mirror of
https://github.com/ArchiveBox/ArchiveBox.git
synced 2026-01-06 19:06:08 +10:00
wip major changes
This commit is contained in:
Nick Sweeting
266
archivebox/plugins/accessibility/on_Snapshot__39_accessibility.js
Executable file
266
archivebox/plugins/accessibility/on_Snapshot__39_accessibility.js
Executable file
@@ -0,0 +1,266 @@
|
||||
#!/usr/bin/env node
|
||||
/**
|
||||
* Extract accessibility tree and page outline from a URL.
|
||||
*
|
||||
* Extracts:
|
||||
* - Page outline (headings h1-h6, sections, articles)
|
||||
* - Iframe tree
|
||||
* - Accessibility snapshot
|
||||
* - ARIA labels and roles
|
||||
*
|
||||
* Usage: on_Snapshot__18_accessibility.js --url=<url> --snapshot-id=<uuid>
|
||||
* Output: Writes accessibility/accessibility.json
|
||||
*
|
||||
* Environment variables:
|
||||
* SAVE_ACCESSIBILITY: Enable accessibility extraction (default: true)
|
||||
*/
|
||||
|
||||
const fs = require('fs');
|
||||
const path = require('path');
|
||||
const puppeteer = require('puppeteer-core');
|
||||
|
||||
// Extractor metadata
|
||||
const EXTRACTOR_NAME = 'accessibility';
|
||||
const OUTPUT_DIR = 'accessibility';
|
||||
const OUTPUT_FILE = 'accessibility.json';
|
||||
const CHROME_SESSION_DIR = 'chrome_session';
|
||||
|
||||
// Parse command line arguments
|
||||
function parseArgs() {
|
||||
const args = {};
|
||||
process.argv.slice(2).forEach(arg => {
|
||||
if (arg.startsWith('--')) {
|
||||
const [key, ...valueParts] = arg.slice(2).split('=');
|
||||
args[key.replace(/-/g, '_')] = valueParts.join('=') || true;
|
||||
}
|
||||
});
|
||||
return args;
|
||||
}
|
||||
|
||||
// Get environment variable with default
|
||||
function getEnv(name, defaultValue = '') {
|
||||
return (process.env[name] || defaultValue).trim();
|
||||
}
|
||||
|
||||
function getEnvBool(name, defaultValue = false) {
|
||||
const val = getEnv(name, '').toLowerCase();
|
||||
if (['true', '1', 'yes', 'on'].includes(val)) return true;
|
||||
if (['false', '0', 'no', 'off'].includes(val)) return false;
|
||||
return defaultValue;
|
||||
}
|
||||
|
||||
// Get CDP URL from chrome_session
|
||||
function getCdpUrl() {
|
||||
const cdpFile = path.join(CHROME_SESSION_DIR, 'cdp_url.txt');
|
||||
if (fs.existsSync(cdpFile)) {
|
||||
return fs.readFileSync(cdpFile, 'utf8').trim();
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
// Extract accessibility info
|
||||
async function extractAccessibility(url) {
|
||||
// Create output directory
|
||||
if (!fs.existsSync(OUTPUT_DIR)) {
|
||||
fs.mkdirSync(OUTPUT_DIR, { recursive: true });
|
||||
}
|
||||
const outputPath = path.join(OUTPUT_DIR, OUTPUT_FILE);
|
||||
|
||||
let browser = null;
|
||||
|
||||
try {
|
||||
// Connect to existing Chrome session
|
||||
const cdpUrl = getCdpUrl();
|
||||
if (!cdpUrl) {
|
||||
return { success: false, error: 'No Chrome session found (chrome_session extractor must run first)' };
|
||||
}
|
||||
|
||||
browser = await puppeteer.connect({
|
||||
browserWSEndpoint: cdpUrl,
|
||||
});
|
||||
|
||||
// Get the page
|
||||
const pages = await browser.pages();
|
||||
const page = pages.find(p => p.url().startsWith('http')) || pages[0];
|
||||
|
||||
if (!page) {
|
||||
return { success: false, error: 'No page found in Chrome session' };
|
||||
}
|
||||
|
||||
// Get accessibility snapshot
|
||||
const accessibilityTree = await page.accessibility.snapshot({ interestingOnly: true });
|
||||
|
||||
// Extract page outline (headings, sections, etc.)
|
||||
const outline = await page.evaluate(() => {
|
||||
const headings = [];
|
||||
const elements = document.querySelectorAll(
|
||||
'h1, h2, h3, h4, h5, h6, a[name], header, footer, article, main, aside, nav, section, figure, summary, table, form, iframe'
|
||||
);
|
||||
|
||||
elements.forEach(elem => {
|
||||
// Skip unnamed anchors
|
||||
if (elem.tagName.toLowerCase() === 'a' && !elem.name) return;
|
||||
|
||||
const tagName = elem.tagName.toLowerCase();
|
||||
const elemId = elem.id || elem.name || elem.getAttribute('aria-label') || elem.role || '';
|
||||
const elemClasses = (elem.className || '').toString().trim().split(/\s+/).slice(0, 3).join(' .');
|
||||
const action = elem.action?.split('/').pop() || '';
|
||||
|
||||
let summary = (elem.innerText || '').slice(0, 128);
|
||||
if (summary.length >= 128) summary += '...';
|
||||
|
||||
let prefix = '';
|
||||
let title = '';
|
||||
|
||||
// Format headings with # prefix
|
||||
const level = parseInt(tagName.replace('h', ''));
|
||||
if (!isNaN(level)) {
|
||||
prefix = '#'.repeat(level);
|
||||
title = elem.innerText || elemId || elemClasses;
|
||||
} else {
|
||||
// For other elements, create breadcrumb path
|
||||
const parents = [tagName];
|
||||
let node = elem.parentNode;
|
||||
while (node && parents.length < 5) {
|
||||
if (node.tagName) {
|
||||
const tag = node.tagName.toLowerCase();
|
||||
if (!['div', 'span', 'p', 'body', 'html'].includes(tag)) {
|
||||
parents.unshift(tag);
|
||||
} else {
|
||||
parents.unshift('');
|
||||
}
|
||||
}
|
||||
node = node.parentNode;
|
||||
}
|
||||
prefix = parents.join('>');
|
||||
|
||||
title = elemId ? `#${elemId}` : '';
|
||||
if (!title && elemClasses) title = `.${elemClasses}`;
|
||||
if (action) title += ` /${action}`;
|
||||
if (summary && !title.includes(summary)) title += `: ${summary}`;
|
||||
}
|
||||
|
||||
// Clean up title
|
||||
title = title.replace(/\s+/g, ' ').trim();
|
||||
|
||||
if (prefix) {
|
||||
headings.push(`${prefix} ${title}`);
|
||||
}
|
||||
});
|
||||
|
||||
return headings;
|
||||
});
|
||||
|
||||
// Get iframe tree
|
||||
const iframes = [];
|
||||
function dumpFrameTree(frame, indent = '>') {
|
||||
iframes.push(indent + frame.url());
|
||||
for (const child of frame.childFrames()) {
|
||||
dumpFrameTree(child, indent + '>');
|
||||
}
|
||||
}
|
||||
dumpFrameTree(page.mainFrame(), '');
|
||||
|
||||
const accessibilityData = {
|
||||
url,
|
||||
headings: outline,
|
||||
iframes,
|
||||
tree: accessibilityTree,
|
||||
};
|
||||
|
||||
// Write output
|
||||
fs.writeFileSync(outputPath, JSON.stringify(accessibilityData, null, 2));
|
||||
|
||||
return { success: true, output: outputPath, accessibilityData };
|
||||
|
||||
} catch (e) {
|
||||
return { success: false, error: `${e.name}: ${e.message}` };
|
||||
} finally {
|
||||
if (browser) {
|
||||
browser.disconnect();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
async function main() {
|
||||
const args = parseArgs();
|
||||
const url = args.url;
|
||||
const snapshotId = args.snapshot_id;
|
||||
|
||||
if (!url || !snapshotId) {
|
||||
console.error('Usage: on_Snapshot__18_accessibility.js --url=<url> --snapshot-id=<uuid>');
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
const startTs = new Date();
|
||||
let status = 'failed';
|
||||
let output = null;
|
||||
let error = '';
|
||||
|
||||
try {
|
||||
// Check if enabled
|
||||
if (!getEnvBool('SAVE_ACCESSIBILITY', true)) {
|
||||
console.log('Skipping accessibility (SAVE_ACCESSIBILITY=False)');
|
||||
status = 'skipped';
|
||||
const endTs = new Date();
|
||||
console.log(`START_TS=${startTs.toISOString()}`);
|
||||
console.log(`END_TS=${endTs.toISOString()}`);
|
||||
console.log(`STATUS=${status}`);
|
||||
console.log(`RESULT_JSON=${JSON.stringify({extractor: EXTRACTOR_NAME, status, url, snapshot_id: snapshotId})}`);
|
||||
process.exit(0);
|
||||
}
|
||||
|
||||
const result = await extractAccessibility(url);
|
||||
|
||||
if (result.success) {
|
||||
status = 'succeeded';
|
||||
output = result.output;
|
||||
const headingCount = result.accessibilityData.headings.length;
|
||||
const iframeCount = result.accessibilityData.iframes.length;
|
||||
console.log(`Accessibility extracted: ${headingCount} headings, ${iframeCount} iframes`);
|
||||
} else {
|
||||
status = 'failed';
|
||||
error = result.error;
|
||||
}
|
||||
} catch (e) {
|
||||
error = `${e.name}: ${e.message}`;
|
||||
status = 'failed';
|
||||
}
|
||||
|
||||
const endTs = new Date();
|
||||
const duration = (endTs - startTs) / 1000;
|
||||
|
||||
// Print results
|
||||
console.log(`START_TS=${startTs.toISOString()}`);
|
||||
console.log(`END_TS=${endTs.toISOString()}`);
|
||||
console.log(`DURATION=${duration.toFixed(2)}`);
|
||||
if (output) {
|
||||
console.log(`OUTPUT=${output}`);
|
||||
}
|
||||
console.log(`STATUS=${status}`);
|
||||
|
||||
if (error) {
|
||||
console.error(`ERROR=${error}`);
|
||||
}
|
||||
|
||||
// Print JSON result
|
||||
const resultJson = {
|
||||
extractor: EXTRACTOR_NAME,
|
||||
url,
|
||||
snapshot_id: snapshotId,
|
||||
status,
|
||||
start_ts: startTs.toISOString(),
|
||||
end_ts: endTs.toISOString(),
|
||||
duration: Math.round(duration * 100) / 100,
|
||||
output,
|
||||
error: error || null,
|
||||
};
|
||||
console.log(`RESULT_JSON=${JSON.stringify(resultJson)}`);
|
||||
|
||||
process.exit(status === 'succeeded' ? 0 : 1);
|
||||
}
|
||||
|
||||
main().catch(e => {
|
||||
console.error(`Fatal error: ${e.message}`);
|
||||
process.exit(1);
|
||||
});
|
||||
Reference in New Issue
Block a user