Web Scraping Google Scholar Profile results with Nodejs

What will be scraped

Google Scholar Profiles API

This section will show the difference between our Google Scholar Profiles API and DIY solution.

The difference is that you don't have to write code from scratch and maintain it. You may also experience blocking from Google and changing the selected selectors. Using a ready-made solution from SerpAPI, you just need to iterate the received JSON. Check out the playground.

First we need to install google-search-results-nodejs. To do this you need to enter in your console: npm i google-search-results-nodejs

const SerpApi = require("google-search-results-nodejs");
const search = new SerpApi.GoogleSearch(process.env.API_KEY);             //your API key from serpapi.com

const searchString = "astronomy";                         // what we want to search
const pagesLimit = Infinity;                              // limit of pages for getting info
let currentPage = 1;                                      // current page of the search

const params = {
  engine: "google_scholar_profiles",                      // search engine
  mauthors: searchString,                                 // search query
  hl: "en",                                               // Parameter defines the language to use for the Google search
};

const getScholarProfilesData = function ({ profiles }) {
  return profiles.map((result) => {
    const { name, link = "link not available", author_id, thumbnail, affiliations, email = "no email info", cited_by, interests } = result;
    return {
      name,
      link,
      author_id,
      photo: thumbnail,
      affiliations,
      email,
      cited_by,
      interests:
        interests?.map((interest) => {
          const { title, link = "link not available" } = interest;
          return {
            title,
            link,
          };
        }) || "no interests",
    };
  });
};

const getJson = (params) => {
  return new Promise((resolve) => {
    search.json(params, resolve);
  });
};

const getResults = async () => {
  const profilesResults = [];
  let nextPageToken;
  while (true) {
    if (currentPage > pagesLimit) break;
    const json = await getJson(params);
    nextPageToken = json.pagination.next_page_token;
    params.after_author = nextPageToken;
    profilesResults.push(...(await getScholarProfilesData(json)));
    if (!nextPageToken) break;
    currentPage++;
  }
  return profilesResults;
};

getResults().then((result) => console.dir(result, { depth: null }))

Code explanation

Declare constants from required libraries:

const SerpApi = require("google-search-results-nodejs");
const search = new SerpApi.GoogleSearch(API_KEY);

Next, we write down what we want to search and the necessary parameters for making a request:

const searchString = "astronomy";
const pagesLimit = Infinity;
let currentPage = 1;

const params = {
  engine: "google_scholar_profiles",
  mauthors: searchString,
  hl: "en",
};

Next, we write a callback function in which we describe what data we need from the result of our request:

const getScholarProfilesData = function ({ profiles }) {
  return profiles.map((result) => {
    const { name, link = "link not available", author_id, thumbnail, affiliations, email = "no email info", cited_by, interests } = result;
    return {
      name,
      link,
      author_id,
      photo: thumbnail,
      affiliations,
      email,
      cited_by,
      interests:
        interests?.map((interest) => {
          const { title, link = "link not available" } = interest;
          return {
            title,
            link,
          };
        }) || "no interests",
    };
  });
};

Next, we wrap the search method from the SerpApi library in a promise to further work with the search results:

const getJson = (params) => {
  return new Promise((resolve) => {
    search.json(params, resolve);
  })
}

And finally, we declare and run the function getResult that gets info from all pages between currentPage and pagesLimit and returns it:

const getResults = async () => {
  const profilesResults = [];
  let nextPageToken;
  while (true) {
    if (currentPage > pagesLimit) break;
    const json = await getJson(params);
    nextPageToken = json.pagination.next_page_token;
    params.after_author = nextPageToken;
    profilesResults.push(...(await getScholarProfilesData(json)));
    if (!nextPageToken) break;
    currentPage++;
  }
  return profilesResults;
};

getResults().then((result) => console.dir(result, { depth: null }))

Output

[
   {
      "name":"Gustavo E. Scuseria",
      "link":"https://scholar.google.com/citations?hl=en&user=6ZiRSwQAAAAJ",
      "photo":"https://scholar.googleusercontent.com/citations?view_op=small_photo&user=6ZiRSwQAAAAJ&citpid=2",
      "affiliations":"Welch Professor of Chemistry, Physics & Astronomy, and Materials Science & …",
      "email":"Verified email at rice.edu",
      "cited_by":295031,
      "interests":[
         {
            "title":"Quantum Chemistry",
            "link":"https://scholar.google.com/citations?hl=en&view_op=search_authors&mauthors=label:quantum_chemistry"
         },
         {
            "title":"Electronic Structure",
            "link":"https://scholar.google.com/citations?hl=en&view_op=search_authors&mauthors=label:electronic_structure"
         },
         {
            "title":"Condensed Matter Physics",
            "link":"https://scholar.google.com/citations?hl=en&view_op=search_authors&mauthors=label:condensed_matter_physics"
         },
         {
            "title":"Materials Science",
            "link":"https://scholar.google.com/citations?hl=en&view_op=search_authors&mauthors=label:materials_science"
         },
         {
            "title":"Nanotechnology",
            "link":"https://scholar.google.com/citations?hl=en&view_op=search_authors&mauthors=label:nanotechnology"
         }
      ]
   },
   ...and other results
]

DIY Preparation

First, we need to create a Node.js* project and add npm packages cheerio to parse parts of the HTML markup, and axios to make a request to a website. To do this, in the directory with our project, open the command line and enter npm init -y, and then npm i cheerio axios.

*If you don't have Node.js installed, you can download it from nodejs.org and follow the installation documentation.

Process

SelectorGadget Chrome extension was used to grab CSS selectors by clicking on the desired element in the browser which then returns a matched CSS selector. If you have any struggles understanding this, we have a dedicated Web Scraping with CSS Selectors blog post at SerpApi.
The GIF below illustrates the approach of selecting different HTML elements using SelectorGadget to get a CSS selector which we'll be calling using cheerio.

DIY Code

const cheerio = require("cheerio");
const axios = require("axios");

const searchString = "astronomy";                        // what we want to search
const encodedString = encodeURI(searchString);          // what we want to search for in URI encoding
const pagesLimit = Infinity;                            // limit of pages for getting info

const domain = `http://scholar.google.com`;

const AXIOS_OPTIONS = {
  headers: {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.4951.64 Safari/537.36",
  },                                                    // adding the User-Agent header as one way to prevent the request from being blocked
  params: {
    mauthors: encodedString,                            // our encoded search string
    hl: "en",                                           // parameter defines the language to use for the Google search
    view_op: "search_authors",                          // parameter defines what kind of search we want to use
  },
};

function buildValidLink(rawLink) {
  if (!rawLink) return "link not available";
  return domain + rawLink;
}

function getHTML(link, options = AXIOS_OPTIONS.headers) {
  return axios.get(link, options).then(function ({ data }) {
    return cheerio.load(data);
  });
}

function fillProfilesData($) {
  const profiles = Array.from($(".gsc_1usr")).map((el) => {
    const link = buildValidLink($(el).find(".gs_ai_name a").attr("href"));

    const authorIdPattern = /user=(?<id>[^&]+)/gm                                   //https://regex101.com/r/oxoQEj/1
    const authorId = link.match(authorIdPattern)[0].replace('user=', '')

    return {
      name: $(el).find(".gs_ai_name a").text().trim(),
      link,
      authorId,
      photo: $(el).find(".gs_ai_pho img").attr("src"),
      affiliations: $(el).find(".gs_ai_aff").text().trim().replace("\n", ""),
      email: $(el).find(".gs_ai_eml").text().trim() || "email not available",
      cited_by: $(el).find(".gs_ai_cby").text().trim(),
      interests: Array.from($(el).find(".gs_ai_one_int")).map((interest) => {
        return {
          title: $(interest).text().trim(),
          link: buildValidLink($(interest).attr("href")),
        };
      }),
    };
  });
  const isNextPage = buildValidLink(
    $(".gs_btnPR:not([disabled])")
      ?.attr("onclick")
      ?.replace("window.location='", "")
      .replaceAll("'", "")
      .replaceAll("\\x3d", "=")
      .replaceAll("\\x26", "&")
  );
  return { profiles, isNextPage };
}

function getScholarProfilesInfo(link) {
  if (!link) {
    return getHTML(`${domain}/citations`, AXIOS_OPTIONS).then(fillProfilesData);
  } else {
    return getHTML(link).then(fillProfilesData);
  }
}

async function startScrape() {
  const allProfiles = [];
  let nextPageLink;
  let currentPage = 1;
  while (true) {
    const data = await getScholarProfilesInfo(nextPageLink);
    allProfiles.push(...data.profiles);
    nextPageLink = data.isNextPage;
    currentPage++;
    if (nextPageLink === "link not available" || currentPage > pagesLimit) break;
  }
  return allProfiles;
}

startScrape().then(console.log);

Code explanation

Declare constants from required libraries:

const cheerio = require("cheerio");
const axios = require("axios");

Next, we write in constants what we want to search for and encode our text into a URI string:

const searchString = "astronomy";
const encodedString = encodeURI(searchString);
const pagesLimit = Infinity;

Next, we write down the necessary parameters for making a request:

const AXIOS_OPTIONS = {
  headers: {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.4951.64 Safari/537.36",
  },
  params: {
    mauthors: encodedString,
    hl: "en",
    view_op: "search_authors",
  },
};

Next, we write a function that helps us change the raw links to the correct links. We need to do this with links because some of them start with "/citations" and some don't have links:

function buildValidLink(rawLink) {
  if (!rawLink) return "link not available";
  return domain + rawLink;
}

Next, we write a function that helps us get request data with axios and return this data parsed with cheerio:

function getHTML(link, options = AXIOS_OPTIONS.headers) {
  return axios.get(link, options).then(function ({ data }) {
    return cheerio.load(data);
  });
}

Next, we write down a function for getting information from page:

function fillProfilesData($) {
  const profiles = Array.from($(".gsc_1usr")).map((el) => {
    const link = buildValidLink($(el).find(".gs_ai_name a").attr("href"));

    const authorIdPattern = /user=(?<id>[^&]+)/gm
    const authorId = link.match(authorIdPattern)[0].replace('user=', '')

    return {
      name: $(el).find(".gs_ai_name a").text().trim(),
      link,
      authorId,
      photo: $(el).find(".gs_ai_pho img").attr("src"),
      affiliations: $(el).find(".gs_ai_aff").text().trim().replace("\n", ""),
      email: $(el).find(".gs_ai_eml").text().trim() || "email not available",
      cited_by: $(el).find(".gs_ai_cby").text().trim(),
      interests: Array.from($(el).find(".gs_ai_one_int")).map((interest) => {
        return {
          title: $(interest).text().trim(),
          link: buildValidLink($(interest).attr("href")),
        };
      }),
    };
  });
  const isNextPage = buildValidLink(
    $(".gs_btnPR:not([disabled])")
      ?.attr("onclick")
      ?.replace("window.location='", "")
      .replaceAll("'", "")
      .replaceAll("\\x3d", "=")
      .replaceAll("\\x26", "&")
  );
  return { profiles, isNextPage };
}

Next, we write down a function for making the first request (when link is not defined) and all other requests:

function getScholarProfilesInfo(link) {
  if (!link) {
    return getHTML(`${domain}/citations`, AXIOS_OPTIONS).then(fillProfilesData);
  } else {
    return getHTML(link).then(fillProfilesData);
  }
}

And finally, a function to get the necessary information from each page and put it in an array:

async function startScrape() {
  const allProfiles = [];
  let nextPageLink;
  let currentPage = 1;
  while (true) {
    const data = await getScholarProfilesInfo(nextPageLink);
    allProfiles.push(...data.profiles);
    nextPageLink = data.isNextPage;
    currentPage++;
    if (nextPageLink === "link not available" || currentPage > pagesLimit) break;
  }
  return allProfiles;
}

Now we can launch our parser. To do this enter node YOUR_FILE_NAME in your command line. Where YOUR_FILE_NAME is the name of your .js file.

Output

📌Note: If you see something like [Object] in your console you can use console.dir(result, { depth: null }) instead console.log(). Watch Node.js documentation for more info.

[
   {
      "name":"Gustavo E. Scuseria",
      "link":"http://scholar.google.com/citations?hl=en&user=6ZiRSwQAAAAJ",
      "photo":"https://scholar.googleusercontent.com/citations?view_op=small_photo&user=6ZiRSwQAAAAJ&citpid=2",
      "affiliations":"Welch Professor of Chemistry, Physics & Astronomy, and Materials Science & …",
      "email":"Verified email at rice.edu",
      "cited_by":"Cited by 295031",
      "interests":[
         {
            "title":"Quantum Chemistry",
            "link":"http://scholar.google.com/citations?hl=en&view_op=search_authors&mauthors=label:quantum_chemistry"
         },
         {
            "title":"Electronic Structure",
            "link":"http://scholar.google.com/citations?hl=en&view_op=search_authors&mauthors=label:electronic_structure"
         },
         {
            "title":"Condensed Matter Physics",
            "link":"http://scholar.google.com/citations?hl=en&view_op=search_authors&mauthors=label:condensed_matter_physics"
         },
         {
            "title":"Materials Science",
            "link":"http://scholar.google.com/citations?hl=en&view_op=search_authors&mauthors=label:materials_science"
         },
         {
            "title":"Nanotechnology",
            "link":"http://scholar.google.com/citations?hl=en&view_op=search_authors&mauthors=label:nanotechnology"
         }
      ]
   },
   ...and other results
]

Links

• Code in the online IDE
• Google Scholar API

If you want to see some projects made with SerpApi, please write me a message.

Join us on Twitter | YouTube

Add a Feature Request💫 or a Bug🐞