47da3e6746
Index an entire YouTube channel or playlist once, then download it into organized <Channel>/<Playlist>/<NNN> - <Title> folders, with incremental re-sync. Built in six rebuild-gated phases (F-K); see ROADMAP-PINCHFLAT.md. - F: channel-walk indexer (/playlists + /videos) -> persisted Source + MediaItem JSON stores; pure classify/dedup logic in indexerCore.ts - G: Windows-safe folder paths + dir sanitizer (collectionOutputTemplate) - H: Library tab + source tree + "Download pending" into the existing queue - I: state-preserving re-index merge + persist-downloaded-on-complete - J: watched sources, RSS fast-check, Task Scheduler + --sync launch (the OS-level scheduling/RSS need a real-install smoke test) - K: .info.json / thumbnail / .description sidecars for media servers Also gitignore .gitea-token. 106 unit tests pass; typecheck + build clean. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
161 lines
5.0 KiB
TypeScript
161 lines
5.0 KiB
TypeScript
import { execFile } from 'child_process'
|
|
import { existsSync } from 'fs'
|
|
import { getYtdlpPath } from './binaries'
|
|
import { fmtBytes } from './download'
|
|
import { cleanError } from './log'
|
|
import { assertHttpUrl } from './url'
|
|
import { entryUrl, fmtDuration, type RawEntry } from './indexerCore'
|
|
import {
|
|
BEST_FORMAT_ID,
|
|
type ProbeResult,
|
|
type MediaInfo,
|
|
type FormatOption,
|
|
type PlaylistInfo,
|
|
type PlaylistEntry
|
|
} from '@shared/ipc'
|
|
|
|
// The slice of `yt-dlp -J` output we actually read.
|
|
interface RawFormat {
|
|
format_id: string
|
|
ext?: string
|
|
vcodec?: string
|
|
acodec?: string
|
|
height?: number
|
|
fps?: number
|
|
tbr?: number
|
|
filesize?: number
|
|
filesize_approx?: number
|
|
}
|
|
|
|
interface RawInfo {
|
|
_type?: string
|
|
title?: string
|
|
uploader?: string
|
|
channel?: string
|
|
duration_string?: string
|
|
thumbnail?: string
|
|
formats?: RawFormat[]
|
|
entries?: RawEntry[]
|
|
}
|
|
|
|
/** Quality proxy for picking the best format at a given height. */
|
|
function score(f: RawFormat): number {
|
|
return (f.tbr ?? 0) + (f.ext === 'mp4' ? 0.5 : 0)
|
|
}
|
|
|
|
function toOption(f: RawFormat): FormatOption {
|
|
const size = f.filesize ?? f.filesize_approx
|
|
const fpsTag = f.fps && f.fps > 30 ? String(Math.round(f.fps)) : ''
|
|
const sizeLabel = size ? fmtBytes(size) : undefined
|
|
const parts = [`${f.height}p${fpsTag}`, f.ext, sizeLabel].filter(Boolean) as string[]
|
|
return {
|
|
id: f.format_id,
|
|
label: parts.join(' · '),
|
|
height: f.height,
|
|
ext: f.ext,
|
|
filesizeLabel: sizeLabel,
|
|
hasAudio: !!f.acodec && f.acodec !== 'none'
|
|
}
|
|
}
|
|
|
|
/** One option per distinct height (best at that height), best-first, plus auto. */
|
|
function buildVideoFormats(raw: RawFormat[]): FormatOption[] {
|
|
const bestByHeight = new Map<number, RawFormat>()
|
|
for (const f of raw) {
|
|
if (!f.vcodec || f.vcodec === 'none' || !f.height) continue
|
|
const cur = bestByHeight.get(f.height)
|
|
if (!cur || score(f) > score(cur)) bestByHeight.set(f.height, f)
|
|
}
|
|
const options = [...bestByHeight.values()]
|
|
.sort((a, b) => (b.height ?? 0) - (a.height ?? 0))
|
|
.map(toOption)
|
|
options.unshift({ id: BEST_FORMAT_ID, label: 'Best available', ext: 'mp4', hasAudio: true })
|
|
return options
|
|
}
|
|
|
|
function buildInfo(data: RawInfo): MediaInfo {
|
|
return {
|
|
title: data.title || 'Untitled',
|
|
channel: data.channel || data.uploader || undefined,
|
|
durationLabel: data.duration_string || undefined,
|
|
thumbnail: data.thumbnail || undefined,
|
|
formats: buildVideoFormats(data.formats ?? [])
|
|
}
|
|
}
|
|
|
|
function buildPlaylist(data: RawInfo): PlaylistInfo {
|
|
const entries: PlaylistEntry[] = []
|
|
;(data.entries ?? []).forEach((e, i) => {
|
|
const url = entryUrl(e)
|
|
if (!url) return // skip entries we can't turn into a downloadable URL
|
|
entries.push({
|
|
index: i + 1,
|
|
id: e.id || String(i + 1),
|
|
title: e.title || `Item ${i + 1}`,
|
|
url,
|
|
durationLabel: fmtDuration(e.duration),
|
|
uploader: e.uploader || e.channel || undefined
|
|
})
|
|
})
|
|
return {
|
|
title: data.title || 'Playlist',
|
|
uploader: data.uploader || data.channel || undefined,
|
|
count: entries.length,
|
|
entries
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Probe a URL with `yt-dlp -J --flat-playlist`. Resolves to a single video (with
|
|
* its format list) or, when the URL is a playlist, the flat list of its entries.
|
|
* `--flat-playlist` is a no-op for a lone video, so one call covers both cases.
|
|
*/
|
|
export function probeMedia(url: string): Promise<ProbeResult> {
|
|
const ytdlp = getYtdlpPath()
|
|
if (!existsSync(ytdlp)) {
|
|
return Promise.resolve({
|
|
ok: false,
|
|
error: `yt-dlp.exe not found at ${ytdlp}\nDrop it into resources/bin/ (see the README there).`
|
|
})
|
|
}
|
|
try {
|
|
assertHttpUrl(url)
|
|
} catch (e) {
|
|
return Promise.resolve({ ok: false, error: (e as Error).message })
|
|
}
|
|
|
|
return new Promise((resolve) => {
|
|
execFile(
|
|
ytdlp,
|
|
// `--` terminates option parsing so the URL can never be read as a flag.
|
|
['-J', '--flat-playlist', '--no-warnings', '--', url],
|
|
{ windowsHide: true, maxBuffer: 64 * 1024 * 1024, timeout: 60_000 },
|
|
(err, stdout, stderr) => {
|
|
if (err) {
|
|
// execFile sets `killed` when it terminated the process on timeout.
|
|
const msg = (err as { killed?: boolean }).killed
|
|
? 'Timed out fetching video info. Check the link or your connection.'
|
|
: cleanError(stderr) || err.message
|
|
resolve({ ok: false, error: msg })
|
|
return
|
|
}
|
|
try {
|
|
const data = JSON.parse(stdout) as RawInfo
|
|
if (data._type === 'playlist' || Array.isArray(data.entries)) {
|
|
const playlist = buildPlaylist(data)
|
|
if (playlist.count === 0) {
|
|
resolve({ ok: false, error: 'This playlist has no downloadable entries.' })
|
|
return
|
|
}
|
|
resolve({ ok: true, kind: 'playlist', playlist })
|
|
} else {
|
|
resolve({ ok: true, kind: 'video', info: buildInfo(data) })
|
|
}
|
|
} catch {
|
|
resolve({ ok: false, error: 'Could not parse video info from yt-dlp.' })
|
|
}
|
|
}
|
|
)
|
|
})
|
|
}
|