immediately.
                program.help();
            }
            let filepath = '';
            if (options.output && options.output !== '-') {
                if (!(0, fs_1.statSync)(options.output)) {
                    console.warn('custom output not exists, path: ' + options.output);
                    process.exit(1);
                }
                filepath = options.output + '/';
            }
            const output = (url, filename, content) => __awaiter(this, void 0, void 0, function* () {
                if (options.output === '-') {
                    console.info(content);
                }
                else {
                    (0, fs_1.writeFile)(filename, content, (err) => {
                        if (err) {
                            console.warn(`${url} => ${err}`);
                            return;
                        }
                        console.info(`${url} => ${filename}`);
                    });
                }
            });
            const cairn = new archiver_1.Archiver();
            for (const url of this.urls) {
                if (!(0, utils_1.isValidURL)(url)) {
                    console.info(`${url} => request url is not specified\n`);
                    continue;
                }
                const filename = filepath + (0, utils_1.createFileName)(url);
                yield cairn
                    .request({ url: url })
                    .options(this.opts)
                    .archive()
                    .then((archived) => __awaiter(this, void 0, void 0, function* () {
                    if (!archived.webpage || typeof archived.webpage.root !== 'function') {
                        return;
                    }
                    const html = archived.webpage.root() ? archived.webpage.root().html() : '';
                    if (!html) {
                        console.warn(`${url} => archival failure. [status: ${archived.status}]`);
                        return;
                    }
                    yield output(url, filename, html || '');
                }))
                    .catch((err) => console.warn(`${url} => ${JSON.stringify(err)}`));
            }
        });
    }
    parser() {
        const program = new commander_1.Command();
        const version = process.env.npm_package_version || '0.0.1';
        program
            .name('cairn')
            .usage('[options] url1 [url2]...[urlN]')
            .version(version, '-v, --version', 'output the current version')
            .description('CLI tool for saving web page as single HTML file');
        program.option('-o, --output <string>', 'path to save archival result');
        program.option('-u, --user-agent <string>', 'set custom user agent');
        program.option('-p, --proxy [protocol://]host[:port]', 'use this proxy');
        program.option('-t, --timeout <number>', 'maximum time (in second) request timeout');
        program
            .option('--no-js', 'disable JavaScript')
            .option('--no-css', 'disable CSS styling')
            .option('--no-embeds', 'remove embedded elements (e.g iframe)')
            .option('--no-medias', 'remove media elements (e.g img, audio)');
        program.parse(process.argv);
        const options = program.opts();
        if (options.proxy)
            this.opts.proxy = options.proxy;
        if (options.userAgent)
            this.opts.userAgent = options.userAgent;
        if (options.timeout)
            this.opts.timeout = parseInt(options.timeout);
        // `no-` to set the option value to false when used.
        this.opts.disableJS = !options.js;
        this.opts.disableCSS = !options.css;
        this.opts.disableEmbeds = !options.embeds;
        this.opts.disableMedias = !options.medias;
        this.urls = program.args;
        return program;
    }
}
new Handler().main();
//# sourceMappingURL=cli.js.map