LinkedIn jobs API: search public job postings as JSON

export TOOLZERHUB_API_KEY=your_key
curl -H "x-api-key: $TOOLZERHUB_API_KEY" \
  "https://api.toolzerhub.com/v1/linkedin/jobs/search?keywords=data%20engineer&location=United%20States"

{
  "job_id": "4454862094",
  "title": "Senior Data Engineer, DX",
  "company": "Atlassian",
  "location": "Salt Lake City, UT",
  "posted_at": "2026-10-18",
  "salary": null,
  "benefits": "Actively Hiring",
  "url": "https://www.linkedin.com/jobs/view/senior-data-engineer-dx-at-atlassian-4454862094"
}

import csv
import os
import re
import sys
import time

import requests

API = "https://api.toolzerhub.com/v1/linkedin"
HEADERS = {"x-api-key": os.environ.get("TOOLZERHUB_API_KEY", "")}
FIELDS = ["query", "location", "job_id", "title", "company", "job_location", "posted_at", "applicants",
          "seniority", "employment_type", "industries", "pay_range", "url"]
# A pay range such as "$130,000 - $180,000", "$155K-$160K" or "$45.00 to $60.00", so a lone
# figure like a signing bonus is not counted.
AMOUNT = r"\d{1,3}(?:,\d{3})+(?:\.\d+)?|\d{2,3}(?:\.\d+)?\s?[kK]\b|\d{2,3}\.\d{2}"
PAY = re.compile(rf"[$£€]\s?(?:{AMOUNT})\s?(?:-|–|—|to)\s?[$£€]?\s?(?:{AMOUNT})")


def get(op, params, tries=3):
    # Retry rate limits, server errors and dropped connections.
    for attempt in range(tries):
        last = attempt == tries - 1
        try:
            r = requests.get(f"{API}/{op}", headers=HEADERS, params=params, timeout=120)
        except requests.RequestException:
            if last:
                raise
            time.sleep(5 * (attempt + 1))
            continue
        if r.status_code in (429, 500, 502, 503, 504) and not last:
            time.sleep(5 * (attempt + 1))
            continue
        r.raise_for_status()
        return r.json()["data"]


def main(query, locations, pages="3", out="linkedin_jobs.csv"):
    with open(out, "w", newline="", encoding="utf-8") as f:
        writer = csv.DictWriter(f, fieldnames=FIELDS)
        writer.writeheader()
        for name in filter(None, (l.strip() for l in locations.split(";"))):
            # Plain text is ambiguous ("Denver" can match Denver, North Carolina), so search by geo_id.
            place = get("geo/typeahead", {"query": name})["hits"][0]
            location = place["display_name"]
            jobs, seen = [], set()
            for page in range(int(pages)):
                data = get("jobs/search", {"keywords": query, "geo_id": place["geo_id"], "start": page * 10})
                for j in data.get("jobs") or []:
                    if j["job_id"] not in seen:
                        seen.add(j["job_id"])
                        jobs.append(j)
                if len(data.get("jobs") or []) < 10:
                    break
            with_pay, over_200, under_25 = 0, 0, 0
            for j in jobs:
                d = get("jobs/detail", {"job_id": j["job_id"]})
                criteria = d.get("criteria") or {}
                pay = PAY.findall(d.get("description_text") or "")
                with_pay += bool(pay)
                # LinkedIn shows "Over 200 applicants" and "Be among the first 25 applicants" instead of a count.
                over_200 += (d.get("applicants") or "").startswith("Over 200")
                under_25 += "first 25" in (d.get("applicants") or "")
                writer.writerow({
                    "query": query, "location": location, "job_id": j["job_id"], "title": j["title"],
                    "company": j["company"], "job_location": j["location"], "posted_at": j.get("posted_at"),
                    "applicants": d.get("applicants"), "seniority": criteria.get("Seniority level"),
                    "employment_type": criteria.get("Employment type"), "industries": criteria.get("Industries"),
                    "pay_range": pay[0] if pay else "", "url": j["url"],
                })
            print(f"{location}: {len(jobs)} jobs, {with_pay} state a pay range, "
                  f"{over_200} with over 200 applicants, {under_25} with under 25")


if __name__ == "__main__":
    if len(sys.argv) < 3:
        sys.exit('usage: python linkedin_jobs.py "software engineer" "San Francisco;Austin" [pages] [out.csv]')
    if not HEADERS["x-api-key"]:
        sys.exit("set TOOLZERHUB_API_KEY first")
    main(*sys.argv[1:])