Pnant
2c766af477
bilibili: - live-verified 2026-06: bilibili 412-blocks yt-dlp in every configuration (latest version, direct, proxied, warmed cookies) while bili-cli works fine without login — so yt-dlp no longer serves this channel (it remains the YouTube backend) - backends = [bili-cli, OpenCLI, B站搜索 API]: bili-cli covers search/hot/rank/video-detail/audio, OpenCLI adds subtitles through the browser session, the search API is the zero-dependency fallback - when a broken candidate is bypassed by a working fallback, its reinstall prescription is appended to the winning message instead of being swallowed - skill docs (social.md + video.md): "do NOT use yt-dlp for bilibili" warning, bili-cli/OpenCLI command groups, curl fallback recipe, B站 audio transcription path via `bili audio` + agent-reach transcribe twitter: - OpenCLI joins as the middle candidate [twitter-cli, OpenCLI, bird] - social.md: explicit 4-step search retry chain (retry → upgrade → OpenCLI → stable-command detour) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
131 lines
4.0 KiB
Markdown
131 lines
4.0 KiB
Markdown
# 视频/播客
|
||
|
||
YouTube、B站、小宇宙播客的字幕和转录。
|
||
|
||
## YouTube (yt-dlp)
|
||
|
||
### 获取视频元数据
|
||
|
||
```bash
|
||
yt-dlp --dump-json "URL"
|
||
```
|
||
|
||
### 下载字幕
|
||
|
||
```bash
|
||
# 下载字幕 (不下载视频)
|
||
yt-dlp --write-sub --write-auto-sub --sub-lang "zh-Hans,zh,en" --skip-download -o "/tmp/%(id)s" "URL"
|
||
|
||
# 然后读取 .vtt 文件
|
||
cat /tmp/VIDEO_ID.*.vtt
|
||
```
|
||
|
||
### 获取评论
|
||
|
||
```bash
|
||
# 提取评论（best-effort，不保证完整）
|
||
yt-dlp --write-comments --skip-download --write-info-json \
|
||
--extractor-args "youtube:max_comments=20" \
|
||
-o "/tmp/%(id)s" "URL"
|
||
# 评论在 .info.json 的 comments 字段中
|
||
```
|
||
|
||
### 搜索视频
|
||
|
||
```bash
|
||
yt-dlp --dump-json "ytsearch5:query"
|
||
```
|
||
|
||
> **字幕注意**: 手动上传的字幕提取可靠；自动生成字幕可能存在行间重复，需后处理。
|
||
> **评论注意**: `--write-comments` 基于网页抓取（非 YouTube Data API），部分评论可能丢失。
|
||
|
||
### 无字幕兜底：Whisper 音频转写
|
||
|
||
```bash
|
||
# 视频没有字幕时的兜底：下载音频并用 Whisper 转写（Groq 免费 key 即可）
|
||
agent-reach transcribe "https://www.youtube.com/watch?v=VIDEO_ID"
|
||
agent-reach transcribe ./local_audio.mp3 -o /tmp/transcript.txt
|
||
```
|
||
|
||
> 需要先配置 key：`agent-reach configure groq-key gsk_xxx`（免费，console.groq.com）
|
||
> 或 `agent-reach configure openai-key sk-xxx`。默认 auto 模式：groq 失败自动降级 openai。
|
||
|
||
## B站 / Bilibili（bili-cli 为主，OpenCLI 补字幕）
|
||
|
||
> ⚠️ **不要用 yt-dlp 读 B站**：B站风控已全面 412 拦截 yt-dlp（实测最新版、直连/代理/带 Cookie 全部无效）。yt-dlp 只用于 YouTube。
|
||
|
||
### 视频详情/搜索/热门/排行 (bili-cli，只读无需登录)
|
||
|
||
```bash
|
||
# 视频详情（标题/UP主/时长/播放互动数据/字幕可用性）
|
||
bili video BVxxx
|
||
|
||
# 搜索视频
|
||
bili search "query" --type video -n 5
|
||
|
||
# 热门视频 / 排行榜
|
||
bili hot -n 10
|
||
bili rank -n 10
|
||
|
||
# 下载音频并切分为 ASR-ready WAV（无字幕时配合 agent-reach transcribe 转写）
|
||
bili audio BVxxx
|
||
```
|
||
|
||
### 字幕 (OpenCLI，需要桌面 Chrome)
|
||
|
||
```bash
|
||
# 字幕逐句带时间轴
|
||
opencli bilibili subtitle BVxxx
|
||
|
||
# OpenCLI 也能搜索/读视频元数据（备选）
|
||
opencli bilibili search "query" -f yaml
|
||
opencli bilibili video BVxxx -f yaml
|
||
```
|
||
|
||
### 零配置兜底：搜索 API 直连
|
||
|
||
```bash
|
||
UA="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36"
|
||
curl -s -c /tmp/bili_ck.txt -o /dev/null -A "$UA" "https://www.bilibili.com/"
|
||
curl -s -b /tmp/bili_ck.txt -A "$UA" -e "https://www.bilibili.com/" \
|
||
"https://api.bilibili.com/x/web-interface/search/all/v2?keyword=QUERY&page=1"
|
||
```
|
||
|
||
> **安装 bili-cli**: `pipx install bilibili-cli`（上游 2026-03 起停更但实测健康；只读场景无需登录，`bili login` 扫码可解锁动态/收藏等个人功能）。
|
||
|
||
## 小宇宙播客 / Xiaoyuzhou Podcast
|
||
|
||
### 转录单集播客（可选 --polish 增强标点）
|
||
|
||
```bash
|
||
# 输出 Markdown 文件到 /tmp/。--polish 让 Llama 3.3 70B 给文稿补中文标点+合理分段
|
||
~/.agent-reach/tools/xiaoyuzhou/transcribe.sh --polish "https://www.xiaoyuzhoufm.com/episode/EPISODE_ID"
|
||
```
|
||
|
||
> 转写 prompt 已要求 Whisper 输出中文标点；若标点效果仍不理想，可加 `--polish` 用 Groq 上免费的 Llama 3.3 70B 补标点+合理分段（9 分钟播客约多 ~7 秒）。每次转写多一轮 LLM 调用，按需使用。
|
||
|
||
### 前置要求
|
||
|
||
1. **ffmpeg**: `brew install ffmpeg`
|
||
2. **Groq API Key** (免费): https://console.groq.com/keys
|
||
3. **配置 Key**: `agent-reach configure groq-key YOUR_KEY`
|
||
4. **首次运行**: `agent-reach install --env=auto` 安装工具
|
||
|
||
### 检查状态
|
||
|
||
```bash
|
||
agent-reach doctor
|
||
```
|
||
|
||
> 输出 Markdown 文件默认保存到 `/tmp/`。
|
||
|
||
## 选择指南
|
||
|
||
| 场景 | 推荐工具 |
|
||
|-----|---------|
|
||
| YouTube 字幕 | yt-dlp |
|
||
| B站视频详情/搜索 | bili-cli |
|
||
| B站字幕 | opencli bilibili subtitle |
|
||
| 播客转录 | 小宇宙 transcribe.sh |
|
||
| 无字幕音视频 | agent-reach transcribe（B站音频先 `bili audio`） |
|