captions
This commit is contained in:
parent
fda3e02823
commit
f9c8ce8f2c
14
README.md
14
README.md
@ -17,6 +17,7 @@ Test in browser: https://api.u2b.cx/test.html
|
||||
|
||||
- `thumbnails`: set to `1`, `true`, `yes`, `on` or whatever to load thumbnails
|
||||
- `icons`: set to `1`, `true`, `yes`, `on` or whatever to load channel icons
|
||||
- `captions`: set to `1`, `true`, `yes`, `on` or whatever if you need access to closed captioning data
|
||||
|
||||
### Example URL
|
||||
|
||||
@ -52,6 +53,7 @@ JSON object:
|
||||
- `y`: (integer) px from top
|
||||
- `width`: (integer)
|
||||
- `height`: (integer)
|
||||
- `captions_vrcurl`?: (integer) index of vrcurl to get the caption data json
|
||||
- `imagesheet_vrcurl`?: (integer) index of the vrcurl for the collage of thumbnails and/or icons
|
||||
- `nextpage_vrcurl`: (integer) index of the vrcurl that will serve the JSON for the next page of results
|
||||
|
||||
@ -61,7 +63,17 @@ JSON object:
|
||||
- `{pool}`: must be same as pool param in search endpoint.
|
||||
- `{index}`: vrcurl index number
|
||||
|
||||
Response may be 302 redirect to youtube url, `image/png` for imagesheet or `application/json` for next page
|
||||
Response may be 302 redirect to youtube url, `image/png` for imagesheet, `application/json` for next page (see response format above) or caption data:
|
||||
|
||||
### Caption JSON format
|
||||
|
||||
- Array of Object
|
||||
- `name`: (string) caption track name like "English" or "English (auto-generated)"
|
||||
- `id`: (string) id like `.en` or `a.en`
|
||||
- `lines`: Array of Object
|
||||
- `start`: (float) video seconds when the caption is displayed
|
||||
- `dur`: (float) seconds to display the caption
|
||||
- `text`: (string) caption text
|
||||
|
||||
# VRCUrls
|
||||
|
||||
|
||||
@ -67,13 +67,14 @@ async function VRCYoutubeSearch(pool, query, options = {}) {
|
||||
height: iconHeight
|
||||
};
|
||||
}
|
||||
if (options.captions) {
|
||||
video.captions_vrcurl = await putVrcUrl(pool, {type: "captions", videoId: video.id});
|
||||
}
|
||||
delete video.thumbnailUrl;
|
||||
delete video.channel.iconUrl;
|
||||
data.results.push(video);
|
||||
}
|
||||
|
||||
|
||||
|
||||
if (continuationData) data.nextpage_vrcurl = await putVrcUrl(pool, {
|
||||
type: "ytContinuation",
|
||||
continuationData,
|
||||
|
||||
8
app.js
8
app.js
@ -4,6 +4,7 @@ import send from "koa-send";
|
||||
import { cachedVRCYoutubeSearch } from "./VRCYoutubeSearch.js"
|
||||
import { getImageSheet } from "./imagesheet.js";
|
||||
import { resolveVrcUrl } from "./vrcurl.js";
|
||||
import { getVideoCaptionsCached } from "./captions.js";
|
||||
import { stringToBoolean } from "./util.js";
|
||||
|
||||
export var app = new Koa();
|
||||
@ -26,7 +27,8 @@ router.get("/search", async ctx => {
|
||||
|
||||
var options = {
|
||||
thumbnails: stringToBoolean(ctx.query.thumbnails),
|
||||
icons: stringToBoolean(ctx.query.icons)
|
||||
icons: stringToBoolean(ctx.query.icons),
|
||||
captions: stringToBoolean(ctx.query.captions)
|
||||
};
|
||||
|
||||
ctx.body = await cachedVRCYoutubeSearch(ctx.query.pool, query, options);
|
||||
@ -55,6 +57,9 @@ router.get("/vrcurl/:pool/:num", async ctx => {
|
||||
case "ytContinuation":
|
||||
ctx.body = await cachedVRCYoutubeSearch(ctx.params.pool, dest.continuationData, dest.options);
|
||||
break;
|
||||
case "captions":
|
||||
ctx.body = await getVideoCaptionsCached(dest.videoId);
|
||||
break;
|
||||
default:
|
||||
ctx.status = 500;
|
||||
}
|
||||
@ -90,7 +95,6 @@ app.use(async (ctx, next) => {
|
||||
}
|
||||
})(ctx.body);
|
||||
ctx.body = JSON.stringify(ctx.body).replaceAll("\\\\u", "\\u");
|
||||
ctx.type = "json";
|
||||
});
|
||||
|
||||
app.use(router.routes());
|
||||
|
||||
43
captions.js
Normal file
43
captions.js
Normal file
@ -0,0 +1,43 @@
|
||||
import { XMLParser } from "fast-xml-parser";
|
||||
|
||||
var xmlParser = new XMLParser({
|
||||
ignoreAttributes: false
|
||||
});
|
||||
|
||||
async function getVideoData(videoId) {
|
||||
var html = await fetch(`https://www.youtube.com/watch?v=${videoId}`).then(res => res.text());
|
||||
|
||||
var ytInitialPlayerResponse = html.match(/var ytInitialPlayerResponse = ({.*});/)[1];
|
||||
ytInitialPlayerResponse = JSON.parse(ytInitialPlayerResponse);
|
||||
|
||||
return ytInitialPlayerResponse;
|
||||
}
|
||||
|
||||
async function getVideoCaptions(videoId) {
|
||||
var ytInitialPlayerResponse = await getVideoData(videoId);
|
||||
if (!ytInitialPlayerResponse.captions) return [];
|
||||
var captionTracks = ytInitialPlayerResponse.captions.playerCaptionsTracklistRenderer.captionTracks;
|
||||
captionTracks = await Promise.all(captionTracks.map(captionTrack => (async () => {
|
||||
var xml = await fetch(captionTrack.baseUrl).then(res => res.text());
|
||||
var parsed = xmlParser.parse(xml);
|
||||
var lines = parsed.transcript.text.map(({ "#text": text, "@_start": start, "@_dur": dur }) => ({ start: Number(start), dur: Number(dur), text }));
|
||||
return {
|
||||
name: captionTrack.name.simpleText,
|
||||
id: captionTrack.vssId,
|
||||
lines
|
||||
};
|
||||
})().catch(error => console.error(error.stack))));
|
||||
return captionTracks;
|
||||
}
|
||||
|
||||
var cache = {};
|
||||
|
||||
export async function getVideoCaptionsCached(videoId) {
|
||||
if (!cache[videoId]) {
|
||||
cache[videoId] = getVideoCaptions(videoId);
|
||||
setTimeout(() => {
|
||||
delete cache[videoId];
|
||||
}, 1000*60*60*6); // 6 hours
|
||||
}
|
||||
return await cache[videoId];
|
||||
}
|
||||
90
package-lock.json
generated
90
package-lock.json
generated
@ -8,10 +8,10 @@
|
||||
"@keyv/sqlite": "^3.6.6",
|
||||
"@koa/router": "^12.0.1",
|
||||
"canvas": "^2.11.2",
|
||||
"fast-xml-parser": "^4.3.4",
|
||||
"keyv": "^4.5.4",
|
||||
"koa": "^2.14.2",
|
||||
"koa-send": "^5.0.1",
|
||||
"node-fetch": "^3.3.2"
|
||||
"koa-send": "^5.0.1"
|
||||
}
|
||||
},
|
||||
"node_modules/@gar/promisify": {
|
||||
@ -362,14 +362,6 @@
|
||||
"node": ">= 0.8"
|
||||
}
|
||||
},
|
||||
"node_modules/data-uri-to-buffer": {
|
||||
"version": "4.0.1",
|
||||
"resolved": "https://registry.npmjs.org/data-uri-to-buffer/-/data-uri-to-buffer-4.0.1.tgz",
|
||||
"integrity": "sha512-0R9ikRb668HB7QDxT1vkpuUBtqc53YyAwMwGeUFKRojY/NWKvdZ+9UYtRfGmhqNbRkTSVpMbmyhXipFFv2cb/A==",
|
||||
"engines": {
|
||||
"node": ">= 12"
|
||||
}
|
||||
},
|
||||
"node_modules/debug": {
|
||||
"version": "4.3.4",
|
||||
"resolved": "https://registry.npmjs.org/debug/-/debug-4.3.4.tgz",
|
||||
@ -491,37 +483,25 @@
|
||||
"resolved": "https://registry.npmjs.org/escape-html/-/escape-html-1.0.3.tgz",
|
||||
"integrity": "sha512-NiSupZ4OeuGwr68lGIeym/ksIZMJodUGOSCZ/FSnTxcrekbvqrgdUxlJOMpijaKZVjAJrWrGs/6Jy8OMuyj9ow=="
|
||||
},
|
||||
"node_modules/fetch-blob": {
|
||||
"version": "3.2.0",
|
||||
"resolved": "https://registry.npmjs.org/fetch-blob/-/fetch-blob-3.2.0.tgz",
|
||||
"integrity": "sha512-7yAQpD2UMJzLi1Dqv7qFYnPbaPx7ZfFK6PiIxQ4PfkGPyNyl2Ugx+a/umUonmKqjhM4DnfbMvdX6otXq83soQQ==",
|
||||
"node_modules/fast-xml-parser": {
|
||||
"version": "4.3.4",
|
||||
"resolved": "https://registry.npmjs.org/fast-xml-parser/-/fast-xml-parser-4.3.4.tgz",
|
||||
"integrity": "sha512-utnwm92SyozgA3hhH2I8qldf2lBqm6qHOICawRNRFu1qMe3+oqr+GcXjGqTmXTMGE5T4eC03kr/rlh5C1IRdZA==",
|
||||
"funding": [
|
||||
{
|
||||
"type": "github",
|
||||
"url": "https://github.com/sponsors/jimmywarting"
|
||||
"url": "https://github.com/sponsors/NaturalIntelligence"
|
||||
},
|
||||
{
|
||||
"type": "paypal",
|
||||
"url": "https://paypal.me/jimmywarting"
|
||||
"url": "https://paypal.me/naturalintelligence"
|
||||
}
|
||||
],
|
||||
"dependencies": {
|
||||
"node-domexception": "^1.0.0",
|
||||
"web-streams-polyfill": "^3.0.3"
|
||||
"strnum": "^1.0.5"
|
||||
},
|
||||
"engines": {
|
||||
"node": "^12.20 || >= 14.13"
|
||||
}
|
||||
},
|
||||
"node_modules/formdata-polyfill": {
|
||||
"version": "4.0.10",
|
||||
"resolved": "https://registry.npmjs.org/formdata-polyfill/-/formdata-polyfill-4.0.10.tgz",
|
||||
"integrity": "sha512-buewHzMvYL29jdeQTVILecSaZKnt/RJWjoZCF5OW60Z67/GmSLBkOFM7qh1PI3zFNtJbaZL5eQu1vLfazOwj4g==",
|
||||
"dependencies": {
|
||||
"fetch-blob": "^3.1.2"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=12.20.0"
|
||||
"bin": {
|
||||
"fxparser": "src/cli/cli.js"
|
||||
}
|
||||
},
|
||||
"node_modules/fresh": {
|
||||
@ -1102,41 +1082,6 @@
|
||||
"resolved": "https://registry.npmjs.org/node-addon-api/-/node-addon-api-4.3.0.tgz",
|
||||
"integrity": "sha512-73sE9+3UaLYYFmDsFZnqCInzPyh3MqIwZO9cw58yIqAZhONrrabrYyYe3TuIqtIiOuTXVhsGau8hcrhhwSsDIQ=="
|
||||
},
|
||||
"node_modules/node-domexception": {
|
||||
"version": "1.0.0",
|
||||
"resolved": "https://registry.npmjs.org/node-domexception/-/node-domexception-1.0.0.tgz",
|
||||
"integrity": "sha512-/jKZoMpw0F8GRwl4/eLROPA3cfcXtLApP0QzLmUT/HuPCZWyB7IY9ZrMeKw2O/nFIqPQB3PVM9aYm0F312AXDQ==",
|
||||
"funding": [
|
||||
{
|
||||
"type": "github",
|
||||
"url": "https://github.com/sponsors/jimmywarting"
|
||||
},
|
||||
{
|
||||
"type": "github",
|
||||
"url": "https://paypal.me/jimmywarting"
|
||||
}
|
||||
],
|
||||
"engines": {
|
||||
"node": ">=10.5.0"
|
||||
}
|
||||
},
|
||||
"node_modules/node-fetch": {
|
||||
"version": "3.3.2",
|
||||
"resolved": "https://registry.npmjs.org/node-fetch/-/node-fetch-3.3.2.tgz",
|
||||
"integrity": "sha512-dRB78srN/l6gqWulah9SrxeYnxeddIG30+GOqK/9OlLVyLg3HPnr6SqOWTWOXKRwC2eGYCkZ59NNuSgvSrpgOA==",
|
||||
"dependencies": {
|
||||
"data-uri-to-buffer": "^4.0.0",
|
||||
"fetch-blob": "^3.1.4",
|
||||
"formdata-polyfill": "^4.0.10"
|
||||
},
|
||||
"engines": {
|
||||
"node": "^12.20.0 || ^14.13.1 || >=16.0.0"
|
||||
},
|
||||
"funding": {
|
||||
"type": "opencollective",
|
||||
"url": "https://opencollective.com/node-fetch"
|
||||
}
|
||||
},
|
||||
"node_modules/node-gyp": {
|
||||
"version": "8.4.1",
|
||||
"resolved": "https://registry.npmjs.org/node-gyp/-/node-gyp-8.4.1.tgz",
|
||||
@ -1595,6 +1540,11 @@
|
||||
"node": ">=8"
|
||||
}
|
||||
},
|
||||
"node_modules/strnum": {
|
||||
"version": "1.0.5",
|
||||
"resolved": "https://registry.npmjs.org/strnum/-/strnum-1.0.5.tgz",
|
||||
"integrity": "sha512-J8bbNyKKXl5qYcR36TIO8W3mVGVHrmmxsd5PAItGkmyzwJvybiw2IVq5nqd0i4LSNSkB/sx9VHllbfFdr9k1JA=="
|
||||
},
|
||||
"node_modules/tar": {
|
||||
"version": "6.2.0",
|
||||
"resolved": "https://registry.npmjs.org/tar/-/tar-6.2.0.tgz",
|
||||
@ -1683,14 +1633,6 @@
|
||||
"node": ">= 0.8"
|
||||
}
|
||||
},
|
||||
"node_modules/web-streams-polyfill": {
|
||||
"version": "3.2.1",
|
||||
"resolved": "https://registry.npmjs.org/web-streams-polyfill/-/web-streams-polyfill-3.2.1.tgz",
|
||||
"integrity": "sha512-e0MO3wdXWKrLbL0DgGnUV7WHVuw9OUvL4hjgnPkIeEvESk74gAITi5G606JtZPp39cd8HA9VQzCIvA49LpPN5Q==",
|
||||
"engines": {
|
||||
"node": ">= 8"
|
||||
}
|
||||
},
|
||||
"node_modules/webidl-conversions": {
|
||||
"version": "3.0.1",
|
||||
"resolved": "https://registry.npmjs.org/webidl-conversions/-/webidl-conversions-3.0.1.tgz",
|
||||
|
||||
@ -3,10 +3,13 @@
|
||||
"@keyv/sqlite": "^3.6.6",
|
||||
"@koa/router": "^12.0.1",
|
||||
"canvas": "^2.11.2",
|
||||
"fast-xml-parser": "^4.3.4",
|
||||
"keyv": "^4.5.4",
|
||||
"koa": "^2.14.2",
|
||||
"koa-send": "^5.0.1",
|
||||
"node-fetch": "^3.3.2"
|
||||
"koa-send": "^5.0.1"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=18.0.0"
|
||||
},
|
||||
"type": "module"
|
||||
}
|
||||
|
||||
@ -1,5 +1,3 @@
|
||||
var fetch = global.fetch || (await import("node-fetch")).default;
|
||||
|
||||
|
||||
export async function searchYouTubeVideos(query) {
|
||||
var url = `https://www.youtube.com/results?search_query=${encodeURIComponent(query.replaceAll(' ', '+'))}&sp=EgIQAQ%253D%253D`;
|
||||
@ -69,16 +67,3 @@ function parseVideoRendererData(data) {
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
|
||||
|
||||
/*
|
||||
var page1 = await searchYouTubeVideos("test video");
|
||||
console.log("page1", page1);
|
||||
var page2 = await continueYouTubeVideoSearch(page1.continuationData);
|
||||
console.log("page2", page2);
|
||||
var page3 = await continueYouTubeVideoSearch(page2.continuationData);
|
||||
console.log("page3", page3);
|
||||
console.log("videos", [...page1.videos, ...page2.videos, ...page3.videos]);
|
||||
debugger;
|
||||
*/
|
||||
@ -12,6 +12,7 @@
|
||||
<label>search: <input id="input" type="text" value="nyan cat" /></label>
|
||||
<label><input id="thumbnails" type="checkbox" checked>thumbnails</label>
|
||||
<label><input id="icons" type="checkbox" checked>icons</label>
|
||||
<label><input id="captions" type="checkbox" checked>captions</label>
|
||||
<button id="start">start</button>
|
||||
</div>
|
||||
|
||||
@ -26,7 +27,7 @@ var lastData;
|
||||
|
||||
start.onclick = () => {
|
||||
output.innerHTML = "";
|
||||
loadData(`/search?pool=test1000&thumbnails=${thumbnails.checked}&icons=${icons.checked}&input=${encodeURIComponent(input.value)}`);
|
||||
loadData(`/search?pool=test1000&thumbnails=${thumbnails.checked}&icons=${icons.checked}&captions=${captions.checked}&input=${encodeURIComponent(input.value)}`);
|
||||
};
|
||||
nextpage.onclick = () => loadData(`/vrcurl/test1000/${lastData.nextpage_vrcurl}`);
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user