implement idac news scrape

4 files changed, 117 insertions, 2 deletions

diff --git a/constants.py b/constants.py
index e1b0369..c252eab 100644
--- a/constants.py
+++ b/constants.py
@@ -23,6 +23,7 @@ CHUNITHM_INTL_NEWS_SITE="https://info-chunithm.sega.com/"
 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/"
+IDAC_NEWS_SITE="https://info-initialdac.sega.jp/"
 
 MUSIC_DIVER_NEWS="https://mypage.musicdiver.jp/api/news?lang=en"
 STREET_FIGHTER_NEWS_SITE="https://sf6ta.jp/info/list"
diff --git a/generate.py b/generate.py
index e94384e..900777d 100644
--- a/generate.py
+++ b/generate.py
@@ -122,6 +122,9 @@ def generate_maimaidx_intl_news_file():
 def generate_chunithm_intl_news_file():
     return generate_news_file("chunithm_intl_news", constants.CHUNITHM_INTL_NEWS_SITE, constants.CHUNITHM_VERSION.VERSE)
 
+def generate_idac_news_file():
+    return generate_news_file("idac_news", constants.IDAC_NEWS_SITE)
+
 def generate_music_diver_news_file():
     return generate_news_file("music_diver_news", constants.MUSIC_DIVER_NEWS)
 
@@ -161,6 +164,7 @@ if __name__ == "__main__":
     chunithm_jp_news_data = generate_chunithm_jp_news_file()
     maimaidx_jp_news_data = generate_maimaidx_jp_news_file()
     ongeki_jp_news_data = generate_ongeki_jp_news_file()
+    idac_news_data = generate_idac_news_file()
     maimaidx_intl_news_data = generate_maimaidx_intl_news_file()
     chunithm_intl_news_data = generate_chunithm_intl_news_file()
     music_diver_news_data = generate_music_diver_news_file()
@@ -184,6 +188,7 @@ if __name__ == "__main__":
         chunithm_jp_news_data,
         maimaidx_jp_news_data,
         ongeki_jp_news_data,
+        idac_news_data,
         maimaidx_intl_news_data,
         chunithm_intl_news_data,
         music_diver_news_data,
diff --git a/news_feed.py b/news_feed.py
index 7c781db..6bd5116 100644
--- a/news_feed.py
+++ b/news_feed.py
@@ -30,6 +30,7 @@ import sega.chuni_intl as chuni_intl
 import sega.maimaidx_jp as maimaidx_jp
 import sega.maimaidx_intl as maimaidx_intl
 import sega.ongeki_jp as ongeki_jp
+import sega.idac as idac
 import taito.music_diver as music_diver
 import taito.street_fighter as street_fighter
 import bandai_namco.taiko as taiko
@@ -159,6 +160,13 @@ def get_news(news_url: str, version=None) -> list:
             news_posts = sorted(ongeki_jp.parse_ongeki_refresh_news_site(site_data), key=lambda x: x['timestamp'], reverse=True)
             news_posts = translate.add_translate_text_to_en(news_posts)
 
+    elif news_url == constants.IDAC_NEWS_SITE:
+        site_data = download_site_as_html(news_url)
+        news_posts = sorted(idac.parse_idac_news_site(site_data), key=lambda x: x['timestamp'], reverse=True)
+        for news in news_posts:
+            promo_image_url = idac.get_promo_image(download_site_as_html(news["url"]))
+            news["images"] = [{'image': promo_image_url, 'link': None}]
+
     elif news_url == constants.MUSIC_DIVER_NEWS:
         api_data = download_site_as_html(news_url)
         news_posts = sorted(music_diver.parse_music_diver_news_json(api_data), key=lambda x: x['timestamp'], reverse=True)
@@ -166,8 +174,6 @@ def get_news(news_url: str, version=None) -> list:
     elif news_url == constants.STREET_FIGHTER_NEWS_SITE:
         site_data = download_site_as_html(news_url)
         news_posts = sorted(street_fighter.parse_sf_news_site(site_data), key=lambda x: x['timestamp'], reverse=True)
-        print(news_posts)
-        exit()
 
 
     elif news_url == constants.TAIKO_BLOG_SITE:
diff --git a/sega/idac.py b/sega/idac.py
new file mode 100644
index 0000000..3b8a444
--- /dev/null
+++ b/sega/idac.py
@@ -0,0 +1,103 @@
+import json
+from bs4 import BeautifulSoup
+import re
+from datetime import datetime
+from urllib.parse import urljoin
+from constants import IDAC_NEWS_SITE
+
+
+def parse_idac_news_site(site_data: str):
+    soup = BeautifulSoup(site_data, "html.parser")
+    news_entries = []
+    articles = soup.find_all('article', class_=lambda x: x and 'post-' in x)
+    for article in articles:
+        try:
+            post_id = None
+            for cls in article.get('class', []):
+                if cls.startswith('post-') and cls[5:].isdigit():
+                    post_id = cls[5:]
+                    break
+
+            if not post_id:
+                continue
+            title_section = article.find('h1', class_='entry-title')
+            if not title_section:
+                continue
+            news_title_link = title_section.find('a', class_='news-title')
+            if not news_title_link:
+                continue
+
+            url = news_title_link.get('href', '')
+            headline = news_title_link.get_text(strip=True)
+            date_span = title_section.find('span', class_='entry_date')
+            if not date_span:
+                continue
+
+            date_text = date_span.get_text(strip=True)
+
+            date_match = re.match(r'(\d{4})年(\d{1,2})月(\d{1,2})日', date_text)
+            if not date_match:
+                continue
+
+            year = int(date_match.group(1))
+            month = int(date_match.group(2))
+            day = int(date_match.group(3))
+
+            # Create datetime object (assuming JST timezone, noon time)
+            try:
+                post_date = datetime(year, month, day, 12, 0)
+                timestamp = int(post_date.timestamp())
+            except ValueError:
+                continue
+            post_type = None
+            categories_list = title_section.find('ul', class_='post-categories')
+            if categories_list:
+                category_link = categories_list.find('a')
+                if category_link:
+                    post_type = category_link.get_text(strip=True)
+            content = ""
+            entry_summary = article.find('div', class_='entry-summary')
+            if entry_summary:
+                content = entry_summary.get_text(strip=True)
+                content = re.sub(r'続きを読む\s*.*$', '', content).strip()
+                content = re.sub(r'\s*…\s*$', '', content).strip()
+            images = []
+            img_tags = article.find_all('img')
+            for img in img_tags:
+                img_src = img.get('src', '')
+                if img_src and not img_src.endswith('.svg'):  # Skip icon/UI images
+                    if img_src.startswith('/'):
+                        img_src = urljoin('https://info-initialdac.sega.jp', img_src)
+                    images.append({
+                        'image': img_src,
+                        'link': url
+                    })
+            news_entry = {
+                'date': post_date.strftime("%Y-%m-%d %H:%M"),
+                'identifier': "IDAC_NEWS",
+                'type': post_type,
+                'timestamp': timestamp,
+                'headline': headline,
+                'content': content if content else headline,
+                'url': url,
+                'images': images,
+                'is_ai_summary': False
+            }
+
+            news_entries.append(news_entry)
+
+        except Exception as e:
+            # Skip malformed entries
+            continue
+
+    return news_entries
+
+
+def get_promo_image(site_data: str) -> str:
+    soup = BeautifulSoup(site_data, "html.parser")
+    entry_content = soup.find('div', class_='entry-content')
+    if entry_content:
+        img_tag = entry_content.find('img')
+        if img_tag:
+            return img_tag.get('src', '')
+    return ''