Subtítulos

Extrae subtítulos y closed captions de YouTube por ID de video, con idioma configurable y origen de subtítulos (autogenerados o proporcionados por el uploader).

Puedes obtener subtítulos y closed captions (CC) de YouTube proporcionando el ID de video de YouTube y un language_code al youtube_subtitles source.

Los subtítulos (closed captions) son distintos de las transcripciones. Para extraer transcripciones estándar, usa el YouTube Transcript source.

Solicitudes de ejemplo

El siguiente ejemplo demuestra cómo recuperar closed captions en inglés de un video de YouTube donde los subtítulos fueron proporcionados por el uploader.

curl 'https://realtime.oxylabs.io/v1/queries' \
--user 'USERNAME:PASSWORD' \
-H 'Content-Type: application/json' \
-d '{
        "source": "youtube_subtitles",
        "query": "c4P_YuNnZ7U",
        "context": [
            {
                "key": "language_code",
                "value": "en"
            },
            {
                "key": "subtitle_origin",
                "value": "uploader_provided"
            }
        ]
    }'

import requests
from pprint import pprint

# Estructura del payload.
payload = {
    'source': 'youtube_subtitles',
    'query': 'c4P_YuNnZ7U',
    'context': [
        {
            'key': 'language_code',
            'value': 'en'
        },
        {
            'key': 'subtitle_origin',
            'value': 'uploader_provided'
        }
    ]
}

# Obtener respuesta.
response = requests.request(
    'POST',
    'https://realtime.oxylabs.io/v1/queries',
    auth=('username', 'password'),
    json=payload,
)

# Imprimir la respuesta JSON con el resultado.
pprint(response.json())

const https = require("https");

const username = "USERNAME";
const password = "PASSWORD";
const body = {
    source: "youtube_subtitles",
    query: "c4P_YuNnZ7U",
    context: [
        {
            key: "language_code",
            value: "en",
        },
        {
            key: "subtitle_origin",
            value: "uploader_provided",
        },
    ],
};

const options = {
    hostname: "realtime.oxylabs.io",
    path: "/v1/queries",
    method: "POST",
    headers: {
        "Content-Type": "application/json",
        Authorization:
            "Basic " + Buffer.from(`${username}:${password}`).toString("base64"),
    },
};

const request = https.request(options, (response) => {
    let data = "";

    response.on("data", (chunk) => {
        data += chunk;
    });

    response.on("end", () => {
        const responseData = JSON.parse(data);
        console.log(JSON.stringify(responseData, null, 2));
    });
});

request.on("error", (error) => {
    console.error("Error:", error);
});

request.write(JSON.stringify(body));
request.end();

# Toda la cadena que envíes debe estar codificada en la URL.

https://realtime.oxylabs.io/v1/queries?source=youtube_subtitles&query=c4P_YuNnZ7U&context=%5B%7B%22key%22%3A%22language_code%22%2C%22value%22%3A%22en%22%7D%2C%7B%22key%22%3A%22subtitle_origin%22%2C%22value%22%3A%22uploader_provided%22%7D%5D&access_token=12345abcde

<?php

$params = array(
    'source' => 'youtube_subtitles',
    'query' => 'c4P_YuNnZ7U',
    'context' => array(
        array(
            'key' => 'language_code',
            'value' => 'en'
        ),
        array(
            'key' => 'subtitle_origin',
            'value' => 'uploader_provided'
        )
    )
);

$ch = curl_init();

curl_setopt($ch, CURLOPT_URL, "https://realtime.oxylabs.io/v1/queries");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($params));
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_USERPWD, "USERNAME" . ":" . "PASSWORD");

$headers = array();
$headers[] = "Content-Type: application/json";
curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);

$result = curl_exec($ch);
echo $result;

if (curl_errno($ch)) {
    echo 'Error:' . curl_error($ch);
}

curl_close($ch);

package main

import (
	"bytes"
	"encoding/json"
	"fmt"
	"io/ioutil"
	"net/http"
)

func main() {
	const Username = "USERNAME"
	const Password = "PASSWORD"

	// Define el payload con los parámetros query y context.
	payload := map[string]interface{}{
		"source": "youtube_subtitles",
		"query":  "c4P_YuNnZ7U",
		"context": []map[string]string{
			{
				"key":   "language_code",
				"value": "en",
			},
			{
				"key":   "subtitle_origin",
				"value": "uploader_provided",
			},
		},
	}

	jsonValue, err := json.Marshal(payload)
	if err != nil {
		fmt.Println("Error al serializar JSON:", err)
		return
	}

	client := &http.Client{}
	request, err := http.NewRequest("POST", "https://realtime.oxylabs.io/v1/queries", bytes.NewBuffer(jsonValue))
	if err != nil {
		fmt.Println("Error creando la solicitud:", err)
		return
	}

	request.SetBasicAuth(Username, Password)
	request.Header.Set("Content-Type", "application/json")

	response, err := client.Do(request)
	if err != nil {
		fmt.Println("Error realizando la solicitud:", err)
		return
	}
	defer response.Body.Close()

	responseText, err := ioutil.ReadAll(response.Body)
	if err != nil {
		fmt.Println("Error leyendo la respuesta:", err)
		return
	}

	fmt.Println(string(responseText))
}

using System;
using System.Collections.Generic;
using System.Net.Http;
using System.Net.Http.Json;
using System.Text;
using System.Threading.Tasks;

namespace OxyApi
{
    class Program
    {
        static async Task Main()
        {
            const string Username = "USERNAME";
            const string Password = "PASSWORD";

            var parameters = new
            {
                source = "youtube_subtitles",
                query = "c4P_YuNnZ7U",
                context = new[]
                {
                    new { key = "language_code", value = "en" },
                    new { key = "subtitle_origin", value = "uploader_provided" }
                }
            };

            var client = new HttpClient();

            Uri baseUri = new Uri("https://realtime.oxylabs.io");
            client.BaseAddress = baseUri;

            var requestMessage = new HttpRequestMessage(HttpMethod.Post, "/v1/queries");
            requestMessage.Content = JsonContent.Create(parameters);

            var authenticationString = $"{Username}:{Password}";
            var base64EncodedAuthenticationString = Convert.ToBase64String(Encoding.UTF8.GetBytes(authenticationString));
            requestMessage.Headers.Add("Authorization", "Basic " + base64EncodedAuthenticationString);

            try
            {
                var response = await client.SendAsync(requestMessage);
                response.EnsureSuccessStatusCode();

                var contents = await response.Content.ReadAsStringAsync();
                Console.WriteLine(contents);
            }
            catch (HttpRequestException e)
            {
                Console.WriteLine($"Request error: {e.Message}");
            }
        }
    }
}

package org.example;

import okhttp3.*;
import org.json.JSONArray;
import org.json.JSONObject;
import java.util.concurrent.TimeUnit;

public class Main implements Runnable {
    private static final String AUTHORIZATION_HEADER = "Authorization";
    public static final String USERNAME = "USERNAME";
    public static final String PASSWORD = "PASSWORD";

    public void run() {
        // Construir el payload JSON con los parámetros de contexto
        JSONObject jsonObject = new JSONObject();
        jsonObject.put("source", "youtube_subtitles");
        jsonObject.put("query", "c4P_YuNnZ7U");

        JSONArray contextArray = new JSONArray();
        contextArray.put(new JSONObject().put("key", "language_code").put("value", "en"));
        contextArray.put(new JSONObject().put("key", "subtitle_origin").put("value", "uploader_provided"));

        jsonObject.put("context", contextArray);

        Authenticator authenticator = (route, response) -> {
            String credential = Credentials.basic(USERNAME, PASSWORD);
            return response
                    .request()
                    .newBuilder()
                    .header(AUTHORIZATION_HEADER, credential)
                    .build();
        };

        var client = new OkHttpClient.Builder()
                .authenticator(authenticator)
                .readTimeout(180, TimeUnit.SECONDS)
                .build();

        var mediaType = MediaType.parse("application/json; charset=utf-8");
        var body = RequestBody.create(jsonObject.toString(), mediaType);
        var request = new Request.Builder()
                .url("https://realtime.oxylabs.io/v1/queries")
                .post(body)
                .build();

        try (var response = client.newCall(request).execute()) {
            if (response.body() != null) {
                try (var responseBody = response.body()) {
                    System.out.println(responseBody.string());
                }
            }
        } catch (Exception exception) {
            System.out.println("Error: " + exception.getMessage());
        }

        System.exit(0);
    }

    public static void main(String[] args) {
        new Thread(new Main()).start();
    }
}

{
    "source": "youtube_subtitles",
    "query": "c4P_YuNnZ7U",
    "context": [
        {
            "key": "language_code",
            "value": "en"
        },
        {
            "key": "subtitle_origin",
            "value": "uploader_provided"
        }
    ]
}

Nuestros ejemplos usan Realtime método de integración. Si deseas usar Proxy Endpoint, o la integración asíncrona Push-Pull consulte la Integration Methods sección.

23KB

YT_subtitles_output.json

Abrir

Valores de parámetros de la solicitud

Genérico

Parámetro

Descripción

Valor por defecto

source

Configura el scraper.

youtube_subtitles

query

ID de video de YouTube.

–

context: language_code

Especifica el idioma de los subtítulos. Encuentra los valores disponibles here. NOTA: Si el language_code no tiene subtítulos / closed captions coincidentes en el video de YouTube, el resultado devuelve un 404 status.

–

context: subtitle_origin

Especifica si recuperar subtítulos que son auto_generated u uploader_provided.

–

callback_url

URL de su endpoint de callback. Más información.

–

– parámetro obligatorio

AnteriorTranscripción SiguienteCanal

Última actualización hace 1 día

¿Te fue útil?

Buenas noches

hashtagSolicitudes de ejemplo

hashtagValores de parámetros de la solicitud

hashtagGenérico

Solicitudes de ejemplo

Valores de parámetros de la solicitud

Genérico