mirror of
https://github.com/jackwener/OpenCLI.git
synced 2026-09-14 18:25:42 +08:00
80eef46b4e
* refactor: move adapters from src/clis/ to root clis/ for monorepo separation Separates CLI adapters from the core runtime to prepare for independent adapter distribution via postinstall fetch. Key changes: - Move src/clis/ → clis/ (adapters at repo root) - Change tsconfig rootDir from "src" to "." so tsc compiles both - Create root-level shim files (registry.ts, errors.ts, etc.) so adapter relative imports (../../registry.js) resolve correctly - Update build-manifest.ts, main.ts paths for new dist/src/ structure - Expand ensureUserCliCompatShims() to cover all adapter import targets (types, utils, logger, launcher, browser/*, download/*, pipeline/*) - Add scripts/fetch-adapters.js postinstall for ~/.opencli/clis/ sync - Update vitest.config.ts adapter test paths - Add package.json files field to exclude adapters from npm package Official adapter files are unconditionally overwritten on update; user-created files not in the manifest are preserved. * fix: add dist/clis/ and cli-manifest.json to npm files, harden fetch-adapters - Add dist/clis/ and dist/cli-manifest.json to package.json files field so built-in adapters and manifest ship with the npm package - Replace execSync with execFileSync to prevent command injection - Add version check to skip redundant adapter fetches - Track tmpRoot explicitly for reliable cleanup * fix: address review blockers — manifest-based updates, global-only fetch, first-run fallback 1. Manifest-based update strategy: - Read old manifest to identify previously-official files - Clean up files removed upstream (in old manifest but not new) - User-created files (never in any manifest) remain untouched 2. Only run fetch-adapters on global install (npm_config_global=true) or explicit OPENCLI_FETCH=1, preventing heavy side effects for local/dev installs 3. First-run fallback in discovery.ts: - ensureUserAdapters() checks for adapter-manifest.json - If missing and ~/.opencli/clis/ is empty, spawns fetch-adapters.js - Guarantees adapters are available even with --ignore-scripts * fix: remove OPENCLI_FETCH env var, use internal _OPENCLI_FIRST_RUN instead * feat: also support OPENCLI_FETCH=1 for explicit adapter fetch trigger * simplify: replace git clone with local copy from dist/clis/ Adapters already ship in the npm package (dist/clis/), so there's no need to clone from GitHub. Copy directly from the installed package: - Eliminates git, curl, tar dependencies - No network calls in postinstall - No timeout/offline issues - Version always matches the installed CLI - ~65 lines of clone/download code replaced by one cpSync loop
171 lines
6.9 KiB
TypeScript
171 lines
6.9 KiB
TypeScript
import { AuthRequiredError, CommandExecutionError } from '../../errors.js';
|
|
import { cli, Strategy } from '../../registry.js';
|
|
import { resolveTwitterQueryId } from './shared.js';
|
|
|
|
const TWEET_RESULT_BY_REST_ID_QUERY_ID = '7xflPyRiUxGVbJd4uWmbfg';
|
|
|
|
cli({
|
|
site: 'twitter',
|
|
name: 'article',
|
|
description: 'Fetch a Twitter Article (long-form content) and export as Markdown',
|
|
domain: 'x.com',
|
|
strategy: Strategy.COOKIE,
|
|
browser: true,
|
|
args: [
|
|
{ name: 'tweet-id', type: 'string', positional: true, required: true, help: 'Tweet ID or URL containing the article' },
|
|
],
|
|
columns: ['title', 'author', 'content', 'url'],
|
|
func: async (page, kwargs) => {
|
|
// Extract tweet ID from URL if needed.
|
|
// Article URLs (x.com/i/article/{articleId}) use a different ID than
|
|
// tweet status URLs — the GraphQL endpoint needs the parent tweet ID.
|
|
let tweetId = kwargs['tweet-id'];
|
|
const isArticleUrl = /\/article\/\d+/.test(tweetId);
|
|
const urlMatch = tweetId.match(/\/(?:status|article)\/(\d+)/);
|
|
if (urlMatch) tweetId = urlMatch[1];
|
|
|
|
if (isArticleUrl) {
|
|
// Navigate to the article page and resolve the parent tweet ID from DOM
|
|
await page.goto(`https://x.com/i/article/${tweetId}`);
|
|
await page.wait(3);
|
|
const resolvedId = await page.evaluate(`
|
|
(function() {
|
|
var links = document.querySelectorAll('a[href*="/status/"]');
|
|
for (var i = 0; i < links.length; i++) {
|
|
var m = links[i].href.match(/\\/status\\/(\\d+)/);
|
|
if (m) return m[1];
|
|
}
|
|
var og = document.querySelector('meta[property="og:url"]');
|
|
if (og && og.content) {
|
|
var m2 = og.content.match(/\\/status\\/(\\d+)/);
|
|
if (m2) return m2[1];
|
|
}
|
|
return null;
|
|
})()
|
|
`);
|
|
if (!resolvedId || typeof resolvedId !== 'string') {
|
|
throw new CommandExecutionError(
|
|
`Could not resolve article ${tweetId} to a tweet ID. The article page may not contain a linked tweet.`,
|
|
);
|
|
}
|
|
tweetId = resolvedId;
|
|
}
|
|
|
|
// Navigate to the tweet page for cookie context
|
|
await page.goto(`https://x.com/i/status/${tweetId}`);
|
|
await page.wait(3);
|
|
const queryId = await resolveTwitterQueryId(page, 'TweetResultByRestId', TWEET_RESULT_BY_REST_ID_QUERY_ID);
|
|
|
|
const result = await page.evaluate(`
|
|
async () => {
|
|
const tweetId = "${tweetId}";
|
|
const ct0 = document.cookie.split(';').map(c=>c.trim()).find(c=>c.startsWith('ct0='))?.split('=')[1];
|
|
if (!ct0) return {error: 'No ct0 cookie — not logged into x.com'};
|
|
|
|
const bearer = 'AAAAAAAAAAAAAAAAAAAAANRILgAAAAAAnNwIzUejRCOuH5E6I8xnZz4puTs%3D1Zv7ttfk8LF81IUq16cHjhLTvJu4FA33AGWWjCpTnA';
|
|
const headers = {
|
|
'Authorization': 'Bearer ' + decodeURIComponent(bearer),
|
|
'X-Csrf-Token': ct0,
|
|
'X-Twitter-Auth-Type': 'OAuth2Session',
|
|
'X-Twitter-Active-User': 'yes'
|
|
};
|
|
|
|
const variables = JSON.stringify({
|
|
tweetId: tweetId,
|
|
withCommunity: false,
|
|
includePromotedContent: false,
|
|
withVoice: false,
|
|
});
|
|
const features = JSON.stringify({
|
|
longform_notetweets_consumption_enabled: true,
|
|
responsive_web_twitter_article_tweet_consumption_enabled: true,
|
|
longform_notetweets_rich_text_read_enabled: true,
|
|
longform_notetweets_inline_media_enabled: true,
|
|
articles_preview_enabled: true,
|
|
responsive_web_graphql_exclude_directive_enabled: true,
|
|
verified_phone_label_enabled: false,
|
|
});
|
|
const fieldToggles = JSON.stringify({
|
|
withArticleRichContentState: true,
|
|
withArticlePlainText: true,
|
|
});
|
|
|
|
const url = '/i/api/graphql/' + ${JSON.stringify(queryId)} + '/TweetResultByRestId?variables='
|
|
+ encodeURIComponent(variables)
|
|
+ '&features=' + encodeURIComponent(features)
|
|
+ '&fieldToggles=' + encodeURIComponent(fieldToggles);
|
|
|
|
const resp = await fetch(url, {headers, credentials: 'include'});
|
|
if (!resp.ok) return {error: 'HTTP ' + resp.status, hint: 'Tweet may not exist or queryId expired'};
|
|
const d = await resp.json();
|
|
|
|
const result = d.data?.tweetResult?.result;
|
|
if (!result) return {error: 'Article not found'};
|
|
|
|
// Unwrap TweetWithVisibilityResults
|
|
const tw = result.tweet || result;
|
|
const legacy = tw.legacy || {};
|
|
const user = tw.core?.user_results?.result;
|
|
const screenName = user?.legacy?.screen_name || user?.core?.screen_name || 'unknown';
|
|
|
|
// Extract article content
|
|
const articleResults = tw.article?.article_results?.result;
|
|
if (!articleResults) {
|
|
// Fallback: return note_tweet text if present
|
|
const noteText = tw.note_tweet?.note_tweet_results?.result?.text;
|
|
if (noteText) {
|
|
return [{
|
|
title: '(Note Tweet)',
|
|
author: screenName,
|
|
content: noteText,
|
|
url: 'https://x.com/' + screenName + '/status/' + tweetId,
|
|
}];
|
|
}
|
|
return {error: 'Tweet ' + tweetId + ' has no article content'};
|
|
}
|
|
|
|
const title = articleResults.title || '(Untitled)';
|
|
const contentState = articleResults.content_state || {};
|
|
const blocks = contentState.blocks || [];
|
|
|
|
// Convert draft.js blocks to Markdown
|
|
const parts = [];
|
|
let orderedCounter = 0;
|
|
for (const block of blocks) {
|
|
const blockType = block.type || 'unstyled';
|
|
if (blockType === 'atomic') continue;
|
|
const text = block.text || '';
|
|
if (!text) continue;
|
|
if (blockType !== 'ordered-list-item') orderedCounter = 0;
|
|
|
|
if (blockType === 'header-one') parts.push('# ' + text);
|
|
else if (blockType === 'header-two') parts.push('## ' + text);
|
|
else if (blockType === 'header-three') parts.push('### ' + text);
|
|
else if (blockType === 'blockquote') parts.push('> ' + text);
|
|
else if (blockType === 'unordered-list-item') parts.push('- ' + text);
|
|
else if (blockType === 'ordered-list-item') {
|
|
orderedCounter++;
|
|
parts.push(orderedCounter + '. ' + text);
|
|
}
|
|
else if (blockType === 'code-block') parts.push('\`\`\`\\n' + text + '\\n\`\`\`');
|
|
else parts.push(text);
|
|
}
|
|
|
|
return [{
|
|
title,
|
|
author: screenName,
|
|
content: parts.join('\\n\\n') || legacy.full_text || '',
|
|
url: 'https://x.com/' + screenName + '/status/' + tweetId,
|
|
}];
|
|
}
|
|
`);
|
|
|
|
if (result?.error) {
|
|
if (String(result.error).includes('No ct0 cookie')) throw new AuthRequiredError('x.com', result.error);
|
|
throw new CommandExecutionError(result.error + (result.hint ? ` (${result.hint})` : ''));
|
|
}
|
|
|
|
return result || [];
|
|
}
|
|
});
|