Fix HTML selectors based on actual page structure

Ruliweb changes:
- Use tr.table_body instead of .table_body tr
- Correct selectors: .subject .subject_link, .writer a, .hit, .recomd, .num_reply, .time
- Remove icons/reply count from title text
- Add debug logging for parsed posts

Arcalive changes:
- Use a.vrow instead of .vrow
- Correct selectors: .col-title .title, .col-author .user-info span[data-filter]
- Selectors: .col-view, .col-rate, .col-time time
- Add debug logging for parsed posts

Both crawlers now match actual HTML structure from pages

crawler/src/crawlers/arcalive.ts

@@ -15,24 +15,34 @@ export class ArcaliveCrawler extends BaseCrawler {
     const $ = cheerio.load(html);
     const posts: Post[] = [];
 
-    // 아카라이브 구조에 맞게 선택자 수정
+    // 실제 아카라이브 HTML 구조에 맞게 수정
-    $('.vrow').each((index, element) => {
+    $('a.vrow').each((index, element) => {
       if (index >= CRAWLER_CONFIG.maxPostsPerBoard) return false;
 
       try {
         const $el = $(element);
 
-        // 공지사항 제외
+        // URL (a 태그의 href)
-        if ($el.hasClass('notice')) return;
+        const url = $el.attr('href') || '';
 
-        const titleEl = $el.find('.title a');
+        // 제목
-        const title = this.cleanText(titleEl.text());
+        const title = this.cleanText($el.find('.col-title .title').text());
-        const url = titleEl.attr('href') || '';
+
-        const author = this.cleanText($el.find('.user-info').text());
+        // 작성자 (data-filter 속성이 있는 span 또는 첫 번째 span)
-        const views = this.parseNumber($el.find('.view-count').text());
+        const authorEl = $el.find('.col-author .user-info span[data-filter]');
-        const comments = this.parseNumber($el.find('.comment-count').text());
+        const author = this.cleanText(authorEl.length > 0 ? authorEl.text() : $el.find('.col-author .user-info span').first().text());
-        const likes = this.parseNumber($el.find('.vote-count').text());
+
-        const timeStr = this.cleanText($el.find('.time').text());
+        // 조회수, 추천수
+        const views = this.parseNumber($el.find('.col-view').text());
+        const likes = this.parseNumber($el.find('.col-rate').text());
+
+        // 댓글 수 (아카라이브는 제목에 포함되어 있을 수 있음, 또는 별도 요소)
+        const commentEl = $el.find('.col-title .comment-count');
+        const comments = commentEl.length > 0 ? this.parseNumber(commentEl.text()) : 0;
+
+        // 시간
+        const timeEl = $el.find('.col-time time');
+        const timeStr = timeEl.length > 0 ? this.cleanText(timeEl.text()) : '';
 
         if (!title) return;
 
@@ -51,6 +61,7 @@ export class ArcaliveCrawler extends BaseCrawler {
         };
 
         posts.push(post);
+        Logger.info(`Parsed Arcalive post: ${title} (views: ${views}, comments: ${comments}, likes: ${likes})`);
       } catch (error) {
         Logger.error(`Error parsing Arcalive post at index ${index}`, error);
       }

crawler/src/crawlers/ruliweb.ts

@@ -15,24 +15,30 @@ export class RuliwebCrawler extends BaseCrawler {
     const $ = cheerio.load(html);
     const posts: Post[] = [];
 
-    // 루리웹 게시판 구조에 맞게 선택자 수정 필요
+    // 실제 루리웹 HTML 구조에 맞게 수정
-    // 실제 페이지를 확인하여 정확한 선택자를 찾아야 함
+    $('tr.table_body').each((index, element) => {
-    $('.table_body tr').each((index, element) => {
       if (index >= CRAWLER_CONFIG.maxPostsPerBoard) return false;
 
       try {
         const $el = $(element);
 
-        // 공지사항 제외
+        // 제목과 URL
-        if ($el.find('.notice').length > 0) return;
+        const titleEl = $el.find('.subject .subject_link');
-
+        const title = this.cleanText(titleEl.clone().children().remove().end().text()); // 아이콘/댓글 수 제외
-        const titleEl = $el.find('.subject a');
-        const title = this.cleanText(titleEl.text());
         const url = titleEl.attr('href') || '';
-        const author = this.cleanText($el.find('.writer').text());
+
+        // 작성자
+        const author = this.cleanText($el.find('.writer a').text());
+
+        // 조회수, 추천수, 댓글수
         const views = this.parseNumber($el.find('.hit').text());
-        const comments = this.parseNumber($el.find('.reply_num').text());
         const likes = this.parseNumber($el.find('.recomd').text());
+
+        // 댓글 수 추출 (예: "(2)" -> 2)
+        const commentText = $el.find('.num_reply').text();
+        const comments = this.parseNumber(commentText);
+
+        // 시간
         const timeStr = this.cleanText($el.find('.time').text());
 
         if (!title) return;
@@ -52,6 +58,7 @@ export class RuliwebCrawler extends BaseCrawler {
         };
 
         posts.push(post);
+        Logger.info(`Parsed Ruliweb post: ${title} (views: ${views}, comments: ${comments}, likes: ${likes})`);
       } catch (error) {
         Logger.error(`Error parsing Ruliweb post at index ${index}`, error);
       }