lucasw89/gacha-event-tracker
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: extract event descriptions from Game8 detail tables

Browse Source 
Column tables already carried a description column, but label/value detail
tables did not — Genshin events had no blurb at all. The page follows each
detail table with a sentence of prose, so take that, skipping the
call-to-action paragraphs, which are navigation rather than description.

Summary coverage goes from 13/22 events to 22/22.

Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
This commit is contained in:
Lucas Winther
2026-08-15 00:39:42 +02:00
co-authored by Claude Opus 5
parent 62f673161b
commit 6fffd283a5
3 changed files with 58 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/ingest/html.ts
+18 -3
View File
@@ -51,10 +51,22 @@ export interface TableNode {
rows: string[][];
}
export interface ParagraphNode {
kind: "p";
text: string;
/**
* True when the paragraph is really a call-to-action link rather than prose.
* Game8 wraps its "… Event Guide" buttons in the same paragraph class as body
* copy, so callers need to tell them apart.
*/
isButton: boolean;
}
export type DocNode =
| { kind: "h2"; text: string }
| { kind: "h3"; text: string }
| TableNode;
| TableNode
| ParagraphNode;
/**
* Walk a document in source order, yielding h2/h3 headings and tables.
@@ -66,16 +78,19 @@ export function scanDocument(rawHtml: string): DocNode[] {
const html = rawHtml.replace(/<!--[\s\S]*?-->/g, "").replace(/\s+/g, " ");
const nodes: DocNode[] = [];
const re = /<h2\b[^>]*>([\s\S]*?)<\/h2>|<h3\b[^>]*>([\s\S]*?)<\/h3>|<table\b[^>]*>([\s\S]*?)<\/table>/gi;
const re =
/<h2\b[^>]*>([\s\S]*?)<\/h2>|<h3\b[^>]*>([\s\S]*?)<\/h3>|<table\b[^>]*>([\s\S]*?)<\/table>|<p\b[^>]*>([\s\S]*?)<\/p>/gi;
for (const m of html.matchAll(re)) {
const [, h2, h3, table] = m;
const [whole, h2, h3, table, p] = m;
if (h2 !== undefined) {
nodes.push({ kind: "h2", text: text(h2) });
} else if (h3 !== undefined) {
nodes.push({ kind: "h3", text: text(h3) });
} else if (table !== undefined) {
nodes.push(readTable(table));
} else if (p !== undefined) {
nodes.push({ kind: "p", text: text(p), isButton: /a-btn/.test(whole) });
}
}