Scholar

Google Scholar scraper allows you to submit search queries and receive structured, parsed data including articles, books, citations, and related links.

The google_scholar data source is designed to retrieve Google Scholar search results, including academic papers, books, citations, and related links.

Request samples

In this example, we make a request to retrieve Google Scholar results for the query best novels.

curl 'https://realtime.oxylabs.io/v1/queries' \
--user 'USERNAME:PASSWORD' \
-H 'Content-Type: application/json' \
-d '{
        "source": "google_scholar",
        "query": "best novels",
        "render": "html",
        "parse": true
    }'

import requests
from pprint import pprint

# Structure payload.
payload = {
  "source": "google_scholar",
  "query": "best novels",
  "render": "html",
  "parse": True
}

# Get response.
response = requests.request(
    '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_scholar",
    query: "best novels",
    render: "html",
    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();

https://realtime.oxylabs.io/v1/queries?source=google_scholar&query=best+novels&render=html&parse=true&access_token=12345abcde

<?php

$params = array(
    'source' => 'google_scholar',
    'query' => 'best novels',
    'render' => 'html',
    '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": "google_scholar",
		"query":  "best novels",
		"render": "html",
		"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.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_scholar",
                query = "best novels",
                render = "html",
                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", "google_scholar");
        jsonObject.put("query", "best novels");
        jsonObject.put("render", "html");
        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();
    }
}

{
    "source": "google_scholar",
    "query": "best novels",
    "render": "html",
    "parse": true
}

We use synchronous Realtime integration method in our examples. If you would like to use Proxy Endpoint or asynchronous Push-Pull integration, refer to the integration methods section.

Request parameters

Parameter

Description

Default Value

source

Sets the scraper. Use google_scholar.

–

query

Search term for the request.

–

render

Enables JavaScript rendering when set to html. More info.

–

parse

Returns parsed data when set to true. See more in output dictionary.

false

callback_url

URL to your callback endpoint. More info.

–

user_agent_type

Device type and browser. The full list can be found here.

desktop

– mandatory parameter

Structured data

Web Scraper API can extract results HTML or JSON response that contains structured data on various elements of the results page.

Structured google_scholar output

{
    "results": [
        {
            "content": {
                "organic": [
                    {
                        "description": "… and exciting as any other for the novel. The mass market paperback came into … book. Its purpose is to celebrate the writers we have loved best, and to proselytize on behalf of their novels…",
                        "inline_links": {
                            "cite_url": "https://scholar.google.com/scholar?q=info:Av0ZOt0npBEJ:scholar.google.com/&output=cite&scirp=0&hl=en",
                            "cited_by": {
                                "cites_id": "1271184825941359874",
                                "total": 15,
                                "url": "https://scholar.google.com/scholar?cites=1271184825941359874&as_sdt=2005&sciodt=0,5&hl=en"
                            },
                            "related_pages_url": "https://scholar.google.com/scholar?q=related:Av0ZOt0npBEJ:scholar.google.com/&scioq=best+novels&hl=en&as_sdt=0,5",
                            "versions": {
                                "cluster_id": "1271184825941359874",
                                "total": 5,
                                "url": "https://scholar.google.com/scholar?cluster=1271184825941359874&hl=en&as_sdt=0,5"
                            }
                        },
                        "pos": 1,
                        "publication_info": {
                            "summary": "C Callil, C Tóibín - 2011 - books.google.com"
                        },
                        "result_id": "Av0ZOt0npBEJ",
                        "result_type": "book",
                        "title": "The Modern Library: The 200 Best Novels in English Since 1950",
                        "url": "https://books.google.com/books?hl=en&lr=&id=EwlNDwAAQBAJ&oi=fnd&pg=PA1903&dq=best+novels&ots=Uiru4xYAcj&sig=exuKH7sr8Y4rAx7cvn15h8lA39Y"
                    },
                    {
                        "description": "… Predicting success of novels and movies: To the best of our knowledge, our work is the first that provides quantitative insights into the unstudied connection between the writing style …",
                        "inline_links": {
                            "cite_url": "https://scholar.google.com/scholar?q=info:r_g8gsmjLJgJ:scholar.google.com/&output=cite&scirp=4&hl=en",
                            "cited_by": {
                                "cites_id": "10965319278609103023",
                                "total": 182,
                                "url": "https://scholar.google.com/scholar?cites=10965319278609103023&as_sdt=2005&sciodt=0,5&hl=en"
                            },
                            "related_pages_url": "https://scholar.google.com/scholar?q=related:r_g8gsmjLJgJ:scholar.google.com/&scioq=best+novels&hl=en&as_sdt=0,5",
                            "versions": {
                                "cluster_id": "10965319278609103023",
                                "total": 10,
                                "url": "https://scholar.google.com/scholar?cluster=10965319278609103023&hl=en&as_sdt=0,5"
                            }
                        },
                        "pos": 5,
                        "publication_info": {
                            "authors": [
                                {
                                    "author_id": "Of8dNP0AAAAJ",
                                    "name": "VG Ashok",
                                    "url": "https://scholar.google.com/citations?user=Of8dNP0AAAAJ&hl=en&oi=sra"
                                },
                                {
                                    "author_id": "aWmHP7IAAAAJ",
                                    "name": "S Feng",
                                    "url": "https://scholar.google.com/citations?user=aWmHP7IAAAAJ&hl=en&oi=sra"
                                },
                                {
                                    "author_id": "vhP-tlcAAAAJ",
                                    "name": "Y Choi",
                                    "url": "https://scholar.google.com/citations?user=vhP-tlcAAAAJ&hl=en&oi=sra"
                                }
                            ],
                            "summary": "VG Ashok, S Feng, Y Choi - … of the 2013 conference on empirical …, 2013 - aclanthology.org"
                        },
                        "resources": [
                            {
                                "file_format": "PDF",
                                "title": "aclanthology.org",
                                "url": "https://aclanthology.org/D13-1181.pdf"
                            }
                        ],
                        "result_id": "r_g8gsmjLJgJ",
                        "result_type": "pdf",
                        "title": "Success with style: Using writing style to predict the success of novels",
                        "url": "https://aclanthology.org/D13-1181.pdf"
                    }
                    // ... up to 8 more organic results
                ],
                "pagination": {
                    "current_page": 1,
                    "next_page": "https://scholar.google.com/scholar?start=10&q=best+novels&hl=en&as_sdt=0,5",
                    "other_pages": {
                        "2": "https://scholar.google.com/scholar?start=10&q=best+novels&hl=en&as_sdt=0,5",
                        "3": "https://scholar.google.com/scholar?start=20&q=best+novels&hl=en&as_sdt=0,5"
                        // ... more page links
                    }
                },
                "parse_status_code": 12000,
                "related_searches": [
                    {
                        "query": "best novels modern library",
                        "url": "https://scholar.google.com/scholar?hl=en&as_sdt=0,5&qsp=1&q=best+novels+modern+library&qst=ib"
                    },
                    {
                        "query": "best novels short stories",
                        "url": "https://scholar.google.com/scholar?hl=en&as_sdt=0,5&qsp=2&q=best+novels+short+stories&qst=ib"
                    }
                    // ... more related searches
                ],
                "search_information": {
                    "query_displayed": "best novels",
                    "time_taken_displayed": 0.15,
                    "total_results_count": 3580000
                }
            },
            "created_at": "2026-07-18 14:00:27",
            "job_id": "7484245708602621953",
            "page": 1,
            "status_code": 200,
            "updated_at": "2026-07-18 14:00:40",
            "url": "https://scholar.google.com/scholar?q=best+novels&hl=en&gl=us"
        }
    ]
}

Output dictionary

The table below presents a detailed list of each top-level element we parse, along with its description and data type.

The number of organic results and certain fields may vary depending on the search query and result type.

Key

Description

Type

url

URL to the Google Scholar search results page.

string

page

Current page number of the search results.

integer

parse_status_code

The status code of the parsing job. Learn more here.

integer

organic

List of organic search results. Includes pos, title, url, description, result_id, result_type, publication_info, inline_links, resources.

array

organic.result_type

Identifies the format of the result (book, pdf, etc.). Omitted when the result is a standard article.

string

organic.publication_info

Summary of the publication. Includes summary (authors, year, publisher/source as a single string) and, when available, a structured authors list with author_id, name, and profile url.

object

organic.inline_links

Academic metadata attached to the result. Includes cite_url, cited_by, related_pages_url, versions.

object

organic.inline_links.cited_by

Citation data for the result. Includes cites_id, total (total citation count), and url (link to citing works).

object

organic.inline_links.related_pages_url

URL to find papers related to the result.

string

organic.inline_links.versions

Alternative versions/links for the same document. Includes cluster_id, total, and url.

object

organic.resources

Direct download links for accessible media, e.g. PDFs. Includes file_format, title, url.

array

pagination

Details about the current and available result pages. Includes current_page, next_page, other_pages.

object

related_searches

Google's suggested related search strings. Includes query and url for each suggestion.

array

search_information

General details about the search. Includes query_displayed, time_taken_displayed, total_results_count.

object

created_at

Timestamp when the scraping job was created.

timestamp

updated_at

Timestamp when the scraping job was finished.

timestamp

job_id

ID of the job associated with the scraping job.

string

status_code

Status code of the scraping job. Learn more here.

integer

PreviousShopping Product NextTrends: Explore

Last updated 22 days ago

Was this helpful?