Google Scholar Author API

Scrape Google Author Profiles and get instant data about the authors and their academic publications.

To enable this engine, set the engine=google_scholar_author parameter.

The Google Scholar Author API is used to scrape author profiles and quickly retrieve data regarding published authors. Make use of these parameters in order to customise your request.

Scrape Google Author Pages

Google Scholar Author API Integration Examples

We will use following URL as an example for this request:

https://serpapi.webscrapingapi.com/v1?engine=google_scholar_author&api_key=<YOUR_API_KEY>&author_id=LSsXyncAAAAJ

Ready to Use Google Scholar Author Scraping Scripts

cURL

curl --request GET --url "https://serpapi.webscrapingapi.com/v1?engine=google_scholar_author&api_key=YOUR_API_KEY&author_id=LSsXyncAAAAJ"

NodeJS

const http = require("https");

const options = {
  "method": "GET",
  "hostname": "serpapi.webscrapingapi.com",
  "port": null,
  "path": "/v1?engine=google_scholar_author&api_key=YOUR_API_KEY&author_id=LSsXyncAAAAJ",
  "headers": {}
};

const req = http.request(options, function (res) {
  const chunks = [];

  res.on("data", function (chunk) {
    chunks.push(chunk);
  });

  res.on("end", function () {
    const body = Buffer.concat(chunks);
    console.log(body.toString());
  });
});

req.end();

Python

import http.client

conn = http.client.HTTPSConnection("serpapi.webscrapingapi.com")

conn.request("GET", "/v1?engine=google_scholar_author&api_key=YOUR_API_KEY&author_id=LSsXyncAAAAJ")

res = conn.getresponse()
data = res.read()

print(data.decode("utf-8"))

PHP

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://serpapi.webscrapingapi.com/v1?engine=google_scholar_author&api_key=YOUR_API_KEY&author_id=LSsXyncAAAAJ",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

Go

package main

import (
	"fmt"
	"net/http"
	"io/ioutil"
)

func main() {

	url := "https://serpapi.webscrapingapi.com/v1?engine=google_scholar_author&api_key=YOUR_API_KEY&author_id=LSsXyncAAAAJ"

	req, _ := http.NewRequest("GET", url, nil)

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := ioutil.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}

Java

HttpResponse<String> response = Unirest.get("https://serpapi.webscrapingapi.com/v1?engine=google_scholar_author&api_key=YOUR_API_KEY&author_id=LSsXyncAAAAJ")
  .asString();

.NET

var client = new RestClient("https://serpapi.webscrapingapi.com/v1?engine=google_scholar_author&api_key=YOUR_API_KEY&author_id=LSsXyncAAAAJ");
var request = new RestRequest(Method.GET);
IRestResponse response = client.Execute(request);

Ruby

require 'uri'
require 'net/http'
require 'openssl'

url = URI("https://serpapi.webscrapingapi.com/v1?engine=google_scholar_author&api_key=YOUR_API_KEY&author_id=LSsXyncAAAAJ")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
http.verify_mode = OpenSSL::SSL::VERIFY_NONE

request = Net::HTTP::Get.new(url)

response = http.request(request)
puts response.read_body

Google Scholar Profiles Parameters

#1: Query Parameter

Parameter	Type	Description
author_id Required	string	The ID of the author you want to scrape.

#2: Request Customisation Parameters

Parameter	Type	Description
device	string	The device used for your search. Can be set to desktop, mobile or tablet.
view_op	string	Is used to view specific parts of the page. It can be set to view_citation or list_colleagues.
sort	string	Sorts the results. Can be set as title to sort by title or pubdate to sort by published date.
citation_id	string	It's used to retrieve a specific citation. It is required when view_op is set on view_citation.

#3: Localisation Parameters

Parameter	Type	Description
hl	string	The language you want to use for your Google Search. List of supported languages

#4: Pagination Parameters

Parameter	Type	Description
start	int	The offset of the Google Search Results. Represents the number of results that you want to skip.
num	int	The number of results returned on each page.

Response Example

{
  "search_parameters": {
    "google_url": "https://scholar.google.com/citations?user=LSsXyncAAAAJ&sourceid=chrome&ie=UTF-8",
    "engine": "google_scholar_author",
    "google_domain": "scholar.google.com",
    "device": "desktop",
    "query": "LSsXyncAAAAJ"
  },
  "author": {
    "name": "Cliff Meyer",
    "affiliations": "Dana-Farber Cancer Institute and Harvard T.H. Chan School of Public Health",
    "email": "Verified email at jimmy.harvard.edu",
    "interests": [
      {
        "link": "https://scholar.google.com/citations?view_op=search_authors&hl=en&mauthors=label:computational_biology",
        "title": "Computational Biology"
      },
      {
        "link": "https://scholar.google.com/citations?view_op=search_authors&hl=en&mauthors=label:epigenetics",
        "title": "Epigenetics"
      },
      {
        "link": "https://scholar.google.com/citations?view_op=search_authors&hl=en&mauthors=label:gene_regulation",
        "title": "Gene Regulation"
      },
      {
        "link": "https://scholar.google.com/citations?view_op=search_authors&hl=en&mauthors=label:genomics",
        "title": "Genomics"
      },
      {
        "link": "https://scholar.google.com/citations?view_op=search_authors&hl=en&mauthors=label:transcription_factors",
        "title": "Transcription Factors"
      }
    ]
  }
}