Collect up to 3000 likers from any LinkedIn post — and export to a .csv file 💞🔵

linkedin_post_likers_scraper.py

# =============================================================================
# Title: LinkedIn Post Likers Scraper
# Description: This script can scrape up to 3000 likers from any LinkedIn post.
# Author: Sasha Bouloudnine
# Date: 2024-03-05
#
# Usage:
# - Install requests using `pip install requests`.
# - Connect to LinkedIn and collect your `li_at` cookie.
# - Get your post URL.
# - Launch the script.
#
# =============================================================================

import requests
import csv
import time
import re


# Update your LI_AT below
# vvvvvvvvvvvvvvvvvvvv

LI_AT = "AQEFARABAAAAAA582xIAAAGN-ncr4gAAAY4eg6_iTQAAs3VybjpsaTplbnRlcnByaXNlQXV0aFRva2VuOmVKeGpaQUFDZGcvUE9TQ2FlMFBHRkJETkVmYjlDU09JWWZlTmJ4V1lJWFhtL0M4R1JnQzJmZ25FXnVybjpsaTplbnRlcnByaXNlUHJvZmlsZToodXJuOmxpOmVudGVycHJpc2VBY2NvdW50OjEyMjE3Nzk0OCwxOTYxMTA0ODQpXnVybjpsaTptZW1iZXI6MzA0NzQwNDUzCJCilw8ToxGdMzR3SPl1TqCZTknBs1duxKFK7L6EsksXVkem6Xq-ZOZRNLuEfpl_6xFR2zcQqQWMPlKPlKJq5AzO8H1mffd4EgVN-MaTu0UEMZdnhd6sLxssWLyAOjDkvPpeab6WM2CfbRitkYiIqyurdTCQrck9Cr3ghlmSBGZlFScZ7xRXu3Xpn3q07cYgenQ5vw"

# Add you URL below
# vvvvvvvvvvvvvvvvvvvv

URL = "https://www.linkedin.com/posts/williamhgates_us-carbon-emissions-fell-in-2023-as-coal-activity-7156808265396285440-EV0P/?utm_source=share&utm_medium=member_desktop"

# Start of the script

HEADERS = {
    'authority': 'www.linkedin.com',
    'accept': 'application/vnd.linkedin.normalized+json+2.1',
    'accept-language': 'fr-FR,fr;q=0.9,en-US;q=0.8,en;q=0.7',
    'cookie': 'li_at=%s; JSESSIONID="%s";',
    'sec-ch-ua': '"Chromium";v="122", "Not(A:Brand";v="24", "Google Chrome";v="122"',
    'sec-ch-ua-mobile': '?0',
    'sec-ch-ua-platform': '"macOS"',
    'sec-fetch-dest': 'empty',
    'sec-fetch-mode': 'cors',
    'sec-fetch-site': 'same-origin',
    'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36',
    'x-li-lang': 'en_US',
    'x-restli-protocol-version': '2.0.0',
}

FIELDNAMES = ["position", "url", "name", "reaction", "connections", "image_url", "input_url"]
DATA = []

class LinkedInLikersScraper(): 

    def __init__(self): 
        self.s = requests.Session()
        # self.s.headers = HEADERS
        self.csrf_token = None

    def get_csrf_token(self): 
        print('[1] getting valid csrf_token')
        response = self.s.get(
            url='https://www.linkedin.com/feed/', 
            headers={
                'authority': 'www.linkedin.com',
                'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
                'accept-language': 'fr-FR,fr;q=0.9',
                'sec-ch-ua': '"Chromium";v="122", "Not(A:Brand";v="24", "Google Chrome";v="122"',
                'sec-ch-ua-mobile': '?0',
                'sec-ch-ua-platform': '"macOS"',
                'sec-fetch-dest': 'document',
                'sec-fetch-mode': 'navigate',
                'sec-fetch-site': 'none',
                'sec-fetch-user': '?1',
                'upgrade-insecure-requests': '1',
                'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36',
            }
        )
        assert response.ok
        cookies_dict = dict(self.s.cookies)
        assert 'JSESSIONID' in cookies_dict.keys()
        self.csrf_token = cookies_dict["JSESSIONID"]
        HEADERS["csrf-token"] = self.csrf_token
        HEADERS["cookie"] = HEADERS["cookie"] % (LI_AT, self.csrf_token)
        print(self.csrf_token)
        print('ok\n')
        time.sleep(1)

    def get_activity_id(self, url): 
        print('[2] getting activity_id')

        # s.headers = headers_get

        _types = ["ugcPost", "activity"]

        response = self.s.get(
            url=url, 
            headers={
                'authority': 'www.linkedin.com',
                'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
                'accept-language': 'fr-FR,fr;q=0.9',
                'cache-control': 'max-age=0',
                'sec-ch-ua': '"Chromium";v="122", "Not(A:Brand";v="24", "Google Chrome";v="122"',
                'sec-ch-ua-mobile': '?0',
                'sec-ch-ua-platform': '"macOS"',
                'sec-fetch-dest': 'document',
                'sec-fetch-mode': 'navigate',
                'sec-fetch-site': 'same-origin',
                'sec-fetch-user': '?1',
                'upgrade-insecure-requests': '1',
                'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36',
            }
        )
        time.sleep(1)
        assert response.ok

        _good_type = None
        _activity_id = None

        for _type in _types: 
            _regex = '(?<=\(urn:li:%s:)\d+' % _type
            activity_ids = re.findall(_regex, response.text)
            activity_ids = list(set(activity_ids))
            if activity_ids and len(activity_ids) == 1: 
                _activity_id = "".join(activity_ids)
                _good_type = _type
                break

        assert all([_activity_id, _good_type])
        print(_activity_id, _good_type)
        print('ok\n')
        return _activity_id, _good_type

    def iter_reviews(self, activity_id, input_url, _type): 
        print('[3] collecting reviews')

        offset = 0
        step = 50
        

        while True: 

            request_url = "https://www.linkedin.com/voyager/api/graphql?includeWebMetadata=true&variables=(count:%s,start:%s,threadUrn:urn%%3Ali%%3A%s%%3A%s)&queryId=voyagerSocialDashReactions.aefc2c6e769fd6de71df5e638b12f76e" % (step, offset, _type, activity_id)

            response = self.s.get(
                request_url, 
                headers=HEADERS
            )

            print(offset, 'ok')
            time.sleep(1)

            try: 
                assert response.ok
            except AssertionError: 
                print(response.text)
                raise
            _included = response.json()["included"]
            if not _included: 
                break
            assert _included and isinstance(_included, list)
            for e in _included: 
                if not 'actorUrn' in e.keys(): 
                    continue
                reactor_lockup = e["reactorLockup"]
                assert reactor_lockup

                try: 
                    position = reactor_lockup["subtitle"]["text"]
                except TypeError: 
                    position = ''
                    pass

                url = reactor_lockup["navigationUrl"]
                name = reactor_lockup["title"]["text"]
                reaction = e["reactionType"]

                try: 
                    connections = reactor_lockup["label"]["text"]
                except TypeError: 
                    connections = ''
                    pass

                try: 
                    _vector_image = reactor_lockup["image"]["attributes"][0]["detailData"]["nonEntityProfilePicture"]["vectorImage"]
                    _root_url = _vector_image["rootUrl"]
                    _large_artifact = _vector_image["artifacts"][-1]["fileIdentifyingUrlPathSegment"]
                    assert all([_root_url, _vector_image])
                    image_url = _root_url+_large_artifact
                except TypeError: 
                    image_url = ''
                    pass

                values = [position, url, name, reaction, connections, image_url, input_url]
                assert all([v is not None for v in values])
                # print(name, url)

                row = dict(zip(FIELDNAMES, values))
                DATA.append(row)

            offset += step

    def save_in_file(self, data): 
        with open('results_linkedin_post_likers_lobstrio.txt', 'w') as g: 
            writer = csv.DictWriter(g, delimiter='\t', fieldnames=FIELDNAMES)
            writer.writeheader()
            for row in data: 
                writer.writerow(row)

def main(): 
    print('[0] starting %s' % URL)
    print('ok\n')
    time.sleep(2)
    l = LinkedInLikersScraper()
    l.get_csrf_token()

    activity_id, _type = l.get_activity_id(URL)
    assert activity_id

    l.iter_reviews(activity_id, URL, _type)

    l.save_in_file(DATA)
    print('done :°')


if __name__ == '__main__':
    main()