35 lines
1.6 KiB
Bash
35 lines
1.6 KiB
Bash
#!/bin/bash
|
||
# fetch_course.sh — 下载 YouTube 课程视频 + 本地转写 + 组装教程
|
||
#
|
||
# 用法:
|
||
# ./fetch_course.sh <playlist_url或单个视频url> <输出目录>
|
||
#
|
||
# 环境变量(可选):
|
||
# PROXY 代理，默认 socks5://192.168.27.96:1080
|
||
# MODEL whisper 模型，默认 base.en（英文用 base.en/small.en，中文用 small）
|
||
# LANG 语言，默认 en（中文用 zh）
|
||
# JOBS 并行数，默认 4
|
||
# FMT yt-dlp 格式，默认 18（360p 渐进式，含音轨；见 README 画质说明）
|
||
set -uo pipefail
|
||
URL="${1:?用法: ./fetch_course.sh <url> <输出目录>}"
|
||
OUT="${2:?缺少输出目录}"
|
||
PROXY="${PROXY:-socks5://192.168.27.96:1080}"
|
||
MODEL="${MODEL:-base.en}"; LG="${LANG:-en}"; JOBS="${JOBS:-4}"; FMT="${FMT:-18}"
|
||
HERE="$(cd "$(dirname "$0")" && pwd)"
|
||
mkdir -p "$OUT/videos" "$OUT/transcripts" "$OUT/clean"
|
||
|
||
if [ ! -s "$OUT/manifest.txt" ]; then
|
||
echo "[*] 枚举视频列表..."
|
||
yt-dlp --proxy "$PROXY" --no-warnings --flat-playlist \
|
||
--print "%(playlist_index)s|%(id)s|%(title)s" "$URL" > "$OUT/_raw.txt" || { echo "枚举失败"; exit 1; }
|
||
python3 "$HERE/course_util.py" manifest "$OUT/_raw.txt" > "$OUT/manifest.txt"
|
||
fi
|
||
echo "[*] 待处理视频: $(grep -c . "$OUT/manifest.txt") 个 | 模型=$MODEL 并行=$JOBS"
|
||
|
||
export PROXY MODEL LANG="$LG" OUT HERE FMT
|
||
grep -v '^[[:space:]]*$' "$OUT/manifest.txt" | xargs -P "$JOBS" -I{} "$HERE/worker.sh" "{}"
|
||
|
||
python3 "$HERE/course_util.py" clean "$OUT"
|
||
echo "[*] 全部完成: $OUT"
|
||
echo "[*] 下一步: 在 $OUT/guides/ 放中文导读(<NN>.txt)后运行 course_util.py build $OUT"
|