新闻搜索

大规模抓取 Google News 结果并获取完全解析的数据。提取文章标题、来源和发布时间。

该 google_search source 旨在检索 Google Search 结果（SERPs）。此子页面专门展示与 Google News 搜索相关的数据。要探索其他结果类型，请阅读此处： 网页搜索, 图片搜索.

要抓取 Google News search，请包含 context:udm 参数，并将值设为 12 或 context:tbm 参数，并将值设为 nws.

查看输出 数据字典 用于每个 News SERP 功能，提供简要说明、截图、已解析的 JSON 代码片段，以及定义每个解析字段的表格。可使用右侧导航或向下滚动页面浏览详情。

请求示例

在下面的示例中，我们发起请求以获取搜索词 adidas.

udm

curl 'https://realtime.oxylabs.io/v1/queries' \\
--user 'USERNAME:PASSWORD' \\
-H 'Content-Type: application/json' \\
-d '{
        "source": "google_search",
        "query": "adidas",
        "parse": true,
        "context": [
            {
                "key": "udm",
                "value": 12
            }
        ]
    }'

import requests
from pprint import pprint

# Structure payload.
payload = {
    'source': 'google_search',
    'query': 'adidas',
    'parse': True,
    'context': [
        {'key': 'udm', 'value': 12},
    ],
}

# Get response.
response = requests.post(
    'https://realtime.oxylabs.io/v1/queries',
    auth=('USERNAME', 'PASSWORD'),
    json=payload,
)

# Print prettified response to stdout.
pprint(response.json())

const https = require("https");

const username = "USERNAME";
const password = "PASSWORD";
const body = {
    source: "google_search",
    query: "adidas",
    parse: true,
    context: [
        { key: "udm", value: 12 },
    ],
};

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' => 'google_search',
    'query' => 'adidas',
    'parse' => true,
    'context' => [
        [
            'key' => 'udm',
            'value' => 12,
        ]
    ]
);

$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": "google_search",
		"query":  "adidas",
		"parse":  true,
		"context": []map[string]interface{}{
			{"key": "udm", "value": 12},
		},
	}

	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 = "google_search",
                query = "adidas",
                parse = true,
                context = new dynamic [] {
                    new { key = "udm", value = 12 },
                }
            };

            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.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() {
        JSONObject jsonObject = new JSONObject();
        jsonObject.put("source", "google_search");
        jsonObject.put("query", "adidas");
        jsonObject.put("parse", true);
        jsonObject.put("context", new JSONArray()
                .put(new JSONObject()
                        .put("key", "udm")
                        .put("value", 12))
        );

        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();
    }
}

tbm

curl 'https://realtime.oxylabs.io/v1/queries' \\
--user 'USERNAME:PASSWORD' \\
-H 'Content-Type: application/json' \\
-d '{
        "source": "google_search",
        "query": "adidas",
        "parse": true,
        "context": [
            {
                "key": "tbm",
                "value": "nws"
            }
        ]
    }'

import requests
from pprint import pprint

# Structure payload.
payload = {
    'source': 'google_search',
    'query': 'adidas',
    'parse': True,
    'context': [
        {'key': 'tbm', 'value': 'nws'},
    ],
}

# Get response.
response = requests.post(
    'https://realtime.oxylabs.io/v1/queries',
    auth=('USERNAME', 'PASSWORD'),
    json=payload,
)

# Print prettified response to stdout.
pprint(response.json())

const https = require("https");

const username = "USERNAME";
const password = "PASSWORD";
const body = {
    source: "google_search",
    query: "adidas",
    parse: true,
    context: [
        { key: "tbm", value: "nws" },
    ],
};

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' => 'google_search',
    'query' => 'adidas',
    'parse' => true,
    'context' => [
        [
            'key' => 'tbm',
            'value' => 'nws',
        ]
    ]
);

$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": "google_search",
		"query":  "adidas",
		"parse":  true,
		"context": []map[string]interface{}{
			{"key": "tbm", "value": "nws"},
		},
	}

	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 = "google_search",
                query = "adidas",
                parse = true,
                context = new dynamic [] {
                    new { key = "tbm", value = "nws" },
                }
            };

            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.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() {
        JSONObject jsonObject = new JSONObject();
        jsonObject.put("source", "google_search");
        jsonObject.put("query", "adidas");
        jsonObject.put("parse", true);
        jsonObject.put("context", new JSONArray()
                .put(new JSONObject()
                        .put("key", "tbm")
                        .put("value", "nws"))
        );

        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": "google_search",
    "query": "adidas",
    "parse": true,
    "context": [
        {
            "key": "tbm",
            "value": "nws"
        }
    ]
}

我们在示例中使用同步 Realtime 集成方法。如果你想使用 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

用于抓取 Google News 搜索结果的基本设置和自定义选项。

参数

描述

默认值

source

设置抓取器。

google_search

query

要搜索的关键词或短语。

context: udm

要获取新闻搜索结果，请将值设为 12。在此查找其他可接受的值此处.

context: tbm

要获取新闻搜索结果，请将值设为 nws。其他可接受的值包括： app, blg, bks, dsc, isch, pts, plcs, rcp, lcl

render

设置为 html 是此来源的必需项。 更多信息.

parse

设为 true时返回解析后的数据。查看输出 数据字典.

false

callback_url

指向你的回调端点的 URL。 更多信息

user_agent_type

设备类型和浏览器。完整列表可见此处.

desktop

- 必需参数

注意： udm 和 tbm context 参数不能在单个抓取请求中同时使用；请选择其中之一。同时使用两者可能导致冲突或意外行为。

Google 高级搜索运算符

在抓取时，将 Google 高级搜索运算符与查询结合使用会很有用。它可以让你自定义搜索范围，确保结果更相关、更聚焦。探索这些特殊命令此处和此处。示例如下。

{
    "source": "google_search",
    "query": "iphone 15 launch inurl:apple",
}

本地化

将搜索结果适配到特定地理位置和语言。

参数

描述

默认值

geo_location

结果应适配的地理位置。正确使用此参数极其重要，以获取正确的数据。更多信息请阅读我们建议的 geo_location 参数结构此处.

locale

Accept-Language 请求头值，它会更改你的 Google 搜索页面网页界面语言。 更多信息.

分页

用于管理搜索结果分页和获取的控制项。

参数

描述

默认值

start_page

起始页码。

1

pages

要获取的页面数。

1

limit

每页要获取的结果数。

10

context:

limit_per_page

如果你想使用相同 IP 地址抓取多个页面，请包含一个 JSON 数组，并使用 page 键指定页码。你还必须通过添加 limit 键指明每页的自然结果数量。 查看示例.

每页限制

要使用此功能，请包含一个 JSON 数组，其中包含以下数据的 JSON 对象：

参数

描述

示例

page

你想抓取的页面编号。任何大于 0 的整数都可以

1

limit

相关页面上的结果数量。任何介于 1 和 100 （含）之间的整数都可以。

90

请求示例

{
    "source": "google_search",
    "query": "adidas",
    "parse": true,
    "context": [
        {
            "key": "limit_per_page",
            "value": [
                {"page": 1, "limit": 10},
                {"page": 2, "limit": 90}
                    ]
        }]
}

筛选

根据各种条件筛选和细化搜索结果的选项。

参数

描述

默认值

context:safe_search

安全搜索。设为 true 以启用它。

false

context: tbs

tbs 参数。此参数类似于一个容器，用于存放更隐晦的 Google 参数，例如按日期限制/排序结果以及其他筛选条件，其中一些取决于 tbm 参数（例如 tbs=app_os:1 仅在 tbm 值 app）。更多信息此处.

其他

用于特殊需求的其他高级设置和控制项。

参数

描述

默认值

context: nfpr

true 将关闭拼写自动更正

false

上下文参数

所有上下文参数都应添加到 context 数组中，作为包含 键 和 值 键值对的对象，例如：

...
"context": [
    {
        "key": "filter",
        "value": "0"
    }
]
...

结构化数据

SERP 爬虫 API 能够提取包含 Google 搜索结果的 HTML 或 JSON 对象，并在结果页的各个元素上提供结构化数据。

google_search 新闻结构化输出

{
    "results": [
        {
            "content": {
                "url": "https://www.google.com/search?q=adidas&tbm=nws&uule=w+CAIQICINdW5pdGVkIHN0YXRlcw&gl=us&hl=en",
                "page": 1,
                "results": {
                    "main": [
                        {
                            "url": "https://www.cnn.com/2022/05/06/business/under-armour-stock-adidas-nike/index.html",
                            "desc": "Tripped-up supply chains and a coronavirus surge in China are causing \nheadaches for top athletic brands.",
                            "title": "Wall Street is fed up with Under Armour, Nike and Adidas",
                            "source": "CNN",
                            "pos_overall": 1,
                            "relative_publish_date": "2 days ago"
                        },
                        ...
                        {
                            "url": "https://www.cnbc.com/2022/05/06/dsw-tests-layout-to-spotlight-brands-like-adidas-crocs-birkenstock.html",
                            "desc": "DSW is trying out a new store look and layout at a location opening this \nweekend in Houston, in an attempt to focus customers' attention on...",
                            "title": "DSW is testing a store layout that puts the spotlight on brands like \nAdidas, Crocs and Birkenstock",
                            "source": "CNBC",
                            "pos_overall": 10,
                            "relative_publish_date": "2 days ago"
                        }
                    ],
                    "total_results_count": 57300000
                },
                "parse_status_code": 12000
            },
            "created_at": "2022-05-09 07:25:03",
            "updated_at": "2022-05-09 07:25:07",
            "page": 1,
            "url": "https://www.google.com/search?q=adidas&tbm=nws&uule=w+CAIQICINdW5pdGVkIHN0YXRlcw&gl=us&hl=en",
            "job_id": "6929330379711060993",
            "status_code": 200,
            "parser_type": "v2"
        }
    ]
}

我们只为 desktop 搜索解析新闻搜索结果。

输出数据字典

HTML 示例

JSON 结构

Google 新闻搜索的结构化输出包括诸如 URL, page, results等字段。下表列出了我们解析的每个 SERP 功能的详细列表，以及其描述和数据类型。表中还包含一些元数据。

特定结果类型的项目和字段数量可能会因搜索查询而异。

键

描述

类型

url

Google 搜索页面的 URL。

字符串

results

包含搜索结果的字典。

数组

results.main

非付费新闻结果列表及其各自的详细信息。

数组

results.additional

热门文章列表及其各自的详细信息。

对象

results.total_results_count

搜索查询找到的结果总数。

数组

parse_status_code

解析任务的状态码。你可以查看所述解析器状态码此处.

整数

created_at

爬取任务创建时的时间戳。

时间戳

updated_at

爬取任务完成时的时间戳。

时间戳

page

相对于 Google SERP 分页的页码。

整数

job_id

与爬取任务关联的任务 ID。

字符串

status_code

爬取任务的状态码。你可以查看所述爬虫状态码此处.

整数

在以下章节中，当某个结果类型有多个项目可用时，解析后的 JSON 代码片段会被缩短。

主要

显示非付费新闻结果列表，并提供每篇文章的相关详细信息。

...
"main": [
    {
        "url": "https://www.yahoo.com/lifestyle/tiger-woods-nikes-epic-partnership-015311819.html",
        "desc": "That there could ever be a world in which Tiger Woods wasn't sponsored by \nNike seemed...",
        "title": "How Tiger Woods and Nike's Epic Partnership Fell Apart",
        "source": "Yahoo",
        "pos_overall": 1,
        "relative_publish_date": "1 day ago"
    },
                       ...
},

...

键（results.main）

描述

类型

url

完整文章的 URL。

字符串

desc

完整文章的简短摘录。

字符串

title

文章标题。

字符串

source

文章发布网站的名称。

字符串

pos_overall

表示该结果在新闻 SERP 主要结果中的总体位置。

整数

relative_publish_date

描述文章发表于多久之前。

字符串

附加

展示热门文章列表，并附带相关详细信息。

...
"additional": [
    {
        "items": [
            {
                "pos": 1,
                "url": "https://www.complex.com/sneakers/a/brendan-dunne/nike-book-1-colorways-haven-hike-rattlesnake",
                "title": "Nike Book 1 Colorways Haven Hike Rattlesnake",
                "source": "Complex",
                "relative_publish_date": "1 day ago"
            },
         ...
        ],
        "pos_overall": 2,
        "section_title": "Devin Booker confirms issues with Nike Book 1 launch"
    }
...

键（results.additional）

描述

类型

items

文章列表及其各自的详细信息。

数组

items.pos

用于标示文章在列表中位置的唯一标识。

整数

items.url

完整文章的 URL。

字符串

items.title

文章标题。

字符串

items.source

文章发布网站的名称。

字符串

items.relative_publish_date

描述文章发表于多久之前。

字符串

pos_overall

表示该结果在新闻 SERP 附加结果中的总体位置。

整数

section_title

附加部分的名称。

字符串

最后更新于 19天前

这有帮助吗？