add maimai DX INTERNATIONAL basic info to scraper

4 files changed, 53 insertions, 1 deletions

diff --git a/constants.py b/constants.py
index 4fb59f9..6ef036e 100644
--- a/constants.py
+++ b/constants.py
@@ -8,6 +8,7 @@ IIDX_PINKY_CRUSH_NEWS_SITE="https://p.eagate.573.jp/game/2dx/32/info/index.html"
 
 CHUNITHM_JP_NEWS_SITE="https://info-chunithm.sega.jp/"
 MAIMAIDX_JP_NEWS_SITE="https://info-maimai.sega.jp/"
+MAIMAIDX_INTL_NEWS_SITE="https://maimai.sega.com/download/"
 ONGEKI_JP_NEWS_SITE="https://info-ongeki.sega.jp/"
 
 class CHUNITHM_VERSION(Enum):
diff --git a/generate.py b/generate.py
index d7f8c6f..e91c8ee 100644
--- a/generate.py
+++ b/generate.py
@@ -91,6 +91,17 @@ if __name__ == "__main__":
             ongeki_jp_news_data = json.load(json_file)['news_posts']
         print("ONGEKI JPN Data not fetched, using existing data.")
 
-    news = create_merged_feed(iidx_news_data, sdvx_news_data, chunithm_jp_news_data, maimaidx_jp_news_data, ongeki_jp_news_data)
+    print("Fetching MAIMAIDX INTL Data")
+    maimaidx_intl_news_data = feed.get_news(constants.MAIMAIDX_INTL_NEWS_SITE, constants.MAIMAIDX_VERSION.PRISM)
+    if len(maimaidx_intl_news_data) != 0:
+        with open(OUTPUT_DIR+'/maimaidx_intl_news.json', 'w') as json_file:
+            json.dump(attach_news_meta_data(maimaidx_intl_news_data), json_file)
+        print("MAIMAIDX INTLN Data fetched and saved.")
+    elif len(maimaidx_intl_news_data) == 0 and os.path.exists(OUTPUT_DIR+'/maimaidx_intl_news.json'):
+        with open(OUTPUT_DIR+'/maimaidx_intl_news.json', 'r') as json_file:
+            maimaidx_intl_news_data = json.load(json_file)['news_posts']
+        print("MAIMAIDX INTL Data not fetched, using existing data.")
+
+    news = create_merged_feed(iidx_news_data, sdvx_news_data, chunithm_jp_news_data, maimaidx_jp_news_data, ongeki_jp_news_data, maimaidx_intl_news_data)
     with open(OUTPUT_DIR+'/news.json', 'w') as json_file:
         json.dump(attach_news_meta_data(news), json_file)
diff --git a/news_feed.py b/news_feed.py
index d796d64..13720a8 100644
--- a/news_feed.py
+++ b/news_feed.py
@@ -22,6 +22,7 @@ import bemani.sdvx as sound_voltex
 import bemani.iidx as iidx
 import sega.chuni_jp as chunithm_jp
 import sega.maimaidx_jp as maimaidx_jp
+import sega.maimaidx_intl as maimaidx_intl
 import sega.ongeki_jp as ongeki_jp
 import constants
 
@@ -38,6 +39,9 @@ def get_news(news_url: str, version=None) -> list:
     elif news_url == constants.MAIMAIDX_JP_NEWS_SITE:
         if version == constants.MAIMAIDX_VERSION.PRISM_PLUS:
             news_posts = sorted(maimaidx_jp.parse_maimaidx_jp_prism_plus_news_site(site_data), key=lambda x: x['timestamp'], reverse=True)
+    elif news_url == constants.MAIMAIDX_INTL_NEWS_SITE:
+        if version == constants.MAIMAIDX_VERSION.PRISM:
+            news_posts = sorted(maimaidx_intl.parse_maimaidx_intl_prism_news_site(site_data), key=lambda x: x['timestamp'], reverse=True)
     elif news_url == constants.ONGEKI_JP_NEWS_SITE:
         if version == constants.ONGEKI_VERSION.REFRESH:
             news_posts = sorted(ongeki_jp.parse_ongeki_refresh_news_site(site_data), key=lambda x: x['timestamp'], reverse=True)
diff --git a/sega/maimaidx_intl.py b/sega/maimaidx_intl.py
new file mode 100644
index 0000000..7769b7c
--- /dev/null
+++ b/sega/maimaidx_intl.py
@@ -0,0 +1,36 @@
+from bs4 import BeautifulSoup
+from datetime import datetime, timezone, timedelta
+import time
+
+def parse_maimaidx_intl_prism_news_site(html: str):
+    soup = BeautifulSoup(html, "html.parser")
+    items = soup.select(".dl--pop__item")
+
+    entries = []
+    for item in items:
+        date_text = item.select_one(".dl--pop__head").text.strip().replace(" UP", "")
+        dt = datetime.strptime(date_text, "%Y.%m.%d").replace(tzinfo=timezone(timedelta(hours=9)))
+        timestamp = int(dt.timestamp())
+
+        img_tag = item.select_one("a.dl--pop__thumb img")
+        image_url = img_tag["srcset"] if img_tag else None
+        full_image_url = image_url.replace("../", "https://maimai.sega.jp/") if image_url else None
+
+        entry = {
+            "date": date_text,
+            "identifier": "MAIMAIDX_INTL_PRISM",
+            "type": None,
+            "timestamp": timestamp,
+            "headline": None,
+            "content": f"New maimai DX International News / maimai DX International の新しいお知らせ\n\n{full_image_url}",
+            "url": None,
+            "images": [
+                {
+                    "image": full_image_url,
+                    "link": None
+                }
+            ]
+        }
+
+        entries.append(entry)
+        return entries