jobspy-js 1.1.0

package/README.md

@@ -0,0 +1,158 @@
+# jobspy-js
+
+TypeScript port of [JobSpy](https://github.com/speedyapply/JobSpy) — scrape job postings from LinkedIn, Indeed, Glassdoor, Google Jobs, Google Careers, ZipRecruiter, Bayt, Naukri & BDJobs.
+
+Uses [wreq-js](https://github.com/nicehash/wreq-js) for browser TLS fingerprint emulation (Chrome/Firefox/Safari).
+
+## Features
+
+- **9 job boards** — LinkedIn, Indeed, Glassdoor, Google Jobs, Google Careers, ZipRecruiter, Bayt, Naukri, BDJobs
+- **3 interfaces** — SDK, CLI, MCP server
+- **Browser emulation** — wreq-js with full TLS fingerprinting (JA3/JA4)
+- **Proxy rotation** — built-in rotating proxy support
+- **Concurrent scraping** — all sites scraped in parallel
+- **Salary extraction** — parses compensation from descriptions when not provided directly
+- **60+ countries** — Indeed/Glassdoor regional domain support
+
+## Supported Sites
+
+| Site | Key | Notes |
+|------|-----|-------|
+| LinkedIn | `linkedin` | HTML scraping |
+| Indeed | `indeed` | GraphQL API |
+| Glassdoor | `glassdoor` | GraphQL API |
+| Google Jobs | `google` | Playwright (headless Chrome); requires clean residential IP or proxy |
+| Google Careers | `google_careers` | Plain HTTP; scrapes jobs at Google the company |
+| ZipRecruiter | `zip_recruiter` | Web scraping |
+| Bayt | `bayt` | HTML scraping |
+| Naukri | `naukri` | REST API |
+| BDJobs | `bdjobs` | REST API |
+
+## Installation
+
+```bash
+npm install jobspy-js
+```
+
+> **Google Jobs** (`google`) uses [Playwright](https://playwright.dev) to execute JavaScript. After installing, run:
+> ```bash
+> npx playwright install chromium
+> ```
+
+## SDK Usage
+
+```ts
+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 ${result.jobs.length} jobs`);
+for (const job of result.jobs) {
+  console.log(`${job.title} at ${job.company} — ${job.job_url}`);
+}
+```
+
+### Parameters
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `site_name` | `string[]` | all sites | Job boards to scrape |
+| `search_term` | `string` | — | Job title / search query |
+| `location` | `string` | — | Job location (e.g. `"San Francisco, CA"`) |
+| `distance` | `number` | `50` | Search radius in miles |
+| `is_remote` | `boolean` | `false` | Filter for remote jobs |
+| `job_type` | `string` | — | `fulltime`, `parttime`, `contract`, `internship` |
+| `results_wanted` | `number` | `15` | Results per site |
+| `country_indeed` | `string` | `"usa"` | Country for Indeed/Glassdoor |
+| `hours_old` | `number` | — | Filter jobs posted within N hours |
+| `description_format` | `string` | `"markdown"` | `markdown`, `html`, or `plain` |
+| `proxies` | `string \| string[]` | — | Proxy servers (`user:pass@host:port`) |
+| `linkedin_fetch_description` | `boolean` | `false` | Fetch full LinkedIn descriptions (slower) |
+| `enforce_annual_salary` | `boolean` | `false` | Convert all salaries to annual |
+
+## CLI
+
+```bash
+# Search for React jobs on LinkedIn
+npx jobspy -s linkedin -q "react developer" -l "New York, NY" -n 20
+
+# Multiple sites, remote only, output to file
+npx jobspy -s linkedin indeed -q "typescript" -r -o results.json
+
+# CSV output
+npx jobspy -s indeed -q "python" -o jobs.csv
+
+# Google Careers (jobs at Google)
+npx jobspy -s google_careers -q "software engineer" -l "USA" -n 10
+```
+
+Run `npx jobspy --help` for all options.
+
+## MCP Server
+
+Add to your MCP client config:
+
+```json
+{
+  "mcpServers": {
+    "jobspy": {
+      "command": "npx",
+      "args": ["-y", "jobspy-js", "--mcp"]
+    }
+  }
+}
+```
+
+The MCP server exposes a `scrape_jobs` tool with all the same parameters as the SDK.
+
+## Development
+
+```bash
+git clone https://github.com/borgius/jobspy-js.git
+cd jobspy-js
+npm install
+
+# Build
+npm run build
+
+# Type check
+npm run typecheck
+
+# Run CLI from source
+npm run cli -- -s linkedin -q "react" -n 5
+
+# Run tests
+npm test
+```
+
+## Project Structure
+
+```
+src/
+├── index.ts              # SDK entry point
+├── scraper.ts            # Main scrapeJobs() orchestrator
+├── types.ts              # All types, enums, country config
+├── utils.ts              # Logger, proxy rotation, HTML helpers
+├── cli/index.ts          # CLI (commander)
+├── mcp/index.ts          # MCP server
+└── scrapers/
+    ├── base.ts           # Abstract Scraper base class
+    ├── indeed/           # GraphQL API
+    ├── linkedin/         # HTML scraping
+    ├── glassdoor/        # GraphQL API
+    ├── google/           # Playwright headless Chrome
+    ├── google-careers/   # Plain HTTP; AF_initDataCallback JSON parsing
+    ├── ziprecruiter/     # Web scraping
+    ├── bayt/             # HTML scraping
+    ├── naukri/           # REST API
+    └── bdjobs/           # REST API
+```
+
+## License
+
+MIT

package/dist/cli/index.d.ts

@@ -0,0 +1 @@
+export {};

package/dist/cli/index.js

@@ -0,0 +1,98 @@
+#!/usr/bin/env node
+import { Command } from "commander";
+import { s as scrapeJobs } from "../shared/scraper-CuXnl6Gf.js";
+import { writeFileSync } from "node:fs";
+const program = new Command();
+program.name("jobspy").description(
+  "Job scraper for LinkedIn, Indeed, Glassdoor, Google, ZipRecruiter, Bayt, Naukri & BDJobs"
+).version("1.0.0").option(
+  "-s, --site <sites...>",
+  "Job boards to scrape (linkedin, indeed, zip_recruiter, glassdoor, google, bayt, naukri, bdjobs)"
+).option("-q, --search-term <term>", "Search term").option("--google-search-term <term>", "Google-specific search term").option("-l, --location <location>", "Job location").option("-d, --distance <miles>", "Distance in miles", "50").option("-r, --remote", "Filter for remote jobs").option(
+  "-t, --job-type <type>",
+  "Job type (fulltime, parttime, contract, internship)"
+).option("--easy-apply", "Filter for easy apply jobs").option("-n, --results <count>", "Number of results wanted", "15").option(
+  "-c, --country <country>",
+  "Country for Indeed/Glassdoor",
+  "usa"
+).option(
+  "-p, --proxies <proxies...>",
+  "Proxy servers (user:pass@host:port)"
+).option(
+  "--format <format>",
+  "Description format (markdown, html, plain)",
+  "markdown"
+).option("--linkedin-fetch-description", "Fetch full LinkedIn descriptions").option(
+  "--linkedin-company-ids <ids...>",
+  "LinkedIn company IDs to filter"
+).option("--offset <offset>", "Start from offset", "0").option(
+  "--hours-old <hours>",
+  "Filter jobs posted within N hours"
+).option("--enforce-annual-salary", "Convert all salaries to annual").option("-v, --verbose <level>", "Verbosity (0=errors, 1=warnings, 2=all)", "0").option("-o, --output <file>", "Output file path (JSON or CSV based on extension)").action(async (opts) => {
+  try {
+    const result = await scrapeJobs({
+      site_name: opts.site,
+      search_term: opts.searchTerm,
+      google_search_term: opts.googleSearchTerm,
+      location: opts.location,
+      distance: parseInt(opts.distance),
+      is_remote: opts.remote ?? false,
+      job_type: opts.jobType,
+      easy_apply: opts.easyApply,
+      results_wanted: parseInt(opts.results),
+      country_indeed: opts.country,
+      proxies: opts.proxies,
+      description_format: opts.format,
+      linkedin_fetch_description: opts.linkedinFetchDescription,
+      linkedin_company_ids: opts.linkedinCompanyIds?.map(Number),
+      offset: parseInt(opts.offset),
+      hours_old: opts.hoursOld ? parseInt(opts.hoursOld) : void 0,
+      enforce_annual_salary: opts.enforceAnnualSalary ?? false,
+      verbose: parseInt(opts.verbose)
+    });
+    console.log(`Found ${result.jobs.length} jobs`);
+    if (opts.output) {
+      const outPath = opts.output;
+      if (outPath.endsWith(".csv")) {
+        writeFileSync(outPath, jobsToCsv(result.jobs));
+        console.log(`Results written to ${outPath}`);
+      } else {
+        writeFileSync(outPath, JSON.stringify(result.jobs, null, 2));
+        console.log(`Results written to ${outPath}`);
+      }
+    } else {
+      for (const job of result.jobs) {
+        const line = [
+          job.site?.padEnd(14),
+          (job.title ?? "").slice(0, 40).padEnd(42),
+          (job.company ?? "").slice(0, 20).padEnd(22),
+          (job.location ?? "").slice(0, 25).padEnd(27),
+          job.date_posted ?? ""
+        ].join("");
+        console.log(line);
+      }
+    }
+  } catch (e) {
+    console.error(`Error: ${e.message}`);
+    process.exit(1);
+  }
+});
+function jobsToCsv(jobs) {
+  if (jobs.length === 0) return "";
+  const headers = Object.keys(jobs[0]);
+  const escape = (val) => {
+    if (val == null) return "";
+    const str = String(val);
+    if (str.includes(",") || str.includes('"') || str.includes("\n")) {
+      return `"${str.replace(/"/g, '""')}"`;
+    }
+    return str;
+  };
+  const lines = [headers.join(",")];
+  for (const job of jobs) {
+    lines.push(headers.map((h) => escape(job[h])).join(","));
+  }
+  return lines.join("\n");
+}
+program.parse();
+//# sourceMappingURL=index.js.map

package/dist/cli/index.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","sources":["../../src/cli/index.ts"],"sourcesContent":["import { Command } from \"commander\";\nimport { scrapeJobs } from \"../scraper\";\nimport { Site } from \"../types\";\nimport { writeFileSync } from \"node:fs\";\n\nconst program = new Command();\n\nprogram\n  .name(\"jobspy\")\n  .description(\n    \"Job scraper for LinkedIn, Indeed, Glassdoor, Google, ZipRecruiter, Bayt, Naukri & BDJobs\",\n  )\n  .version(\"1.0.0\")\n  .option(\n    \"-s, --site <sites...>\",\n    \"Job boards to scrape (linkedin, indeed, zip_recruiter, glassdoor, google, bayt, naukri, bdjobs)\",\n  )\n  .option(\"-q, --search-term <term>\", \"Search term\")\n  .option(\"--google-search-term <term>\", \"Google-specific search term\")\n  .option(\"-l, --location <location>\", \"Job location\")\n  .option(\"-d, --distance <miles>\", \"Distance in miles\", \"50\")\n  .option(\"-r, --remote\", \"Filter for remote jobs\")\n  .option(\n    \"-t, --job-type <type>\",\n    \"Job type (fulltime, parttime, contract, internship)\",\n  )\n  .option(\"--easy-apply\", \"Filter for easy apply jobs\")\n  .option(\"-n, --results <count>\", \"Number of results wanted\", \"15\")\n  .option(\n    \"-c, --country <country>\",\n    \"Country for Indeed/Glassdoor\",\n    \"usa\",\n  )\n  .option(\n    \"-p, --proxies <proxies...>\",\n    \"Proxy servers (user:pass@host:port)\",\n  )\n  .option(\n    \"--format <format>\",\n    \"Description format (markdown, html, plain)\",\n    \"markdown\",\n  )\n  .option(\"--linkedin-fetch-description\", \"Fetch full LinkedIn descriptions\")\n  .option(\n    \"--linkedin-company-ids <ids...>\",\n    \"LinkedIn company IDs to filter\",\n  )\n  .option(\"--offset <offset>\", \"Start from offset\", \"0\")\n  .option(\n    \"--hours-old <hours>\",\n    \"Filter jobs posted within N hours\",\n  )\n  .option(\"--enforce-annual-salary\", \"Convert all salaries to annual\")\n  .option(\"-v, --verbose <level>\", \"Verbosity (0=errors, 1=warnings, 2=all)\", \"0\")\n  .option(\"-o, --output <file>\", \"Output file path (JSON or CSV based on extension)\")\n  .action(async (opts) => {\n    try {\n      const result = await scrapeJobs({\n        site_name: opts.site,\n        search_term: opts.searchTerm,\n        google_search_term: opts.googleSearchTerm,\n        location: opts.location,\n        distance: parseInt(opts.distance),\n        is_remote: opts.remote ?? false,\n        job_type: opts.jobType,\n        easy_apply: opts.easyApply,\n        results_wanted: parseInt(opts.results),\n        country_indeed: opts.country,\n        proxies: opts.proxies,\n        description_format: opts.format,\n        linkedin_fetch_description: opts.linkedinFetchDescription,\n        linkedin_company_ids: opts.linkedinCompanyIds?.map(Number),\n        offset: parseInt(opts.offset),\n        hours_old: opts.hoursOld ? parseInt(opts.hoursOld) : undefined,\n        enforce_annual_salary: opts.enforceAnnualSalary ?? false,\n        verbose: parseInt(opts.verbose),\n      });\n\n      console.log(`Found ${result.jobs.length} jobs`);\n\n      if (opts.output) {\n        const outPath = opts.output as string;\n        if (outPath.endsWith(\".csv\")) {\n          writeFileSync(outPath, jobsToCsv(result.jobs));\n          console.log(`Results written to ${outPath}`);\n        } else {\n          writeFileSync(outPath, JSON.stringify(result.jobs, null, 2));\n          console.log(`Results written to ${outPath}`);\n        }\n      } else {\n        // Print summary table to stdout\n        for (const job of result.jobs) {\n          const line = [\n            job.site?.padEnd(14),\n            (job.title ?? \"\").slice(0, 40).padEnd(42),\n            (job.company ?? \"\").slice(0, 20).padEnd(22),\n            (job.location ?? \"\").slice(0, 25).padEnd(27),\n            job.date_posted ?? \"\",\n          ].join(\"\");\n          console.log(line);\n        }\n      }\n    } catch (e: any) {\n      console.error(`Error: ${e.message}`);\n      process.exit(1);\n    }\n  });\n\nfunction jobsToCsv(jobs: any[]): string {\n  if (jobs.length === 0) return \"\";\n  const headers = Object.keys(jobs[0]);\n  const escape = (val: any): string => {\n    if (val == null) return \"\";\n    const str = String(val);\n    if (str.includes(\",\") || str.includes('\"') || str.includes(\"\\n\")) {\n      return `\"${str.replace(/\"/g, '\"\"')}\"`;\n    }\n    return str;\n  };\n  const lines = [headers.join(\",\")];\n  for (const job of jobs) {\n    lines.push(headers.map((h) => escape(job[h])).join(\",\"));\n  }\n  return lines.join(\"\\n\");\n}\n\nprogram.parse();\n"],"names":[],"mappings":";;;;AAKA,MAAM,UAAU,IAAI,QAAA;AAEpB,QACG,KAAK,QAAQ,EACb;AAAA,EACC;AACF,EACC,QAAQ,OAAO,EACf;AAAA,EACC;AAAA,EACA;AACF,EACC,OAAO,4BAA4B,aAAa,EAChD,OAAO,+BAA+B,6BAA6B,EACnE,OAAO,6BAA6B,cAAc,EAClD,OAAO,0BAA0B,qBAAqB,IAAI,EAC1D,OAAO,gBAAgB,wBAAwB,EAC/C;AAAA,EACC;AAAA,EACA;AACF,EACC,OAAO,gBAAgB,4BAA4B,EACnD,OAAO,yBAAyB,4BAA4B,IAAI,EAChE;AAAA,EACC;AAAA,EACA;AAAA,EACA;AACF,EACC;AAAA,EACC;AAAA,EACA;AACF,EACC;AAAA,EACC;AAAA,EACA;AAAA,EACA;AACF,EACC,OAAO,gCAAgC,kCAAkC,EACzE;AAAA,EACC;AAAA,EACA;AACF,EACC,OAAO,qBAAqB,qBAAqB,GAAG,EACpD;AAAA,EACC;AAAA,EACA;AACF,EACC,OAAO,2BAA2B,gCAAgC,EAClE,OAAO,yBAAyB,2CAA2C,GAAG,EAC9E,OAAO,uBAAuB,mDAAmD,EACjF,OAAO,OAAO,SAAS;AACtB,MAAI;AACF,UAAM,SAAS,MAAM,WAAW;AAAA,MAC9B,WAAW,KAAK;AAAA,MAChB,aAAa,KAAK;AAAA,MAClB,oBAAoB,KAAK;AAAA,MACzB,UAAU,KAAK;AAAA,MACf,UAAU,SAAS,KAAK,QAAQ;AAAA,MAChC,WAAW,KAAK,UAAU;AAAA,MAC1B,UAAU,KAAK;AAAA,MACf,YAAY,KAAK;AAAA,MACjB,gBAAgB,SAAS,KAAK,OAAO;AAAA,MACrC,gBAAgB,KAAK;AAAA,MACrB,SAAS,KAAK;AAAA,MACd,oBAAoB,KAAK;AAAA,MACzB,4BAA4B,KAAK;AAAA,MACjC,sBAAsB,KAAK,oBAAoB,IAAI,MAAM;AAAA,MACzD,QAAQ,SAAS,KAAK,MAAM;AAAA,MAC5B,WAAW,KAAK,WAAW,SAAS,KAAK,QAAQ,IAAI;AAAA,MACrD,uBAAuB,KAAK,uBAAuB;AAAA,MACnD,SAAS,SAAS,KAAK,OAAO;AAAA,IAAA,CAC/B;AAED,YAAQ,IAAI,SAAS,OAAO,KAAK,MAAM,OAAO;AAE9C,QAAI,KAAK,QAAQ;AACf,YAAM,UAAU,KAAK;AACrB,UAAI,QAAQ,SAAS,MAAM,GAAG;AAC5B,sBAAc,SAAS,UAAU,OAAO,IAAI,CAAC;AAC7C,gBAAQ,IAAI,sBAAsB,OAAO,EAAE;AAAA,MAC7C,OAAO;AACL,sBAAc,SAAS,KAAK,UAAU,OAAO,MAAM,MAAM,CAAC,CAAC;AAC3D,gBAAQ,IAAI,sBAAsB,OAAO,EAAE;AAAA,MAC7C;AAAA,IACF,OAAO;AAEL,iBAAW,OAAO,OAAO,MAAM;AAC7B,cAAM,OAAO;AAAA,UACX,IAAI,MAAM,OAAO,EAAE;AAAA,WAClB,IAAI,SAAS,IAAI,MAAM,GAAG,EAAE,EAAE,OAAO,EAAE;AAAA,WACvC,IAAI,WAAW,IAAI,MAAM,GAAG,EAAE,EAAE,OAAO,EAAE;AAAA,WACzC,IAAI,YAAY,IAAI,MAAM,GAAG,EAAE,EAAE,OAAO,EAAE;AAAA,UAC3C,IAAI,eAAe;AAAA,QAAA,EACnB,KAAK,EAAE;AACT,gBAAQ,IAAI,IAAI;AAAA,MAClB;AAAA,IACF;AAAA,EACF,SAAS,GAAQ;AACf,YAAQ,MAAM,UAAU,EAAE,OAAO,EAAE;AACnC,YAAQ,KAAK,CAAC;AAAA,EAChB;AACF,CAAC;AAEH,SAAS,UAAU,MAAqB;AACtC,MAAI,KAAK,WAAW,EAAG,QAAO;AAC9B,QAAM,UAAU,OAAO,KAAK,KAAK,CAAC,CAAC;AACnC,QAAM,SAAS,CAAC,QAAqB;AACnC,QAAI,OAAO,KAAM,QAAO;AACxB,UAAM,MAAM,OAAO,GAAG;AACtB,QAAI,IAAI,SAAS,GAAG,KAAK,IAAI,SAAS,GAAG,KAAK,IAAI,SAAS,IAAI,GAAG;AAChE,aAAO,IAAI,IAAI,QAAQ,MAAM,IAAI,CAAC;AAAA,IACpC;AACA,WAAO;AAAA,EACT;AACA,QAAM,QAAQ,CAAC,QAAQ,KAAK,GAAG,CAAC;AAChC,aAAW,OAAO,MAAM;AACtB,UAAM,KAAK,QAAQ,IAAI,CAAC,MAAM,OAAO,IAAI,CAAC,CAAC,CAAC,EAAE,KAAK,GAAG,CAAC;AAAA,EACzD;AACA,SAAO,MAAM,KAAK,IAAI;AACxB;AAEA,QAAQ,MAAA;"}

package/dist/index.d.ts

@@ -0,0 +1,2 @@
+export { Site, JobType, CompensationInterval, DescriptionFormat, SalarySource, type JobPost, type JobResponse, type Compensation, type Location, type ScrapeJobsParams, type ScraperInput, type Country, DESIRED_COLUMNS, getCountry, displayLocation, } from './types';
+export { scrapeJobs } from './scraper';

package/dist/index.js

@@ -0,0 +1,13 @@
+import { C, D, a, J, S, b, d, g, s } from "./shared/scraper-CuXnl6Gf.js";
+export {
+  C as CompensationInterval,
+  D as DESIRED_COLUMNS,
+  a as DescriptionFormat,
+  J as JobType,
+  S as SalarySource,
+  b as Site,
+  d as displayLocation,
+  g as getCountry,
+  s as scrapeJobs
+};
+//# sourceMappingURL=index.js.map

package/dist/index.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","sources":[],"sourcesContent":[],"names":[],"mappings":";"}

package/dist/mcp/index.d.ts

@@ -0,0 +1 @@
+export {};

package/dist/mcp/index.js

@@ -0,0 +1,113 @@
+#!/usr/bin/env node
+import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
+import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
+import { z } from "zod";
+import { s as scrapeJobs } from "../shared/scraper-CuXnl6Gf.js";
+const server = new McpServer({
+  name: "jobspy",
+  version: "1.0.0"
+});
+server.tool(
+  "scrape_jobs",
+  "Scrape job listings from multiple job boards (LinkedIn, Indeed, Glassdoor, Google, ZipRecruiter, Bayt, Naukri, BDJobs)",
+  {
+    site_name: z.array(
+      z.enum([
+        "linkedin",
+        "indeed",
+        "zip_recruiter",
+        "glassdoor",
+        "google",
+        "bayt",
+        "naukri",
+        "bdjobs"
+      ])
+    ).optional().describe(
+      "Job boards to scrape. Defaults to all. Options: linkedin, indeed, zip_recruiter, glassdoor, google, bayt, naukri, bdjobs"
+    ),
+    search_term: z.string().optional().describe("Search term / job title to search for"),
+    google_search_term: z.string().optional().describe("Google-specific search term (overrides search_term for Google)"),
+    location: z.string().optional().describe("Job location (e.g. 'San Francisco, CA')"),
+    distance: z.number().optional().default(50).describe("Search radius in miles"),
+    is_remote: z.boolean().optional().default(false).describe("Filter for remote jobs"),
+    job_type: z.enum(["fulltime", "parttime", "contract", "internship"]).optional().describe("Filter by job type"),
+    results_wanted: z.number().optional().default(10).describe("Number of results to return per site"),
+    country_indeed: z.string().optional().default("usa").describe("Country for Indeed/Glassdoor (e.g. 'usa', 'uk', 'canada')"),
+    hours_old: z.number().optional().describe("Filter jobs posted within the last N hours"),
+    description_format: z.enum(["markdown", "html", "plain"]).optional().default("markdown").describe("Format for job descriptions"),
+    linkedin_fetch_description: z.boolean().optional().default(false).describe("Fetch full descriptions from LinkedIn (slower)")
+  },
+  async (params) => {
+    try {
+      const result = await scrapeJobs({
+        site_name: params.site_name,
+        search_term: params.search_term,
+        google_search_term: params.google_search_term,
+        location: params.location,
+        distance: params.distance,
+        is_remote: params.is_remote,
+        job_type: params.job_type,
+        results_wanted: params.results_wanted,
+        country_indeed: params.country_indeed,
+        hours_old: params.hours_old,
+        description_format: params.description_format,
+        linkedin_fetch_description: params.linkedin_fetch_description
+      });
+      if (result.jobs.length === 0) {
+        return {
+          content: [
+            {
+              type: "text",
+              text: "No jobs found matching the search criteria."
+            }
+          ]
+        };
+      }
+      const summary = result.jobs.map((job, i) => {
+        const parts = [
+          `${i + 1}. **${job.title}**`,
+          `   Company: ${job.company ?? "N/A"}`,
+          `   Location: ${job.location ?? "N/A"}${job.is_remote ? " (Remote)" : ""}`,
+          `   URL: ${job.job_url}`
+        ];
+        if (job.date_posted) parts.push(`   Posted: ${job.date_posted}`);
+        if (job.min_amount && job.max_amount) {
+          parts.push(
+            `   Salary: ${job.currency ?? "$"}${job.min_amount.toLocaleString()} - ${job.currency ?? "$"}${job.max_amount.toLocaleString()} (${job.interval ?? "yearly"})`
+          );
+        }
+        if (job.job_type) parts.push(`   Type: ${job.job_type}`);
+        return parts.join("\n");
+      }).join("\n\n");
+      return {
+        content: [
+          {
+            type: "text",
+            text: `Found ${result.jobs.length} jobs:
+
+${summary}`
+          }
+        ]
+      };
+    } catch (e) {
+      return {
+        content: [
+          {
+            type: "text",
+            text: `Error scraping jobs: ${e.message}`
+          }
+        ],
+        isError: true
+      };
+    }
+  }
+);
+async function main() {
+  const transport = new StdioServerTransport();
+  await server.connect(transport);
+}
+main().catch((e) => {
+  console.error("MCP server error:", e);
+  process.exit(1);
+});
+//# sourceMappingURL=index.js.map

package/dist/mcp/index.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","sources":["../../src/mcp/index.ts"],"sourcesContent":["import { McpServer } from \"@modelcontextprotocol/sdk/server/mcp.js\";\nimport { StdioServerTransport } from \"@modelcontextprotocol/sdk/server/stdio.js\";\nimport { z } from \"zod\";\nimport { scrapeJobs } from \"../scraper\";\n\nconst server = new McpServer({\n  name: \"jobspy\",\n  version: \"1.0.0\",\n});\n\nserver.tool(\n  \"scrape_jobs\",\n  \"Scrape job listings from multiple job boards (LinkedIn, Indeed, Glassdoor, Google, ZipRecruiter, Bayt, Naukri, BDJobs)\",\n  {\n    site_name: z\n      .array(\n        z.enum([\n          \"linkedin\",\n          \"indeed\",\n          \"zip_recruiter\",\n          \"glassdoor\",\n          \"google\",\n          \"bayt\",\n          \"naukri\",\n          \"bdjobs\",\n        ]),\n      )\n      .optional()\n      .describe(\n        \"Job boards to scrape. Defaults to all. Options: linkedin, indeed, zip_recruiter, glassdoor, google, bayt, naukri, bdjobs\",\n      ),\n    search_term: z\n      .string()\n      .optional()\n      .describe(\"Search term / job title to search for\"),\n    google_search_term: z\n      .string()\n      .optional()\n      .describe(\"Google-specific search term (overrides search_term for Google)\"),\n    location: z.string().optional().describe(\"Job location (e.g. 'San Francisco, CA')\"),\n    distance: z\n      .number()\n      .optional()\n      .default(50)\n      .describe(\"Search radius in miles\"),\n    is_remote: z.boolean().optional().default(false).describe(\"Filter for remote jobs\"),\n    job_type: z\n      .enum([\"fulltime\", \"parttime\", \"contract\", \"internship\"])\n      .optional()\n      .describe(\"Filter by job type\"),\n    results_wanted: z\n      .number()\n      .optional()\n      .default(10)\n      .describe(\"Number of results to return per site\"),\n    country_indeed: z\n      .string()\n      .optional()\n      .default(\"usa\")\n      .describe(\"Country for Indeed/Glassdoor (e.g. 'usa', 'uk', 'canada')\"),\n    hours_old: z\n      .number()\n      .optional()\n      .describe(\"Filter jobs posted within the last N hours\"),\n    description_format: z\n      .enum([\"markdown\", \"html\", \"plain\"])\n      .optional()\n      .default(\"markdown\")\n      .describe(\"Format for job descriptions\"),\n    linkedin_fetch_description: z\n      .boolean()\n      .optional()\n      .default(false)\n      .describe(\"Fetch full descriptions from LinkedIn (slower)\"),\n  },\n  async (params) => {\n    try {\n      const result = await scrapeJobs({\n        site_name: params.site_name,\n        search_term: params.search_term,\n        google_search_term: params.google_search_term,\n        location: params.location,\n        distance: params.distance,\n        is_remote: params.is_remote,\n        job_type: params.job_type,\n        results_wanted: params.results_wanted,\n        country_indeed: params.country_indeed,\n        hours_old: params.hours_old,\n        description_format: params.description_format,\n        linkedin_fetch_description: params.linkedin_fetch_description,\n      });\n\n      if (result.jobs.length === 0) {\n        return {\n          content: [\n            {\n              type: \"text\" as const,\n              text: \"No jobs found matching the search criteria.\",\n            },\n          ],\n        };\n      }\n\n      // Format jobs as a readable summary + structured data\n      const summary = result.jobs\n        .map((job, i) => {\n          const parts = [\n            `${i + 1}. **${job.title}**`,\n            `   Company: ${job.company ?? \"N/A\"}`,\n            `   Location: ${job.location ?? \"N/A\"}${job.is_remote ? \" (Remote)\" : \"\"}`,\n            `   URL: ${job.job_url}`,\n          ];\n          if (job.date_posted) parts.push(`   Posted: ${job.date_posted}`);\n          if (job.min_amount && job.max_amount) {\n            parts.push(\n              `   Salary: ${job.currency ?? \"$\"}${job.min_amount.toLocaleString()} - ${job.currency ?? \"$\"}${job.max_amount.toLocaleString()} (${job.interval ?? \"yearly\"})`,\n            );\n          }\n          if (job.job_type) parts.push(`   Type: ${job.job_type}`);\n          return parts.join(\"\\n\");\n        })\n        .join(\"\\n\\n\");\n\n      return {\n        content: [\n          {\n            type: \"text\" as const,\n            text: `Found ${result.jobs.length} jobs:\\n\\n${summary}`,\n          },\n        ],\n      };\n    } catch (e: any) {\n      return {\n        content: [\n          {\n            type: \"text\" as const,\n            text: `Error scraping jobs: ${e.message}`,\n          },\n        ],\n        isError: true,\n      };\n    }\n  },\n);\n\nasync function main() {\n  const transport = new StdioServerTransport();\n  await server.connect(transport);\n}\n\nmain().catch((e) => {\n  console.error(\"MCP server error:\", e);\n  process.exit(1);\n});\n"],"names":[],"mappings":";;;;;AAKA,MAAM,SAAS,IAAI,UAAU;AAAA,EAC3B,MAAM;AAAA,EACN,SAAS;AACX,CAAC;AAED,OAAO;AAAA,EACL;AAAA,EACA;AAAA,EACA;AAAA,IACE,WAAW,EACR;AAAA,MACC,EAAE,KAAK;AAAA,QACL;AAAA,QACA;AAAA,QACA;AAAA,QACA;AAAA,QACA;AAAA,QACA;AAAA,QACA;AAAA,QACA;AAAA,MAAA,CACD;AAAA,IAAA,EAEF,WACA;AAAA,MACC;AAAA,IAAA;AAAA,IAEJ,aAAa,EACV,OAAA,EACA,SAAA,EACA,SAAS,uCAAuC;AAAA,IACnD,oBAAoB,EACjB,OAAA,EACA,SAAA,EACA,SAAS,gEAAgE;AAAA,IAC5E,UAAU,EAAE,OAAA,EAAS,SAAA,EAAW,SAAS,yCAAyC;AAAA,IAClF,UAAU,EACP,OAAA,EACA,SAAA,EACA,QAAQ,EAAE,EACV,SAAS,wBAAwB;AAAA,IACpC,WAAW,EAAE,QAAA,EAAU,SAAA,EAAW,QAAQ,KAAK,EAAE,SAAS,wBAAwB;AAAA,IAClF,UAAU,EACP,KAAK,CAAC,YAAY,YAAY,YAAY,YAAY,CAAC,EACvD,WACA,SAAS,oBAAoB;AAAA,IAChC,gBAAgB,EACb,OAAA,EACA,SAAA,EACA,QAAQ,EAAE,EACV,SAAS,sCAAsC;AAAA,IAClD,gBAAgB,EACb,OAAA,EACA,SAAA,EACA,QAAQ,KAAK,EACb,SAAS,2DAA2D;AAAA,IACvE,WAAW,EACR,OAAA,EACA,SAAA,EACA,SAAS,4CAA4C;AAAA,IACxD,oBAAoB,EACjB,KAAK,CAAC,YAAY,QAAQ,OAAO,CAAC,EAClC,WACA,QAAQ,UAAU,EAClB,SAAS,6BAA6B;AAAA,IACzC,4BAA4B,EACzB,UACA,SAAA,EACA,QAAQ,KAAK,EACb,SAAS,gDAAgD;AAAA,EAAA;AAAA,EAE9D,OAAO,WAAW;AAChB,QAAI;AACF,YAAM,SAAS,MAAM,WAAW;AAAA,QAC9B,WAAW,OAAO;AAAA,QAClB,aAAa,OAAO;AAAA,QACpB,oBAAoB,OAAO;AAAA,QAC3B,UAAU,OAAO;AAAA,QACjB,UAAU,OAAO;AAAA,QACjB,WAAW,OAAO;AAAA,QAClB,UAAU,OAAO;AAAA,QACjB,gBAAgB,OAAO;AAAA,QACvB,gBAAgB,OAAO;AAAA,QACvB,WAAW,OAAO;AAAA,QAClB,oBAAoB,OAAO;AAAA,QAC3B,4BAA4B,OAAO;AAAA,MAAA,CACpC;AAED,UAAI,OAAO,KAAK,WAAW,GAAG;AAC5B,eAAO;AAAA,UACL,SAAS;AAAA,YACP;AAAA,cACE,MAAM;AAAA,cACN,MAAM;AAAA,YAAA;AAAA,UACR;AAAA,QACF;AAAA,MAEJ;AAGA,YAAM,UAAU,OAAO,KACpB,IAAI,CAAC,KAAK,MAAM;AACf,cAAM,QAAQ;AAAA,UACZ,GAAG,IAAI,CAAC,OAAO,IAAI,KAAK;AAAA,UACxB,eAAe,IAAI,WAAW,KAAK;AAAA,UACnC,gBAAgB,IAAI,YAAY,KAAK,GAAG,IAAI,YAAY,cAAc,EAAE;AAAA,UACxE,WAAW,IAAI,OAAO;AAAA,QAAA;AAExB,YAAI,IAAI,YAAa,OAAM,KAAK,cAAc,IAAI,WAAW,EAAE;AAC/D,YAAI,IAAI,cAAc,IAAI,YAAY;AACpC,gBAAM;AAAA,YACJ,cAAc,IAAI,YAAY,GAAG,GAAG,IAAI,WAAW,gBAAgB,MAAM,IAAI,YAAY,GAAG,GAAG,IAAI,WAAW,gBAAgB,KAAK,IAAI,YAAY,QAAQ;AAAA,UAAA;AAAA,QAE/J;AACA,YAAI,IAAI,SAAU,OAAM,KAAK,YAAY,IAAI,QAAQ,EAAE;AACvD,eAAO,MAAM,KAAK,IAAI;AAAA,MACxB,CAAC,EACA,KAAK,MAAM;AAEd,aAAO;AAAA,QACL,SAAS;AAAA,UACP;AAAA,YACE,MAAM;AAAA,YACN,MAAM,SAAS,OAAO,KAAK,MAAM;AAAA;AAAA,EAAa,OAAO;AAAA,UAAA;AAAA,QACvD;AAAA,MACF;AAAA,IAEJ,SAAS,GAAQ;AACf,aAAO;AAAA,QACL,SAAS;AAAA,UACP;AAAA,YACE,MAAM;AAAA,YACN,MAAM,wBAAwB,EAAE,OAAO;AAAA,UAAA;AAAA,QACzC;AAAA,QAEF,SAAS;AAAA,MAAA;AAAA,IAEb;AAAA,EACF;AACF;AAEA,eAAe,OAAO;AACpB,QAAM,YAAY,IAAI,qBAAA;AACtB,QAAM,OAAO,QAAQ,SAAS;AAChC;AAEA,OAAO,MAAM,CAAC,MAAM;AAClB,UAAQ,MAAM,qBAAqB,CAAC;AACpC,UAAQ,KAAK,CAAC;AAChB,CAAC;"}

package/dist/scraper.d.ts

@@ -0,0 +1,58 @@
+import { ScrapeJobsParams } from './types';
+export interface ScrapeJobsResult {
+    jobs: FlatJobRecord[];
+}
+export interface FlatJobRecord {
+    id?: string;
+    site: string;
+    job_url: string;
+    job_url_direct?: string;
+    title: string;
+    company?: string;
+    location?: string;
+    date_posted?: string;
+    job_type?: string;
+    salary_source?: string;
+    interval?: string;
+    min_amount?: number;
+    max_amount?: number;
+    currency?: string;
+    is_remote?: boolean;
+    job_level?: string;
+    job_function?: string;
+    listing_type?: string;
+    emails?: string;
+    description?: string;
+    company_industry?: string;
+    company_url?: string;
+    company_logo?: string;
+    company_url_direct?: string;
+    company_addresses?: string;
+    company_num_employees?: string;
+    company_revenue?: string;
+    company_description?: string;
+    skills?: string;
+    experience_range?: string;
+    company_rating?: number;
+    company_reviews_count?: number;
+    vacancy_count?: number;
+    work_from_home_type?: string;
+}
+/**
+ * Scrapes jobs from multiple job boards concurrently.
+ *
+ * @example
+ * ```ts
+ * 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`);
+ * ```
+ */
+export declare function scrapeJobs(params?: ScrapeJobsParams): Promise<ScrapeJobsResult>;

package/dist/scrapers/base.d.ts

@@ -0,0 +1,15 @@
+import { Session } from 'wreq-js';
+import { JobResponse, ScraperInput, Site } from '../types';
+import { ProxyRotator } from '../utils';
+export declare abstract class Scraper {
+    readonly site: Site;
+    protected proxyRotator: ProxyRotator;
+    protected session: Session;
+    constructor(site: Site, options?: {
+        proxies?: string | string[] | null;
+    });
+    protected initSession(browser?: string, insecure?: boolean): Promise<void>;
+    protected fetchWithProxy(url: string, init?: any): Promise<any>;
+    abstract scrape(input: ScraperInput): Promise<JobResponse>;
+    close(): Promise<void>;
+}

package/dist/scrapers/bayt/index.d.ts

@@ -0,0 +1,13 @@
+import { Scraper } from '../base';
+import { JobResponse, ScraperInput } from '../../types';
+export declare class Bayt extends Scraper {
+    private baseUrl;
+    private delay;
+    private bandDelay;
+    constructor(options?: {
+        proxies?: string | string[] | null;
+    });
+    scrape(input: ScraperInput): Promise<JobResponse>;
+    private fetchJobs;
+    private extractJobInfo;
+}

package/dist/scrapers/bdjobs/index.d.ts

@@ -0,0 +1,14 @@
+import { Scraper } from '../base';
+import { JobResponse, ScraperInput } from '../../types';
+export declare class BDJobs extends Scraper {
+    private searchUrl;
+    private jobDetailsBaseUrl;
+    private scraper_input;
+    constructor(options?: {
+        proxies?: string | string[] | null;
+    });
+    scrape(input: ScraperInput): Promise<JobResponse>;
+    private fetchPage;
+    private processItem;
+    private parseLocation;
+}

package/dist/scrapers/glassdoor/constants.d.ts

@@ -0,0 +1,3 @@
+export declare const HEADERS: Record<string, string>;
+export declare const QUERY_TEMPLATE = "\n  query JobSearchResultsQuery(\n    $excludeJobListingIds: [Long!],\n    $keyword: String,\n    $locationId: Int,\n    $locationType: LocationTypeEnum,\n    $numJobsToShow: Int!,\n    $pageCursor: String,\n    $pageNumber: Int,\n    $filterParams: [FilterParams],\n    $originalPageUrl: String,\n    $seoFriendlyUrlInput: String,\n    $parameterUrlInput: String,\n    $seoUrl: Boolean\n  ) {\n    jobListings(\n      contextHolder: {\n        searchParams: {\n          excludeJobListingIds: $excludeJobListingIds,\n          keyword: $keyword,\n          locationId: $locationId,\n          locationType: $locationType,\n          numPerPage: $numJobsToShow,\n          pageCursor: $pageCursor,\n          pageNumber: $pageNumber,\n          filterParams: $filterParams,\n          originalPageUrl: $originalPageUrl,\n          seoFriendlyUrlInput: $seoFriendlyUrlInput,\n          parameterUrlInput: $parameterUrlInput,\n          seoUrl: $seoUrl,\n          searchType: SR\n        }\n      }\n    ) {\n      jobListings {\n        ...JobView\n        __typename\n      }\n      paginationCursors { cursor pageNumber __typename }\n      totalJobsCount\n      __typename\n    }\n  }\n\n  fragment JobView on JobListingSearchResult {\n    jobview {\n      header {\n        adOrderId advertiserType adOrderSponsorshipLevel ageInDays\n        divisionEmployerName easyApply\n        employer { id name shortName __typename }\n        employerNameFromSearch goc gocConfidence gocId\n        jobCountryId jobLink jobResultTrackingKey jobTitleText\n        locationName locationType locId needsCommission\n        payCurrency payPeriod\n        payPeriodAdjustedPay { p10 p50 p90 __typename }\n        rating salarySource savedJobId sponsored __typename\n      }\n      job { description importConfigId jobTitleId jobTitleText listingId __typename }\n      jobListingAdminDetails {\n        cpcVal importConfigId jobListingId jobSourceId\n        userEligibleForAdminJobDetails __typename\n      }\n      overview { shortName squareLogoUrl __typename }\n      __typename\n    }\n    __typename\n  }";
+export declare const FALLBACK_TOKEN = "Ft6oHEWlRZrxDww95Cpazw:0pGUrkb2y3TyOpAIqF2vbPmUXoXVkD3oEGDVkvfeCerceQ5-n8mBg3BovySUIjmCPHCaW0H2nQVdqzbtsYqf4Q:wcqRqeegRUa9MVLJGyujVXB7vWFPjdaS1CtrrzJq-ok";

package/dist/scrapers/glassdoor/index.d.ts

@@ -0,0 +1,19 @@
+import { Scraper } from '../base';
+import { JobResponse, ScraperInput } from '../../types';
+export declare class Glassdoor extends Scraper {
+    private baseUrl;
+    private scraper_input;
+    private seenUrls;
+    private jobsPerPage;
+    private maxPages;
+    constructor(options?: {
+        proxies?: string | string[] | null;
+    });
+    scrape(input: ScraperInput): Promise<JobResponse>;
+    private getCsrfToken;
+    private fetchJobsPage;
+    private processJob;
+    private parseCompensation;
+    private fetchDescription;
+    private getLocation;
+}

package/dist/scrapers/google/constants.d.ts

@@ -0,0 +1,2 @@
+export declare const HEADERS_INITIAL: Record<string, string>;
+export declare const HEADERS_JOBS: Record<string, string>;

package/dist/scrapers/google/index.d.ts

@@ -0,0 +1,21 @@
+import { Scraper } from '../base';
+import { JobResponse, ScraperInput } from '../../types';
+export declare class Google extends Scraper {
+    private searchUrl;
+    private jobsUrl;
+    private scraper_input;
+    private seenUrls;
+    private jobsPerPage;
+    private browser;
+    private pw_page;
+    constructor(options?: {
+        proxies?: string | string[] | null;
+    });
+    scrape(input: ScraperInput): Promise<JobResponse>;
+    private getInitialCursorAndJobs;
+    private findInitialJobs;
+    private getJobsNextPage;
+    private parseJobs;
+    private findJobInfo;
+    private parseJob;
+}

package/dist/scrapers/google-careers/index.d.ts

@@ -0,0 +1,13 @@
+import { Scraper } from '../base';
+import { JobResponse, ScraperInput } from '../../types';
+export declare class GoogleCareers extends Scraper {
+    private baseUrl;
+    private scraper_input;
+    private jobsPerPage;
+    constructor(options?: {
+        proxies?: string | string[] | null;
+    });
+    scrape(input: ScraperInput): Promise<JobResponse>;
+    private buildUrl;
+    private parseJob;
+}

package/dist/scrapers/indeed/constants.d.ts

@@ -0,0 +1,2 @@
+export declare const JOB_SEARCH_QUERY = "\n    query GetJobData {\n        jobSearch(\n        {what}\n        {location}\n        limit: 100\n        {cursor}\n        sort: RELEVANCE\n        {filters}\n        ) {\n        pageInfo {\n            nextCursor\n        }\n        results {\n            trackingKey\n            job {\n            source {\n                name\n            }\n            key\n            title\n            datePublished\n            dateOnIndeed\n            description {\n                html\n            }\n            location {\n                countryName\n                countryCode\n                admin1Code\n                city\n                postalCode\n                streetAddress\n                formatted {\n                short\n                long\n                }\n            }\n            compensation {\n                estimated {\n                currencyCode\n                baseSalary {\n                    unitOfWork\n                    range {\n                    ... on Range {\n                        min\n                        max\n                    }\n                    }\n                }\n                }\n                baseSalary {\n                unitOfWork\n                range {\n                    ... on Range {\n                    min\n                    max\n                    }\n                }\n                }\n                currencyCode\n            }\n            attributes {\n                key\n                label\n            }\n            employer {\n                relativeCompanyPageUrl\n                name\n                dossier {\n                    employerDetails {\n                    addresses\n                    industry\n                    employeesLocalizedLabel\n                    revenueLocalizedLabel\n                    briefDescription\n                    ceoName\n                    ceoPhotoUrl\n                    }\n                    images {\n                        headerImageUrl\n                        squareLogoUrl\n                    }\n                    links {\n                    corporateWebsite\n                }\n                }\n            }\n            recruit {\n                viewJobUrl\n                detailedSalary\n                workSchedule\n            }\n            }\n        }\n        }\n    }\n    ";
+export declare const API_HEADERS: Record<string, string>;

package/dist/scrapers/indeed/index.d.ts

@@ -0,0 +1,19 @@
+import { Scraper } from '../base';
+import { JobResponse, ScraperInput } from '../../types';
+export declare class Indeed extends Scraper {
+    private apiUrl;
+    private baseUrl;
+    private apiCountryCode;
+    private seenUrls;
+    private scraper_input;
+    constructor(options?: {
+        proxies?: string | string[] | null;
+    });
+    scrape(input: ScraperInput): Promise<JobResponse>;
+    private scrapePage;
+    private buildFilters;
+    private processJob;
+    private getJobType;
+    private getCompensation;
+    private isRemote;
+}

package/dist/scrapers/linkedin/constants.d.ts

@@ -0,0 +1 @@
+export declare const HEADERS: Record<string, string>;

package/dist/scrapers/linkedin/index.d.ts

@@ -0,0 +1,20 @@
+import { Scraper } from '../base';
+import { JobResponse, ScraperInput } from '../../types';
+export declare class LinkedIn extends Scraper {
+    private baseUrl;
+    private delay;
+    private bandDelay;
+    private scraper_input;
+    private urlRegex;
+    constructor(options?: {
+        proxies?: string | string[] | null;
+    });
+    scrape(input: ScraperInput): Promise<JobResponse>;
+    private processJob;
+    private getJobDetails;
+    private parseCriteria;
+    private parseJobType;
+    private parseJobUrlDirect;
+    private getLocation;
+    private isJobRemote;
+}