feat: add support for DDR World

3 files changed, 60 insertions, 2 deletions

diff --git a/bemani/ddr.py b/bemani/ddr.py
new file mode 100644
index 0000000..947728c
--- /dev/null
+++ b/bemani/ddr.py
@@ -0,0 +1,56 @@
+from bs4 import BeautifulSoup
+from datetime import datetime
+from urllib.parse import urljoin
+import time
+import re
+
+def parse_ddr_world_news_site(html: str):
+    base_url = "https://p.eagate.573.jp"
+    soup = BeautifulSoup(html, 'html.parser')
+    news_entries = []
+
+    for div in soup.select("div#info > div.news_one"):
+        if 'none' in div.get('style', ''):
+            continue
+        title_tag = div.select_one("div.news_title > div.title")
+        date_tag  = div.select_one("div.news_title > div.date")
+        headline  = title_tag.get_text(strip=True) if title_tag else None
+        date_str  = date_tag.get_text(strip=True)  if date_tag  else None
+
+        try:
+            dt = datetime.strptime(date_str, "%Y/%m/%d")
+            date_iso  = dt.strftime("%Y-%m-%d")
+            timestamp = int(time.mktime(dt.timetuple()))
+        except Exception:
+            date_iso, timestamp = None, None
+
+        paras = [p.get_text(strip=True, separator="\n")
+                 for p in div.find_all("p", recursive=False)]
+        if not paras:
+            for child in div.find_all(recursive=False):
+                cls = child.get("class", [])
+                if "news_title" in cls or "img_news_center" in cls:
+                    continue
+                if child.name == "div":
+                    paras.append(child.get_text(strip=True, separator="\n"))
+        content = "\n\n".join(paras) if paras else None
+
+        # image (use data-src if present)
+        img = div.select_one("div.img_news_center img")
+        raw_src = img.get("data-src") or img.get("src") if img else None
+        image_url = urljoin(base_url, raw_src) if raw_src else None
+
+        news_entries.append({
+            "date":       date_iso,
+            "identifier": "DDR_WORLD",
+            "type":       None,
+            "timestamp":  timestamp,
+            "headline":   headline,
+            "content":    content,
+            "url":        base_url,
+            "images": {
+                "image": image_url,
+                "link":  None
+            }
+        })
+    return news_entries
diff --git a/bemani/iidx.py b/bemani/iidx.py
index c13e05f..cc69fe1 100644
--- a/bemani/iidx.py
+++ b/bemani/iidx.py
@@ -7,7 +7,8 @@ KEY_TERMS_TL = [
     ("クプロ", "QPro")
 ]
 
-def parse_pinky_crush_news_site(html: str, base_url):
+def parse_pinky_crush_news_site(html: str):
+    base_url = "https://p.eagate.573.jp"
     type_map = {
         "i_01": "NEWSONG",
         "i_02": "RANKING",
diff --git a/bemani/sdvx.py b/bemani/sdvx.py
index a87fe44..c77f198 100644
--- a/bemani/sdvx.py
+++ b/bemani/sdvx.py
@@ -2,7 +2,8 @@ from bs4 import BeautifulSoup
 from datetime import datetime
 from urllib.parse import urljoin
 
-def parse_exceed_gear_news_site(html: str, base_url: str):
+def parse_exceed_gear_news_site(html: str):
+    base_url = "https://p.eagate.573.jp"
     soup = BeautifulSoup(html, 'html.parser')
     news_list = soup.select('.tab ul.news li')