Scrape ResearchGate Profile Page in Python

What will be scraped

image

Prerequisites

Basic knowledge scraping with CSS selectors

CSS selectors declare which part of the markup a style applies to thus allowing to extract of data from matching tags and attributes.

If you haven't scraped with CSS selectors, there's a dedicated blog post of mine about how to use CSS selectors when web-scraping that covers what it is, pros and cons, and why they're matter from a web-scraping perspective and show the most common approaches of using CSS selectors when web scraping.

Reduce the chance of being blocked

There's a chance that a request might be blocked. Have a look at how to reduce the chance of being blocked while web-scraping, there are eleven methods to bypass blocks from most websites.

Install libraries:

pip install parsel playwright

Full Code

from parsel import Selector
from playwright.sync_api import sync_playwright
import json, re 


def scrape_researchgate_profile(profile: str):
    with sync_playwright() as p:

        profile_data = {
            "basic_info": {},
            "about": {},
            "co_authors": [],
            "publications": [],
        }

        browser = p.chromium.launch(headless=True, slow_mo=50)
        page = browser.new_page(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")
        page.goto(f"https://www.researchgate.net/profile/{profile}")
        selector = Selector(text=page.content())

        profile_data["basic_info"]["name"] = selector.css(".nova-legacy-e-text.nova-legacy-e-text--size-xxl::text").get()
        profile_data["basic_info"]["institution"] = selector.css(".nova-legacy-v-institution-item__stack-item a::text").get()
        profile_data["basic_info"]["department"] = selector.css(".nova-legacy-e-list__item.nova-legacy-v-institution-item__meta-data-item:nth-child(1)").xpath("normalize-space()").get()
        profile_data["basic_info"]["current_position"] = selector.css(".nova-legacy-e-list__item.nova-legacy-v-institution-item__info-section-list-item").xpath("normalize-space()").get()
        profile_data["basic_info"]["lab"] = selector.css(".nova-legacy-o-stack__item .nova-legacy-e-link--theme-bare b::text").get()

        profile_data["about"]["number_of_publications"] = re.search(r"\d+", selector.css(".nova-legacy-c-card__body .nova-legacy-o-grid__column:nth-child(1)").xpath("normalize-space()").get()).group()
        profile_data["about"]["reads"] = re.search(r"\d+", selector.css(".nova-legacy-c-card__body .nova-legacy-o-grid__column:nth-child(2)").xpath("normalize-space()").get()).group()
        profile_data["about"]["citations"] = re.search(r"\d+", selector.css(".nova-legacy-c-card__body .nova-legacy-o-grid__column:nth-child(3)").xpath("normalize-space()").get()).group()
        profile_data["about"]["introduction"] = selector.css(".nova-legacy-o-stack__item .Linkify").xpath("normalize-space()").get()
        profile_data["about"]["skills"] = selector.css(".nova-legacy-l-flex__item .nova-legacy-e-badge ::text").getall()

        for co_author in selector.css(".nova-legacy-c-card--spacing-xl .nova-legacy-c-card__body--spacing-inherit .nova-legacy-v-person-list-item"):
            profile_data["co_authors"].append({
                "name": co_author.css(".nova-legacy-v-person-list-item__align-content .nova-legacy-e-link::text").get(),
                "link": co_author.css(".nova-legacy-l-flex__item a::attr(href)").get(),
                "avatar": co_author.css(".nova-legacy-l-flex__item .lite-page-avatar img::attr(data-src)").get(),
                "current_institution": co_author.css(".nova-legacy-v-person-list-item__align-content li").xpath("normalize-space()").get()
            })

        for publication in selector.css("#publications+ .nova-legacy-c-card--elevation-1-above .nova-legacy-o-stack__item"):
            profile_data["publications"].append({
                "title": publication.css(".nova-legacy-v-publication-item__title .nova-legacy-e-link--theme-bare::text").get(),
                "date_published": publication.css(".nova-legacy-v-publication-item__meta-data-item span::text").get(),
                "authors": publication.css(".nova-legacy-v-person-inline-item__fullname::text").getall(),
                "publication_type": publication.css(".nova-legacy-e-badge--theme-solid::text").get(),
                "description": publication.css(".nova-legacy-v-publication-item__description::text").get(),
                "publication_link": publication.css(".nova-legacy-c-button-group__item .nova-legacy-c-button::attr(href)").get(),
            })


        print(json.dumps(profile_data, indent=2, ensure_ascii=False))

        browser.close()


scrape_researchgate_profile(profile="Agnis-Stibe")

Code explanation

Import libraries:

from parsel import Selector
from playwright.sync_api import sync_playwright
import re, json, time
CodeExplanation
parselto parse HTML/XML documents. Supports XPath.
playwrightto render the page with a browser instance.
reto match parts of the data with regular expression.
jsonto convert Python dictionary to JSON string.

Define a function:

def scrape_researchgate_profile(profile: str):
    # ...
CodeExplanation
profile: strto tell Python that profile should be an str.

Open a playwright with a context manager:

with sync_playwright() as p:
    # ...

Define the structure of the extracted data:

profile_data = {
    "basic_info": {},
    "about": {},
    "co_authors": [],
    "publications": [],
}

Lunch a browser instance, open and goto the page and pass response to HTML/XML parser:

browser = p.chromium.launch(headless=True, slow_mo=50)
page = browser.new_page(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")
page.goto(f"https://www.researchgate.net/profile/{profile}")
selector = Selector(text=page.content())
CodeExplanation
p.chromium.launch()to launch Chromium browser instance.
headlessto explicitly tell playwright to run in headless mode even though it's a default value.
slow_moto tell playwright to slow down execution.
browser.new_page()to open new page. user_agent is used to act a real user makes a request from the browser. If not used, it will default to playwright value which is None. Check what's your user-agent.

Update basic_info dictionary key, create new keys, and assing extracted data:

profile_data["basic_info"]["name"] = selector.css(".nova-legacy-e-text.nova-legacy-e-text--size-xxl::text").get()
profile_data["basic_info"]["institution"] = selector.css(".nova-legacy-v-institution-item__stack-item a::text").get()
profile_data["basic_info"]["department"] = selector.css(".nova-legacy-e-list__item.nova-legacy-v-institution-item__meta-data-item:nth-child(1)").xpath("normalize-space()").get()
profile_data["basic_info"]["current_position"] = selector.css(".nova-legacy-e-list__item.nova-legacy-v-institution-item__info-section-list-item").xpath("normalize-space()").get()
profile_data["basic_info"]["lab"] = selector.css(".nova-legacy-o-stack__item .nova-legacy-e-link--theme-bare b::text").get()
CodeExplanation
profile_data["basic_info"]["name"]to access earlier created basic_info key, and then create a new ["name"] key, and assign extracted data.
css()to parse data from the passed CSS selector(s). Every CSS query traslates to XPath using csselect package under the hood.
::textto extract textual data from the node.
get()to get actual data from a matched node
xpath("normalize-space()")to parse blank text node as well. By default, blank text node is be skipped by XPath.

Update about dictionary key, create new keys, and assing extracted data:

profile_data["about"]["number_of_publications"] = re.search(r"\d+", selector.css(".nova-legacy-c-card__body .nova-legacy-o-grid__column:nth-child(1)").xpath("normalize-space()").get()).group()
profile_data["about"]["reads"] = re.search(r"\d+", selector.css(".nova-legacy-c-card__body .nova-legacy-o-grid__column:nth-child(2)").xpath("normalize-space()").get()).group()
profile_data["about"]["citations"] = re.search(r"\d+", selector.css(".nova-legacy-c-card__body .nova-legacy-o-grid__column:nth-child(3)").xpath("normalize-space()").get()).group()
profile_data["about"]["introduction"] = selector.css(".nova-legacy-o-stack__item .Linkify").xpath("normalize-space()").get()
profile_data["about"]["skills"] = selector.css(".nova-legacy-l-flex__item .nova-legacy-e-badge ::text").getall()
CodeExplanation
profile_data["basic_info"]["name"]to access earlier created basic_info key, and then create a new ["name"] key, and assign extracted data.
re.search(r"\d+", <returned_data_from_parsel>).group()to extract digit data via re.search() regular expression \d+ from the returned string. group() is to extract substring that was matched by the regular expression.
css()to parse data from the passed CSS selector(s). Every CSS query traslates to XPath using csselect package under the hood.
::textto extract textual data from the node.
get()/getall()to get actual data from a matched node, or to get a list of matched data from nodes.
xpath("normalize-space()")to parse blank text node as well. By default, blank text node is be skipped by XPath.

Iterate over co-authors and extract individual co-author, and append to the temporary list:

for co_author in selector.css(".nova-legacy-c-card--spacing-xl .nova-legacy-c-card__body--spacing-inherit .nova-legacy-v-person-list-item"):
    profile_data["co_authors"].append({
        "name": co_author.css(".nova-legacy-v-person-list-item__align-content .nova-legacy-e-link::text").get(),
        "link": co_author.css(".nova-legacy-l-flex__item a::attr(href)").get(),
        "avatar": co_author.css(".nova-legacy-l-flex__item .lite-page-avatar img::attr(data-src)").get(),
        "current_institution": co_author.css(".nova-legacy-v-person-list-item__align-content li").xpath("normalize-space()").get()
    })
CodeExplanation
::attr(attribute)to extract attribute data from the node.

Next is to iterate over all publications and extract individual publications, and append to a temporary list:

for publication in selector.css("#publications+ .nova-legacy-c-card--elevation-1-above .nova-legacy-o-stack__item"):
    profile_data["publications"].append({
        "title": publication.css(".nova-legacy-v-publication-item__title .nova-legacy-e-link--theme-bare::text").get(),
        "date_published": publication.css(".nova-legacy-v-publication-item__meta-data-item span::text").get(),
        "authors": publication.css(".nova-legacy-v-person-inline-item__fullname::text").getall(),
        "publication_type": publication.css(".nova-legacy-e-badge--theme-solid::text").get(),
        "description": publication.css(".nova-legacy-v-publication-item__description::text").get(),
        "publication_link": publication.css(".nova-legacy-c-button-group__item .nova-legacy-c-button::attr(href)").get(),
    })

Print extracted data, and close browser instance:

print(json.dumps(profile_data, indent=2, ensure_ascii=False))

browser.close()


# call function. "profiles" could be a list of authors.
# author name should be with a "-", otherwise ResearchGate doesn't recognize it.
scrape_researchgate_profile(profile="Agnis-Stibe")

Part of the JSON output:

{
  "basic_info": {
    "name": "Agnis Stibe",
    "institution": "EM Normandie Business School",
    "department": "Supply Chain Management & Decision Sciences",
    "current_position": "Artificial Inteligence Program Director",
    "lab": "Riga Technical University"
  },
  "about": {
    "number_of_publications": "71",
    "reads": "40",
    "citations": "572",
    "introduction": "4x TEDx speaker, MIT alum, YouTube creator. Globally recognized corporate consultant and scientific advisor at AgnisStibe.com. Provides a science-driven STIBE method and practical tools for hyper-performance. Academic Director on Artificial Intelligence and Professor of Transformation at EM Normandie Business School. Paris Lead of Silicon Valley founded Transformative Technology community. At the renowned Massachusetts Institute of Technology, he established research on Persuasive Cities.",
    "skills": [
      "Social Influence",
      "Behavior Change",
      "Persuasive Design",
      "Motivational Psychology",
      "Artificial Intelligence",
      "Change Management",
      "Business Transformation"
    ]
  },
  "co_authors": [
    {
      "name": "Mina Khan",
      "link": "profile/Mina-Khan-2",
      "avatar": "https://i1.rgstatic.net/ii/profile.image/387771463159814-1469463329918_Q64/Mina-Khan-2.jpg",
      "current_institution": "Massachusetts Institute of Technology"
    }, ... other co-authors
  ],
  "publications": [
    {
      "title": "Change Masters: Using the Transformation Gene to Empower Hyper-Performance at Work",
      "date_published": "May 2020",
      "authors": [
        "Agnis Stibe"
      ],
      "publication_type": "Article",
      "description": "Achieving hyper-performance is an essential aim not only for organizations and societies but also for individuals. Digital transformation is reshaping the workplace so fast that people start falling behind, with their poor attitudes remaining the ultimate obstacle. The alignment of human-machine co-evolution is the only sustainable strategy for the...",
      "publication_link": "https://www.researchgate.net/publication/342716663_Change_Masters_Using_the_Transformation_Gene_to_Empower_Hyper-Performance_at_Work"
    }, ... other publications
  ]
}

Join us on Twitter | YouTube

Add a Feature Request💫 or a Bug🐞