refactor(loldle): consume loldle.net's raw schema directly

Drop the in-scraper normalization step — champions.json now mirrors the
exact shape emitted by loldle.net's JS bundle. Records use _id,
championId, championName, arrays for positions/species/regions/
range_type, "Male"/"Female"/"Other" gender strings, and a full
YYYY-MM-DD release_date.

Comparison is schema-aware: multi-value keys accept arrays directly,
the year axis parses YYYY out of the ISO date, and exact compares stay
case-insensitive.
This commit is contained in:
2026-04-22 13:29:55 +07:00
parent 615dc8174c
commit df46e4ee22
10 changed files with 3193 additions and 1509 deletions
+26 -34
View File
@@ -22,18 +22,8 @@ import { resolve } from "node:path";
const LOLDLE_CLASSIC = "https://loldle.net/classic";
const LANE_MAP = {
top: "top",
jungle: "jungle",
middle: "mid",
bottom: "bottom",
support: "support",
};
const GENDER_MAP = { male: "male", female: "female", other: "divers" };
const CHAMPION_RECORD_RX =
/\{_id:"[a-f0-9]+",championId:"[^"]+",championName:"([^"]+)",gender:"([^"]+)",positions:\[([^\]]+)\],species:\[([^\]]+)\],resource:"([^"]+)",range_type:\[([^\]]+)\],regions:\[([^\]]+)\],release_date:"(\d{4})-\d{2}-\d{2}"\}/g;
/\{_id:"([a-f0-9]+)",championId:"([^"]+)",championName:"([^"]+)",gender:"([^"]+)",positions:\[([^\]]+)\],species:\[([^\]]+)\],resource:"([^"]+)",range_type:\[([^\]]+)\],regions:\[([^\]]+)\],release_date:"(\d{4}-\d{2}-\d{2})"\}/g;
async function fetchText(url) {
const res = await fetch(url);
@@ -45,10 +35,6 @@ function parseJsArrayStrings(inner) {
return [...inner.matchAll(/"([^"]+)"/g)].map((m) => m[1]);
}
function normalizeRegion(name) {
return name.toLowerCase().replace(/\s+/g, "-");
}
async function scrapeLoldle() {
const html = await fetchText(LOLDLE_CLASSIC);
const scriptMatch = html.match(/<script\s+src="(js\/index\.[^"]+\.js)"/);
@@ -59,27 +45,33 @@ async function scrapeLoldle() {
const seen = new Set();
const records = [];
for (const m of bundle.matchAll(CHAMPION_RECORD_RX)) {
const [, name, gender, positionsRaw, speciesRaw, resource, rangeTypeRaw, regionsRaw, year] = m;
if (seen.has(name)) continue;
seen.add(name);
const lanes = parseJsArrayStrings(positionsRaw)
.map((p) => LANE_MAP[p.toLowerCase()])
.filter(Boolean);
const regions = parseJsArrayStrings(regionsRaw).map(normalizeRegion);
const species = parseJsArrayStrings(speciesRaw).map((s) => s.toLowerCase());
const rangeType = parseJsArrayStrings(rangeTypeRaw)[0]?.toLowerCase();
const [
,
_id,
championId,
championName,
gender,
positions,
species,
resource,
rangeType,
regions,
releaseDate,
] = m;
if (seen.has(championName)) continue;
seen.add(championName);
records.push({
id: name,
name,
gender: GENDER_MAP[gender.toLowerCase()] ?? "divers",
species: species.join(","),
_id,
championId,
championName,
gender,
positions: parseJsArrayStrings(positions),
species: parseJsArrayStrings(species),
resource,
attackType: rangeType === "melee" ? "close" : "range",
region: regions.join(","),
lane: lanes.join(","),
releaseDate: Number(year),
range_type: parseJsArrayStrings(rangeType),
regions: parseJsArrayStrings(regions),
release_date: releaseDate,
});
}
@@ -88,7 +80,7 @@ async function scrapeLoldle() {
"loldle.net: zero champion records parsed — bundle format changed, update CHAMPION_RECORD_RX",
);
}
records.sort((a, b) => a.name.localeCompare(b.name));
records.sort((a, b) => a.championName.localeCompare(b.championName));
return records;
}