ming
4ca570a39f
Adds agent_reach/transcribe.py (download → compress → chunk → transcribe with provider fallback, fully mocked tests). Maintainer follow-up on the branch: wired an agent-reach transcribe CLI subcommand + skill docs so agents can actually invoke it, added the missing configure openai-key branch the error hint referenced, removed two dead static methods. 103 tests pass; wheel-gate clean.
72 lines
2.7 KiB
Python
72 lines
2.7 KiB
Python
# -*- coding: utf-8 -*-
|
||
"""YouTube — check if yt-dlp is available with JS runtime."""
|
||
|
||
import shutil
|
||
|
||
from agent_reach.utils.paths import get_ytdlp_config_path, render_ytdlp_fix_command
|
||
from agent_reach.utils.text import read_utf8_text
|
||
|
||
from .base import Channel
|
||
|
||
|
||
class YouTubeChannel(Channel):
|
||
name = "youtube"
|
||
description = "YouTube 视频和字幕"
|
||
backends = ["yt-dlp"]
|
||
tier = 0
|
||
|
||
def can_handle(self, url: str) -> bool:
|
||
from urllib.parse import urlparse
|
||
|
||
d = urlparse(url).netloc.lower()
|
||
return "youtube.com" in d or "youtu.be" in d
|
||
|
||
def check(self, config=None):
|
||
if not shutil.which("yt-dlp"):
|
||
return "off", "yt-dlp 未安装。安装：pip install yt-dlp"
|
||
# Check JS runtime
|
||
has_js = shutil.which("deno") or shutil.which("node")
|
||
if not has_js:
|
||
return "warn", (
|
||
"yt-dlp 已安装但缺少 JS runtime（YouTube 必须）。\n"
|
||
" 安装 Node.js 或 deno，然后运行：agent-reach install"
|
||
)
|
||
# Check yt-dlp config for --js-runtimes
|
||
# Deno works out of the box; Node.js requires explicit config
|
||
has_deno = shutil.which("deno")
|
||
if not has_deno:
|
||
ytdlp_config = get_ytdlp_config_path()
|
||
has_js_config = False
|
||
if ytdlp_config.exists():
|
||
has_js_config = "--js-runtimes" in read_utf8_text(ytdlp_config)
|
||
if not has_js_config:
|
||
return "warn", (
|
||
f"yt-dlp 已安装但未配置 JS runtime。运行：\n {render_ytdlp_fix_command()}"
|
||
)
|
||
# Surface transcription readiness so `doctor` reports it.
|
||
msg = "可提取视频信息和字幕"
|
||
if config is not None:
|
||
providers = []
|
||
if config.is_configured("groq_whisper"):
|
||
providers.append("groq")
|
||
if config.is_configured("openai_whisper"):
|
||
providers.append("openai")
|
||
if providers:
|
||
if not shutil.which("ffmpeg"):
|
||
msg += "（音频转写需安装 ffmpeg）"
|
||
else:
|
||
msg += f"，可转写音频（{'→'.join(providers)}）"
|
||
return "ok", msg
|
||
|
||
def transcribe(self, url: str, *, provider: str = "auto", config=None) -> str:
|
||
"""Download a YouTube video's audio and return its transcript.
|
||
|
||
Delegates to :func:`agent_reach.transcribe.transcribe`. Imported lazily
|
||
so the channel module stays cheap to import for users who never
|
||
transcribe.
|
||
"""
|
||
from agent_reach.transcribe import transcribe as _transcribe
|
||
|
||
return _transcribe(url, provider=provider, config=config)
|
||
|