URL

Google URL 抓取器可轻松从任何 Google 页面检索内容。提供简单集成方式和多语言代码示例。

该 google source 旨在从各种 Google 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 Google 页面对应的直接 URL 即可。我们不会删除任何参数，也不会以任何其他方式更改你的 URL。

请求示例

在下面的示例中，API 将检索一个 Google Scholar 搜索页面。

curl 'https://realtime.oxylabs.io/v1/queries' \
--user 'USERNAME:PASSWORD' \
-H 'Content-Type: application/json' \
-d '{
        "source": "google",
        "url": "https://scholar.google.com/scholar?hl=en&q=newton&btnG=&as_sdt=1%2C5&as_sdtp="
    }'

import requests
from pprint import pprint

# 结构化负载。
payload = {
    'source': 'google',
    'url': 'https://scholar.google.com/scholar?hl=en&q=newton&btnG=&as_sdt=1%2C5&as_sdtp='
}

# 获取响应。
response = requests.request(
    'POST',
    'https://realtime.oxylabs.io/v1/queries',
    auth=('USERNAME', 'PASSWORD'),
    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: "google",
    query: "https://scholar.google.com/scholar?hl=en&q=newton&btnG=&as_sdt=1%2C5&as_sdtp=",
};

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();

# URL 必须进行编码，以转义 `&` 和 `=` 字符：
# URL: https://scholar.google.com/scholar?hl=en&q=newton&btnG=&as_sdt=1%2C5&as_sdtp=
# 编码后的 URL: https%3A%2F%2Fscholar.google.com%2Fscholar%3Fhl%3Den%26q%3Dnewton%26btnG%3D%26as_sdt%3D1%252C5%26as_sdtp%3D

https://Realtime.oxylabs.io/v1/queries?source=google&url=https%3A%2F%2Fscholar.google.com%2Fscholar%3Fhl%3Den%26q%3Dnewton%26btnG%3D%26as_sdt%3D1%252C5%26as_sdtp%3D&access_token=12345abcde

<?php

$params = array(
    'source' => 'google',
    'url' => 'https://scholar.google.com/scholar?hl=en&q=newton&btnG=&as_sdt=1%2C5&as_sdtp='
);

$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",
		"url":    "https://scholar.google.com/scholar?hl=en&q=newton&btnG=&as_sdt=1%2C5&as_sdtp=",
	}

	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",
                query = "https://scholar.google.com/scholar?hl=en&q=newton&btnG=&as_sdt=1%2C5&as_sdtp="
            };

            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", "google");
        jsonObject.put("url", "https://scholar.google.com/scholar?hl=en&q=newton&btnG=&as_sdt=1%2C5&as_sdtp=");

        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。

google

url

Google 页面对应的直接 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 Google 页面类型.

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

geo_location

结果应适配的地理位置。正确使用此参数对于获取正确数据极其重要。有关更多信息，请阅读我们建议的 geo_location 参数结构这里.

- 必填参数

输出示例

{
    "results": [
        {
            "content":"<!doctype html>\n<html lang=\"en\">\n<head>
            ...
            </script></body>\n</html>\n",            
            "created_at": "2024-05-27 12:28:27",
            "updated_at": "2024-05-27 12:28:30",
            "page": 1,
            "url": "https://scholar.google.com/scholar?hl=en&q=newton&btnG=&as_sdt=1%2C5&as_sdtp=",
            "job_id": "7200835246005180417",
            "status_code": 200
        }
    ]
}

最后更新于 25天前

这有帮助吗？

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", "google");
        jsonObject.put("url", "https://scholar.google.com/scholar?hl=en&q=newton&btnG=&as_sdt=1%2C5&as_sdtp=");

        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();
    }
}