PeerTube/server/core/helpers/youtube-dl/youtube-dl-info-builder.ts

208 lines
5.4 KiB
TypeScript
Raw Normal View History

import { CONSTRAINTS_FIELDS, VIDEO_CATEGORIES, VIDEO_LANGUAGES, VIDEO_LICENCES } from '../../initializers/constants.js'
import { peertubeTruncate } from '../core-utils.js'
import { isUrlValid } from '../custom-validators/activitypub/misc.js'
2023-08-28 10:55:04 +02:00
import { isArray } from '../custom-validators/misc.js'
export type YoutubeDLInfo = {
name?: string
description?: string
category?: number
language?: string
licence?: number
nsfw?: boolean
tags?: string[]
thumbnailUrl?: string
ext?: string
2022-09-16 09:37:07 +02:00
originallyPublishedAtWithoutTime?: Date
Channel sync (#5135) * Add external channel URL for channel update / creation (#754) * Disallow synchronisation if user has no video quota (#754) * More constraints serverside (#754) * Disable sync if server configuration does not allow HTTP import (#754) * Working version synchronizing videos with a job (#754) TODO: refactoring, too much code duplication * More logs and try/catch (#754) * Fix eslint error (#754) * WIP: support synchronization time change (#754) * New frontend #754 * WIP: Create sync front (#754) * Enhance UI, sync creation form (#754) * Warning message when HTTP upload is disallowed * More consistent names (#754) * Binding Front with API (#754) * Add a /me API (#754) * Improve list UI (#754) * Implement creation and deletion routes (#754) * Lint (#754) * Lint again (#754) * WIP: UI for triggering import existing videos (#754) * Implement jobs for syncing and importing channels * Don't sync videos before sync creation + avoid concurrency issue (#754) * Cleanup (#754) * Cleanup: OpenAPI + API rework (#754) * Remove dead code (#754) * Eslint (#754) * Revert the mess with whitespaces in constants.ts (#754) * Some fixes after rebase (#754) * Several fixes after PR remarks (#754) * Front + API: Rename video-channels-sync to video-channel-syncs (#754) * Allow enabling channel sync through UI (#754) * getChannelInfo (#754) * Minor fixes: openapi + model + sql (#754) * Simplified API validators (#754) * Rename MChannelSync to MChannelSyncChannel (#754) * Add command for VideoChannelSync (#754) * Use synchronization.enabled config (#754) * Check parameters test + some fixes (#754) * Fix conflict mistake (#754) * Restrict access to video channel sync list API (#754) * Start adding unit test for synchronization (#754) * Continue testing (#754) * Tests finished + convertion of job to scheduler (#754) * Add lastSyncAt field (#754) * Fix externalRemoteUrl sort + creation date not well formatted (#754) * Small fix (#754) * Factorize addYoutubeDLImport and buildVideo (#754) * Check duplicates on channel not on users (#754) * factorize thumbnail generation (#754) * Fetch error should return status 400 (#754) * Separate video-channel-import and video-channel-sync-latest (#754) * Bump DB migration version after rebase (#754) * Prettier states in UI table (#754) * Add DefaultScope in VideoChannelSyncModel (#754) * Fix audit logs (#754) * Ensure user can upload when importing channel + minor fixes (#754) * Mark synchronization as failed on exception + typos (#754) * Change REST API for importing videos into channel (#754) * Add option for fully synchronize a chnanel (#754) * Return a whole sync object on creation to avoid tricks in Front (#754) * Various remarks (#754) * Single quotes by default (#754) * Rename synchronization to video_channel_synchronization * Add check.latest_videos_count and max_per_user options (#754) * Better channel rendering in list #754 * Allow sorting with channel name and state (#754) * Add missing tests for channel imports (#754) * Prefer using a parent job for channel sync * Styling * Client styling Co-authored-by: Chocobozzz <me@florianbigard.com>
2022-08-10 09:53:39 +02:00
webpageUrl?: string
urls?: string[]
2023-08-28 10:55:04 +02:00
chapters?: {
timecode: number
title: string
}[]
}
export class YoutubeDLInfoBuilder {
private readonly info: any
constructor (info: any) {
this.info = { ...info }
}
getInfo () {
const obj = this.buildVideoInfo(this.normalizeObject(this.info))
if (obj.name && obj.name.length < CONSTRAINTS_FIELDS.VIDEOS.NAME.min) obj.name += ' video'
return obj
}
private normalizeObject (obj: any) {
const newObj: any = {}
for (const key of Object.keys(obj)) {
// Deprecated key
if (key === 'resolution') continue
const value = obj[key]
if (typeof value === 'string') {
newObj[key] = value.normalize()
} else {
newObj[key] = value
}
}
return newObj
}
private buildOriginallyPublishedAt (obj: any) {
let originallyPublishedAt: Date = null
const uploadDateMatcher = /^(\d{4})(\d{2})(\d{2})$/.exec(obj.upload_date)
if (uploadDateMatcher) {
originallyPublishedAt = new Date()
originallyPublishedAt.setHours(0, 0, 0, 0)
const year = parseInt(uploadDateMatcher[1], 10)
// Month starts from 0
const month = parseInt(uploadDateMatcher[2], 10) - 1
const day = parseInt(uploadDateMatcher[3], 10)
originallyPublishedAt.setFullYear(year, month, day)
}
return originallyPublishedAt
}
private buildVideoInfo (obj: any): YoutubeDLInfo {
return {
name: this.titleTruncation(obj.title),
description: this.descriptionTruncation(obj.description),
category: this.getCategory(obj.categories),
licence: this.getLicence(obj.license),
language: this.getLanguage(obj.language),
nsfw: this.isNSFW(obj),
tags: this.getTags(obj.tags),
thumbnailUrl: obj.thumbnail || undefined,
urls: this.buildAvailableUrl(obj),
2022-09-16 09:37:07 +02:00
originallyPublishedAtWithoutTime: this.buildOriginallyPublishedAt(obj),
Channel sync (#5135) * Add external channel URL for channel update / creation (#754) * Disallow synchronisation if user has no video quota (#754) * More constraints serverside (#754) * Disable sync if server configuration does not allow HTTP import (#754) * Working version synchronizing videos with a job (#754) TODO: refactoring, too much code duplication * More logs and try/catch (#754) * Fix eslint error (#754) * WIP: support synchronization time change (#754) * New frontend #754 * WIP: Create sync front (#754) * Enhance UI, sync creation form (#754) * Warning message when HTTP upload is disallowed * More consistent names (#754) * Binding Front with API (#754) * Add a /me API (#754) * Improve list UI (#754) * Implement creation and deletion routes (#754) * Lint (#754) * Lint again (#754) * WIP: UI for triggering import existing videos (#754) * Implement jobs for syncing and importing channels * Don't sync videos before sync creation + avoid concurrency issue (#754) * Cleanup (#754) * Cleanup: OpenAPI + API rework (#754) * Remove dead code (#754) * Eslint (#754) * Revert the mess with whitespaces in constants.ts (#754) * Some fixes after rebase (#754) * Several fixes after PR remarks (#754) * Front + API: Rename video-channels-sync to video-channel-syncs (#754) * Allow enabling channel sync through UI (#754) * getChannelInfo (#754) * Minor fixes: openapi + model + sql (#754) * Simplified API validators (#754) * Rename MChannelSync to MChannelSyncChannel (#754) * Add command for VideoChannelSync (#754) * Use synchronization.enabled config (#754) * Check parameters test + some fixes (#754) * Fix conflict mistake (#754) * Restrict access to video channel sync list API (#754) * Start adding unit test for synchronization (#754) * Continue testing (#754) * Tests finished + convertion of job to scheduler (#754) * Add lastSyncAt field (#754) * Fix externalRemoteUrl sort + creation date not well formatted (#754) * Small fix (#754) * Factorize addYoutubeDLImport and buildVideo (#754) * Check duplicates on channel not on users (#754) * factorize thumbnail generation (#754) * Fetch error should return status 400 (#754) * Separate video-channel-import and video-channel-sync-latest (#754) * Bump DB migration version after rebase (#754) * Prettier states in UI table (#754) * Add DefaultScope in VideoChannelSyncModel (#754) * Fix audit logs (#754) * Ensure user can upload when importing channel + minor fixes (#754) * Mark synchronization as failed on exception + typos (#754) * Change REST API for importing videos into channel (#754) * Add option for fully synchronize a chnanel (#754) * Return a whole sync object on creation to avoid tricks in Front (#754) * Various remarks (#754) * Single quotes by default (#754) * Rename synchronization to video_channel_synchronization * Add check.latest_videos_count and max_per_user options (#754) * Better channel rendering in list #754 * Allow sorting with channel name and state (#754) * Add missing tests for channel imports (#754) * Prefer using a parent job for channel sync * Styling * Client styling Co-authored-by: Chocobozzz <me@florianbigard.com>
2022-08-10 09:53:39 +02:00
ext: obj.ext,
2023-08-28 10:55:04 +02:00
webpageUrl: obj.webpage_url,
chapters: isArray(obj.chapters)
? obj.chapters.map((c: { start_time: number, title: string }) => ({ timecode: c.start_time, title: c.title }))
: []
}
}
private buildAvailableUrl (obj: any) {
const urls: string[] = []
if (obj.url) urls.push(obj.url)
if (obj.urls) {
if (Array.isArray(obj.urls)) urls.push(...obj.urls)
else urls.push(obj.urls)
}
const formats = Array.isArray(obj.formats)
? obj.formats
: []
for (const format of formats) {
if (!format.url) continue
urls.push(format.url)
}
const thumbnails = Array.isArray(obj.thumbnails)
? obj.thumbnails
: []
for (const thumbnail of thumbnails) {
if (!thumbnail.url) continue
urls.push(thumbnail.url)
}
if (obj.thumbnail) urls.push(obj.thumbnail)
for (const subtitleKey of Object.keys(obj.subtitles || {})) {
const subtitles = obj.subtitles[subtitleKey]
if (!Array.isArray(subtitles)) continue
for (const subtitle of subtitles) {
if (!subtitle.url) continue
urls.push(subtitle.url)
}
}
return urls.filter(u => u && isUrlValid(u))
}
private titleTruncation (title: string) {
return peertubeTruncate(title, {
length: CONSTRAINTS_FIELDS.VIDEOS.NAME.max,
separator: /,? +/,
omission: ' […]'
})
}
private descriptionTruncation (description: string) {
if (!description || description.length < CONSTRAINTS_FIELDS.VIDEOS.DESCRIPTION.min) return undefined
return peertubeTruncate(description, {
length: CONSTRAINTS_FIELDS.VIDEOS.DESCRIPTION.max,
separator: /,? +/,
omission: ' […]'
})
}
private isNSFW (info: any) {
return info?.age_limit >= 16
}
private getTags (tags: string[]) {
if (Array.isArray(tags) === false) return []
return tags
.filter(t => t.length < CONSTRAINTS_FIELDS.VIDEOS.TAG.max && t.length > CONSTRAINTS_FIELDS.VIDEOS.TAG.min)
.map(t => t.normalize())
.slice(0, 5)
}
private getLicence (licence: string) {
if (!licence) return undefined
if (licence.includes('Creative Commons Attribution')) return 1
for (const key of Object.keys(VIDEO_LICENCES)) {
const peertubeLicence = VIDEO_LICENCES[key]
if (peertubeLicence.toLowerCase() === licence.toLowerCase()) return parseInt(key, 10)
}
return undefined
}
private getCategory (categories: string[]) {
if (!categories) return undefined
const categoryString = categories[0]
if (!categoryString || typeof categoryString !== 'string') return undefined
if (categoryString === 'News & Politics') return 11
for (const key of Object.keys(VIDEO_CATEGORIES)) {
const category = VIDEO_CATEGORIES[key]
if (categoryString.toLowerCase() === category.toLowerCase()) return parseInt(key, 10)
}
return undefined
}
private getLanguage (language: string) {
return VIDEO_LANGUAGES[language] ? language : undefined
}
}