LinkedIn Scraper

app.py

from voyager import Voyager

def main():
    voyager = Voyager()

    sample_job_id = 3785477367

    job = voyager.get_job(sample_job_id)
    print(f"{job = }")
    print("*"*40)

    job_clean = voyager.get_job(sample_job_id, clean=True)
    print(f"{job_clean = }")
    print("*"*40)

    jobs_clean = voyager.get_jobs(list(range(sample_job_id - 100, sample_job_id)), clean=True)
    print(f"{jobs_clean = }")
    print("*"*40)
    
    
if __name__ == "__main__":
    main()

voyager.py

# NOTE: Fill the li_at variable at line 46

import requests

class Voyager:

    def __init__(self):
        self.session = self._create_session()
        self.url = "https://www.linkedin.com/voyager/api/voyagerJobsJobPostings/"
        self.keys = [
            "jobPostingUrl",
            "title",
            "formattedLocation",
            "formattedExperienceLevel",
            "formattedEmploymentStatus",
            "formattedJobFunctions",
            "formattedIndustries",
            "formattedSalaryDescription",
            "benefits",
            "localizedCostPerApplicantChargeableRegion",
            "workRemoteAllowed",
            #"originalListedAt",
            "views",
            #"applies",
            "applyMethod"
        ]


    def get_job(self, job_id, clean=False):
        r = self.session.get(self.url + str(job_id))
        if clean:
            return {key: r.json().get(key) for key in self.keys}
        return r.json()


    def get_jobs(self, job_ids, clean=False):
        ids = ",".join([str(job_id) for job_id in job_ids])
        r = self.session.get(f"{self.url}?ids=List({ids})")
        if clean:
            return [{key: item.get(key) for key in self.keys} for item in r.json().get("results").values()]
        return r.json()
        

    def _create_session(self):
        token = "1251184134771286165"
        li_at = "" # Get this cookie after you logged in to linkedin.

        headers = {
            "User-Agent": "LinkedIn/9.28.7219 CFNetwork/1410.0.3 Darwin/22.6.0",
            "Accept": "application/json",
            "Csrf-Token": f"ajax:{token}",
            "Cookie": f'JSESSIONID="ajax:{token}"; li_at={li_at}'
        }

        session = requests.Session()
        session.headers.update(headers)
        return session