From d6c2824bc67cfb708763fba9412c6610d9cd05bb Mon Sep 17 00:00:00 2001
From: Pinapelz <yukais@pinapelz.com>
Date: Thu, 17 Apr 2025 12:08:12 -0700
Subject: add generic parser for eamusement games

information is different and some is better suited for our format than others
---
 konami/eamuse_app.py | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)
 create mode 100644 konami/eamuse_app.py

(limited to 'konami')

diff --git a/konami/eamuse_app.py b/konami/eamuse_app.py
new file mode 100644
index 0000000..b552477
--- /dev/null
+++ b/konami/eamuse_app.py
@@ -0,0 +1,51 @@
+from bs4 import BeautifulSoup
+from datetime import datetime
+from urllib.parse import urljoin
+import time
+
+BASE_URL = "https://eam.573.jp"
+
+def parse_news_page(html: str, identifier: str):
+    soup = BeautifulSoup(html, "html.parser")
+    entries = []
+
+    for li in soup.select("ul > li.ef"):
+        a_tag = li.find("a", href=True)
+        url = urljoin(BASE_URL, a_tag["href"]) if a_tag else None
+
+        date_text = li.select_one(".post-date")
+        if not date_text:
+            continue
+        raw_date = date_text.get_text(strip=True).replace("年", "/").replace("月", "/").replace("日", "")
+        try:
+            date_obj = datetime.strptime(raw_date, "%Y/%m/%d")
+        except ValueError:
+            continue
+        date_str = date_obj.strftime("%Y-%m-%d")
+        timestamp = int(time.mktime(date_obj.timetuple()))
+
+        content_tag = li.select_one(".article-text")
+        content = content_tag.get_text(strip=True) if content_tag else None
+
+        img_tag = li.select_one(".article-img img")
+        image_url = img_tag["src"] if img_tag else None
+        images = []
+        if image_url:
+            images.append({
+                "image": image_url,
+                "link": url
+            })
+
+        entry = {
+            "date": date_str,
+            "identifier": identifier,
+            "type": None,
+            "timestamp": timestamp,
+            "headline": None,
+            "content": content,
+            "url": url,
+            "images": images
+        }
+        entries.append(entry)
+
+    return entries
-- 
cgit v1.2.3