/** * Weibo Scraper + Downloader (ESM) * * Usage: *   node weibo.js "https://weibo.com/xxx/xxx" *   node weibo.js "https://weibo.com/xxx/xxx" --download */import { mkdir } from 'node:fs/promises';import { join } from 'node:path';import { createWriteStream } from 'node:fs';import { pipeline } from 'node:stream/promises';import { Readable } from 'node:stream';const UA =  'Mozilla/5.0 (iPhone; CPU iPhone OS 17_0 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.0 Mobile/15E148 Safari/604.1';const HEADERS = {  'User-Agent': UA,  Accept: 'application/json, text/plain, */*',  Referer: 'https://m.weibo.cn/',  'X-Requested-With': 'XMLHttpRequest',  'MWeibo-Pwa': '1',};const BASE62 = '0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ';function base62Decode(str) {  let num = 0n;  for (const c of str) {    num = num * 62n + BigInt(BASE62.indexOf(c));  }  return num.toString();}function midToId(mid) {  if (/^\d+$/.test(mid)) return mid;  let result = '';  for (let i = mid.length; i > 0; i -= 4) {    const start = Math.max(0, i - 4);    let num = base62Decode(mid.slice(start, i));    if (start > 0) num = num.padStart(7, '0');    result = num + result;  }  return result.replace(/^0+/, '') || '0';}function parseWeiboUrl(url) {  url = url.trim();  if (url.includes('t.cn/')) return { type: 'short', shortUrl: url };  let m = url.match(/weibo\.com\/(?:u\/)?(\d+)\/([A-Za-z0-9]+)/);  if (m) return { uid: m[1], mid: m[2], id: midToId(m[2]) };  m = url.match(/weibo\.com\/(?:detail|status)\/(\d+)/);  if (m) return { id: m[1] };  m = url.match(/m\.weibo\.cn\/(?:detail|status)\/([A-Za-z0-9]+)/);  if (m) {    const v = m[1];    return /^\d+$/.test(v) ? { id: v } : { mid: v, id: midToId(v) };  }  m = url.match(/m\.weibo\.cn\/(\d+)\/([A-Za-z0-9]+)/);  if (m) return { uid: m[1], mid: m[2], id: midToId(m[2]) };  if (/^[A-Za-z0-9]{8,12}$/.test(url)) return { mid: url, id: midToId(url) };  if (/^\d{15,20}$/.test(url)) return { id: url };  throw new Error('URL tidak dikenali');}async function resolveShortUrl(shortUrl) {  const res = await fetch(shortUrl, {    method: 'HEAD',    redirect: 'manual',    headers: { 'User-Agent': UA },  });  const loc = res.headers.get('location');  if (!loc) throw new Error('Gagal resolve short link');  return loc;}async function fetchStatus(idOrMid, cookie = '') {  const id = /^\d+$/.test(idOrMid) ? idOrMid : midToId(idOrMid);  const headers = { ...HEADERS };  if (cookie) headers.Cookie = cookie;  const res = await fetch(`https://m.weibo.cn/statuses/show?id=${id}`, { headers });  if (!res.ok) throw new Error(`HTTP ${res.status}`);  const json = await res.json();  if (json.ok !== 1) throw new Error(json.msg || 'Gagal ambil data');  return json.data;}function extractMedia(data) {  const medias = [];  if (data.pics?.length) {    for (const pic of data.pics) {      const url = pic.large?.url || pic.url;      medias.push({        type: 'image',        url: url?.replace(/\/orj\d+\//, '/large/') || url,        thumbnail: pic.url,        livePhoto: pic.videoSrc || null,      });    }  }  if (data.pic_infos) {    for (const info of Object.values(data.pic_infos)) {      const largest = info.largest || info.original || info.large || info.mw2000;      medias.push({        type: 'image',        url: largest?.url,        thumbnail: info.thumbnail?.url,        livePhoto: info.video_src || null,      });    }  }  const pi = data.page_info;  if (pi?.type === 'video' || pi?.media_info) {    const mi = pi.media_info || {};    const urls = pi.urls || {};    const list = [];    if (urls.mp4_720p_mp4) list.push({ quality: '720p', url: urls.mp4_720p_mp4 });    if (urls.mp4_hd_mp4 || mi.stream_url_hd) {      list.push({ quality: 'HD', url: urls.mp4_hd_mp4 || mi.stream_url_hd });    }    if (urls.mp4_ld_mp4 || mi.stream_url) {      list.push({ quality: 'LD', url: urls.mp4_ld_mp4 || mi.stream_url });    }    if (mi.playback_list) {      for (const item of mi.playback_list) {        if (item.play_info?.url) {          list.push({            quality: item.meta?.quality_desc || item.meta?.label || 'unknown',            url: item.play_info.url,          });        }      }    }    const seen = new Set();    const unique = list.filter((q) => {      if (seen.has(q.url)) return false;      seen.add(q.url);      return true;    });    if (unique.length) {      medias.push({        type: 'video',        url: unique[0].url,        quality: unique[0].quality,        allQualities: unique,        duration: mi.duration,        cover: pi.page_pic?.url,        title: pi.content1 || pi.page_title,        playCount: pi.play_count,      });    }  }  return medias;}function parseMetadata(data) {  const u = data.user || {};  const profileUrl = u.profile_url    ? u.profile_url.startsWith('http')      ? u.profile_url      : `https://weibo.com${u.profile_url}`    : null;  return {    id: data.id || data.mid,    mid: data.bid || data.mblogid,    text: (data.text || '').replace(/<[^>]+>/g, '').trim(),    createdAt: data.created_at,    source: (data.source || '').replace(/<[^>]+>/g, ''),    region: data.region_name,    reposts: data.reposts_count,    comments: data.comments_count,    attitudes: data.attitudes_count,    user: {      id: u.id,      screenName: u.screen_name,      profileUrl,      avatar: u.avatar_hd || u.profile_image_url,      verified: u.verified,      verifiedReason: u.verified_reason,      followers: u.followers_count_str || u.followers_count,      description: u.description,    },    medias: extractMedia(data),  };}async function downloadFile(url, destPath, cookie = '') {  const headers = {    'User-Agent': UA,    Accept: '*/*',    Referer: 'https://weibo.com/',    Origin: 'https://weibo.com',  };  if (cookie) headers.Cookie = cookie;  let res = await fetch(url, { headers, redirect: 'follow' });  if (!res.ok) {    headers.Referer = 'https://m.weibo.cn/';    headers.Origin = 'https://m.weibo.cn';    res = await fetch(url, { headers, redirect: 'follow' });    if (!res.ok) throw new Error(`HTTP ${res.status}`);  }  await mkdir(join(destPath, '..'), { recursive: true });  await pipeline(Readable.fromWeb(res.body), createWriteStream(destPath));  return destPath;}async function scrapeWeibo(url, options = {}) {  const { cookie = '', download = false, outDir = './weibo_download' } = options;  let parsed = parseWeiboUrl(url);  if (parsed.type === 'short') {    const resolved = await resolveShortUrl(parsed.shortUrl);    parsed = parseWeiboUrl(resolved);  }  const data = await fetchStatus(parsed.id || parsed.mid, cookie);  const meta = parseMetadata(data);  if (download && meta.medias.length) {    await mkdir(outDir, { recursive: true });    const safeName = (meta.user.screenName || 'user').replace(/[\/\\?%*:|"<>]/g, '_');    const base = `${safeName}_${meta.id}`;    for (let i = 0; i < meta.medias.length; i++) {      const m = meta.medias[i];      if (!m.url) continue;      const candidates = m.allQualities?.length        ? m.allQualities.map((q) => q.url)        : [m.url];      const ext = m.type === 'video' ? 'mp4' : 'jpg';      const index = String(i + 1).padStart(2, '0');      const filename = `${base}_${index}.${ext}`;      const dest = join(outDir, filename);      let success = false;      for (const cand of candidates) {        try {          await downloadFile(cand, dest, cookie);          m.localPath = dest;          m.url = cand;          console.log(`✓ ${filename}`);          success = true;          break;        } catch (e) {          console.warn(`  gagal kualitas, coba berikutnya... (${e.message})`);        }      }      if (!success) console.error(`✗ Gagal download media #${i + 1}`);    }  }  return meta;}// CLIconst url = process.argv[2];if (!url) {  console.error('Usage: node weibo.js <url> [--download]');  process.exit(1);}scrapeWeibo(url, {  download: process.argv.includes('--download'),})  .then((meta) => console.log(JSON.stringify(meta, null, 2)))  .catch((err) => {    console.error('Error:', err.message);    process.exit(1);  });