feat: 支持非utf-8编码的网站采集

2025-07-05 16:56:39 +00:00 · 2025-03-14 20:39:57 +08:00
parent 85b64bbc10
commit 73502a279b
8 changed files with 57 additions and 13 deletions
--- a/novel-crawl/src/main/java/com/java2nb/novel/utils/Constants.java
+++ b/novel-crawl/src/main/java/com/java2nb/novel/utils/Constants.java
@ -24,4 +24,9 @@ public class Constants {
     * 爬取小说http请求失败重试次数
     */
    public static final Integer HTTP_FAIL_RETRY_COUNT = 3;
+
+    /**
+     * 爬虫默认编码
+     */
+    public static final String CRAWL_DEFAULT_CHARSET = "UTF-8";
 }