extract_links.py

#!/usr/bin/env python3
"""Extract all links from a web page using Plasmate's SOM."""
import subprocess
import json
import sys

url = sys.argv[1] if len(sys.argv) > 1 else "https://news.ycombinator.com"

result = subprocess.run(["plasmate", "fetch", url], capture_output=True, text=True)

if result.returncode != 0:
    print(f"Error: {result.stderr}", file=sys.stderr)
    sys.exit(1)

som = json.loads(result.stdout)
print(f"Links from: {som.get('title', url)}\n")

links = []
for region in som.get("regions", []):
    for el in region.get("elements", []):
        if el.get("role") == "link" and el.get("href"):
            links.append({
                "text": el.get("text", "").strip(),
                "href": el["href"],
                "region": region.get("role", "unknown"),
            })

print(f"Found {len(links)} links:\n")
for i, link in enumerate(links, 1):
    text = link["text"][:60] if link["text"] else "(no text)"
    print(f"  {i:3d}. [{link['region']}] {text}")
    print(f"       → {link['href']}")

# Optionally save as JSON
if "--json" in sys.argv:
    output_file = "links.json"
    with open(output_file, "w") as f:
        json.dump(links, f, indent=2)
    print(f"\nSaved to {output_file}")