Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat(media-provider): stream support #671

Merged
merged 3 commits into from
Dec 6, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion packages/metascraper-amazon/package.json
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@
"@metascraper/helpers": "^5.39.0"
},
"devDependencies": {
"ava": "latest"
"ava": "5"
},
"engines": {
"node": ">= 16"
Expand Down
2 changes: 1 addition & 1 deletion packages/metascraper-audio/package.json
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@
"p-reflect": "~2.1.0"
},
"devDependencies": {
"ava": "latest"
"ava": "5"
},
"engines": {
"node": ">= 16"
Expand Down
2 changes: 1 addition & 1 deletion packages/metascraper-clearbit/package.json
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@
"lodash": "~4.17.21"
},
"devDependencies": {
"ava": "latest"
"ava": "5"
},
"engines": {
"node": ">= 16"
Expand Down
2 changes: 1 addition & 1 deletion packages/metascraper-description/package.json
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@
"@metascraper/helpers": "^5.39.0"
},
"devDependencies": {
"ava": "latest"
"ava": "5"
},
"engines": {
"node": ">= 16"
Expand Down
2 changes: 1 addition & 1 deletion packages/metascraper-feed/package.json
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@
"@metascraper/helpers": "^5.39.0"
},
"devDependencies": {
"ava": "latest"
"ava": "5"
},
"engines": {
"node": ">= 16"
Expand Down
2 changes: 1 addition & 1 deletion packages/metascraper-helpers/package.json
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,7 @@
"video-extensions": "~1.2.0"
},
"devDependencies": {
"ava": "latest",
"ava": "5",
"cheerio": "latest"
},
"engines": {
Expand Down
3 changes: 2 additions & 1 deletion packages/metascraper-iframe/package.json
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,8 @@
"p-reflect": "~2.1.0"
},
"devDependencies": {
"ava": "latest",
"ava": "5",
"cacheable-lookup": "6",
"cheerio": "latest"
},
"engines": {
Expand Down
12 changes: 7 additions & 5 deletions packages/metascraper-iframe/test/index.js
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
'use strict'

const CacheableLookup = require('cacheable-lookup')
const { readFile } = require('fs/promises')
const { resolve } = require('path')
const test = require('ava')
Expand All @@ -12,19 +13,20 @@ const createMetascraper = (...args) =>
require('metascraper')([createMetascraperIframe(...args)])

test('provide `gotOpts`', async t => {
const cache = new Map()
console.log('running')
const dnsCache = new CacheableLookup()
const html = await readFile(resolve(__dirname, 'fixtures/genially.html'))
const url = 'https://view.genial.ly/5dc53cfa759d2a0f4c7db5f4'
const metascraper = createMetascraper({ gotOpts: { cache } })
const metascraper = createMetascraper({ gotOpts: { dnsCache } })

const metadataOne = await metascraper({
url,
html,
iframe: { maxWidth: 350 }
})

t.truthy(metadataOne.iframe)
t.is(cache.size, 2)

t.is(dnsCache._cache.size, 2)

const metadataTwo = await metascraper({
url,
Expand All @@ -33,7 +35,7 @@ test('provide `gotOpts`', async t => {
})

t.truthy(metadataTwo.iframe)
t.is(cache.size, 4)
t.is(dnsCache._cache.size, 2)
})

test('provide `iframe`', async t => {
Expand Down
2 changes: 1 addition & 1 deletion packages/metascraper-instagram/package.json
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@
"lodash": "~4.17.21"
},
"devDependencies": {
"ava": "latest"
"ava": "5"
},
"engines": {
"node": ">= 16"
Expand Down
2 changes: 1 addition & 1 deletion packages/metascraper-lang/package.json
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@
"@metascraper/helpers": "^5.39.0"
},
"devDependencies": {
"ava": "latest"
"ava": "5"
},
"engines": {
"node": ">= 16"
Expand Down
2 changes: 1 addition & 1 deletion packages/metascraper-logo-favicon/package.json
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@
"reachable-url": "~1.7.1"
},
"devDependencies": {
"ava": "latest"
"ava": "5"
},
"engines": {
"node": ">= 16"
Expand Down
2 changes: 1 addition & 1 deletion packages/metascraper-manifest/package.json
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@
"lodash": "~4.17.21"
},
"devDependencies": {
"ava": "latest"
"ava": "5"
},
"engines": {
"node": ">= 16"
Expand Down
2 changes: 1 addition & 1 deletion packages/metascraper-media-provider/package.json
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@
},
"devDependencies": {
"@kikobeats/time-span": "latest",
"ava": "latest",
"ava": "5",
"parse-proxy-uri": "latest",
"pretty-ms": "latest",
"unique-random-array": "2"
Expand Down
43 changes: 26 additions & 17 deletions packages/metascraper-media-provider/src/index.js
Original file line number Diff line number Diff line change
Expand Up @@ -68,42 +68,51 @@ const isDownloadable = ({ url }) =>
new URL(url).searchParams.get('download') === '1'

const getFormatUrls =
({ orderBy }) =>
(input, filters) => {
(basicFilters, { orderBy }) =>
(input, extraFilters, { isStream }) => {
const filters = extraFilters.concat(basicFilters({ isStream }))

const formats = get(input, 'formats') ||
get(input, 'entries[0].formats') || [input]

const url = chain(formats)
.filter(overEvery(filters))
.orderBy(orderBy, 'asc')
.map('url')
.map(isStream ? 'manifest_url' : 'url')
.last()
.value()

return !isEmpty(url) ? url : undefined
}

const getVideoUrls = getFormatUrls({ orderBy: 'tbr' })

const getAudioUrls = getFormatUrls({ orderBy: 'abr' })

const VIDEO_FILTERS = [
hasVideo,
isMp4,
const VIDEO_FILTERS = ({ isStream }) =>
[
isStream ? undefined : hasVideo,
isMp4,
isHttps,
negate(isDownloadable),
isStream ? undefined : negate(isM3u8),
negate(isMpd),
isStream ? undefined : hasVideoCodec
].filter(Boolean)

const AUDIO_FILTERS = () => [
hasAudio,
isHttps,
negate(isDownloadable),
negate(isM3u8),
negate(isMpd),
hasVideoCodec
hasAudioCodec
]

const AUDIO_FILTERS = [hasAudio, isHttps, negate(isDownloadable), hasAudioCodec]
const getVideoUrls = getFormatUrls(VIDEO_FILTERS, { orderBy: 'tbr' })

const getAudioUrls = getFormatUrls(AUDIO_FILTERS, { orderBy: 'abr' })

const getVideo = data =>
getVideoUrls(data, [hasAudioCodec, ...VIDEO_FILTERS]) ||
getVideoUrls(data, VIDEO_FILTERS)
getVideoUrls(data, [hasAudioCodec], { isStream: false }) ||
getVideoUrls(data, [], { isStream: false }) ||
getVideoUrls(data, [], { isStream: true })

const getAudio = data => getAudioUrls(data, AUDIO_FILTERS)
const getAudio = data => getAudioUrls(data, [], { isStream: false })

const getAuthor = ({ uploader, creator, uploader_id: uploaderId }) =>
find([creator, uploader, uploaderId], str => authorFn(str))
Expand Down
5 changes: 3 additions & 2 deletions packages/metascraper-media-provider/test/fixtures/generate.js
Original file line number Diff line number Diff line change
Expand Up @@ -6,14 +6,15 @@ const fs = require('fs/promises')

const { getFlags } = require('../../src/get-media/provider/generic')

const [, , url, filename] = process.argv
let [, , url, filename] = process.argv

if (!url) throw new TypeError('process.argv[2] should be an url')
if (!filename) throw new TypeError('process.argv[3] should be a filename')
if (!filename.endsWith('.json')) filename += '.json'
;(async () => {
const flags = getFlags({ url })
const payload = await youtubedl(url, flags)
const filepath = path.resolve(__dirname, 'provider', `${filename}.json`)
const filepath = path.resolve(__dirname, 'provider', filename)
await fs.writeFile(filepath, JSON.stringify(payload, null, 2))
console.log('Done at', filepath, '✨')
})()
Loading