Pnant
b0e010c6cc
Extracted from #318 (the UTF-8/doctor core, minus the env-wrapper feature): - new agent_reach/utils/process.py: utf8_subprocess_env() + mcporter_utf8_env_args() — Windows GBK consoles otherwise corrupt Chinese output from mcporter/MCP child processes - weibo/douyin/linkedin checks and weibo install/registration now pass the UTF-8 env (and register the MCP server with --env PYTHONUTF8=1) - youtube: extract _has_js_runtime_config() with an OSError guard so an unreadable yt-dlp config can't crash doctor - test_skill_command: open SKILL.md with explicit utf-8 (Windows GBK default broke these tests) Co-authored-by: chidao <2980933590@qq.com> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
79 lines
2.8 KiB
Python
79 lines
2.8 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
|
||
|
||
|
||
def _has_js_runtime_config(config_path) -> bool:
|
||
"""Return whether yt-dlp config explicitly enables a JS runtime."""
|
||
try:
|
||
if not config_path.exists():
|
||
return False
|
||
return "--js-runtimes" in read_utf8_text(config_path)
|
||
except OSError:
|
||
return False
|
||
|
||
|
||
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()
|
||
if not _has_js_runtime_config(ytdlp_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)
|
||
|