SEO content research: extract the H2/H3 outlines of Google's top-5 for any keyword — https://quantumproxies.io/serp-api

competitor-outline-analyzer.py

# SEO content research: fetch Google's top-5 for a keyword, extract each
# page's heading outline (H2/H3), and print them side by side — what you
# must cover to compete for that query.
#
# SERP + extraction: https://quantumproxies.io/serp-api +
# https://quantumproxies.io/extract-api (one key for both:
# app.quantumproxies.io/api-keys)
#
#   QP_API_KEY=qp_live_... python competitor-outline-analyzer.py "best vpn 2026"

import os, re, sys
import requests

BASE = "https://app.quantumproxies.io/api/v1/scraper"
HEADERS = {"Authorization": f"Bearer {os.environ['QP_API_KEY']}"}

query = sys.argv[1] if len(sys.argv) > 1 else "web scraping api"

serp = requests.post(f"{BASE}/serp", headers=HEADERS, timeout=90, json={
    "query": query, "engine": "google", "country": "us", "num": 5,
}).json()

for hit in serp.get("organic", []):
    print(f'\n#{hit["rank"]}  {hit["title"]}\n    {hit["link"]}')
    try:
        page = requests.post(f"{BASE}/extract", headers=HEADERS, timeout=120,
                             json={"url": hit["link"], "format": "markdown"}).json()
        headings = re.findall(r"(?m)^(#{2,3})\s+(.+)$", page.get("content", ""))
        for hashes, text in headings[:15]:
            print(f'    {"  " * (len(hashes) - 2)}- {text.strip()}')
    except Exception as e:
        print(f"    (could not extract: {e})")

# Read the outlines as a checklist: topics that appear in 3+ of the top-5
# are table stakes; topics NO ONE covers are your differentiation angle.