URL

使用网页爬虫API 按 URL 抓取 Amazon 页面。文档包含请求示例、解析输出、JS 渲染、地理位置和用户代理选项。

该 amazon source 的设计用于从各种 Amazon URL 中检索内容。这意味着你无需发送多个参数，只需提供所需 Amazon 页面的直接 URL 给我们即可。我们不会剥离任何参数，也不会以其他任何方式更改你的 URL。

请求示例

在下面的代码示例中，我们发起请求以检索 ASIN 的 Amazon 商品页面 B08Y6Z944Q.

curl 'https://realtime.oxylabs.io/v1/queries' \
--user 'USERNAME:PASSWORD' \
-H 'Content-Type: application/json' \
-d '{
        "source": "amazon", 
        "url": "https://www.amazon.co.uk/dp/B08Y6Z944Q/",
        "parse": true
    }'

import requests
from pprint import pprint


# 结构化负载。
payload = {
    'source': 'amazon',
    'url': 'https://www.amazon.co.uk/dp/B08Y6Z944Q/',
    'parse': True
}

# 获取响应。
response = requests.request(
    'POST',
    'https://realtime.oxylabs.io/v1/queries',
    auth=('USERNAME', 'PASSWORD'), #你的凭据填写在这里
    json=payload,
)

# 不返回作业状态和结果 URL 的响应，而是返回
# 返回包含结果的 JSON。
pprint(response.json())

const https = require("https");

const username = "USERNAME";
const password = "PASSWORD";
const body = {
    source: "amazon",
    url: "https://www.amazon.co.uk/dp/B08Y6Z944Q/",
    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',
    'url' => 'https://www.amazon.co.uk/dp/B08Y6Z944Q/',
    '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",
		"url":    "https://www.amazon.co.uk/dp/B08Y6Z944Q/",
		"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",
                url = "https://www.amazon.co.uk/dp/B08Y6Z944Q/",
                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");
        jsonObject.put("url", "https://www.amazon.co.uk/dp/B08Y6Z944Q/");
        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();
    }
}

输出示例

{
    "results": [
        {
            "content": {
                "ads": [
                    {
                        "pos": 1,
                        "asin": "B0CH3JJN66",
                        "type": "organic_also_viewed",
                        "price": 375,
                        "title": "三星 55 英寸 AU7020 UHD HDR 4K 智能电视（2023）- Crystal UHD 4K 智能电视，配备 HDR 画质、Adaptive Sound Lite、PurColour ",
                        "images": [
                            "https://m.media-amazon.com/images/I/71Dxs5msCcL._AC_SS57_.jpg",
                            "https://m.media-amazon.com/images/I/61rH38KyMnL.jpg",
                            "https://m.media-amazon.com/images/I/71xvR9thu1L.jpg"
                        ],
                        "rating": 4.5,
                        "location": "carousel",
                        "price_upper": 375,
                        "reviews_count": 45,
                        "is_prime_eligible": true
                    },
                    {
                        "pos": 2,
                        "asin": "B0BW9RPQPW",
                        "type": "organic_also_viewed",
                        "price": 362,
                        "title": "50 英寸 CU7110 UHD HDR 智能电视（2023）- 4K Crystal Processor、Adaptive Sound Audio、PurColour、内置游戏 TV Hub、Strea",
                        "images": [
                            "https://m.media-amazon.com/images/I/81eKwOlfhTL._AC_SS57_.jpg",
                            "https://m.media-amazon.com/images/I/619tbh+PSSL.jpg",
                            "https://m.media-amazon.com/images/I/81iuMoHZWhL.jpg"
                        ],
                        "rating": 4.5,
                        "location": "carousel",
                        "price_upper": 362,
                        "reviews_count": 45,
                        "is_prime_eligible": true
                    },
                    {...}
                ],
                "url": "https://www.amazon.co.uk/dp/B08Y6Z944Q/",
                "asin": "B08Y6Z944Q",
                "page": 1,
                "brand": "Samsung",
                "price": 0,
                "stock": "",
                "title": "三星 AU7100 50 英寸（2021）\u00e2\u20ac\u201c Crystal 4K 智能电视，配备 HDR10+ 画质、Adaptive Sound、Motion Xcelerator 画面、Samsung Q-Symphony 音频和游戏模式 - UE50AU7100KXXU",
                "coupon": "",
                "images": [
                    "https://m.media-amazon.com/images/I/71Urp17dnYL._AC_SL1500_.jpg",
                    ...
                    "https://m.media-amazon.com/images/I/51yb9wscZTL._AC_SL1500_.jpg"
                ],
                "rating": 4.5,
                "category": [
                    {
                        "ladder": [
                            {
                                "url": "/tv-bluray-dvd-home-cinema/b/ref=dp_bc_aui_C_1?ie=UTF8&node=560858",
                                "name": "家庭影院、电视与视频"
                            },
                            {
                                "url": "/LED-Smart-4K-TVs/b/ref=dp_bc_aui_C_2?ie=UTF8&node=560864",
                                "name": "电视"
                            }
                        ]
                    }
                ],
                "currency": "GBP",
                "delivery": [],
                "_warnings": [
                    "无法解析价格数量。",
                    "无法解析价格。",
                    "无法解析描述。"
                ],
                "page_type": "产品",
                "price_sns": 0,
                "variation": [
                    {
                        "asin": "B08Y7182XL",
                        "selected": false,
                        "dimensions": {
                            "Size Name": "85\""
                        }
                    },
                    {
                        "asin": "B08Y733RV1",
                        "selected": false,
                        "dimensions": {
                            "Size Name": "43\""
                        }
                    },
                    {...}
                ],
                "has_videos": true,
                "sales_rank": [
                    {
                        "rank": 28405,
                        "ladder": [
                            {
                                "url": "/gp/bestsellers/electronics/ref=pd_zg_ts_electronics",
                                "name": "电子产品与摄影"
                            }
                        ]
                    },
                    {
                        "rank": 479,
                        "ladder": [
                            {
                                "url": "/gp/bestsellers/electronics/560864/ref=pd_zg_hrsr_electronics",
                                "name": "电视"
                            }
                        ]
                    }
                ],
                "top_review": "这款电视以这个价格来说非常出色，画质惊艳，尤其是在流媒体服务上，而这也是我们大多数时候观看的内容。我先在网上阅读了大量专业评测，它们都给出了很高评价，我也没有失望。需要进行不少设置，我还得调整一些选项才能得到最佳画面。起初画面太暗，尤其是在 Amazon Prime 上。看来这在 Prime 上是个特定问题。关闭 \"Brightness Optimisation\" 后，我得到了好得多的画面。我们也不喜欢 4K LED 电视带来的 \"ultra real\" 效果。切换到 \"Filmmaker Mode\" 后就解决了。音质还可以，不过我们本来就使用 soundbar。我尤其喜欢电视附带的两个遥控器。一个是传统遥控器，按键很多：我最初用它完成了所有设置，包括控制 BluRay 播放器和 soundbar。等一切都正常工作后，我换成了更小的遥控器，它只有最基本的按键，但外观和手感更精致，按键的 \"click\" 感也比大号遥控器更好。观看地面数字电视也没问题，不过不如流媒体服务那么好。我们不是玩家，所以无法评价游戏表现。总之，这是一台很棒的电视，而且物超所值。\n  \n阅读更多",
                "asin_in_url": "B08Y6Z944Q",
                "description": "",
                "parent_asin": "B09DLFS6JN",
                "price_upper": 0,
                "pricing_str": "",
                "pricing_url": "https://www.amazon.co.uk/gp/offer-listing/B08Y6Z944Q?startIndex=0",
                "manufacturer": "Samsung",
                "price_buybox": -1,
                "product_name": "三星 AU7100 50 英寸（2021）\u00e2\u20ac\u201c Crystal 4K 智能电视，配备 HDR10+ 画质、Adaptive Sound、Motion Xcelerator 画面、Samsung Q-Symphony 音频和游戏模式 - UE50AU7100KXXU",
                "bullet_points": "AU7100 带来卓越家庭娱乐体验 – 一款智能超高清电视，集多种功能于一身。三星 50 英寸 AU7100 智能电视融合惊艳画质、鲜艳色彩、清晰音频和醒目的超薄贴合设计，提升你的生活空间。\n凭借惊艳 4K 获得强劲画面 – 你的 50 英寸智能电视配备 Dynamic Crystal Colour 和 Contrast Enhancer，因此你可以以惊艳的 4K 细节观看所有喜爱的节目，色彩更鲜明，对比度带来更清晰的画面。\n在电视上通过 Adaptive Sound 体验完美音频——你的三星电视会根据屏幕内容在每个场景中自动调整声音，让你仿佛置身其中。添加三星 soundbar 后，Q-Symphony 可带来影院级体验。\n升级你的办公设置，或用三星电视投入游戏——PC on TV 让你可以通过 Smart TV 远程访问办公室电脑，让你在客厅就能完成一切。我们的 Smart TV 还提供沉浸式游戏模式。\n开始体验三星电视——我们相信电视不仅仅是用来观看的。它应该激发你、震撼你、包围你并让你沉浸其中。从高品质画面到优雅设计，我们的电视不断突破可能性的边界，也不断拓展电视的定义。",
                "price_initial": 0,
                "pricing_count": 1,
                "reviews_count": 2067,
                "sns_discounts": [],
                "developer_info": [],
                "price_shipping": 0,
                "product_details": {
                    "asin": "B08Y6Z944Q",
                    "batteries": "需要 2 节 AAA 电池。（已包含）",
                    "manufacturer": "Samsung",
                    "item_model_number": "UE50AU7100KXXU",
                    "product_dimensions": "5.99 x 111.68 x 64.42 cm; 11.4 kg",
                    "date_first_available": "2021年3月2日"
                },
                "featured_merchant": [],
                "is_prime_eligible": false,
                "parse_status_code": 12005,
                "product_dimensions": "5.99 x 111.68 x 64.42 cm; 11.4 kg",
                "answered_questions_count": 0,
                "rating_stars_distribution": [
                    {
                        "rating": 5,
                        "percentage": 74
                    },
                    {
                        "rating": 4,
                        "percentage": 15
                    },
                    {...}
                ]
            },
            "created_at": "2024-07-01 10:35:28",
            "updated_at": "2024-07-01 10:35:32",
            "page": 1,
            "url": "https://www.amazon.co.uk/dp/B08Y6Z944Q/",
            "job_id": "7213490386797350913",
            "status_code": 200,
            "parser_type": ""
        }
    ]
}

我们使用同步的 Realtime 集成方法作为示例。如果您想使用 Proxy Endpoint 或异步 Push-Pull 集成，请参阅 集成方法 部分。

请求参数值

通用

Google URL 爬取的基础设置和自定义选项。

参数

说明

默认值

source

设置爬虫。

amazon

url

到 Amazon 页面的直接 URL（链接）

render

设置为 html. 更多信息.

parse

设置为 true. 仅限于特定类型的 URL Amazon 页面类型.

false

callback_url

您的回调端点 URL。 更多信息.

user_agent_type

设备类型和浏览器。完整列表可在这里.

desktop

- 必填参数

本地化

根据特定地理位置和语言调整结果。

参数

说明

默认值

geo_location

该 送达至 位置。请参阅我们关于使用此参数的指南这里.

locale

Accept-Language 标头值，用于设置 Amazon 页面界面语言。 更多信息.

重要： 在大多数页面类型中，Amazon 会根据客户的配送地点来定制返回结果。因此，我们建议使用 geo_location 参数来设置您首选的配送地点。您可以阅读更多关于在 Amazon 中使用 geo_location 的内容这里.

其他

适用于专门需求的其他高级设置和控制项。

参数

说明

默认值

context: 货币

设置货币。查看可用值这里.

取决于市场。查看默认值这里.

最后更新于 27天前

这有帮助吗？