【发布时间】:2025-11-29 16:40:02
【问题描述】:
我正在编写一个爬虫,并且在该爬虫中我不想爬取某些页面(排除某些链接以使其不被爬取)。所以我为那个页面写了排除项。这段代码有什么问题..尽管编写了排除项,但仍会调用此 http://www.host.com/technology/ 网址。我不希望任何以此网址 http://www.host.com/technology/ 开头的网址被抓取..
public class MyCrawler extends WebCrawler {
Pattern filters = Pattern.compile(".*(\\.(css|js|bmp|gif|jpe?g"
+ "|png|tiff?|mid|mp2|mp3|mp4" + "|wav|avi|mov|mpeg|ram|m4v|pdf"
+ "|rm|smil|wmv|swf|wma|zip|rar|gz))$");
List<String> exclusions;
public MyCrawler() {
exclusions = new ArrayList<String>();
//Add here all your exclusions
//I do not want this url to get crawled..
exclusions.add("http://www.host.com/technology/");
}
public boolean shouldVisit(WebURL url) {
String href = url.getURL().toLowerCase();
System.out.println(href);
if (filters.matcher(href).matches()) {
System.out.println("noooo");
return false;
}
if (exclusions.contains(href)) {//why this loop is not working??
System.out.println("Yes2");
return false;
}
if (href.startsWith("http://www.host.com/")) {
System.out.println("Yes1");
return true;
}
System.out.println("No");
return false;
}
public void visit(Page page) {
int docid = page.getWebURL().getDocid();
String url = page.getWebURL().getURL();
String text = page.getText();
List<WebURL> links = page.getURLs();
int parentDocid = page.getWebURL().getParentDocid();
System.out.println("=============");
System.out.println("Docid: " + docid);
System.out.println("URL: " + url);
System.out.println("Text length: " + text.length());
System.out.println("Number of links: " + links.size());
System.out.println("Docid of parent page: " + parentDocid);
System.out.println("=============");
}
}
【问题讨论】:
标签: java web-crawler