mirror of
https://github.com/webrecorder/browsertrix-crawler.git
synced 2025-10-19 14:33:17 +00:00
0e0b85d7c3
* fix typo in setting crawler.capturePrefix which caused directFetchCapture() to fail, causing non-HTML urls to fail. - wrap directFetchCapture() to retry browser loading in case of failure * custom link extraction improvements (improvements for #25) - extractLinks() returns a list of link URLs to allow for more flexibility in custom driver - rename queueUrls() to queueInScopeUrls() to indicate the filtering is performed - loadPage accepts a list of select opts {selector, extract, isAttribute} and defaults to {"a[href]", "href", false} - tests: add test for custom driver which uses custom selector * tests - tests: all tests uses 'test-crawls' instead of crawls - consolidation: combine initial crawl + rollover, combine warc, text tests into basic_crawl.test.js - add custom driver test and fixture to test custom link extraction * add to CHANGES, bump to 0.4.2
44 lines
1.2 KiB
JavaScript
44 lines
1.2 KiB
JavaScript
const yaml = require("js-yaml");
|
|
const child_process = require("child_process");
|
|
const fs = require("fs");
|
|
|
|
test("pass config file via stdin", async () => {
|
|
jest.setTimeout(30000);
|
|
|
|
const configYaml = fs.readFileSync("tests/fixtures/crawl-2.yaml", "utf8");
|
|
const config = yaml.load(configYaml);
|
|
|
|
try {
|
|
const proc = child_process.execSync("docker run -i -v $PWD/test-crawls:/crawls webrecorder/browsertrix-crawler crawl --config stdin --scopeExcludeRx webrecorder.net/202", {input: configYaml, stdin: "inherit", encoding: "utf8"});
|
|
|
|
console.log(proc);
|
|
}
|
|
catch (error) {
|
|
console.log(error);
|
|
}
|
|
|
|
const crawledPages = fs.readFileSync("test-crawls/collections/config-stdin/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);
|
|
expect(url.indexOf("webrecorder.net/202")).toEqual(-1);
|
|
}
|
|
|
|
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/config-stdin/config-stdin.wacz")).toBe(true);
|
|
|
|
});
|