weibo-hub

name

weibo-hub

description

A skill for reading and writing Weibo data using Python + UV, powered by httpx. Cookies are auto-acquired via browser_use get_cookies for authentication — no manual copying needed. Supports trending searches, hot feed, following feed, keyword search, weibo details/comments/reposts, user profiles/weibos/following/followers, etc. Trigger when user mentions "Weibo", "weibo", "weibo-hub", "Weibo trending", "scrape Weibo", "search Weibo", "Weibo comments", "Weibo users", or any scenario requiring programmatic access to Weibo data.

weibo-hub

Forked from: jackwener/weibo-cli (Apache-2.0)

This skill simplifies the original repo as follows:

• Removed click / rich / browser-cookie3 / qrcode / pyyaml dependencies
• Retained only httpx as a third-party dependency
• Removed CLI layer, all functionality packaged as sync Python API
• Auth changed to browser_use get_cookies extract → call setup_credential() to save
• Data directory changed to /var/minis/workspace/weibo-hub/

---

File Structure

/var/minis/skills/weibo-hub/
├── SKILL.md
├── pyproject.toml          # httpx only
└── scripts/
    ├── __init__.py
    ├── constants.py        # API endpoints, Headers, path constants
    ├── exceptions.py       # WeiboError exception hierarchy
    ├── auth.py             # Credential persistence (no browser-cookie3)
    └── client.py           # WeiboClient core class (all APIs)

---

Authentication Flow (Check Before Each Use)

weibo-hub uses browser cookie authentication, extracted via browser_use get_cookies from weibo.com, no browser-cookie3 needed, no QR scan required.

Step 1: Extract Cookies with browser_use

# In agent call:
browser_use(action="navigate", url="https://weibo.com")
# Confirm logged in then:
browser_use(action="get_cookies", url="https://weibo.com")
# Record the returned offload env file path

Step 2: Read from Env File and Save Credential

import sys, os, subprocess, json

# Load cookie env vars (path from get_cookies offload file)
env_file = "/var/minis/offloads/env_cookies_xxx.sh"   # Replace with actual path
result = subprocess.run(
    f". {env_file} && python3 -c \"import os,json; print(json.dumps(dict(os.environ)))\"",
    shell=True, capture_output=True, text=True
)
env = json.loads(result.stdout)

# Parse cookie dict (COOKIE_ prefix variables)
cookies = {
    k[len("COOKIE_"):]: v
    for k, v in env.items()
    if k.startswith("COOKIE_")
}

# Save credential
sys.path.insert(0, "/var/minis/skills/weibo-hub")
from scripts.client import WeiboClient
WeiboClient.setup_credential(cookies)

Key Cookies: SUB, SUBP (required), more is better. Credential saved to /var/minis/workspace/weibo-hub/credential.json, valid for 7 days, auto-warns when expired.

---

Environment Setup

cd /var/minis/skills/weibo-hub
uv sync

---

Quick Start

import sys
sys.path.insert(0, "/var/minis/skills/weibo-hub")
from scripts.client import WeiboClient

with WeiboClient() as client:

    # ── Trending / Hot Search (no login required) ───────────────
    topics = client.hot_search()          # Trending sidebar (~52 items)
    for t in topics[:10]:
        print(f"#{t.get('realtime_hot_show_label','')} {t.get('word','')}")

    band = client.hot_band()              # Full trending list
    trends = client.trending()            # Real-time search suggestions

    # ── Feed (hot no login, following requires login) ───────────
    hot = client.hot_feed(count=10)       # Hot timeline
    home = client.home_feed(count=20)     # Following timeline

    # ── Search (mobile API) ──────────────────────────────────────
    results = client.search("artificial intelligence", page=1)
    for w in results[:5]:
        print(w.get("text", "")[:80])

    # ── Weibo Detail / Comments / Reposts (login required) ────
    wb = client.detail("Qw06Kd98p")
    cmt = client.comments("WeiboID", count=20)
    rep = client.reposts("WeiboID", count=10)

    # ── User (login required) ────────────────────────────────────
    me = client.me()                      # Current logged-in user
    user = client.profile("1699432410")   # Specified user profile
    weibos = client.user_weibos("1699432410", page=1)
    following = client.following("1699432410", page=1)
    followers = client.followers("1699432410", page=1)

---

API Reference

No Login Required (Public)

Method	Description
hot_search()	Trending sidebar (~52 items)
hot_band()	Full trending list
trending()	Real-time search suggestions
hot_feed(count, max_id)	Hot timeline
search(keyword, page)	Keyword search weibos

Login Required (Cookie Auth)

Method	Description
me()	Current logged-in user info
home_feed(count, max_id)	Following timeline
detail(mblogid)	Single weibo detail
comments(weibo_id, count, max_id)	Weibo comments list
reposts(weibo_id, page, count)	Weibo reposts list
profile(uid)	User profile
user_weibos(uid, page, count)	User weibo list
following(uid, page)	User following list
followers(uid, page)	User followers list

Auth

Method	Description
WeiboClient.setup_credential(cookies)	Save cookie credential (static method)

---

Anti-Detection Notes

Consistent with upstream weibo-cli:

• Gaussian jitter: Each request interval = request_delay + gauss(0.3, 0.15), ~1s
• 5% long pause: Random trigger of 2-5s extra delay, simulating reading behavior
• Exponential backoff: HTTP 429/5xx retry up to 3 times, wait 2^n seconds
• Chrome 145 UA: Desktop User-Agent, consistent with browser fingerprint

---

Notes

• First use must call WeiboClient.setup_credential(cookies) to save credential
• Credential file: /var/minis/workspace/weibo-hub/credential.json, permissions 0600
• Required Cookies: SUB + SUBP, missing these will cause setup_credential() to raise ValueError
• Cookie auto-warns expiration after 7 days; re-extract required
• Trending/hot feed/search do not require login; profile/detail/home_feed require valid cookies
• search() uses mobile API (m.weibo.cn), result format differs slightly