工作中遇到了一個場景，需要使用Sogou微信的熱門文章做展示，調研了一段時間，沒有發現有比較好用的免費介面，所以自己寫了一個，非常簡單。

儲存Sogou熱門文章需要的類：

/**
 * @author TangLei
 */
public class Article{

    //頭像圖片
    private String headImg;
    //標題
    private String topic;
    //文章連結
    private String articleUrl;
    //文章圖片
    private String articleImg;
    //閱讀次數
    private
 
 String readCount;
    //時間戳
    private String time;

    public String getHeadImg() {
        return headImg;
    }

    public void setHeadImg(String headImg) {
        this.headImg = headImg;
    }

    public String getTopic() {
        return topic;
    }

    public void setTopic(String topic) {
        this
 
.topic = topic;
    }

    public String getArticleUrl() {
        return articleUrl;
    }

    public void setArticleUrl(String articleUrl) {
        this.articleUrl = articleUrl;
    }

    public String getArticleImg() {
        return articleImg;
    }

    public void setArticleImg(String articleImg) {
        this
 
.articleImg = articleImg;
    }

    public String getReadCount() {
        return readCount;
    }

    public void setReadCount(String readCount) {
        this.readCount = readCount;
    }

    public String getTime() {
        return time;
    }

    public void setTime(String time) {
        this.time = time;
    }
}

爬蟲實現：

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

import com.alibaba.fastjson.JSON;

/**
 * 網路爬蟲，獲取搜狗微信搜尋_訂閱號及文章內容
 * @author TangLei
 */
public class Crawler {

    public String doCrawler(String url) {
        return dealPage(getPage(url));
    }

    /**
     * 讀取整個網頁
     * 
     * @param url:網頁地址
     * @return 整個網頁的內容
     */
    private String getPage(String url) {
        StringBuffer buffer = new StringBuffer();
        BufferedReader reader = null;
        try {
            URL realUrl = new URL(url);
            URLConnection conn = realUrl.openConnection();
            conn.connect();
            reader = new BufferedReader(new InputStreamReader(conn.getInputStream(), "UTF-8"));
            String line = null;
            while ((line = reader.readLine()) != null) {
                buffer.append(line).append("\r\n");
            }
        } catch (IOException e) {
            e.printStackTrace();
            System.out.println("read web page error : " + e.getMessage());
        } finally {
            try {
                reader.close();
            } catch (IOException e) {
                e.printStackTrace();
                System.out.println("close reader error : " + e.getMessage());
            }
        }
        return buffer.toString();
    }

    /**
     * 對讀取到的網頁進行處理擷取有用資訊
     * 
     * @param page
     *            網頁內容
     * @return 擷取到的資訊
     */
    private String dealPage(String page) {

        //所有的正則表示式
        Pattern[] patterns = new Pattern[4];
        patterns[0] = Pattern.compile("<p><img src=\"[a-zA-z]+://[^\\s]*");
        patterns[1] = Pattern.compile("<h4><a uigs=.*</a></h4>");
        patterns[2] = Pattern.compile("<img src=.*\" onload=\"vrImgLoad\\(this,'fit',110,110\\)\"");
        patterns[3] = Pattern.compile("閱讀&nbsp;.*</bb>");

        //首先計算有多少篇文章
        int articleCount = 0;
        Matcher matcher = patterns[0].matcher(page);
        while (matcher.find()) {
            articleCount++;
        }

        //根據文章數量建立相應長度的陣列
        Article[] articles = new Article[articleCount];
        for (int i = 0; i < articleCount; i++) {
            articles[i] = new Article();
        }

        //開始處理
        int index = 0;
        for (int i = 0; i < patterns.length; i++) {

            index = 0;
            matcher = patterns[i].matcher(page);
            while (matcher.find()) {
                String find = matcher.group();
                if(i==0){
                    String[] splits = find.split("\"");
                    if(index<articleCount){
                        articles[index].setHeadImg(splits[1]);
                    }
                }else if (i == 1){
                    String[] splits = find.split("\"");
                    if(index<articleCount){
                        articles[index].setArticleUrl(splits[3]);
                        articles[index].setTopic(splits[6].substring(1,splits[6].length()-9));
                    }
                }else if (i == 2){
                    String[] splits = find.split("\"");
                    if(index<articleCount){
                        articles[index].setArticleImg(splits[1]);
                    }
                }else if (i == 3){
                    String[] splits = find.split("&nbsp;");
                    if(index<articleCount){
                        articles[index].setReadCount(splits[1]);
                        articles[index].setTime(splits[4].substring(13, 23));
                    }
                }
                index++;
            }
        }
        return JSON.toJSONString(articles);
    }

    public static void main(String[] args) throws Exception {
        String url = "http://weixin.sogou.com";
        Crawler crawler = new Crawler();
        System.out.println(crawler.doCrawler(url));
    }
}

非常簡單的一個爬蟲，可以參考一下，作為爬蟲入門看一下也非常好。