bilibili-hub

Files (6)

• SKILL.md
• pyproject.toml
• __init__.py · scripts/
• client.py · scripts/
• exceptions.py · scripts/
• payloads.py · scripts/

SKILL.md (first lines)

# bilibili-hub

> **Modified from**: [jackwener/bilibili-cli](https://github.com/jackwener/bilibili-cli) (Apache-2.0)
>
> This skill simplifies and modifies the original repository as follows:
> - Removed the `browser-cookie3` / `click` / `rich` / `PyYAML` / `qrcode` dependencies
> - Changed cookie authentication to accept a `dict` directly or read from environment variables, without automatic browser extraction
> - Removed the CLI layer (`commands/`), QR login, formatters, and related components
> - Kept all API methods and wrapped them uniformly as synchronous interfaces (`asyncio.run`)
> - Core dependency: `bilibili-api-python`, a third-party SDK that reverse engineers the Bilibili API
> - In the Minis environment, cookies are obtained automatically through `browser_use get_cookies`

---

## File Structure

```
/var/minis/skills/bilibili-hub/
├── SKILL.md
├── pyproject.toml          # bilibili-api-python + aiohttp
└── scripts/
    ├── __init__.py
    ├── exceptions.py       # 6 structured exception types
    ├── payloads.py         # Data structure normalization (normalize_* functions)
    └── client.py           # BiliClient core class (all API methods)
```

---

## Authentication Methods

The Bilibili Web API uses three key cookies:

| Cookie | Description |
|--------|------|
| `SESSDATA` | User session (required for read operations) |
| `bili_jct` | CSRF token (required for write operations: likes, coins, posting dynamics, etc.) |
| `DedeUserID` | User ID (recommended) |
| `buvid3` | Device ID (recommended; reduces the likelihood of triggering risk control) |

### Method 1: Automatically retrieve via `browser_use` (preferred in Minis environments)

1. Use `browser_use navigate` to open `https://www.bilibili.com` and confirm that you are logged in.
2. Use `browser_use get_cookies` to retrieve cookies (raw values do not appear in the conversation).
3. Load the offload env file:

```bash
. /var/minis/offloads/env_cookies_www_bilibili_com_xxx.sh
export BILI_SESSDATA="$COOKIE_SESSDATA"
export BILI_JCT="$COOKIE_BILI_JCT"
export BILI_USERID="$COOKIE_DEDEUSERID"
export BILI_BUVID3="$COOKIE_BUVID3"
```

> **Note**: `get_cookies` only applies to the current page's domain. Navigate to `https://www.bilibili.com` before calling it.

### Method 2: Manually retrieve from browser DevTools

1. Log in to Bilibili, then open DevTools -> Application -> Cookies -> `https://www.bilibili.com`.
2. Find the values of `SESSDATA`, `bili_jct`, and `DedeUserID`.
3. Store them in the Minis environment variables: `BILI_SESSDATA` / `BILI_JCT` / `BILI_USERID`.

### Ways to pass cookies (three methods)

```python
# Method 1: From environment variables (recommended)
client = BiliClient.from_env()

# Method 2: Pass a dict directly
client = BiliClient({
    "SESSDATA":   os.environ["BILI_SESSDATA"],
    "bili_jct":   os.environ["BILI_JCT"],
    "DedeUserID": os.environ["BILI_USERID"],
})

# Method 3: Read-only operations (no write permissions required)
client = BiliClient({"SESSDATA": os.environ["BILI_SESSDATA"]})
```

---

## Quick Start

### Environment setup

```bash
cd /var/minis/skills/bilibili-hub
uv sync
```

### Calling as a Python library

```python
import os, json, sys
sys.path.insert(0, "/var/minis/skills/bilibili-hub")
from scripts.client import BiliClient

client = BiliClient.from_env()

# Current user information
me = client.whoami()
print("User:", me.get("name"), "UID:", me.get("mid"))

# Search videos
videos = client.search_videos("Python Tutorial", count=5)
for v in videos:
    print(f"  {v['bvid']} {v['title']} ({v['duration']})")

# Get video details (including subtitles)
detail = client.get_video("BV1xx411c7mD", subtitle=True)
print(detail["video"]["title"])
print(detail["subtitle"]["text"][:200])

# Popular videos
hot = client.get_hot(count=10)
for v in hot:
    print(f"  {v['bvid']} {v['title']} 👁{v['stats']['view']}")
```

From Willian8021743/windows-ai-toolkit, MIT.

More from Willian8021743/windows-ai-toolkit