thermograph/cities.py
Emi Griffith c3a11ee994 SEO: per-city Wikipedia blurbs + travel/compare CTA on city pages (#98)
Add unique editorial content so the programmatic pages don't read as templated:
- gen_flavor.py seeds backend/cities_flavor.json with a short descriptive blurb per
  city from Wikipedia's free REST summary API (no key), validating each match by
  comparing article coordinates to the city's lat/lon so the wrong 'Springfield'
  never attaches. Retries + modest concurrency; ~700/750 cities get a blurb, the
  rest render without one. Text is CC BY-SA, attributed with a 'via Wikipedia' link.
- City pages show the blurb under the intro and a travel callout that deep-links to
  the compare page with the city pre-loaded (/compare#loc=lat,lon) — the visitor
  just adds their own city. Month pages get the same seasonal 'visiting in {month}?'
  compare link. Both add unique per-page text and internal links.
- cities.py gains flavor(slug); tests cover the blurb + attribution + compare CTA.
2026-07-16 00:39:47 +00:00

69 lines
2.3 KiB
Python

"""Access to the curated city set (backend/cities.json) that gets crawlable
climate pages. Loaded once, lazily; regenerate the JSON with gen_cities.py."""
import json
import os
_PATH = os.path.join(os.path.dirname(__file__), "cities.json")
_FLAVOR_PATH = os.path.join(os.path.dirname(__file__), "cities_flavor.json")
_CITIES: list[dict] | None = None
_BY_SLUG: dict[str, dict] | None = None
_FLAVOR: dict[str, dict] | None = None
def _load() -> list[dict]:
global _CITIES, _BY_SLUG
if _CITIES is None:
with open(_PATH, encoding="utf-8") as f:
_CITIES = json.load(f)
_BY_SLUG = {c["slug"]: c for c in _CITIES}
return _CITIES
def all_cities() -> list[dict]:
return _load()
def all_slugs() -> list[str]:
return [c["slug"] for c in _load()]
def get(slug: str) -> dict | None:
"""The city for a slug, or None (→ 404)."""
_load()
return _BY_SLUG.get(slug)
def flavor(slug: str) -> dict | None:
"""A city's descriptive blurb {extract, url, title} from cities_flavor.json, or
None when we have no confident match (the page renders fine without it)."""
global _FLAVOR
if _FLAVOR is None:
try:
with open(_FLAVOR_PATH, encoding="utf-8") as f:
_FLAVOR = json.load(f)
except (OSError, ValueError):
_FLAVOR = {}
return _FLAVOR.get(slug)
def display_name(city: dict) -> str:
"""Human label: 'Seattle, Washington, United States' (drops repeated admin1)."""
parts = [city["name"]]
if city.get("admin1") and city["admin1"] != city["name"]:
parts.append(city["admin1"])
if city.get("country"):
parts.append(city["country"])
return ", ".join(parts)
def by_country() -> dict[str, list[dict]]:
"""Cities grouped by country (population-descending within each), country keys
ordered by their largest city — for the /climate hub's crawlable link graph."""
groups: dict[str, list[dict]] = {}
for c in _load():
key = c.get("country") or c.get("country_code") or "Other"
groups.setdefault(key, []).append(c)
for v in groups.values():
v.sort(key=lambda x: -x["population"])
# order countries by their biggest city's population (most prominent first)
return dict(sorted(groups.items(), key=lambda kv: -kv[1][0]["population"]))