alex/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2026-04-06 07:47:53 +10:00
Code Issues Packages Projects Releases Wiki Activity

way better plugin hooks system wip

Browse Source
This commit is contained in:
Nick Sweeting
2025-12-28 03:39:59 -08:00
parent a38624a4dd
commit 50e527ec65
156 changed files with 10275 additions and 7149 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
archivebox/plugins/accessibility/on_Snapshot__39_accessibility.js
View File

@@ -23,7 +23,7 @@ const puppeteer = require('puppeteer-core');
const EXTRACTOR_NAME = 'accessibility';
const OUTPUT_DIR = '.';
const OUTPUT_FILE = 'accessibility.json';
const CHROME_SESSION_DIR = '../chrome_session';
const CHROME_SESSION_DIR = '../chrome';
// Parse command line arguments
function parseArgs() {
@@ -49,7 +49,23 @@ function getEnvBool(name, defaultValue = false) {
return defaultValue;
}
// Get CDP URL from chrome_session
// Wait for chrome tab to be fully loaded
async function waitForChromeTabLoaded(timeoutMs = 60000) {
const navigationFile = path.join(CHROME_SESSION_DIR, 'navigation.json');
const startTime = Date.now();
while (Date.now() - startTime < timeoutMs) {
if (fs.existsSync(navigationFile)) {
return true;
}
// Wait 100ms before checking again
await new Promise(resolve => setTimeout(resolve, 100));
}
return false;
}
// Get CDP URL from chrome plugin
function getCdpUrl() {
const cdpFile = path.join(CHROME_SESSION_DIR, 'cdp_url.txt');
if (fs.existsSync(cdpFile)) {
@@ -69,7 +85,7 @@ async function extractAccessibility(url) {
// Connect to existing Chrome session
const cdpUrl = getCdpUrl();
if (!cdpUrl) {
return { success: false, error: 'No Chrome session found (chrome_session extractor must run first)' };
return { success: false, error: 'No Chrome session found (chrome plugin must run first)' };
}
browser = await puppeteer.connect({
@@ -207,6 +223,12 @@ async function main() {
process.exit(0);
}
// 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 extractAccessibility(url);
if (result.success) {