mirror of
https://github.com/orangecoding/fredy.git
synced 2026-06-16 12:31:07 +00:00
adding ability to add proxies for cloak
This commit is contained in:
@@ -14,6 +14,7 @@ import * as similarityCache from '../similarity-check/similarityCache.js';
|
||||
import { isRunning, markFinished, markRunning } from './run-state.js';
|
||||
import { sendToUsers } from '../sse/sse-broker.js';
|
||||
import * as puppeteerExtractor from '../extractor/puppeteerExtractor.js';
|
||||
import { getSettings } from '../storage/settingsStorage.js';
|
||||
|
||||
/**
|
||||
* Initializes the job execution service.
|
||||
@@ -160,6 +161,14 @@ export function initJobExecutionService({ providers, settings, intervalMs }) {
|
||||
}
|
||||
let browser;
|
||||
try {
|
||||
// Read the proxy live (not from the startup snapshot) so changing it in the
|
||||
// UI takes effect on the next run without a backend restart. An empty value
|
||||
// disables the proxy. Routing the headless browser through a (German
|
||||
// residential) proxy avoids datacenter-IP based bot detection on the
|
||||
// Puppeteer-based providers (immowelt, immonet, kleinanzeigen, ...).
|
||||
const liveSettings = await getSettings();
|
||||
const proxyUrl = typeof liveSettings?.proxyUrl === 'string' ? liveSettings.proxyUrl.trim() : '';
|
||||
|
||||
const jobProviders = job.provider.filter(
|
||||
(p) => providers.find((loaded) => loaded.metaInformation.id === p.id) != null,
|
||||
);
|
||||
@@ -175,7 +184,7 @@ export function initJobExecutionService({ providers, settings, intervalMs }) {
|
||||
}
|
||||
|
||||
if (!browser && matchedProvider.config.getListings == null) {
|
||||
browser = await puppeteerExtractor.launchBrowser(matchedProvider.config.url, {});
|
||||
browser = await puppeteerExtractor.launchBrowser(matchedProvider.config.url, proxyUrl ? { proxyUrl } : {});
|
||||
}
|
||||
|
||||
await new FredyPipelineExecutioner(matchedProvider.config, job, prov.id, similarityCache, browser).execute();
|
||||
|
||||
Reference in New Issue
Block a user