alex/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2026-04-04 23:07:56 +10:00
Code Issues Packages Projects Releases Wiki Activity

continue renaming extractor to plugin, add plan for hook concurrency, add chrome kill helper script

Browse Source
This commit is contained in:
Nick Sweeting
2025-12-28 05:29:24 -08:00
parent d2e65cfd38
commit 4ccb0863bb
53 changed files with 456 additions and 493 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
archivebox/plugins/dom/on_Snapshot__36_dom.js
View File

@@ -23,7 +23,7 @@ const path = require('path');
const puppeteer = require('puppeteer-core');
// Extractor metadata
const EXTRACTOR_NAME = 'dom';
const PLUGIN_NAME = 'dom';
const OUTPUT_DIR = '.';
const OUTPUT_FILE = 'output.html';
const CHROME_SESSION_DIR = '../chrome';
@@ -252,10 +252,14 @@ async function main() {
}));
process.exit(0);
} else {
// Wait for page to be fully loaded
const pageLoaded = await waitForChromeTabLoaded(60000);
if (!pageLoaded) {
throw new Error('Page not loaded after 60s (chrome_navigate must complete first)');
// Only wait for page load if using shared Chrome session
const cdpUrl = getCdpUrl();
if (cdpUrl) {
// Wait for page to be fully loaded
const pageLoaded = await waitForChromeTabLoaded(60000);
if (!pageLoaded) {
throw new Error('Page not loaded after 60s (chrome_navigate must complete first)');
}
}
const result = await dumpDom(url);