AI Newsletter Digest improvements: fixed QP soft line break decoding, URL extraction, and content cleaning

This commit is contained in:
Krilly
2026-03-04 13:29:22 +00:00
parent 29a98137a7
commit 57dd294675
13706 changed files with 2114953 additions and 237629 deletions

View File

@@ -0,0 +1,53 @@
# X No-API Bot (Starter)
Safe starter for using X without official API.
## What this does
- `login`: saves browser session cookie/state
- `fetch`: read-only fetch from X search timeline
- `post`: optional posting (disabled by default)
## Setup
```bash
cd /home/openclaw/.openclaw/workspace/automations/x-no-api-bot
cp .env.example .env
npm install
npx playwright install chromium
```
## 1) Login once
```bash
npm run login
```
A browser opens. Log in to X manually, then press Enter in terminal.
## 2) Read-only fetch
```bash
npm run fetch
```
Outputs JSON and saves a log under `logs/`.
## 3) Optional posting (off by default)
Edit `.env`:
```ini
ENABLE_POSTING=true
```
Then draft a post:
```bash
npm run post -- "Hello from no-API automation"
```
Publish only with explicit confirm:
```bash
npm run post -- "Hello from no-API automation" --confirm
```
## Cron (read-only)
Example every 30 min:
```cron
*/30 * * * * cd /home/openclaw/.openclaw/workspace/automations/x-no-api-bot && /usr/bin/npm run fetch >> logs/cron.log 2>&1
```
## Notes
- UI can change and break selectors.
- Keep activity low-volume to reduce account risk.
- Prefer read-only monitoring unless you explicitly need posting.

View File

@@ -0,0 +1,72 @@
{
"name": "x-no-api-bot",
"version": "0.1.0",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "x-no-api-bot",
"version": "0.1.0",
"dependencies": {
"dotenv": "^16.4.5",
"playwright": "^1.52.0"
}
},
"node_modules/dotenv": {
"version": "16.6.1",
"resolved": "https://registry.npmjs.org/dotenv/-/dotenv-16.6.1.tgz",
"integrity": "sha512-uBq4egWHTcTt33a72vpSG0z3HnPuIl6NqYcTrKEg2azoEyl2hpW0zqlxysq2pK9HlDIHyHyakeYaYnSAwd8bow==",
"license": "BSD-2-Clause",
"engines": {
"node": ">=12"
},
"funding": {
"url": "https://dotenvx.com"
}
},
"node_modules/fsevents": {
"version": "2.3.2",
"resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.2.tgz",
"integrity": "sha512-xiqMQR4xAeHTuB9uWm+fFRcIOgKBMiOBP+eXiyT7jsgVCq1bkVygt00oASowB7EdtpOHaaPgKt812P9ab+DDKA==",
"hasInstallScript": true,
"license": "MIT",
"optional": true,
"os": [
"darwin"
],
"engines": {
"node": "^8.16.0 || ^10.6.0 || >=11.0.0"
}
},
"node_modules/playwright": {
"version": "1.58.2",
"resolved": "https://registry.npmjs.org/playwright/-/playwright-1.58.2.tgz",
"integrity": "sha512-vA30H8Nvkq/cPBnNw4Q8TWz1EJyqgpuinBcHET0YVJVFldr8JDNiU9LaWAE1KqSkRYazuaBhTpB5ZzShOezQ6A==",
"license": "Apache-2.0",
"dependencies": {
"playwright-core": "1.58.2"
},
"bin": {
"playwright": "cli.js"
},
"engines": {
"node": ">=18"
},
"optionalDependencies": {
"fsevents": "2.3.2"
}
},
"node_modules/playwright-core": {
"version": "1.58.2",
"resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.58.2.tgz",
"integrity": "sha512-yZkEtftgwS8CsfYo7nm0KE8jsvm6i/PTgVtB8DL726wNf6H2IMsDuxCpJj59KDaxCtSnrWan2AeDqM7JBaultg==",
"license": "Apache-2.0",
"bin": {
"playwright-core": "cli.js"
},
"engines": {
"node": ">=18"
}
}
}
}

View File

@@ -0,0 +1,16 @@
{
"name": "x-no-api-bot",
"version": "0.1.0",
"private": true,
"description": "No-API X automation starter using Playwright (read-only by default)",
"type": "module",
"scripts": {
"login": "node src/login.js",
"fetch": "node src/fetch.js",
"post": "node src/post.js"
},
"dependencies": {
"dotenv": "^16.4.5",
"playwright": "^1.52.0"
}
}

View File

@@ -0,0 +1,28 @@
import fs from 'node:fs';
import path from 'node:path';
import dotenv from 'dotenv';
dotenv.config();
export const ROOT = process.cwd();
export const STATE_DIR = path.join(ROOT, 'state');
export const LOG_DIR = path.join(ROOT, 'logs');
export const SESSION_FILE = path.join(STATE_DIR, 'x-session.json');
if (!fs.existsSync(STATE_DIR)) fs.mkdirSync(STATE_DIR, { recursive: true });
if (!fs.existsSync(LOG_DIR)) fs.mkdirSync(LOG_DIR, { recursive: true });
export const ENABLE_POSTING = String(process.env.ENABLE_POSTING || 'false').toLowerCase() === 'true';
export const X_QUERY = process.env.X_QUERY || '(AI OR OpenClaw) lang:en -is:retweet';
export const MAX_TWEETS = Number(process.env.MAX_TWEETS || 10);
export const USER_AGENT = process.env.USER_AGENT;
export function nowStamp() {
return new Date().toISOString();
}
export function writeJsonLog(name, data) {
const file = path.join(LOG_DIR, `${name}-${Date.now()}.json`);
fs.writeFileSync(file, JSON.stringify(data, null, 2));
return file;
}

View File

@@ -0,0 +1,65 @@
import fs from 'node:fs';
import { chromium } from 'playwright';
import {
SESSION_FILE,
USER_AGENT,
X_QUERY,
MAX_TWEETS,
nowStamp,
writeJsonLog
} from './common.js';
const hasSession = fs.existsSync(SESSION_FILE);
if (!hasSession) {
console.error('No session found. Run: npm run login');
process.exit(1);
}
const browser = await chromium.launch({ headless: true });
const context = await browser.newContext({
storageState: SESSION_FILE,
userAgent: USER_AGENT || undefined,
viewport: { width: 1366, height: 900 }
});
const page = await context.newPage();
const url = `https://x.com/search?q=${encodeURIComponent(X_QUERY)}&src=typed_query&f=live`;
await page.goto(url, { waitUntil: 'domcontentloaded', timeout: 60000 });
await page.waitForTimeout(2500);
const tweets = await page.evaluate((maxTweets) => {
const out = [];
const articles = Array.from(document.querySelectorAll('article'));
for (const a of articles) {
if (out.length >= maxTweets) break;
const textNode = a.querySelector('[data-testid="tweetText"]');
const userNode = a.querySelector('a[role="link"][href*="/"]');
const timeNode = a.querySelector('time');
const linkNode = a.querySelector('a[href*="/status/"]');
const text = textNode?.innerText?.trim();
const user = userNode?.getAttribute('href') || null;
const when = timeNode?.getAttribute('datetime') || null;
const link = linkNode ? `https://x.com${linkNode.getAttribute('href')}` : null;
if (text) out.push({ text, user, when, link });
}
return out;
}, MAX_TWEETS);
const payload = {
ts: nowStamp(),
query: X_QUERY,
count: tweets.length,
tweets
};
const file = writeJsonLog('x-fetch', payload);
console.log(JSON.stringify(payload, null, 2));
console.log(`\nSaved log: ${file}`);
await browser.close();

View File

@@ -0,0 +1,26 @@
import fs from 'node:fs';
import { chromium } from 'playwright';
import { SESSION_FILE, USER_AGENT } from './common.js';
console.log('Starting X login capture...');
console.log('A browser will open. Log in manually, then press ENTER here to save session.');
const browser = await chromium.launch({ headless: false });
const context = await browser.newContext({
userAgent: USER_AGENT || undefined,
viewport: { width: 1366, height: 900 }
});
const page = await context.newPage();
await page.goto('https://x.com/i/flow/login', { waitUntil: 'domcontentloaded' });
process.stdin.resume();
await new Promise((resolve) => {
process.stdout.write('\nPress ENTER after login completes in browser...\n');
process.stdin.once('data', () => resolve());
});
await context.storageState({ path: SESSION_FILE });
console.log(`Saved session to ${SESSION_FILE}`);
await browser.close();
process.exit(0);

View File

@@ -0,0 +1,45 @@
import fs from 'node:fs';
import { chromium } from 'playwright';
import { ENABLE_POSTING, SESSION_FILE, USER_AGENT } from './common.js';
const text = process.argv.slice(2).join(' ').trim();
if (!text) {
console.error('Usage: npm run post -- "your post text"');
process.exit(1);
}
if (!ENABLE_POSTING) {
console.error('Posting is disabled. Set ENABLE_POSTING=true in .env to enable.');
process.exit(1);
}
if (!fs.existsSync(SESSION_FILE)) {
console.error('No session found. Run: npm run login');
process.exit(1);
}
const browser = await chromium.launch({ headless: true });
const context = await browser.newContext({
storageState: SESSION_FILE,
userAgent: USER_AGENT || undefined,
viewport: { width: 1366, height: 900 }
});
const page = await context.newPage();
await page.goto('https://x.com/compose/post', { waitUntil: 'domcontentloaded', timeout: 60000 });
await page.waitForSelector('[data-testid="tweetTextarea_0"]', { timeout: 20000 });
await page.fill('[data-testid="tweetTextarea_0"]', text);
// Safety: we require explicit --confirm to actually click Post
const confirmed = process.argv.includes('--confirm');
if (!confirmed) {
console.log('Draft prepared, not posted. Re-run with --confirm to publish.');
await browser.close();
process.exit(0);
}
await page.click('[data-testid="tweetButtonInline"]');
await page.waitForTimeout(2000);
console.log('Post submitted.');
await browser.close();