mirror of
https://github.com/webrecorder/browsertrix-crawler.git
synced 2025-10-19 14:33:17 +00:00
277314f2de
* switch base image to chrome/chromium 105 with node 18.x * convert all source to esm for node 18.x, remove unneeded node-fetch dependency * ci: use node 18.x, update to latest actions * tests: convert to esm, run with --experimental-vm-modules * tests: set higher default timeout (90s) for all tests * tests: rename driver test fixture to .mjs for loading in jest * bump to 0.8.0
67 lines
1.9 KiB
JavaScript
67 lines
1.9 KiB
JavaScript
import fs from "fs";
|
|
import yaml from "js-yaml";
|
|
|
|
import util from "util";
|
|
import {exec as execCallback } from "child_process";
|
|
|
|
const exec = util.promisify(execCallback);
|
|
|
|
|
|
test("check yaml config file with seed list is used", async () => {
|
|
try{
|
|
|
|
await exec("docker run -v $PWD/test-crawls:/crawls -v $PWD/tests/fixtures:/tests/fixtures webrecorder/browsertrix-crawler crawl --config /tests/fixtures/crawl-1.yaml --depth 0");
|
|
}
|
|
catch (error) {
|
|
console.log(error);
|
|
}
|
|
|
|
const crawledPages = fs.readFileSync("test-crawls/collections/configtest/pages/pages.jsonl", "utf8");
|
|
const pages = new Set();
|
|
|
|
for (const line of crawledPages.trim().split("\n")) {
|
|
const url = JSON.parse(line).url;
|
|
if (url) {
|
|
pages.add(url);
|
|
}
|
|
}
|
|
|
|
const config = yaml.load(fs.readFileSync("tests/fixtures/crawl-1.yaml", "utf8"));
|
|
|
|
let foundAllSeeds = true;
|
|
|
|
for (const seed of config.seeds) {
|
|
const url = new URL(seed).href;
|
|
if (!pages.has(url)) {
|
|
foundAllSeeds = false;
|
|
}
|
|
}
|
|
expect(foundAllSeeds).toBe(true);
|
|
|
|
expect(fs.existsSync("test-crawls/collections/configtest/configtest.wacz")).toBe(true);
|
|
|
|
});
|
|
|
|
test("check yaml config file will be overwritten by command line", async () => {
|
|
try{
|
|
|
|
await exec("docker run -v $PWD/test-crawls:/crawls -v $PWD/tests/fixtures:/tests/fixtures webrecorder/browsertrix-crawler crawl --collection configtest-2 --config /tests/fixtures/crawl-1.yaml --url https://www.example.com --timeout 20000");
|
|
}
|
|
catch (error) {
|
|
console.log(error);
|
|
}
|
|
|
|
const crawledPages = fs.readFileSync("test-crawls/collections/configtest-2/pages/pages.jsonl", "utf8");
|
|
const pages = new Set();
|
|
|
|
for (const line of crawledPages.trim().split("\n")) {
|
|
const url = JSON.parse(line).url;
|
|
if (url) {
|
|
pages.add(url);
|
|
}
|
|
}
|
|
|
|
expect(pages.has("https://www.example.com/")).toBe(true);
|
|
expect(pages.size).toBe(1);
|
|
|
|
});
|