init commit

1 files changed, 46 insertions, 0 deletions

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