1. 程式人生 > >java爬蟲的幾個例項

java爬蟲的幾個例項

單個網頁爬取

package redis.list;

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

/**
 * 訪問單個新聞頁:
 * http://www.huxiu.com/article/102062/1.html 需要:標題,內容
 */
public class SingleArticle {

    public static void main(String[] args) throws Exception {
        // 第一步:訪問頁面
        String url = "http://www.huxiu.com/article/102062/1.html";
        Document document = Jsoup.connect(url).get();

        // 第二步:解析頁面
        Elements titleElements = document.getElementsByTag("title");
        String title = titleElements.get(0).text();

        Elements elements = document.select("div #article_content");
        String content = elements.text();

        // 第三步:列印
        System.out.println("title:" + title);
        System.out.println("content:" + content);
    }

}

爬網站上的文章

package redis.list;

import org.jsoup.Jsoup;
import org.jsoup.helper.StringUtil;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import redis.clients.jedis.Jedis;

import java.util.Date;
import java.util.List;

public class Crawler {
    //定義需要爬取的url list
    private static final String redisUrlsWillKey = "crawler:urls:will";
    //如果需要去重的話,可以使用set儲存已經爬起過的url

    public static void main(String[] args) throws Exception {
        //準備Url
        String startUrl = "https://www.huxiu.com";
        String domain = "http://www.huxiu.com/";
        //獲取文章Url
        getUrls(startUrl, domain);
        //處理url,下載文章的內容並列印
        parserUrl();
    }

    private static void parserUrl() throws Exception {
        Jedis jedis = new Jedis("127.0.0.1", 6379);
        //從右邊彈出一個url
        while (true) {
            String url = jedis.rpop(redisUrlsWillKey);
            try {
                Article article = parser(url);
                System.out.println("++++++++"+article);
            } catch (Exception e) {
//                jedis.lpush(redisUrlsWillKey, url);
            }
        }
    }

    private static Article parser(String url) throws Exception {
        Document articleDocument = Jsoup.connect(url).get();
        Article article = new Article();
        // 封裝作者的資訊
        Elements author = articleDocument
                .getElementsByClass("author-name");
        article.setAuthor(StringUtil.isBlank(author.text()) ? "jingzhongyue"
                : author.text());
        // 抽取文章日期
        Elements date = articleDocument
                .getElementsByClass("article-time");
        article.setDate(StringUtil.isBlank(date.text()) ? new Date()
                : DateUtil.getDate(date.text()));
        // 抽取文章標題
        Elements title = articleDocument.getElementsByTag("title");
        article.setTitle(title.text());
        // 抽取文章編號
        // http://www.huxiu.com/article/124698/1.html
        String id = url.substring(29);
        int index = id.indexOf("/");
        id = id.substring(0, index);
        article.setId(id);
        // 抽取文章正文
        StringBuffer stringBuffer = new StringBuffer();
        Elements contents = articleDocument
                .getElementsByAttribute("id");
        for (Element element : contents) {
            String idTag = element.attr("id");
            if ("article_content".equals(idTag)) {
                Elements childs = element.children();
                Elements pElements = childs.tagName("p");
                for (Element element2 : pElements) {
                    stringBuffer.append(element2.text());
                }
            }
        }
        return article;
    }

    private static void getUrls(String startUrl, String domain) throws Exception {
        Jedis jedis = new Jedis("127.0.0.1", 6379);
        Document document = Jsoup.connect(startUrl).get();
        Elements elements = document.getElementsByAttribute("href");
        for (Element element : elements) {
            String endUrl = element.attr("href");
            if (endUrl.contains("article")) {
                String url = domain + endUrl;
                System.out.println(url);
                jedis.lpush(redisUrlsWillKey, url);
            }
        }
    }

}