201206030/novel-plus
1
0
Fork 0
mirror of https://github.com/201206030/novel-plus.git synced 2025-04-26 01:10:52 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

perf: 爬虫分类规则优化

Browse Source
This commit is contained in:
xiongxiaoyang 2025-03-14 19:03:30 +08:00
parent 74d7ea7000
commit 6d0ab33757
1 changed files with 15 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
novel-crawl/src/main/java/com/java2nb/novel/service/impl/CrawlServiceImpl.java
View File

@ -255,12 +255,21 @@ public class CrawlServiceImpl implements CrawlService {
while (page <= totalPage) {
try {
if (StringUtils.isNotBlank(ruleBean.getCatIdRule().get("catId" + catId))) {
//拼接分类URL
String catBookListUrl = ruleBean.getBookListUrl()
.replace("{catId}", ruleBean.getCatIdRule().get("catId" + catId))
.replace("{page}", page + "");
String catIdRule = ruleBean.getCatIdRule().get("catId" + catId);
if (StringUtils.isNotBlank(catIdRule)) {
String catBookListUrl = "";
if (StringUtils.isNotBlank(ruleBean.getBookListUrl())) {
// 兼容老规则
// 拼接分类URL
catBookListUrl = ruleBean.getBookListUrl()
.replace("{catId}", catIdRule)
.replace("{page}", page + "");
} else {
// 新规则
// 拼接分类URL
catBookListUrl = catIdRule.replace("{page}", page + "");
}
log.info("catBookListUrl：{}", catBookListUrl);
String bookListHtml = crawlHttpClient.get(catBookListUrl);
if (bookListHtml != null) {