1.优化爬虫编写规则，兼容更多网站 2.新增书趣阁书源

2025-07-02 23:46:38 +00:00 · 2020-05-18 14:01:49 +08:00
parent 8c2e43c04f
commit 92ce982899
10 changed files with 339 additions and 79 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
@ -14,4 +14,9 @@ public class Constants {
     * 访问量默认值
     */
    public static final Long VISIT_COUNT_DEFAULT = 100L;
+
+    /**
+     * 爬取小说http请求中无效的内容长度
+     */
+    public static final int INVALID_HTML_LENGTH = 1000;
 }