卖家

使用 Oxylabs 网页爬虫API 爬取 Amazon 卖家页面。通过 JS 渲染、地理定位和代码示例获取评分、反馈、资料数据等。

该 amazon_sellers 数据源用于检索 Amazon 卖家页面。

探索输出 数据字典 针对卖家，提供简要描述、截图、解析后的 JSON 代码片段，以及定义每个解析字段的表格。使用右侧导航或向下滚动页面浏览详细信息。

请求示例

在下面的代码示例中，我们发出请求以检索卖家 ID 的卖家页面 A2MUQS6AX5GGR 在 amazon.de 市场。

curl 'https://realtime.oxylabs.io/v1/queries' \
--user 'USERNAME:PASSWORD' \
-H 'Content-Type: application/json' \
-d '{
        "source": "amazon_sellers", 
        "domain": "de", 
        "query": "A2MUQS6AX5GGR",
        "parse": true
    }'

import requests
from pprint import pprint


# 结构化负载。
payload = {
    'source': 'amazon_sellers',
    'domain': 'de',
    'query': 'A2MUQS6AX5GGR',
    'parse': True
}


# 获取响应。
response = requests.request(
    'POST',
    'https://realtime.oxylabs.io/v1/queries',
    auth=('USERNAME', 'PASSWORD'),
    json=payload,
)

# 将美化后的响应打印到 stdout。
pprint(response.json())

const https = require("https");

const username = "USERNAME";
const password = "PASSWORD";
const body = {
    source: "amazon_sellers",
    domain: "de",
    query: "A2MUQS6AX5GGR",
    parse: true,
};

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();

<?php

$params = array(
    'source' => 'amazon_sellers',
    'domain' => 'de',
    'query' => 'A2MUQS6AX5GGR',
    'parse' => true
);

$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": "amazon_sellers",
		"domain": "de",
		"query":  "A2MUQS6AX5GGR",
		"parse":  true,
	}

	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 = "amazon_sellers",
                domain = "de",
                query = "A2MUQS6AX5GGR",
                parse = true
            };

            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", "amazon_sellers");
        jsonObject.put("domain", "de");
        jsonObject.put("query", "A2MUQS6AX5GGR");
        jsonObject.put("parse", true);

        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();
    }
}

我们在示例中使用同步的 Realtime 集成方法。如果您希望使用 Proxy Endpoint 或异步的 Push-Pull 集成，请参阅 集成方法 部分。

请求参数值

通用

抓取 Amazon 卖家页面的基本设置和自定义选项。

参数

说明

默认值

source

设置要使用的爬虫。

amazon_sellers

query

卖家 ID 代码。

render

设置为时启用 JavaScript 渲染 html. 更多信息.

parse

设置为时返回已解析的数据 true. 探索输出 数据字典.

false

callback_url

您的回调端点的 URL。 更多信息.

user_agent_type

设备类型和浏览器。完整列表可在此处.

desktop

- 必填参数

本地化

将结果调整为特定地理位置、域和语言。

参数

说明

默认值

geo_location

该 交付到 位置。有关使用此参数的指南，请参阅此处.

domain

Amazon 的域名本地化。可用域名的完整列表可在此处.

com

locale

Accept-Language 请求头的值，用于设置 Amazon 页面界面的语言。 更多信息.

重要： 在大多数页面类型中，Amazon 会根据客户的交付位置调整返回的结果。因此，我们建议使用 geo_location 参数来设置您偏好的交付位置。您可以阅读有关在 Amazon 中使用 geo_location 的更多信息此处.

结构化数据

下面您可以找到一个 结构化输出示例 用于 amazon_sellers。请注意，目前我们仅支持针对 desktop 设备类型的解析输出。不过，没有明显理由使用其它设备类型获取卖家页面，因为卖家数据在所有设备上将完全相同。

Amazon_sellers 结构化输出

{
    "results": [
        {
            "content": {
                "url": "https://www.amazon.com/sp?seller=A151FB8X73UXPJ",
                "query": "A151FB8X73UXPJ",
                "rating": 4.5,
                "page_type": "Seller",
                "description": "Service with a smile! Gamer Girlz LLC loves making our customers happy by providing the quickest service & highest quality products. Every order is packaged with care & includes a special THANK YOU for choosing Gamer Girlz to provide you with the first class shopping experience you deserve!",
                "business_name": "Gamer Girlz",
                "recent_feedback": [
                    {
                        "feedback": "The product never came, and was very very expensive. Wasn't eligible for refund for some reason.",
                        "rated_by": "By Juli on May 8, 2022.",
                        "rating_stars": 1
                    },
                    {
                        "feedback": "Favorite game",
                        "rated_by": "By DF on May 8, 2022.",
                        "rating_stars": 5
                    },
                    {
                        "feedback": "It works perfectly and I love the games on it.",
                        "rated_by": "By John on May 8, 2022.",
                        "rating_stars": 5
                    },
                    {
                        "feedback": "All the games I got came super fast and it amazing condition! Would definitely buy from them again and recommend seller to others!",
                        "rated_by": "By Brianna c. on May 6, 2022.",
                        "rating_stars": 5
                    },
                    {
                        "feedback": "They were fast with shipping and provided quality merchandise. A label of authenticity was included with the game I bought to ensure me that I bought a genuine version.",
                        "rated_by": "By anonymous  on May 6, 2022.",
                        "rating_stars": 5
                    }
                ],
                "business_address": "1020 Michigan St. Sandpoint ID 83864 US",
                "parse_status_code": 12000,
                "feedback_summary_table": {
                    "counts": {
                        "30_days": 44,
                        "90_days": 146,
                        "all_time": 7857,
                        "12_months": 611
                    },
                    "neutral": {
                        "30_days": "5%",
                        "90_days": "2%",
                        "all_time": "2%",
                        "12_months": "1%"
                    },
                    "negative": {
                        "30_days": "7%",
                        "90_days": "7%",
                        "all_time": "3%",
                        "12_months": "8%"
                    },
                    "positive": {
                        "30_days": "89%",
                        "90_days": "91%",
                        "all_time": "95%",
                        "12_months": "91%"
                    }
                }
            },
            "created_at": "2022-05-09 06:57:47",
            "updated_at": "2022-05-09 06:57:50",
            "page": 1,
            "url": "https://www.amazon.com/sp?seller=A151FB8X73UXPJ",
            "job_id": "6929323518437886977",
            "status_code": 200,
            "parser_type": ""
        }
    ]
}

输出数据字典

HTML 示例

JSON 结构

该 amazon_sellers 结构化输出包括类似于 URL, query, rating，以及其他字段。下表列出了我们解析的每个字段的详细列表、其描述和数据类型。表中还包括一些元数据。

键

说明

类型

url

Amazon 卖家页面的 URL。

string

query

作为原始搜索词使用的 13 字符卖家 ID。

string

rating

卖家的评分。

integer

page_type

Amazon 页面类型。

string

description

关于卖家的简短描述。

string

seller_name

卖家的名称。

string

business_name

企业名称。

string

recent_feedback

包含最近反馈项及其各自详细信息的列表。

array

business_address

企业地址。

string

parse_status_code

解析作业的状态代码。您可以查看解析器状态代码的说明此处.

integer

feedback_summary_data

有关卖家评分的可用详细信息列表。

object

created_at

创建爬取作业的时间戳。

timestamp

updated_at

爬取作业完成的时间戳。

timestamp

job_id

与爬取作业关联的作业 ID。

integer

status_code

爬取作业的状态代码。您可以查看爬虫状态代码的说明此处.

integer

parser_type

用于解析数据的解析器类型。

string

在以下各节中，如果结果类型有多于一项，解析后的 JSON 代码片段会被缩短。

反馈汇总数据

该 feedback_summary_data 是为 Amazon 市场上特定商品列表提供的反馈统计。反馈汇总数据包含不同时间段的信息，允许卖家和分析师跟踪客户情绪随时间的变化。

...               
 "feedback_summary_data": {
    "1_month": {
        "count": 3,
        "1_star": "33%",
        "2_star": "0%",
        "3_star": "0%",
        "4_star": "33%",
        "5_star": "33%"
    },
    "3_month": {
        "count": 10,
        "1_star": "10%",
        "2_star": "0%",
        "3_star": "0%",
        "4_star": "20%",
        "5_star": "70%"
    },
 ...
}
...

键 (content.feedback_summary_data)

说明

类型

1_month/3_month/12_month/all_time

用于按定义的时间范围查看评分信息的筛选器。

object

1_month/3_month/12_month/all_time.count

某一时间段内可用的评论数量。

integer

1_month-all_time.1_star-5_star

某一时间段内评分星级的百分比分布。

百分比

最后更新于9天前

这有帮助吗？

下午好

hashtag请求示例

hashtag请求参数值

hashtag通用

hashtag本地化

hashtag结构化数据

hashtag输出数据字典

hashtagHTML 示例

hashtagJSON 结构

hashtag最近反馈

hashtag反馈汇总数据

请求示例

请求参数值

通用

本地化

结构化数据

输出数据字典

HTML 示例

JSON 结构

最近反馈

反馈汇总数据