sec-edgar-parser/dist/main.js

A tool for scraping SEC edgar archive documents found at https://www.sec.gov/Archives/edgar/data

"use strict";
Object.defineProperty(exports, "__esModule", { value: true });
const tslib_1 = require("tslib");
const promises_1 = tslib_1.__importDefault(require("node:fs/promises"));
const parser_1 = require("./parser");
const urls = [
    "https://www.sec.gov/Archives/edgar/data/1766724/000117266123003414/0001172661-23-003414.txt",
    "https://www.sec.gov/Archives/edgar/data/314169/000137647423000077/0001376474-23-000077.txt",
];
function getLastSegmentWithoutExtension(urlString) {
    const url = new URL(urlString);
    const pathnameParts = url.pathname.split("/");
    const lastSegment = pathnameParts[pathnameParts.length - 1];
    const lastSegmentWithoutExtension = lastSegment.split(".")[0];
    return lastSegmentWithoutExtension;
}
(() => tslib_1.__awaiter(void 0, void 0, void 0, function* () {
    const promises = [];
    for (let index = 0; index < urls.length; index++) {
        const url = urls[index];
        const email = process.argv[2];
        if (!email || !email.includes("@")) {
            throw new Error("Please provide a valid email address as a command line argument");
        }
        const promise = ((url) => tslib_1.__awaiter(void 0, void 0, void 0, function* () {
            console.log(`Calling: ${url}`);
            const accessionNumber = getLastSegmentWithoutExtension(url);
            const obj = yield (0, parser_1.getObjectFromUrl)(url, email);
            const outputPath = `/tmp/SEC-output-${accessionNumber}.json`;
            yield promises_1.default.writeFile(outputPath, JSON.stringify(obj, null, 2), "utf-8");
            console.log(`output: ${outputPath}`);
        }))(url);
        promises.push(promise);
    }
    yield Promise.all(promises);
}))();