You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
19 lines
425 B
19 lines
425 B
package com.example.datacollect.strategy;
|
|
|
|
import com.example.datacollect.model.Article;
|
|
import org.jsoup.nodes.Document;
|
|
import java.util.List;
|
|
import java.util.regex.Pattern;
|
|
|
|
public interface CrawlStrategy {
|
|
List<Article> parse(String url, Document doc);
|
|
boolean supports(String url);
|
|
|
|
default int getPriority() {
|
|
return 1;
|
|
}
|
|
|
|
default Pattern getPattern() {
|
|
return null;
|
|
}
|
|
}
|