Files
jackwener__opencli/clis/twitter/thread.js
Dylanwoo 666a955fac feat(twitter): expose has_media and media_urls columns (#1115)
Adds two additive columns to the Twitter read commands (search, timeline,
tweets, thread, likes):

- has_media: boolean — true if the tweet contains any photo, video, or GIF
- media_urls: string[] — photo URLs and mp4 variant URLs for videos/GIFs,
  extracted from legacy.extended_entities.media (falls back to entities.media)

The INTERCEPT/COOKIE payloads already carry this data; this change only
extends the row-mapping layer, so no new network work is needed. Pattern
mirrors #465 (time column).

Shared extraction helper lives in clis/twitter/shared.js so all five
adapters stay consistent, with unit coverage for photo, video (mp4 variant
selection), animated_gif, entities.media fallback, and the empty case.

Closes #1107
2026-04-21 23:02:22 +08:00

154 lines
6.6 KiB
JavaScript

import { cli, Strategy } from '@jackwener/opencli/registry';
import { AuthRequiredError, CommandExecutionError } from '@jackwener/opencli/errors';
import { extractMedia } from './shared.js';
// ── Twitter GraphQL constants ──────────────────────────────────────────
const BEARER_TOKEN = 'AAAAAAAAAAAAAAAAAAAAANRILgAAAAAAnNwIzUejRCOuH5E6I8xnZz4puTs%3D1Zv7ttfk8LF81IUq16cHjhLTvJu4FA33AGWWjCpTnA';
const TWEET_DETAIL_QUERY_ID = 'nBS-WpgA6ZG0CyNHD517JQ';
const FEATURES = {
responsive_web_graphql_exclude_directive_enabled: true,
verified_phone_label_enabled: false,
creator_subscriptions_tweet_preview_api_enabled: true,
responsive_web_graphql_timeline_navigation_enabled: true,
responsive_web_graphql_skip_user_profile_image_extensions_enabled: false,
longform_notetweets_consumption_enabled: true,
longform_notetweets_rich_text_read_enabled: true,
longform_notetweets_inline_media_enabled: true,
freedom_of_speech_not_reach_fetch_enabled: true,
};
const FIELD_TOGGLES = { withArticleRichContentState: true, withArticlePlainText: false };
function buildTweetDetailUrl(tweetId, cursor) {
const vars = {
focalTweetId: tweetId,
referrer: 'tweet',
with_rux_injections: false,
includePromotedContent: false,
rankingMode: 'Recency',
withCommunity: true,
withQuickPromoteEligibilityTweetFields: true,
withBirdwatchNotes: true,
withVoice: true,
};
if (cursor)
vars.cursor = cursor;
return `/i/api/graphql/${TWEET_DETAIL_QUERY_ID}/TweetDetail`
+ `?variables=${encodeURIComponent(JSON.stringify(vars))}`
+ `&features=${encodeURIComponent(JSON.stringify(FEATURES))}`
+ `&fieldToggles=${encodeURIComponent(JSON.stringify(FIELD_TOGGLES))}`;
}
function extractTweet(r, seen) {
if (!r)
return null;
const tw = r.tweet || r;
const l = tw.legacy || {};
if (!tw.rest_id || seen.has(tw.rest_id))
return null;
seen.add(tw.rest_id);
const u = tw.core?.user_results?.result;
const noteText = tw.note_tweet?.note_tweet_results?.result?.text;
const screenName = u?.legacy?.screen_name || u?.core?.screen_name || 'unknown';
return {
id: tw.rest_id,
author: screenName,
text: noteText || l.full_text || '',
likes: l.favorite_count || 0,
retweets: l.retweet_count || 0,
in_reply_to: l.in_reply_to_status_id_str || undefined,
created_at: l.created_at,
url: `https://x.com/${screenName}/status/${tw.rest_id}`,
...extractMedia(l),
};
}
function parseTweetDetail(data, seen) {
const tweets = [];
let nextCursor = null;
const instructions = data?.data?.threaded_conversation_with_injections_v2?.instructions
|| data?.data?.tweetResult?.result?.timeline?.instructions
|| [];
for (const inst of instructions) {
for (const entry of inst.entries || []) {
// Cursor entries
const c = entry.content;
if (c?.entryType === 'TimelineTimelineCursor' || c?.__typename === 'TimelineTimelineCursor') {
if (c.cursorType === 'Bottom' || c.cursorType === 'ShowMore')
nextCursor = c.value;
continue;
}
if (entry.entryId?.startsWith('cursor-bottom-') || entry.entryId?.startsWith('cursor-showMore-')) {
nextCursor = c?.itemContent?.value || c?.value || nextCursor;
continue;
}
// Direct tweet entry
const tw = extractTweet(c?.itemContent?.tweet_results?.result, seen);
if (tw)
tweets.push(tw);
// Conversation module (nested replies)
for (const item of c?.items || []) {
const nested = extractTweet(item.item?.itemContent?.tweet_results?.result, seen);
if (nested)
tweets.push(nested);
}
}
}
return { tweets, nextCursor };
}
// ── CLI definition ────────────────────────────────────────────────────
cli({
site: 'twitter',
name: 'thread',
description: 'Get a tweet thread (original + all replies)',
domain: 'x.com',
strategy: Strategy.COOKIE,
browser: true,
args: [
{ name: 'tweet-id', positional: true, type: 'string', required: true },
{ name: 'limit', type: 'int', default: 50 },
],
columns: ['id', 'author', 'text', 'likes', 'retweets', 'url', 'has_media', 'media_urls'],
func: async (page, kwargs) => {
let tweetId = kwargs['tweet-id'];
const urlMatch = tweetId.match(/\/status\/(\d+)/);
if (urlMatch)
tweetId = urlMatch[1];
// Navigate to x.com for cookie context
await page.goto('https://x.com');
await page.wait(3);
// Extract CSRF token — the only thing we need from the browser
const ct0 = await page.evaluate(`() => {
return document.cookie.split(';').map(c=>c.trim()).find(c=>c.startsWith('ct0='))?.split('=')[1] || null;
}`);
if (!ct0)
throw new AuthRequiredError('x.com', 'Not logged into x.com (no ct0 cookie)');
// Build auth headers in TypeScript
const headers = JSON.stringify({
'Authorization': `Bearer ${decodeURIComponent(BEARER_TOKEN)}`,
'X-Csrf-Token': ct0,
'X-Twitter-Auth-Type': 'OAuth2Session',
'X-Twitter-Active-User': 'yes',
});
// Paginate — fetch in browser, parse in TypeScript
const allTweets = [];
const seen = new Set();
let cursor = null;
for (let i = 0; i < 5; i++) {
const apiUrl = buildTweetDetailUrl(tweetId, cursor);
// Browser-side: just fetch + return JSON (3 lines)
const data = await page.evaluate(`async () => {
const r = await fetch("${apiUrl}", { headers: ${headers}, credentials: 'include' });
return r.ok ? await r.json() : { error: r.status };
}`);
if (data?.error) {
if (allTweets.length === 0)
throw new CommandExecutionError(`HTTP ${data.error}: Tweet not found or queryId expired`);
break;
}
// TypeScript-side: type-safe parsing + cursor extraction
const { tweets, nextCursor } = parseTweetDetail(data, seen);
allTweets.push(...tweets);
if (!nextCursor || nextCursor === cursor)
break;
cursor = nextCursor;
}
return allTweets.slice(0, kwargs.limit);
},
});