はてなブックマークからブックマーク数をスクレイピング

HatenaBookmark.java

package info.bouzuya.hateb;

import java.io.IOException;
import java.util.List;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.nodes.TextNode;
import org.jsoup.select.Elements;

public class HatenaBookmark {
    private final HatenaAuth auth;

    public HatenaBookmark() {
        this(null);
    }

    public HatenaBookmark(HatenaAuth auth) {
        this.auth = auth;
    }

    public int getCount() {
        if (auth == null) {
            throw new IllegalStateException("need login");
        }
        return getCount(this.auth.getUsername());
    }

    public int getCount(String username) {
        if (username == null || username.isEmpty()) {
            throw new IllegalArgumentException("username is null or empty.");
        }

        String url = "http://b.hatena.ne.jp/" + username + "/";
        String cssQuery = ".sidebar .hatena-module-profile ul li";
        Document document = getDocument(url);
        Elements elements = document.select(cssQuery);
        for (Element element : elements) {
            Element label = element.select("span.label").first();
            String labelText = (label == null ? "" : label.text());
            if (!labelText.equals("ブックマーク数")) {
                continue;
            }

            List<TextNode> textNodes = element.textNodes();
            StringBuilder sb = new StringBuilder();
            for (TextNode textNode : textNodes) {
                sb.append(textNode.text());
            }
            String countString = sb.toString().trim();

            return Integer.parseInt(countString);
        }

        throw new IllegalStateException("not found");
    }

    private Document getDocument(String url) {
        try {
            return Jsoup.connect(url).get();
        } catch (IOException e) {
            throw new RuntimeException(e);
        }
    }

    public static void main(String[] args) {
        HatenaBookmark hateb = new HatenaBookmark();
        System.out.println(hateb.getCount("bouzuya"));
    }
}

Jsoup の使用例を兼ねている。