hotfix: okky xss path selector

in-seo · Jan 12, 2025 · 8b3bc52 · 8b3bc52
1 parent 76ca224
commit 8b3bc52
Showing 1 changed file with 5 additions and 4 deletions.
diff --git a/SouP/src/main/java/Matching/SouP/crawler/okky/OkkyService.java b/SouP/src/main/java/Matching/SouP/crawler/okky/OkkyService.java
@@ -8,6 +8,7 @@
 import lombok.extern.slf4j.Slf4j;
 import org.jsoup.Jsoup;
 import org.jsoup.nodes.Document;
+import org.jsoup.nodes.Element;
 import org.jsoup.select.Elements;
 import org.openqa.selenium.WebDriver;
 import org.springframework.stereotype.Service;
@@ -35,11 +36,11 @@ public void getOkkyPostData() {
                 driver.get(urlOkky + "?page=" + Page);
                 String html = driver.getPageSource();
                 Document doc = Jsoup.parse(html);
-                for (int i = 23; i > 4; i--) {  //오래된 글부터 크롤링  그럼 반드시 최신글은 DB에서 가장 밑에꺼임.
-                    if(i==10) // 공지, 광고 제거
-                        continue;
-                    Elements element = doc.select("#__next > main > div > div:nth-child(2) > div > div:nth-child(5) > div > ul > li:nth-child(" + i + ")");
+                Elements elements = doc.select("#__next > main > div > div:nth-child(2) > div > div:nth-child(5) > div > ul > li[class*='py']");
+                for (int i = elements.size() - 1; i >= 0; i--) {
+                    Element element = elements.get(i);
                     Elements title = element.select("div > div.my-2 > a");
+                    // 여기서 각 element에 대한 처리를 진행
                     String postName = title.text();
                     String num;
                     try {