201206030/novel-plus
1
0
Fork 0
mirror of https://github.com/201206030/novel-plus.git synced 2025-05-16 23:08:30 +00:00
Code Issues Packages Releases Wiki Activity

fix(novel-crawl): 修复部分源无法停止的问题

Browse Source
This commit is contained in:
xiongxiaoyang 2025-05-12 17:48:24 +08:00
parent 4f474b91a8
commit 55d5deea74
1 changed files with 39 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

79
novel-crawl/src/main/java/com/java2nb/novel/service/impl/CrawlServiceImpl.java
View File

@ -256,53 +256,52 @@ public class CrawlServiceImpl implements CrawlService {
try {
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);
if (StringUtils.isBlank(catIdRule) || Thread.currentThread().isInterrupted()) {
return;
}
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, ruleBean.getCharset());
if (bookListHtml != null) {
Pattern bookIdPatten = Pattern.compile(ruleBean.getBookIdPatten());
Matcher bookIdMatcher = bookIdPatten.matcher(bookListHtml);
boolean isFindBookId = bookIdMatcher.find();
while (isFindBookId) {
try {
//1.阻塞过程（使用了 sleep,同步锁的 wait,socket 中的 receiver,accept 等方法时）
//捕获中断异常InterruptedException来退出线程。
//2.非阻塞过程中通过判断中断标志来退出线程。
if (Thread.currentThread().isInterrupted()) {
return;
}
String bookId = bookIdMatcher.group(1);
parseBookAndSave(catId, ruleBean, sourceId, bookId);
} catch (Exception e) {
log.error(e.getMessage(), e);
String bookListHtml = crawlHttpClient.get(catBookListUrl, ruleBean.getCharset());
if (bookListHtml != null) {
Pattern bookIdPatten = Pattern.compile(ruleBean.getBookIdPatten());
Matcher bookIdMatcher = bookIdPatten.matcher(bookListHtml);
boolean isFindBookId = bookIdMatcher.find();
while (isFindBookId) {
try {
//1.阻塞过程（使用了 sleep,同步锁的 wait,socket 中的 receiver,accept 等方法时）
//捕获中断异常InterruptedException来退出线程。
//2.非阻塞过程中通过判断中断标志来退出线程。
if (Thread.currentThread().isInterrupted()) {
return;
}
isFindBookId = bookIdMatcher.find();
String bookId = bookIdMatcher.group(1);
parseBookAndSave(catId, ruleBean, sourceId, bookId);
} catch (Exception e) {
log.error(e.getMessage(), e);
}
Pattern totalPagePatten = Pattern.compile(ruleBean.getTotalPagePatten());
Matcher totalPageMatcher = totalPagePatten.matcher(bookListHtml);
boolean isFindTotalPage = totalPageMatcher.find();
if (isFindTotalPage) {
isFindBookId = bookIdMatcher.find();
}
totalPage = Integer.parseInt(totalPageMatcher.group(1));
}
Pattern totalPagePatten = Pattern.compile(ruleBean.getTotalPagePatten());
Matcher totalPageMatcher = totalPagePatten.matcher(bookListHtml);
boolean isFindTotalPage = totalPageMatcher.find();
if (isFindTotalPage) {
totalPage = Integer.parseInt(totalPageMatcher.group(1));
}
}