mirror of
https://github.com/webrecorder/browsertrix-crawler.git
synced 2025-10-19 14:33:17 +00:00
f35d495103
* Add screenshot and thumbnail functionality Introduces a --screenshot CLI option, which takes a comma-separated list of screenshot types: view,fullPage,thumbnail. In addition, this commit: - Adds '--experimental-global-webcrypto' to ensure webcrypto is available in node - Deprecates newContext, instead always using page context for 1 worker and window context for >1 worker * Separate screenshotTypes into exported const Co-authored-by: Emma Dickson <emmadickson@Emmas-MacBook-Air.local>
34 lines
969 B
JavaScript
34 lines
969 B
JavaScript
import child_process from "child_process";
|
|
import fs from "fs";
|
|
|
|
|
|
test("ensure custom driver with custom selector crawls JS files as pages", async () => {
|
|
try {
|
|
child_process.execSync("docker run -v $PWD/tests/fixtures:/tests/fixtures -v $PWD/test-crawls:/crawls webrecorder/browsertrix-crawler crawl --url https://www.iana.org/ --collection custom-driver-1 --driver /tests/fixtures/driver-1.mjs");
|
|
}
|
|
catch (error) {
|
|
console.log(error);
|
|
}
|
|
|
|
const crawledPages = fs.readFileSync("test-crawls/collections/custom-driver-1/pages/pages.jsonl", "utf8");
|
|
const pages = new Set();
|
|
|
|
for (const line of crawledPages.trim().split("\n")) {
|
|
const url = JSON.parse(line).url;
|
|
if (!url) {
|
|
continue;
|
|
}
|
|
pages.add(url);
|
|
}
|
|
|
|
console.log(pages);
|
|
|
|
const expectedPages = new Set([
|
|
"https://www.iana.org/",
|
|
"https://www.iana.org/_js/jquery.js",
|
|
"https://www.iana.org/_js/iana.js"
|
|
]);
|
|
|
|
expect(pages).toEqual(expectedPages);
|
|
|
|
});
|