feat: 원본 RSS 소스 이미지를 대표 이미지로 우선 사용

- RSS 수집 시 media:thumbnail, media:content, enclosure, <img> 태그에서 이미지 추출
- source_image를 topic → article → publisher로 전달
- 발행 시 우선순위: 원본 소스 이미지 → Pexels → Unsplash

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

bots/collector_bot.py

@@ -373,6 +373,35 @@ def collect_product_hunt(sources_cfg: dict) -> list[dict]:
     return items
 
 
+def _extract_rss_image(entry) -> str:
+    """RSS entry에서 대표 이미지 URL 추출"""
+    # 1) media:thumbnail
+    if hasattr(entry, 'media_thumbnail') and entry.media_thumbnail:
+        return entry.media_thumbnail[0].get('url', '')
+    # 2) media:content (type이 image인 것)
+    if hasattr(entry, 'media_content') and entry.media_content:
+        for mc in entry.media_content:
+            if 'image' in mc.get('type', '') or mc.get('medium') == 'image':
+                return mc.get('url', '')
+        # type 없어도 url이 이미지 확장자면
+        url = entry.media_content[0].get('url', '')
+        if any(ext in url.lower() for ext in ['.jpg', '.jpeg', '.png', '.webp']):
+            return url
+    # 3) enclosures
+    if hasattr(entry, 'enclosures') and entry.enclosures:
+        for enc in entry.enclosures:
+            if 'image' in enc.get('type', ''):
+                return enc.get('href', '') or enc.get('url', '')
+    # 4) summary/description 안의 <img> 태그
+    desc = entry.get('summary', '') or entry.get('description', '')
+    if '<img' in desc:
+        import re
+        match = re.search(r'<img[^>]+src=["\']([^"\']+)["\']', desc)
+        if match:
+            return match.group(1)
+    return ''
+
+
 def collect_rss_feeds(sources_cfg: dict) -> list[dict]:
     """설정된 RSS 피드 수집"""
     items = []
@@ -392,6 +421,8 @@ def collect_rss_feeds(sources_cfg: dict) -> list[dict]:
                 combined = title_text + desc_text
                 kr_chars = sum(1 for c in combined if '\uac00' <= c <= '\ud7a3')
                 is_english = kr_chars / max(len(combined), 1) < 0.05
+                # 원본 기사 대표 이미지 추출
+                image_url = _extract_rss_image(entry)
                 items.append({
                     'topic': title_text,
                     'description': desc_text,
@@ -404,6 +435,7 @@ def collect_rss_feeds(sources_cfg: dict) -> list[dict]:
                     '_trust_override': trust,
                     '_rss_category': feed_cfg.get('category', ''),
                     'is_english': is_english,
+                    'source_image': image_url,
                 })
         except Exception as e:
             logger.warning(f"RSS 수집 실패 ({url}): {e}")