2 files changed, 106 insertions, 0 deletions
diff --git a/bemani/iidx.py b/bemani/iidx.py
new file mode 100644
index 0000000..e20dd7d
--- /dev/null
+++ b/bemani/iidx.py
@@ -0,0 +1,60 @@
+from bs4 import BeautifulSoup
+from datetime import datetime
+from urllib.parse import urljoin
+import re
+
+
+def parse_pinky_crush_news_site(html: str, base_url):
+    type_map = {
+        "i_01": "NEWSONG",
+        "i_02": "RANKING",
+        "i_03": "EVENT",
+        "i_04": "SHOP",
+        "i_05": "OTHER"
+    }
+    soup = BeautifulSoup(html, "html.parser")
+    news_items = []
+
+    for li in soup.select("#info-news > li"):
+        date_elem = li.select_one(".news-main > li:nth-of-type(1)")
+        headline_elem = li.select_one(".news-main > li:nth-of-type(2)")
+        content_elem = li.select_one(".news-main > li:nth-of-type(3)")
+        type_class = li.get("class", [None])[0]
+        if not (date_elem and content_elem):
+            continue
+        date_str = date_elem.text.strip()
+        try:
+            dt = datetime.strptime(date_str, "%Y/%m/%d")
+            timestamp = int(dt.timestamp())
+        except ValueError:
+            timestamp = None
+
+        headline = headline_elem.a.text.strip() if headline_elem.a else headline_elem.text.strip()
+
+        for a in content_elem.select("a[href]"):
+            href = urljoin(base_url, a["href"])
+            text = a.get_text(strip=True)
+            a.replace_with(f"[{text}]({href})")
+
+        for br in content_elem.find_all("br"):
+            br.replace_with("\n")
+
+        content = content_elem.get_text().strip()
+
+        content = content.replace(
+            "                              e-amusement ベーシックコース                          ",
+            " e-amusement ベーシックコース "
+        )
+        content = content.replace("※", "\n※")
+        content = re.sub(r"\n[ \t]+", "\n", content)
+        content = re.sub(r'\s*/\s*', '/', content)
+        news_items.append({
+            "date": date_str,
+            "type": type_map[type_class],
+            "timestamp": timestamp,
+            "headline": headline,
+            "content": content,
+            "images": [],
+        })
+
+    return news_items
diff --git a/bemani/sdvx.py b/bemani/sdvx.py
new file mode 100644
index 0000000..55d97ef
--- /dev/null
+++ b/bemani/sdvx.py
@@ -0,0 +1,46 @@
+from bs4 import BeautifulSoup
+from datetime import datetime
+from urllib.parse import urljoin
+
+def parse_exceed_gear_news_site(html: str, base_url: str):
+    soup = BeautifulSoup(html, 'html.parser')
+    news_list = soup.select('.tab ul.news li')
+
+    entries = []
+    for li in news_list:
+        date = li.select_one('strong')
+        pre = li.select_one('pre')
+
+        if not date or not pre:
+            continue
+        date_str = date.text.strip()
+        try:
+            dt = datetime.strptime(date_str, "%Y.%m.%d")
+            timestamp = int(dt.timestamp())
+        except ValueError:
+            timestamp = None
+        headline = li.select_one('p.notice')
+        headline_text = headline.text.strip() if headline else None
+        for tag in pre.select('font, b, u, span'):
+            tag.unwrap()
+        content = pre.get_text(separator='\n', strip=True)
+        images = []
+        for img in pre.select('img'):
+            src = img.get('data-original') or img.get('src')
+            if not src or src.startswith('data:'):
+                continue
+            src = urljoin(base_url, src)
+            parent = img.find_parent('a')
+            href = urljoin(base_url, parent['href']) if parent and parent.has_attr('href') else None
+            images.append({'image': src, 'link': href})
+
+        entries.append({
+            'date': date_str,
+            'type': None,
+            'timestamp': timestamp,
+            'headline': headline_text,
+            'content': content,
+            'images': images
+        })
+
+    return entries