add maimai DX JPN scraping

1 files changed, 48 insertions, 0 deletions

diff --git a/sega/maimaidx_jp.py b/sega/maimaidx_jp.py
new file mode 100644
index 0000000..5a88ef1
--- /dev/null
+++ b/sega/maimaidx_jp.py
@@ -0,0 +1,48 @@
+from bs4 import BeautifulSoup
+from datetime import datetime, timezone, timedelta
+from urllib.parse import urljoin
+import re
+
+def parse_maimaidx_jp_prism_plus_news_site(html: str):
+    soup = BeautifulSoup(html, "html.parser")
+    base_url = "https://info-maimai.sega.jp/"
+    news_items = []
+
+    news_boxes = soup.select(".maiPager-content .newsBox")
+    for box in news_boxes:
+        a_tag = box.select_one("a")
+        url = urljoin(base_url, a_tag["href"]) if a_tag and a_tag.get("href") else None
+
+        img_tag = box.select_one("img")
+        image_url = urljoin(base_url, img_tag["src"]) if img_tag else None
+
+        date_tag = box.select_one(".newsDate")
+        raw_date = date_tag.get_text(strip=True) if date_tag else None
+
+        jst = timezone(timedelta(hours=9))
+        try:
+            dt = datetime.strptime(raw_date.split(" ")[0], "%Y.%m.%d").replace(tzinfo=jst)
+            timestamp = int(dt.timestamp())
+        except:
+            dt = None
+            timestamp = 0
+
+        headline_tag = box.select_one(".newsLink")
+        headline = headline_tag.get_text(strip=True) if headline_tag else None
+        content = box.get_text(separator="\n", strip=True)
+        identifier = re.sub(r"\W+", "-", headline.lower()) if headline else "unknown"
+        news_items.append({
+            "date": raw_date,
+            "identifier": identifier,
+            "type": None,
+            "timestamp": timestamp,
+            "headline": headline,
+            "content": content,
+            "url": url,
+            "images": [{
+                "image": image_url,
+                "link": url
+            }] if image_url else []
+        })
+
+    return news_items