Add RIPS 八王子 and MatchVox 八王子 scrapers

Both venues are RinkyDink-affiliated live houses in Hachioji.
WordPress + My Calendar plugin; parses mc-list HTML for date, title,
artist, OPEN/START times, and price across 3 months.

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

3 files changed, 298 insertions, 0 deletions

diff --git a/app/scrapers/index.ts b/app/scrapers/index.ts
index fa0df9b..21e6847 100644
--- a/app/scrapers/index.ts
+++ b/app/scrapers/index.ts
@@ -23,6 +23,8 @@ import { scraper as shimokitazawaEra } from "./shimokitazawa-era";
 import { scraper as duoMusicExchange } from "./duo-music-exchange";
 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";
 
 export const ALL_SCRAPERS: Scraper[] = [
   liquidRoom,
@@ -45,6 +47,8 @@ export const ALL_SCRAPERS: Scraper[] = [
   duoMusicExchange,
   denAtsu,
   buzzfrontYokohama,
+  ripsHachioji,
+  matchvoxHachioji,
 ];
 
 export type { Scraper } from "./base";
diff --git a/app/scrapers/matchvox-hachioji.ts b/app/scrapers/matchvox-hachioji.ts
new file mode 100644
index 0000000..ff31788
--- /dev/null
+++ b/app/scrapers/matchvox-hachioji.ts
@@ -0,0 +1,147 @@
+/**
+ * MatchVox 八王子 — http://matchvox.rinkydink.info/matchvox/schedule
+ *
+ * WordPress + My Calendar プラグイン（RIPS と同一構造）。
+ * イベント構造:
+ *   <ul class='mc-list'>
+ *     <li id='list-YYYY-MM-DD' class='mc-events ...'>
+ *       <strong class="event-date">5/1(金)</strong>
+ *       <div class='list-event ...'>
+ *         <meta itemprop='startDate' content='YYYY-MM-DDTHH:MM:SS' />
+ *         <h3 class='event-title summary'>タイトル</h3>
+ *         <div class='longdesc description'>
+ *           <p>アーティスト1<br/>アーティスト2</p>
+ *           <p>OPEN HH:MM START HH:MM<br/>adv:XXXX door:XXXX</p>
+ *         </div>
+ *       </div>
+ *     </li>
+ *   </ul>
+ *
+ * ?yr=YYYY&month=M&dy&cid=... でページネーション
+ */
+import * as cheerio from "cheerio";
+import type { Scraper, VenueMeta } from "./base";
+import type { EventInput } from "~/lib/db.server";
+
+export const venue: VenueMeta = {
+  id: "matchvox-hachioji",
+  name: "MatchVox 八王子",
+  url: "http://matchvox.rinkydink.info/matchvox",
+  area: "八王子",
+};
+
+const SCHEDULE_BASE = "http://matchvox.rinkydink.info/matchvox/schedule";
+const CID = "mc-35df894f2fa16157a96dd95b6cded5c1";
+
+function parseHtml(html: string): EventInput[] {
+  const $ = cheerio.load(html);
+  const events: EventInput[] = [];
+
+  $("ul.mc-list > li[id^='list-']").each((_, li) => {
+    const $li = $(li);
+    const dateMatch = $li.attr("id")?.match(/^list-(\d{4}-\d{2}-\d{2})$/);
+    if (!dateMatch) return;
+    const date = dateMatch[1];
+
+    $li.find("div.list-event").each((_, eventEl) => {
+      const $event = $(eventEl);
+
+      const title = $event.find("h3.event-title").text().trim();
+      if (!title) return;
+
+      let artist: string | null = null;
+      let open_time: string | null = null;
+      let start_time: string | null = null;
+      let price: string | null = null;
+      let image_url: string | null = null;
+
+      const $desc = $event.find("div.longdesc.description");
+      if ($desc.length) {
+        image_url = $desc.find("img").first().attr("src") ?? null;
+
+        const paragraphs: string[] = [];
+        $desc.find("p").each((_, p) => {
+          const $p = $(p).clone();
+          $p.find("br").replaceWith("\n");
+          const text = $p.text().trim();
+          if (text) paragraphs.push(text);
+        });
+
+        const timeParaIdx = paragraphs.findIndex((p) =>
+          /(?:open|pen)\s+\d{1,2}:\d{2}/i.test(p)
+        );
+
+        if (timeParaIdx !== -1) {
+          const timePara = paragraphs[timeParaIdx];
+          const openMatch = timePara.match(/(?:open|pen)\s+(\d{1,2}:\d{2})/i);
+          const startMatch = timePara.match(/start\s+(\d{1,2}:\d{2})/i);
+          if (openMatch) open_time = openMatch[1];
+          if (startMatch) start_time = startMatch[1];
+
+          const priceLines = timePara
+            .split("\n")
+            .map((l) => l.trim())
+            .filter((l) => /adv|door/i.test(l));
+          if (priceLines.length) price = priceLines.join(" / ");
+
+          const artistLines = paragraphs
+            .filter((_, i) => i !== timeParaIdx)
+            .flatMap((p) => p.split("\n").map((l) => l.trim()))
+            .filter((l) => l && !/^出演$/.test(l));
+          if (artistLines.length) artist = artistLines.join("、");
+        } else if (paragraphs.length) {
+          const artistLines = paragraphs
+            .flatMap((p) => p.split("\n").map((l) => l.trim()))
+            .filter((l) => l && !/^出演$/.test(l));
+          if (artistLines.length) artist = artistLines.join("、");
+        }
+      }
+
+      events.push({
+        venue_id: venue.id,
+        title,
+        artist,
+        date,
+        open_time,
+        start_time,
+        price,
+        image_url,
+        ticket_url:
+          $event
+            .find(
+              "a[href*='livepocket'], a[href*='eplus'], a[href*='pia'], a[href*='l-tike'], a[href*='tiget']"
+            )
+            .first()
+            .attr("href") ?? null,
+        source_url: SCHEDULE_BASE,
+      });
+    });
+  });
+
+  return events;
+}
+
+export const scraper: Scraper = {
+  venue,
+  async scrape(): Promise<EventInput[]> {
+    const now = new Date();
+    const urls = [0, 1, 2].map((offset) => {
+      const d = new Date(now.getFullYear(), now.getMonth() + offset, 1);
+      return `${SCHEDULE_BASE}?yr=${d.getFullYear()}&month=${d.getMonth() + 1}&dy&cid=${CID}`;
+    });
+
+    const htmls = await Promise.all(
+      urls.map((url) => fetch(url).then((r) => (r.ok ? r.text() : "")))
+    );
+
+    const seen = new Set<string>();
+    return htmls
+      .flatMap(parseHtml)
+      .filter((e) => {
+        const key = `${e.date}|${e.title}`;
+        if (seen.has(key)) return false;
+        seen.add(key);
+        return true;
+      });
+  },
+};
diff --git a/app/scrapers/rips-hachioji.ts b/app/scrapers/rips-hachioji.ts
new file mode 100644
index 0000000..bfed498
--- /dev/null
+++ b/app/scrapers/rips-hachioji.ts
@@ -0,0 +1,147 @@
+/**
+ * RIPS 八王子 — http://rips.rinkydink.info/rips/schedule
+ *
+ * WordPress + My Calendar プラグイン。
+ * イベント構造:
+ *   <ul class='mc-list'>
+ *     <li id='list-YYYY-MM-DD' class='mc-events ...'>
+ *       <strong class="event-date">5/1(金)</strong>
+ *       <div class='list-event ...'>
+ *         <meta itemprop='startDate' content='YYYY-MM-DDTHH:MM:SS' />
+ *         <h3 class='event-title summary'>タイトル</h3>
+ *         <div class='longdesc description'>
+ *           <p>アーティスト1<br/>アーティスト2</p>
+ *           <p>OPEN HH:MM START HH:MM<br/>adv:XXXX door:XXXX</p>
+ *         </div>
+ *       </div>
+ *     </li>
+ *   </ul>
+ *
+ * ?yr=YYYY&month=M&dy&cid=... でページネーション
+ */
+import * as cheerio from "cheerio";
+import type { Scraper, VenueMeta } from "./base";
+import type { EventInput } from "~/lib/db.server";
+
+export const venue: VenueMeta = {
+  id: "rips-hachioji",
+  name: "RIPS 八王子",
+  url: "http://rips.rinkydink.info/rips",
+  area: "八王子",
+};
+
+const SCHEDULE_BASE = "http://rips.rinkydink.info/rips/schedule";
+const CID = "mc-35df894f2fa16157a96dd95b6cded5c1";
+
+function parseHtml(html: string): EventInput[] {
+  const $ = cheerio.load(html);
+  const events: EventInput[] = [];
+
+  $("ul.mc-list > li[id^='list-']").each((_, li) => {
+    const $li = $(li);
+    const dateMatch = $li.attr("id")?.match(/^list-(\d{4}-\d{2}-\d{2})$/);
+    if (!dateMatch) return;
+    const date = dateMatch[1];
+
+    $li.find("div.list-event").each((_, eventEl) => {
+      const $event = $(eventEl);
+
+      const title = $event.find("h3.event-title").text().trim();
+      if (!title) return;
+
+      let artist: string | null = null;
+      let open_time: string | null = null;
+      let start_time: string | null = null;
+      let price: string | null = null;
+      let image_url: string | null = null;
+
+      const $desc = $event.find("div.longdesc.description");
+      if ($desc.length) {
+        image_url = $desc.find("img").first().attr("src") ?? null;
+
+        const paragraphs: string[] = [];
+        $desc.find("p").each((_, p) => {
+          const $p = $(p).clone();
+          $p.find("br").replaceWith("\n");
+          const text = $p.text().trim();
+          if (text) paragraphs.push(text);
+        });
+
+        const timeParaIdx = paragraphs.findIndex((p) =>
+          /(?:open|pen)\s+\d{1,2}:\d{2}/i.test(p)
+        );
+
+        if (timeParaIdx !== -1) {
+          const timePara = paragraphs[timeParaIdx];
+          const openMatch = timePara.match(/(?:open|pen)\s+(\d{1,2}:\d{2})/i);
+          const startMatch = timePara.match(/start\s+(\d{1,2}:\d{2})/i);
+          if (openMatch) open_time = openMatch[1];
+          if (startMatch) start_time = startMatch[1];
+
+          const priceLines = timePara
+            .split("\n")
+            .map((l) => l.trim())
+            .filter((l) => /adv|door/i.test(l));
+          if (priceLines.length) price = priceLines.join(" / ");
+
+          const artistLines = paragraphs
+            .filter((_, i) => i !== timeParaIdx)
+            .flatMap((p) => p.split("\n").map((l) => l.trim()))
+            .filter((l) => l && !/^出演$/.test(l));
+          if (artistLines.length) artist = artistLines.join("、");
+        } else if (paragraphs.length) {
+          const artistLines = paragraphs
+            .flatMap((p) => p.split("\n").map((l) => l.trim()))
+            .filter((l) => l && !/^出演$/.test(l));
+          if (artistLines.length) artist = artistLines.join("、");
+        }
+      }
+
+      events.push({
+        venue_id: venue.id,
+        title,
+        artist,
+        date,
+        open_time,
+        start_time,
+        price,
+        image_url,
+        ticket_url:
+          $event
+            .find(
+              "a[href*='livepocket'], a[href*='eplus'], a[href*='pia'], a[href*='l-tike'], a[href*='tiget']"
+            )
+            .first()
+            .attr("href") ?? null,
+        source_url: SCHEDULE_BASE,
+      });
+    });
+  });
+
+  return events;
+}
+
+export const scraper: Scraper = {
+  venue,
+  async scrape(): Promise<EventInput[]> {
+    const now = new Date();
+    const urls = [0, 1, 2].map((offset) => {
+      const d = new Date(now.getFullYear(), now.getMonth() + offset, 1);
+      return `${SCHEDULE_BASE}?yr=${d.getFullYear()}&month=${d.getMonth() + 1}&dy&cid=${CID}`;
+    });
+
+    const htmls = await Promise.all(
+      urls.map((url) => fetch(url).then((r) => (r.ok ? r.text() : "")))
+    );
+
+    const seen = new Set<string>();
+    return htmls
+      .flatMap(parseHtml)
+      .filter((e) => {
+        const key = `${e.date}|${e.title}`;
+        if (seen.has(key)) return false;
+        seen.add(key);
+        return true;
+      });
+  },
+};