feat: scrape tournament meta from Wikipedia, drop world_cup.csv

Add worldcup.meta.json per year with host, teams_count, winner, runner_up,
third_place, fourth_place — derived from match results (Final/Third-place
match) with infobox as fallback for edge cases like 1950's round-robin final.

Fix infobox host extraction to handle <br>-separated multi-host entries
(2002: Japan / South Korea). Fix squad scraper to filter out zero-player
phantom sections that Wikipedia appends (References, Captains, etc.).

Drop app/data/world_cup.csv and the PLACEMENTS/parseCsv code in seed.ts —
all tournament metadata now comes from the scraped JSON files.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

scripts/scrape-wikipedia.ts

@@ -49,6 +49,14 @@ type Stadium = { name: string; city: string }
 type Player = { name: string; number?: number; pos?: string; date_of_birth?: string }
 type Squad = { name: string; players: Player[] }
 type Group = { name: string; teams: string[] }
+type Meta = {
+  host: string
+  teams_count: number | null
+  winner: string | null
+  runner_up: string | null
+  third_place: string | null
+  fourth_place: string | null
+}
 
 // ── Fetch ──────────────────────────────────────────────────────────────────
 
@@ -309,10 +317,99 @@ function processHeading(text: string, level: number, state: State): void {
 
 // ── Main year scraper ──────────────────────────────────────────────────────
 
+// ── Infobox parsing ────────────────────────────────────────────────────────
+
+function parseInfobox($: CheerioAPI): Partial<Meta> {
+  const result: Partial<Meta> = {}
+
+  function tdText($td: Cheerio<Element>): string {
+    const $clone = $td.clone()
+    $clone.find('br').replaceWith(' / ')
+    $clone.find('sup, img').remove()
+    return $clone.text().replace(/\[\d+\]/g, '').replace(/\s+/g, ' ').trim()
+  }
+
+  function tdFirstLink($td: Cheerio<Element>): string | null {
+    let name: string | null = null
+    $td.find('a').each((_, a) => {
+      const t = $(a).clone().find('img').remove().end().text().trim()
+      if (t && !/\[\d+\]/.test(t)) { name = t; return false }
+    })
+    return name ?? (tdText($td) || null)
+  }
+
+  function tdAllLinks($td: Cheerio<Element>): string {
+    const names: string[] = []
+    $td.find('a').each((_, a) => {
+      const t = $(a).clone().find('img').remove().end().text().trim()
+      if (t && !/\[\d+\]/.test(t)) names.push(t)
+    })
+    return names.length ? names.join(' / ') : tdText($td)
+  }
+
+  $('table.infobox').first().find('tr').each((_, tr) => {
+    const $tr = $(tr)
+    const label = $tr.find('th').text().trim().toLowerCase()
+    const $td = $tr.find('td').first()
+    if (!$td.length) return
+    if (/host countr/i.test(label)) {
+      result.host = tdAllLinks($td)
+    } else if (/^teams$/i.test(label)) {
+      const m = $td.text().match(/\d+/)
+      if (m) result.teams_count = parseInt(m[0])
+    } else if (/champion/i.test(label)) {
+      result.winner = tdFirstLink($td)
+    } else if (/runners?.up/i.test(label)) {
+      result.runner_up = tdFirstLink($td)
+    } else if (/third.place/i.test(label)) {
+      result.third_place = tdFirstLink($td)
+    } else if (/fourth.place/i.test(label)) {
+      result.fourth_place = tdFirstLink($td)
+    }
+  })
+
+  return result
+}
+
+// ── Placement derivation ───────────────────────────────────────────────────
+
+function derivePlacements(matches: Match[]): Pick<Meta, 'winner' | 'runner_up' | 'third_place' | 'fourth_place'> {
+  function matchWinner(m: Match): [string, string] | null {
+    if (!m.score) return null
+    const [h, a] = m.score.et ?? m.score.ft ?? [0, 0]
+    if (h > a) return [m.team1, m.team2]
+    if (a > h) return [m.team2, m.team1]
+    if (m.score.p) {
+      const [ph, pa] = m.score.p
+      if (ph > pa) return [m.team1, m.team2]
+      if (pa > ph) return [m.team2, m.team1]
+    }
+    return null
+  }
+
+  let winner: string | null = null, runner_up: string | null = null
+  let third_place: string | null = null, fourth_place: string | null = null
+
+  for (const m of matches) {
+    if (m.round === 'Final') {
+      const result = matchWinner(m)
+      if (result) { [winner, runner_up] = result }
+    } else if (m.round === 'Third-place match') {
+      const result = matchWinner(m)
+      if (result) { [third_place, fourth_place] = result }
+    }
+  }
+
+  return { winner, runner_up, third_place, fourth_place }
+}
+
+// ── Year result ────────────────────────────────────────────────────────────
+
 type YearResult = {
   matches: Match[]
   stadiums: Map<string, Stadium>
   groups: Map<string, Set<string>>
+  meta: Meta
 }
 
 async function scrapeYear(year: number, mainHtml: string): Promise<YearResult> {
@@ -406,7 +503,18 @@ async function scrapeYear(year: number, mainHtml: string): Promise<YearResult> {
     process.stdout.write(`[+${page.slice(-8)}] `)
   }
 
-  return { matches, stadiums, groups }
+  const infobox = parseInfobox($)
+  const placements = derivePlacements(matches)
+  const meta: Meta = {
+    host: infobox.host ?? '',
+    teams_count: infobox.teams_count ?? null,
+    winner:      placements.winner      ?? infobox.winner      ?? null,
+    runner_up:   placements.runner_up   ?? infobox.runner_up   ?? null,
+    third_place: placements.third_place ?? infobox.third_place ?? null,
+    fourth_place:placements.fourth_place?? infobox.fourth_place?? null,
+  }
+
+  return { matches, stadiums, groups, meta }
 }
 
 // ── Squad page scraper ─────────────────────────────────────────────────────
@@ -465,7 +573,7 @@ function scrapeSquads(html: string): Squad[] {
     currentTeam.players.push(player)
   })
 
-  return squads
+  return squads.filter(s => s.players.length > 0)
 }
 
 // ── Output ─────────────────────────────────────────────────────────────────
@@ -476,10 +584,17 @@ function writeOutput(
   stadiums: Map<string, Stadium>,
   groups: Map<string, Set<string>>,
   squads: Squad[],
+  meta: Meta,
 ): void {
   const dir = path.join(DATA_DIR, String(year))
   mkdirSync(dir, { recursive: true })
 
+  writeFileSync(
+    path.join(dir, 'worldcup.meta.json'),
+    JSON.stringify(meta, null, 2),
+    'utf-8',
+  )
+
   writeFileSync(
     path.join(dir, 'worldcup.json'),
     JSON.stringify({ matches }, null, 2),
@@ -529,14 +644,14 @@ async function main() {
     const mainHtml = await fetchWikiHtml(`${year}_FIFA_World_Cup`)
     if (!mainHtml) { console.log('FAILED'); continue }
 
-    const { matches, stadiums, groups } = await scrapeYear(year, mainHtml)
+    const { matches, stadiums, groups, meta } = await scrapeYear(year, mainHtml)
 
     await delay(600)
 
     const squadHtml = await fetchWikiHtml(`${year}_FIFA_World_Cup_squads`)
     const squads = squadHtml ? scrapeSquads(squadHtml) : []
 
-    writeOutput(year, matches, stadiums, groups, squads)
+    writeOutput(year, matches, stadiums, groups, squads, meta)
 
     console.log(`${matches.length} matches, ${stadiums.size} stadiums, ${groups.size} groups, ${squads.length} teams`)