Scraping Jobs

import { scrapeJobs } from "jobspy-js";

const result = await scrapeJobs({
  site_name: ["indeed", "linkedin"],
  search_term: "software engineer",
  location: "San Francisco, CA",
  results_wanted: 20,
});

console.log(`Found ${result.jobs.length} jobs`);

interface ScrapeJobsResult {
  jobs: FlatJobRecord[];
  totalScraped: number;
  newCount: number;
  profile?: {
    name: string;
    lastRunAt: string | null;
    stateFile: string;
  };
}

async function scrapeJobs(
  params?: ScrapeJobsParams
): Promise<ScrapeJobsResult>

interface ScrapeJobsResult {
  jobs: FlatJobRecord[];
  totalScraped: number;
  newCount: number;
  profile?: {
    name: string;
    lastRunAt: string | null;
    stateFile: string;
  };
}

import { scrapeJobs } from "jobspy-js";

const { jobs } = await scrapeJobs({
  site_name: "indeed",
  search_term: "software engineer",
  location: "New York, NY",
});

console.log(`Found ${jobs.length} jobs`);
for (const job of jobs) {
  console.log(`${job.title} at ${job.company}`);
}

const { jobs } = await scrapeJobs({
  site_name: ["linkedin", "indeed", "glassdoor"],
  search_term: "data scientist",
  location: "San Francisco, CA",
  results_wanted: 25,
});

// Group results by site
const bySite = jobs.reduce((acc, job) => {
  if (!acc[job.site]) acc[job.site] = [];
  acc[job.site].push(job);
  return acc;
}, {} as Record<string, typeof jobs>);

for (const [site, siteJobs] of Object.entries(bySite)) {
  console.log(`${site}: ${siteJobs.length} jobs`);
}

const { jobs } = await scrapeJobs({
  site_name: ["linkedin", "indeed"],
  search_term: "frontend developer",
  is_remote: true,
  enforce_annual_salary: true,
});

const wellPaid = jobs.filter(
  (j) => j.min_amount && j.min_amount >= 100000
);
console.log(`${wellPaid.length} remote jobs paying $100k+`);

// Jobs posted in the last 24 hours
const { jobs } = await scrapeJobs({
  site_name: ["linkedin", "indeed"],
  search_term: "machine learning engineer",
  hours_old: 24,
  description_format: "plain",
});

// Only jobs from Google and Microsoft on LinkedIn
const { jobs } = await scrapeJobs({
  site_name: "linkedin",
  search_term: "product manager",
  linkedin_company_ids: [1441, 1035],
  linkedin_fetch_description: true,
});

// First run - returns all jobs
const run1 = await scrapeJobs({
  site_name: ["indeed", "linkedin"],
  search_term: "react developer",
  location: "Austin, TX",
  profile: "frontend-jobs",
});
console.log(`First run: ${run1.jobs.length} jobs`);

// Second run (hours later) - returns only new jobs
const run2 = await scrapeJobs({
  site_name: ["indeed", "linkedin"],
  search_term: "react developer",
  location: "Austin, TX",
  profile: "frontend-jobs",
});
console.log(`Second run: ${run2.jobs.length} new jobs`);
console.log(`Total scraped: ${run2.totalScraped}`);
console.log(`Already seen: ${run2.totalScraped - run2.newCount}`);

const { jobs } = await scrapeJobs({
  site_name: ["linkedin", "indeed", "glassdoor"],
  search_term: "developer",
});

// You'll get results from whichever sites succeeded
if (jobs.length === 0) {
  console.log("No jobs found from any site");
}

try {
  const { jobs } = await scrapeJobs({
    site_name: ["linkedin", "indeed"],
    search_term: "developer",
  });
  
  if (jobs.length === 0) {
    console.log("No jobs found - try broadening your search");
  }
} catch (err) {
  // Only throws if all scrapers fail or params are invalid
  console.error("Scrape failed:", err);
}

const { jobs } = await scrapeJobs({
  search_term: "developer",
  verbose: 2,
});