🦅 UpworkHawk — Upwork Job Scraper + AI Job Matcher

Scrape full Upwork job details from a single link, multiple links, or a keyword search — then let the built-in AI score how well each job fits your own skills, grade the client's quality, gauge the competition, and draft a proposal for you.

Quick start (simplest way)

Paste one Upwork job URL into the jobUrl field and run the Actor. That's it — the full job details land in the Output tab.

{
  "jobUrl": "https://www.upwork.com/jobs/~0123456789abcdef"
}

Features

• Scrape any Upwork job URL — title, full description, budget, job type, experience level, duration, skills, and proposal count.
• Extract Upwork client information — country, city, total spent, hires, payment-verified status, member-since date.
• AI match score against your own skills — set userSkills and every job gets scored A–F for how well it fits you, with matched and missing skills broken out.
• Auto-generate an Upwork proposal draft — a ready-to-edit cover letter for every job, using your name and portfolio link.
• Grade Upwork clients by quality — an A–F score built from spend, hires, and payment verification, plus a plain-English recommendation ("Consider skipping — low spend/rating" or similar).
• Estimate competition and a fair bid range — proposal-count-based difficulty rating with a suggested bid_min/bid_max for the job.
• Search Upwork jobs by keyword — leave the URL fields empty and set searchQuery to pull a page of matching jobs instead of one link.
• Filter results by job type, experience level, client country, minimum client rating, minimum client spend, or payment-verified-only.
• Unlock logged-in-only client data — paste your own Upwork session cookie to also get the client's star rating, review count, jobs-posted count, hire rate, average hourly rate paid, their full recent job history (freelancers hired, dates, feedback), and their other open jobs. Upwork hides all of this from anonymous visitors by design — without a cookie these fields are simply absent, never guessed or faked.

Use cases

• Freelancers deciding what to apply to — paste a batch of job links from your Upwork feed and instantly see which ones actually match your skills, which clients are worth the risk, and get a proposal draft ready to send.
• Agencies triaging leads for their team — filter a keyword search down to payment-verified, high-spend clients only, so nobody wastes connects on a low-quality post.
• Market research on Upwork job trends — pull a category's job listings to see typical budgets, required skills, and experience-level demand.
• Automated proposal pipelines — feed job URLs in from your own monitoring tool and get structured JSON back, ready to pipe into a spreadsheet, Slack alert, or n8n/Make workflow.

Input

Field	What it does
jobUrl	One Upwork job link — the simplest option
jobUrls	Multiple Upwork job links at once
searchQuery	Keyword search instead of specific links
jobType, experienceLevel, clientCountry, minClientRating, minClientSpend, paymentVerifiedOnly	Filters
upworkCookie	Your own Upwork session cookie — unlocks logged-in-only client fields
userSkills, userName, portfolioUrl	Powers the AI match score and proposal draft
maxResults	Cap on jobs returned in search mode

Full field-by-field descriptions and defaults are in the Actor's Input tab.

Output example

{
  "title": "Seeking Lead Generation & Email List Building Specialist",
  "budget": "$5.00",
  "job_type": "Fixed-price",
  "skills": ["Lead Generation", "Email List Building", "Web Research"],
  "client_country": "United States",
  "client_total_spent": "$3.5K",
  "client_hires": 197,
  "match_score": 50,
  "match_grade": "C",
  "client_quality_grade": "D",
  "competition_level": "Easy",
  "suggested_bid_min": 50,
  "suggested_bid_max": 300,
  "ai_proposal_draft": "..."
}

How it works

A layered fetch strategy tries the cheapest method first and only falls back to a real browser when needed: Upwork's own GraphQL search API → a TLS-impersonating HTTP client → Scrapling's StealthyFetcher (a real Cloudflare-clearing browser) → a dedicated Camoufox/patchright browser pass. Every attempt is logged, and a job that genuinely couldn't be reached comes back as an honest "not found" result — never fabricated data.

FAQ

Does this need my Upwork login? No — the core features (job content, AI scoring, client basics) work fully anonymously. Your own cookie is optional and only unlocks the extra fields Upwork already shows you once you're signed in (rating, job history, etc.).

Will it work on a proxy-blocked or removed job link? An old, filled, or removed listing (or one that redirects to a generic category page instead of 404ing) comes back as a clean "not found" — never fake data dressed up as a real job.

Can I run this on a schedule? Yes — set up an Apify Schedule pointed at this Actor with your usual input, same as any other Actor.

Why do some client fields come back empty? Client rating, review count, jobs-posted count, hire rate, avg hourly rate paid, and job history are hidden by Upwork from anonymous visitors — that's Upwork's own privacy design, not a bug here. Provide upworkCookie to see them.

Notes

• Uses a residential proxy (recommended, prefilled in the Input tab) — Upwork blocks datacenter IPs outright.
• Reads only Upwork's own public job pages and search API. No account takeover, no unauthorized access — just what any visitor (or, with your own cookie, what you) can already see.