URL

Veja como você pode começar a raspar URLs do Bing.

O bing source foi projetado para recuperar o conteúdo de URLs diretas de várias páginas do Bing. Em vez de enviar vários parâmetros, você pode nos fornecer uma URL direta para a página do Bing المطلوبة. Não removemos nenhum parâmetro nem alteramos suas URLs de nenhuma outra forma.

Exemplos de solicitação

Neste exemplo, fazemos uma solicitação para recuperar um resultado para a URL fornecida.

curl 'https://realtime.oxylabs.io/v1/queries' \
--user 'USERNAME:PASSWORD' \
-H 'Content-Type: application/json' \
-d '{
        "source": "bing",
        "url": "https://www.bing.com/search?q=nike"
    }'

import requests
from pprint import pprint

# Estruture o payload.
payload = {
    'source': 'bing',
    'url': 'https://www.bing.com/search?q=nike'
}

# Obtenha a resposta.
response = requests.request(
    'POST',
    'https://realtime.oxylabs.io/v1/queries',
    auth=('USERNAME', 'PASSWORD'),
    json=payload,
)

# Instead of response with job status and results url, this will return the
# Resposta JSON com resultados.
pprint(response.json())

const https = require("https");

const username = "USERNAME";
const password = "PASSWORD";
const body = {
    source: "bing",
    query: "https://www.bing.com/search?q=nike",
};

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();

# A URL precisa ser codificada para escapar dos caracteres `&` e `=`:
# URL: https://bing.com/search/?text=nike&
# URL codificada: https%3A%2F%2Fbing.com%2Fsearch%2F%3Ftext%3Dnike%26

https://realtime.oxylabs.io/v1/queries?source=bing&url=https%3A%2F%2Fwww.bing.com%2Fsearch%3Fq%3Dnike&access_token=12345abcde

<?php

$params = array(
    'source' => 'bing',
    'url' => 'https://www.bing.com/search?q=nike'
);

$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"

	payload := map[string]interface{}{
		"source": "bing",
		"url":    "https://www.bing.com/search?q=nike",
	}

	jsonValue, _ := json.Marshal(payload)

	client := &http.Client{}
	request, _ := http.NewRequest("POST",
		"https://realtime.oxylabs.io/v1/queries",
		bytes.NewBuffer(jsonValue),
	)

	request.SetBasicAuth(Username, Password)
	response, _ := client.Do(request)

	responseText, _ := ioutil.ReadAll(response.Body)
	fmt.Println(string(responseText))
}

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

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

            var parameters = new {
                source = "bing",
                url = "https://www.bing.com/search?q=nike"
            };

            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(System.Text.ASCIIEncoding.UTF8.GetBytes(authenticationString));
            requestMessage.Headers.Add("Authorization", "Basic " + base64EncodedAuthenticationString);

            var response = await client.SendAsync(requestMessage);
            var contents = await response.Content.ReadAsStringAsync();

            Console.WriteLine(contents);
        }
    }
}

package org.example;

import okhttp3.*;
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() {
        JSONObject jsonObject = new JSONObject();
        jsonObject.put("source", "bing");
        jsonObject.put("url", "https://www.bing.com/search?q=nike");

        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();
    }
}

Exemplo de saída

{
    "results": [
        {
            "content": "<!DOCTYPE html>
            CONTENT
            </html>",
            "created_at": "2024-07-01 08:46:47",
            "updated_at": "2024-07-01 08:46:48",
            "page": 1,
            "url": "https://www.bing.com/search?q=nike",
            "job_id": "7213463035497697281",
            "status_code": 200
        }
    ]
}

Usamos o método de integração Realtime síncrona em nossos exemplos. Se você quiser usar Proxy Endpoint ou a integração assíncrona Push-Pull , consulte a seção métodos de integração .

Valores dos parâmetros da solicitação

Parâmetro

Descrição

Valor padrão

source

Define o scraper.

bing

url

URL direta (link) para a página do Bing

render

Habilita a renderização de JavaScript quando definido como html. Mais informações.

parse

Retorna dados analisados quando definido como true. Limitado a URLs de tipos específicos de páginas do Bing.

callback_url

URL para seu endpoint de callback. Mais informações

user_agent_type

Tipo de dispositivo e navegador. A lista completa pode ser encontrada aqui.

desktop

geo_location

Especifica a localização dos resultados da pesquisa. Suporta formatos de cidade, estado, país ou coordenadas. Leia mais.

- parâmetro obrigatório

AnteriorPesquisa PróximoLLMs e IA

Atualizado há 26 dias

Isto foi útil?

package org.example;

import okhttp3.*;
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() {
        JSONObject jsonObject = new JSONObject();
        jsonObject.put("source", "bing");
        jsonObject.put("url", "https://www.bing.com/search?q=nike");

        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();
    }
}