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
28 lines
1.1 KiB
JavaScript
28 lines
1.1 KiB
JavaScript
import fs from "fs";
|
|
import zlib from "zlib";
|
|
import child_process from "child_process";
|
|
|
|
test("check that the warcinfo file works as expected on the command line", async () => {
|
|
try{
|
|
const configYaml = fs.readFileSync("tests/fixtures/crawl-2.yaml", "utf8");
|
|
const proc = child_process.execSync("docker run -i -v $PWD/test-crawls:/crawls webrecorder/browsertrix-crawler crawl --config stdin --limit 1 --collection warcinfo --combineWARC", {input: configYaml, stdin: "inherit", encoding: "utf8"});
|
|
|
|
console.log(proc);
|
|
}
|
|
catch (error) {
|
|
console.log(error);
|
|
}
|
|
|
|
const warcData = fs.readFileSync("test-crawls/collections/warcinfo/warcinfo_0.warc.gz");
|
|
|
|
const data = zlib.gunzipSync(warcData);
|
|
|
|
const string = data.toString("utf8");
|
|
|
|
expect(string.indexOf("operator: test")).toBeGreaterThan(-1);
|
|
expect(string.indexOf("host: hostname")).toBeGreaterThan(-1);
|
|
expect(string.match(/Browsertrix-Crawler \d[\w.-]+ \(with warcio.js \d[\w.-]+ pywb \d[\w.-]+\)/)).not.toEqual(null);
|
|
expect(string.indexOf("format: WARC File Format 1.0")).toBeGreaterThan(-1);
|
|
|
|
|
|
});
|