Add scrapers for 新宿MARZ and 東高円寺U.F.O.CLUB

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

3 files changed, 254 insertions, 0 deletions

diff --git a/app/scrapers/index.ts b/app/scrapers/index.ts
index 21e6847..79e8125 100644
--- a/app/scrapers/index.ts
+++ b/app/scrapers/index.ts
@@ -25,6 +25,8 @@ import { scraper as denAtsu } from "./den-atsu";
 import { scraper as buzzfrontYokohama } from "./buzzfront-yokohama";
 import { scraper as ripsHachioji } from "./rips-hachioji";
 import { scraper as matchvoxHachioji } from "./matchvox-hachioji";
+import { scraper as marzShinjuku } from "./marz-shinjuku";
+import { scraper as ufoclubHigashikoenji } from "./ufoclub-higashikoenji";
 
 export const ALL_SCRAPERS: Scraper[] = [
   liquidRoom,
@@ -49,6 +51,8 @@ export const ALL_SCRAPERS: Scraper[] = [
   buzzfrontYokohama,
   ripsHachioji,
   matchvoxHachioji,
+  marzShinjuku,
+  ufoclubHigashikoenji,
 ];
 
 export type { Scraper } from "./base";
diff --git a/app/scrapers/marz-shinjuku.ts b/app/scrapers/marz-shinjuku.ts
new file mode 100644
index 0000000..06c0bcc
--- /dev/null
+++ b/app/scrapers/marz-shinjuku.ts
@@ -0,0 +1,117 @@
+/**
+ * 新宿MARZ — http://www.marz.jp/schedule/YYYY/MM/
+ *
+ * DOM構造:
+ *   <article id="eXXXX">
+ *     <a href="detail-url"><div class="img"><img src="..."><time datetime="YYYY-MM-DD"></div></a>
+ *     <h1><a href="...">タイトル</a></h1>
+ *     <div class="desc">
+ *       <div class="entrybody"><p>【LIVE】<br/>アーティスト名</p> ...</div>
+ *       <div class="entryex"><p>open HH:MM / start HH:MM<br/>adv¥XXX / door¥XXX<br/>...</p></div>
+ *     </div>
+ *   </article>
+ */
+import * as cheerio from "cheerio";
+import type { Scraper, VenueMeta } from "./base";
+import type { EventInput } from "~/lib/db.server";
+
+export const venue: VenueMeta = {
+  id: "marz-shinjuku",
+  name: "新宿MARZ",
+  url: "http://www.marz.jp",
+  area: "新宿",
+  capacity: 200,
+};
+
+async function scrapeMonth(year: number, month: number): Promise<EventInput[]> {
+  const url = `http://www.marz.jp/schedule/${year}/${String(month).padStart(2, "0")}/`;
+  const res = await fetch(url);
+  if (!res.ok) throw new Error(`HTTP ${res.status} for ${url}`);
+  const $ = cheerio.load(await res.text());
+  const events: EventInput[] = [];
+
+  $("article").each((_, el) => {
+    const $el = $(el);
+
+    const date = $el.find("time[datetime]").attr("datetime");
+    if (!date) return;
+
+    const title = $el.find("h1 a").first().text().trim();
+    if (!title) return;
+
+    const source_url = $el.find("a[href]").first().attr("href") ?? null;
+    const image_url = $el.find(".img img").attr("src") ?? null;
+    const ticket_url =
+      $el
+        .find(".entrybody a[href]")
+        .filter((_, a) => {
+          const h = $(a).attr("href") ?? "";
+          return h.startsWith("http") && !h.includes("marz.jp");
+        })
+        .first()
+        .attr("href") ?? null;
+
+    // Artist lines: clone entrybody, replace <br> with \n, filter out labels/ticket lines
+    const $body = $el.find(".entrybody").clone();
+    $body.find("br").replaceWith("\n");
+    const artistLines = $body
+      .text()
+      .split("\n")
+      .map((l) => l.trim())
+      .filter(
+        (l) => l && !l.includes("【") && !l.startsWith("■") && !l.startsWith("※")
+      );
+    const artist = artistLines.length > 0 ? artistLines.join(" / ") : null;
+
+    // Time and price from entryex
+    const $ex = $el.find(".entryex").clone();
+    $ex.find("br").replaceWith("\n");
+    const exLines = $ex
+      .text()
+      .split("\n")
+      .map((l) => l.trim())
+      .filter(Boolean);
+
+    const timeLine = exLines[0] ?? "";
+    const openMatch = timeLine.match(/open\s+(\d{1,2}:\d{2})/i);
+    const startMatch = timeLine.match(/start\s+(\d{1,2}:\d{2})/i);
+    const priceLine =
+      exLines.find((l, i) => i > 0 && /[¥￥]|adv|door/i.test(l)) ?? null;
+
+    events.push({
+      venue_id: venue.id,
+      title,
+      artist,
+      date,
+      open_time: openMatch?.[1] ?? null,
+      start_time: startMatch?.[1] ?? null,
+      price: priceLine,
+      ticket_url,
+      image_url,
+      source_url,
+    });
+  });
+
+  return events;
+}
+
+export const scraper: Scraper = {
+  venue,
+  async scrape(): Promise<EventInput[]> {
+    const now = new Date();
+    const next = new Date(now.getFullYear(), now.getMonth() + 1, 1);
+
+    const [thisMonth, nextMonth] = await Promise.all([
+      scrapeMonth(now.getFullYear(), now.getMonth() + 1),
+      scrapeMonth(next.getFullYear(), next.getMonth() + 1),
+    ]);
+
+    const seen = new Set<string>();
+    return [...thisMonth, ...nextMonth].filter((e) => {
+      const key = `${e.date}|${e.title}`;
+      if (seen.has(key)) return false;
+      seen.add(key);
+      return true;
+    });
+  },
+};
diff --git a/app/scrapers/ufoclub-higashikoenji.ts b/app/scrapers/ufoclub-higashikoenji.ts
new file mode 100644
index 0000000..85749f9
--- /dev/null
+++ b/app/scrapers/ufoclub-higashikoenji.ts
@@ -0,0 +1,133 @@
+/**
+ * 東高円寺 U.F.O.CLUB — https://www.ufoclub.jp/schedule/
+ *
+ * WordPress テーマ。fetch に Mozilla UA が必要（curl は 2 バイトを返す）。
+ *
+ * DOM構造:
+ *   <div class="month">2026年6月</div>   ← 年月の取得元
+ *   <table class="schedule-table"><tbody>
+ *     <tr>
+ *       <th>1</th>            ← 日
+ *       <td>MON</td>          ← 曜日（スキップ）
+ *       <td>
+ *         <strong>【タイトル】</strong><br/>
+ *         /LIVE; artist1, artist2
+ *         /DJ; dj1
+ *       </td>
+ *       <td class="td_open">OPEN 18:30~<br/>START 19:00~</td>
+ *       <td class="td_charge">ADV.¥2800(+1D)<br/>DOOR.¥3300(+1D)</td>
+ *     </tr>
+ *   </tbody></table>
+ *
+ * 月ナビ: /schedule/ (当月) / /schedule/next-month (翌月)
+ */
+import * as cheerio from "cheerio";
+import type { Scraper, VenueMeta } from "./base";
+import type { EventInput } from "~/lib/db.server";
+
+export const venue: VenueMeta = {
+  id: "ufoclub-higashikoenji",
+  name: "東高円寺 U.F.O.CLUB",
+  url: "https://www.ufoclub.jp",
+  area: "東高円寺",
+  capacity: 120,
+};
+
+const UA =
+  "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36";
+
+async function scrapePage(url: string): Promise<EventInput[]> {
+  const res = await fetch(url, { headers: { "User-Agent": UA } });
+  if (!res.ok) throw new Error(`HTTP ${res.status} for ${url}`);
+  const $ = cheerio.load(await res.text());
+  const events: EventInput[] = [];
+
+  // Parse year and month from <div class="month">2026年6月</div>
+  const monthText = $("div.month").first().text().trim();
+  const monthMatch = monthText.match(/(\d{4})年(\d{1,2})月/);
+  if (!monthMatch) return events;
+  const year = parseInt(monthMatch[1], 10);
+  const month = parseInt(monthMatch[2], 10);
+
+  $("table.schedule-table tbody tr").each((_, row) => {
+    const $row = $(row);
+
+    // Day from <th>
+    const day = parseInt($row.find("th").text().trim(), 10);
+    if (isNaN(day)) return;
+    const date = `${year}-${String(month).padStart(2, "0")}-${String(day).padStart(2, "0")}`;
+
+    // Event td is the 2nd <td> (index 1; 0 = day-of-week)
+    const $eventTd = $row.find("td").eq(1);
+    const title = $eventTd.find("strong").text().replace(/^【|】$/g, "").trim();
+    if (!title) return;
+
+    // Artists: text after </strong>, lines starting with /LIVE; /DJ; /MC;
+    const $tdClone = $eventTd.clone();
+    $tdClone.find("strong").remove();
+    $tdClone.find("br").replaceWith("\n");
+    const afterTitle = $tdClone.text();
+    const artistParts: string[] = [];
+    for (const line of afterTitle.split("\n")) {
+      const t = line.replace(/\s+/g, " ").trim();
+      const liveM = t.match(/^\/LIVE;\s*(.+)/i);
+      const djM = t.match(/^\/DJ;\s*(.+)/i);
+      const mcM = t.match(/^\/MC;\s*(.+)/i);
+      if (liveM) artistParts.push(liveM[1].trim());
+      else if (djM) artistParts.push(`DJ: ${djM[1].trim()}`);
+      else if (mcM) artistParts.push(`MC: ${mcM[1].trim()}`);
+    }
+    const artist = artistParts.length > 0 ? artistParts.join(" / ") : null;
+
+    // Open / Start time from td.td_open
+    const $openTd = $row.find("td.td_open").clone();
+    $openTd.find("br").replaceWith("\n");
+    const openText = $openTd.text();
+    const openMatch = openText.match(/OPEN\s+(\d{1,2}:\d{2})/i);
+    const startMatch = openText.match(/START\s+(\d{1,2}:\d{2})/i);
+
+    // Price from td.td_charge (first two lines: ADV / DOOR)
+    const $chargeTd = $row.find("td.td_charge").clone();
+    $chargeTd.find("br").replaceWith("\n");
+    const chargeLines = $chargeTd
+      .text()
+      .split("\n")
+      .map((l) => l.trim())
+      .filter(Boolean);
+    const price =
+      chargeLines.length >= 2
+        ? `${chargeLines[0]} / ${chargeLines[1]}`
+        : (chargeLines[0] ?? null);
+
+    events.push({
+      venue_id: venue.id,
+      title,
+      artist,
+      date,
+      open_time: openMatch?.[1] ?? null,
+      start_time: startMatch?.[1] ?? null,
+      price,
+      source_url: url,
+    });
+  });
+
+  return events;
+}
+
+export const scraper: Scraper = {
+  venue,
+  async scrape(): Promise<EventInput[]> {
+    const [thisMonth, nextMonth] = await Promise.all([
+      scrapePage("https://www.ufoclub.jp/schedule/"),
+      scrapePage("https://www.ufoclub.jp/schedule/next-month"),
+    ]);
+
+    const seen = new Set<string>();
+    return [...thisMonth, ...nextMonth].filter((e) => {
+      const key = `${e.date}|${e.title}`;
+      if (seen.has(key)) return false;
+      seen.add(key);
+      return true;
+    });
+  },
+};