本文整理汇总了Java中us.codecraft.webmagic.model.annotation.TargetUrl类的典型用法代码示例。如果您正苦于以下问题:Java TargetUrl类的具体用法?Java TargetUrl怎么用?Java TargetUrl使用的例子?那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。
TargetUrl类属于us.codecraft.webmagic.model.annotation包,在下文中一共展示了TargetUrl类的1个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Java代码示例。
示例1: validate
import us.codecraft.webmagic.model.annotation.TargetUrl; //导入依赖的package包/类
@SuppressWarnings({ "rawtypes", "unchecked" })
@Override
protected boolean validate(String url) {
Map<Class, PageModelPipeline> map = this.modelPipeline.getPageModelPipelines();
Set<Class> classSet = map.keySet();
Iterator<Class> iter = classSet.iterator();
if (iter.hasNext()) {
Class clazz = iter.next();
Annotation annotation = clazz.getAnnotation(TargetUrl.class);
List<Pattern> targetUrlPatterns = new ArrayList<Pattern>();
if (annotation == null) {
targetUrlPatterns.add(Pattern.compile(".*"));
} else {
TargetUrl targetUrl = (TargetUrl) annotation;
String[] value = targetUrl.value();
for (String s : value) {
targetUrlPatterns.add(Pattern.compile("(" + s.replace(".", "\\.").replace("*", "[^\"'#]*") + ")"));
}
}
boolean match = false;
for(Pattern p : targetUrlPatterns) {
Matcher m = p.matcher(url);
if (m.find()) {
match = true;
break;
}
}
if (!match && !targetUrlPatterns.isEmpty()) {
logger.warn(String.format("the url(%s) don't match the targeUrl regex(%s)", url, targetUrlPatterns.get(0)));
}
return match;
}
return super.validate(url);
}