网易云云音乐评论十分有趣,于是就想写个爬虫爬取评论。但是不熟悉Python,就用java写了个。
主要使用了HttpClient,,Jsoup, 队列, 线程, log4j,poi生成Excel保存结果, 书写过程中主要一个问题就是评论获取,网易对其进行了加密,进行好一番搜索才找到解决方法。爬取歌单数,top歌曲数都可以动态进行配置.
目录结构
主程序
package personal.mario.main;
import java.io.IOException;
import java.util.List;
import org.apache.http.client.ClientProtocolException;
import org.apache.log4j.Logger;
import org.apache.poi.hssf.usermodel.HSSFSheet;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import personal.mario.bean.MusicCommentMessage;
import personal.mario.service.HtmlFetcherService;
import personal.mario.service.HtmlParserService;
import personal.mario.service.MusicListQueueService;
import personal.mario.service.MusicQueueService;
import personal.mario.service.TopMusicCalculateService;
import personal.mario.utils.Constants;
import personal.mario.utils.GenerateExcelUtils;
/*
* 主逻辑
* author timeless.li
* 2016-10-26
* */
public class NetEaseCrawler implements Runnable {
private int totalMusicList = Constants.MUSIC_LIST_COUNT;
private int limit = Constants.PER_PAGE;
private int offset =Constants.OFFSET;
private HSSFWorkbook commentMessageWorkbook = new HSSFWorkbook();
private List<MusicCommentMessage> ms = null;
private static Logger logger = Logger.getLogger(NetEaseCrawler.class);
@Override
public void run() {
try {
//初始化待爬取的歌单URL队列
initUncrawledMusicListQueue();
//记录所有爬取出来的歌曲数,包含重复歌曲
int count = 0;
//歌曲信息Excel初始化
HSSFSheet commentMessageSheet = GenerateExcelUtils.generateCommentMessageExcelInit(commentMessageWorkbook);
//开始根据歌单爬取
while (!MusicListQueueService.isUncrawledMusicListEmpty()) {
//填充待爬取歌曲队列
fillUncrawledMusicQueue(MusicListQueueService.getTopMusicList());
//歌曲队列为空就返回上层循环填充歌曲队列
while (!MusicQueueService.isUncrawledMusicQueueEmpty()) {
//取出待爬取歌曲ID
String songId = MusicQueueService.getTopMusicUrl();
//判断是否已经爬取过
if (!MusicQueueService.isMusicCrawled(songId)) {
//获取到爬取结果&