Source

scraping/launchPuppeteerBrowserSession.js

"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());
    });
};
var __generator = (this && this.__generator) || function (thisArg, body) {
    var _ = { label: 0, sent: function() { if (t[0] & 1) throw t[1]; return t[1]; }, trys: [], ops: [] }, f, y, t, g;
    return g = { next: verb(0), "throw": verb(1), "return": verb(2) }, typeof Symbol === "function" && (g[Symbol.iterator] = function() { return this; }), g;
    function verb(n) { return function (v) { return step([n, v]); }; }
    function step(op) {
        if (f) throw new TypeError("Generator is already executing.");
        while (_) try {
            if (f = 1, y && (t = op[0] & 2 ? y["return"] : op[0] ? y["throw"] || ((t = y["return"]) && t.call(y), 0) : y.next) && !(t = t.call(y, op[1])).done) return t;
            if (y = 0, t) op = [op[0] & 2, t.value];
            switch (op[0]) {
                case 0: case 1: t = op; break;
                case 4: _.label++; return { value: op[1], done: false };
                case 5: _.label++; y = op[1]; op = [0]; continue;
                case 7: op = _.ops.pop(); _.trys.pop(); continue;
                default:
                    if (!(t = _.trys, t = t.length > 0 && t[t.length - 1]) && (op[0] === 6 || op[0] === 2)) { _ = 0; continue; }
                    if (op[0] === 3 && (!t || (op[1] > t[0] && op[1] < t[3]))) { _.label = op[1]; break; }
                    if (op[0] === 6 && _.label < t[1]) { _.label = t[1]; t = op; break; }
                    if (t && _.label < t[2]) { _.label = t[2]; _.ops.push(op); break; }
                    if (t[2]) _.ops.pop();
                    _.trys.pop(); continue;
            }
            op = body.call(thisArg, _);
        } catch (e) { op = [6, e]; y = 0; } finally { f = t = 0; }
        if (op[0] & 5) throw op[1]; return { value: op[0] ? op[1] : void 0, done: true };
    }
};
Object.defineProperty(exports, "__esModule", { value: true });
var chromium = require("chrome-aws-lambda");
require("chrome-aws-lambda/bin/aws.tar.br");
require("chrome-aws-lambda/bin/chromium.br");
require("chrome-aws-lambda/bin/swiftshader.tar.br");
// 240s
var DEFAULT_TIMEOUT = 240000;
/**
 * Helpers to scrape data from html with Puppeteer library.
 * It is ready to run on any serverless environment like AWS lambda.
 *
 * @param getBatchData
 * @param defaultTimeout Default to 240000 (ms)
 * @category scraping
 * @module launchPuppeteerBrowserSession
 */
function launchPuppeteerBrowserSession(getBatchData, defaultTimeout) {
    if (defaultTimeout === void 0) { defaultTimeout = DEFAULT_TIMEOUT; }
    return __awaiter(this, void 0, void 0, function () {
        var browser, _a, _b, page, data, _i, getBatchData_1, getEach, _c, _d;
        var _e;
        return __generator(this, function (_f) {
            switch (_f.label) {
                case 0:
                    browser = null;
                    _f.label = 1;
                case 1:
                    _f.trys.push([1, , 9, 12]);
                    _b = (_a = chromium.puppeteer).launch;
                    _e = {
                        args: chromium.args,
                        defaultViewport: chromium.defaultViewport
                    };
                    return [4 /*yield*/, chromium.executablePath];
                case 2: return [4 /*yield*/, _b.apply(_a, [(_e.executablePath = _f.sent(),
                            _e.headless = chromium.headless,
                            _e.ignoreHTTPSErrors = true,
                            _e)])];
                case 3:
                    // Open the headless browser
                    browser = _f.sent();
                    if (!browser)
                        throw new Error('browser is not defined after launch');
                    return [4 /*yield*/, browser.newPage()
                        // Set default timeout
                    ];
                case 4:
                    page = _f.sent();
                    // Set default timeout
                    page.setDefaultTimeout(defaultTimeout);
                    data = [];
                    _i = 0, getBatchData_1 = getBatchData;
                    _f.label = 5;
                case 5:
                    if (!(_i < getBatchData_1.length)) return [3 /*break*/, 8];
                    getEach = getBatchData_1[_i];
                    _d = (_c = data).push;
                    return [4 /*yield*/, getEach(page)];
                case 6:
                    _d.apply(_c, [_f.sent()]);
                    _f.label = 7;
                case 7:
                    _i++;
                    return [3 /*break*/, 5];
                case 8: 
                // Run function to get data
                return [2 /*return*/, data];
                case 9:
                    if (!browser) return [3 /*break*/, 11];
                    return [4 /*yield*/, browser.close()];
                case 10:
                    _f.sent();
                    _f.label = 11;
                case 11: return [7 /*endfinally*/];
                case 12: return [2 /*return*/];
            }
        });
    });
}
exports.default = launchPuppeteerBrowserSession;