# Clone the repo
git clone https://github.com/karpathy/jobs
cd jobs
 
# Install dependencies (uses uv)
uv sync
uv run playwright install chromium

OPENROUTER_API_KEY=your_openrouter_key_here

# 1. Scrape BLS pages (non-headless Playwright; BLS blocks bots)
#    Results cached in html/ — only needed once
uv run python scrape.py
 
# 2. Convert raw HTML → clean Markdown in pages/
uv run python process.py
 
# 3. Extract structured fields → occupations.csv
uv run python make_csv.py
 
# 4. Score AI exposure via LLM (uses OpenRouter API, saves scores.json)
uv run python score.py
 
# 5. Merge CSV + scores → site/data.json for the frontend
uv run python build_site_data.py
 
# 6. Serve the visualization locally
cd site && python -m http.server 8000
# Open http://localhost:8000

# score.py (simplified structure)
SYSTEM_PROMPT = """
You are evaluating occupations for exposure to humanoid robotics over the next 10 years.
Score each occupation from 0 to 10:
- 0 = no meaningful exposure (e.g., requires fine social judgment, non-physical)
- 5 = moderate exposure (some tasks automatable, but humans still central)
- 10 = high exposure (repetitive physical tasks, predictable environments)
Consider: physical task complexity, environment predictability, dexterity requirements,
cost of robot vs human, regulatory barriers.
Respond ONLY with JSON: {"score": <int 0-10>, "rationale": "<1-2 sentences>"}
"""

# The pipeline reads each occupation's Markdown from pages/,
# sends it to the LLM, and writes results to scores.json
# scores.json structure:
{
  "software-developers": {
    "score": 1,
    "rationale": "Software development is digital and cognitive; humanoid robots provide no advantage."
  },
  "construction-laborers": {
    "score": 7,
    "rationale": "Physical, repetitive outdoor tasks are targets for humanoid robotics, though unstructured environments remain challenging."
  }
  // ... 342 occupations total
}

uv run python build_site_data.py
cd site && python -m http.server 8000

{
  "title": "Software Developers",
  "url": "https://www.bls.gov/ooh/computer-and-information-technology/software-developers.htm",
  "category": "Computer and Information Technology",
  "slug": "software-developers"
}

slug, title, category, median_pay, education, job_count, growth_percent, growth_outlook

software-developers, Software Developers, Computer and Information Technology,
130160, Bachelor's degree, 1847900, 17, Much faster than average

{
  "slug": "software-developers",
  "title": "Software Developers",
  "category": "Computer and Information Technology",
  "median_pay": 130160,
  "education": "Bachelor's degree",
  "job_count": 1847900,
  "growth_percent": 17,
  "growth_outlook": "Much faster than average",
  "ai_score": 9,
  "ai_rationale": "AI is deeply transforming software development workflows..."
}

<!-- In site/index.html, find the layer toggle buttons -->
<button onclick="setLayer('ai_score')">Digital AI Exposure</button>
 
<!-- Add your new layer button -->
<button onclick="setLayer('robotics_score')">Humanoid Robotics</button>

// In the colorScale function, add a case for your new field:
function getColor(d, layer) {
  if (layer === 'robotics_score') {
    // scores 0-10, blue = low exposure, red = high
    return d3.interpolateRdYlBu(1 - d.robotics_score / 10);
  }
  // ... existing cases
}

uv run python make_prompt.py
# Produces prompt.md (~45K tokens)
# Paste into Claude, GPT-4, Gemini, etc. for data-grounded conversation

# scrape.py key behavior
browser = await p.chromium.launch(headless=False)  # Must be visible
# Pages saved to html/<slug>.html
# Already-scraped pages are skipped (cached)

import json, os
with open("scores.json") as f:
    existing = json.load(f)
with open("occupations.json") as f:
    all_occupations = json.load(f)
# Find gaps
missing = [o for o in all_occupations if o["slug"] not in existing]
print(f"Missing scores: {len(missing)}")
# Then run score.py with a filter for missing slugs

from parse_detail import parse_occupation_page
from pathlib import Path
html = Path("html/software-developers.html").read_text()
data = parse_occupation_page(html)
print(data["median_pay"])     # e.g. 130160
print(data["job_count"])      # e.g. 1847900
print(data["growth_outlook"]) # e.g. "Much faster than average"

import pandas as pd
df = pd.read_csv("occupations.csv")
# Top 10 highest paying occupations
top_pay = df.nlargest(10, "median_pay")[["title", "median_pay", "growth_outlook"]]
print(top_pay)
# Filter: fast growth + high pay
high_value = df[
    (df["growth_percent"] > 10) &
    (df["median_pay"] > 80000)
].sort_values("median_pay", ascending=False)

import pandas as pd, json
df = pd.read_csv("occupations.csv")
with open("scores.json") as f:
    scores = json.load(f)
df["ai_score"] = df["slug"].map(lambda s: scores.get(s, {}).get("score"))
df["ai_rationale"] = df["slug"].map(lambda s: scores.get(s, {}).get("rationale"))
# High AI exposure, high pay — reshaping, not disappearing
high_exposure_high_pay = df[
    (df["ai_score"] >= 8) &
    (df["median_pay"] > 100000)
][["title", "median_pay", "ai_score", "growth_outlook"]]
print(high_exposure_high_pay)

uv run playwright install --with-deps chromium

# Always rebuild site data after changing scores.json
uv run python build_site_data.py