mirror of
https://github.com/tiennm99/miti99bot.git
synced 2026-04-28 04:20:38 +00:00
tiennm99
df46e4ee22
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.
96 lines
3.0 KiB
JavaScript
96 lines
3.0 KiB
JavaScript
#!/usr/bin/env node
|
|
/**
|
|
* @file scrape-loldle-data — rebuilds src/modules/loldle/champions.json from
|
|
* loldle.net's JS bundle, the canonical source for the classic-mode axes:
|
|
* gender, species, resource, attackType, region, lane, releaseDate.
|
|
*
|
|
* loldle.net embeds the full champion array in plaintext inside its JS bundle
|
|
* at `<script src="js/index.<hash>.js">`, one record per champion with the
|
|
* exact shape the bot needs. No CryptoJS decoding, no ddragon merge.
|
|
*
|
|
* Writes src/modules/loldle/champions.json. The bot imports this JSON
|
|
* directly via `with { type: "json" }` (Node 24 + wrangler 4.x).
|
|
*
|
|
* Usage:
|
|
* node scripts/scrape-loldle-data.js
|
|
*
|
|
* Schedule: weekly via .github/workflows/scrape-loldle-data.yml
|
|
*/
|
|
|
|
import { writeFileSync } from "node:fs";
|
|
import { resolve } from "node:path";
|
|
|
|
const LOLDLE_CLASSIC = "https://loldle.net/classic";
|
|
|
|
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;
|
|
|
|
async function fetchText(url) {
|
|
const res = await fetch(url);
|
|
if (!res.ok) throw new Error(`fetch ${url}: ${res.status} ${res.statusText}`);
|
|
return res.text();
|
|
}
|
|
|
|
function parseJsArrayStrings(inner) {
|
|
return [...inner.matchAll(/"([^"]+)"/g)].map((m) => m[1]);
|
|
}
|
|
|
|
async function scrapeLoldle() {
|
|
const html = await fetchText(LOLDLE_CLASSIC);
|
|
const scriptMatch = html.match(/<script\s+src="(js\/index\.[^"]+\.js)"/);
|
|
if (!scriptMatch) throw new Error("loldle.net: could not locate index.js script tag in HTML");
|
|
const bundleUrl = `https://loldle.net/${scriptMatch[1]}`;
|
|
const bundle = await fetchText(bundleUrl);
|
|
|
|
const seen = new Set();
|
|
const records = [];
|
|
for (const m of bundle.matchAll(CHAMPION_RECORD_RX)) {
|
|
const [
|
|
,
|
|
_id,
|
|
championId,
|
|
championName,
|
|
gender,
|
|
positions,
|
|
species,
|
|
resource,
|
|
rangeType,
|
|
regions,
|
|
releaseDate,
|
|
] = m;
|
|
if (seen.has(championName)) continue;
|
|
seen.add(championName);
|
|
|
|
records.push({
|
|
_id,
|
|
championId,
|
|
championName,
|
|
gender,
|
|
positions: parseJsArrayStrings(positions),
|
|
species: parseJsArrayStrings(species),
|
|
resource,
|
|
range_type: parseJsArrayStrings(rangeType),
|
|
regions: parseJsArrayStrings(regions),
|
|
release_date: releaseDate,
|
|
});
|
|
}
|
|
|
|
if (records.length === 0) {
|
|
throw new Error(
|
|
"loldle.net: zero champion records parsed — bundle format changed, update CHAMPION_RECORD_RX",
|
|
);
|
|
}
|
|
records.sort((a, b) => a.championName.localeCompare(b.championName));
|
|
return records;
|
|
}
|
|
|
|
const root = resolve(import.meta.dirname, "..");
|
|
const jsonPath = resolve(root, "src/modules/loldle/champions.json");
|
|
|
|
console.log("scraping loldle.net…");
|
|
const records = await scrapeLoldle();
|
|
console.log(` parsed ${records.length} champions`);
|
|
|
|
writeFileSync(jsonPath, `${JSON.stringify(records, null, 4)}\n`);
|
|
console.log(`wrote ${jsonPath}`);
|