上次学了jsoup之后,发现一些动态生成的网页内容是无法抓取的,于是又学习了htmlunit,下面是抓取酷狗音乐与qq音乐链接的例子:
酷狗音乐:
import java.io.BufferedInputStream;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.net.URL;
import java.net.URLEncoder;
import java.util.UUID;
import java.util.regex.Matcher;
import java.util.regex.Pattern; import org.jsoup.nodes.Element; import com.alibaba.fastjson.JSONArray;
import com.alibaba.fastjson.JSONObject;
import com.gargoylesoftware.htmlunit.BrowserVersion;
import com.gargoylesoftware.htmlunit.NicelyResynchronizingAjaxController;
import com.gargoylesoftware.htmlunit.Page;
import com.gargoylesoftware.htmlunit.WebClient; public class worm7 {
private static String name="离骚";
public static WebClient getWebClient(boolean flag){
WebClient webClient = new WebClient(BrowserVersion.FIREFOX_45);
webClient.getOptions().setUseInsecureSSL(true);
webClient.getOptions().setCssEnabled(false);
webClient.getOptions().setThrowExceptionOnFailingStatusCode(false);
webClient.getOptions().setThrowExceptionOnScriptError(false);
webClient.getOptions().setRedirectEnabled(true);
webClient.getOptions().setAppletEnabled(false);
webClient.getOptions().setJavaScriptEnabled(flag);
webClient.getOptions().setTimeout(60000);
webClient.getOptions().setPrintContentOnFailingStatusCode(false);
webClient.setAjaxController(new NicelyResynchronizingAjaxController());
return webClient;
}
public static String getMp3Url(WebClient webClient){
FileOutputStream outputStream = null;
InputStream inputStream = null;
BufferedInputStream bis = null;
try {
Page page=webClient.getPage("http://songsearch.kugou.com/song_search_v2?"
+ "callback=jQuery112408395432201569397_1532930925600"
+ "&keyword="+URLEncoder.encode(name, "utf-8")
+ "&page=1"
+ "&pagesize=30"
+ "&userid=-1"
+ "&clientver="
+ "&platform=WebFilter"
+ "&tag=em"
+ "&filter=2"
+ "&iscorrection=1"
+ "&privilege_filter=0"
+ "&_="+System.currentTimeMillis());
//System.out.println(page.getWebResponse().getContentAsString());
//System.out.println(zzee(page.getWebResponse().getContentAsString(),"(?<=\\(\\{).*?(?=\\}\\))"));
JSONObject job=JSONObject.parseObject("{"+zzee(page.getWebResponse().getContentAsString(),"(?<=\\(\\{).*?(?=\\}\\))")+"}").getJSONObject("data");
System.out.println("job:"+job);
JSONArray list=job.getJSONArray("lists");
System.out.println("list"+list);
for(int i=0;i<list.size();i++){
String id1=list.getJSONObject(i).getString("FileHash");
String id2=list.getJSONObject(i).getString("AlbumID");
String detailUrl="http://www.kugou.com/yy/index.php?r=play/getdata"
+ "&hash="+id1
+ "&album_id="+id2
+ "&_="+System.currentTimeMillis();
Page page2=webClient.getPage(detailUrl);
JSONObject job2=JSONObject.parseObject(page2.getWebResponse().getContentAsString()).getJSONObject("data");
System.out.println("标题:"+job2.getString("audio_name"));
//System.out.println("歌词:"+job2.getString("lyrics"));
System.out.println("mp3:"+job2.getString("play_url")); String outImage = job2.getString("audio_name")+ ".mp3";
URL imgUrl = new URL(job2.getString("play_url"));//获取输入流
inputStream = imgUrl.openConnection().getInputStream();
//将输入流信息放入缓冲流提升读写速度
bis = new BufferedInputStream(inputStream);
//读取字节娄
byte[] buf = new byte[1024];
//生成文件
outputStream = new FileOutputStream("f://"+ outImage);
int size = 0;
//边读边写
while ((size = bis.read(buf)) != -1) {
outputStream.write(buf, 0, size);
}
//刷新文件流
outputStream.flush(); }
} catch (Exception e) {
e.printStackTrace();
}
return name; }
private static String zzee(String str, String zz) {
String list = null;
Pattern p = Pattern.compile(zz);
Matcher m = p.matcher(str);
while (m.find()) {
list = m.group();
} return list;
}
public static void main(String[] args) {
WebClient webClient=getWebClient(false);
getMp3Url(webClient);
}
}
运行结果:
qq音乐抓取实例:
import java.io.BufferedInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.net.MalformedURLException;
import java.net.URL;
import java.net.URLEncoder;
import java.util.UUID;
import java.util.regex.Matcher;
import java.util.regex.Pattern; import org.jsoup.nodes.Element; import com.alibaba.fastjson.JSON;
import com.alibaba.fastjson.JSONArray;
import com.alibaba.fastjson.JSONObject;
import com.gargoylesoftware.htmlunit.BrowserVersion;
import com.gargoylesoftware.htmlunit.NicelyResynchronizingAjaxController;
import com.gargoylesoftware.htmlunit.Page;
import com.gargoylesoftware.htmlunit.WebClient; public class worm6 {
private static String name="离骚";
static String id1=null;
static String id2=null;
static String id3=null;
static String id4=null;
static String name1=null;
static String name2=null;
static String url = null;
static JSONObject job2=null;
public static WebClient getWebClient(boolean flag){
WebClient webClient = new WebClient(BrowserVersion.FIREFOX_45);
webClient.getOptions().setUseInsecureSSL(true);
webClient.getOptions().setCssEnabled(false);
webClient.getOptions().setThrowExceptionOnFailingStatusCode(false);
webClient.getOptions().setThrowExceptionOnScriptError(false);
webClient.getOptions().setRedirectEnabled(true);
webClient.getOptions().setAppletEnabled(false);
webClient.getOptions().setJavaScriptEnabled(flag);
webClient.getOptions().setTimeout(60000);
webClient.getOptions().setPrintContentOnFailingStatusCode(false);
webClient.setAjaxController(new NicelyResynchronizingAjaxController());
return webClient;
}
public static String getMp3Url(WebClient webClient){ try {
Page page=webClient.getPage("https://c.y.qq.com/soso/fcgi-bin/client_search_cp?"
+ "ct=24"
+ "&qqmusic_ver=1298"
+ "&new_json=1"
+ "&remoteplace=txt.yqq.center"
+ "&searchid=36047978388657978"
+ "&t=0"
+ "&aggr=1"
+ "&cr=1"
+ "&catZhida=1"
+ "&lossless=0"
+ "&p=1"
+ "&n=20"
+ "&w="+URLEncoder.encode(name, "utf-8")
+ "&g_tk=5381"
+ "&jsonpCallback=MusicJsonCallback6176591962889693"
+ "&loginUin=0"
+ "&hostUin=0"
+ "&format=jsonp"
+ "&inCharset=utf8"
+ "&outCharset=utf-8"
+ "¬ice=0"
+ "&platform=yqq"
+ "&needNewCode=0"
);
//System.out.println("page:"+page);
//System.out.println("------"+page.getWebResponse().getContentAsString());
//System.out.println("======"+zzee(page.getWebResponse().getContentAsString(),"(?<=\\(\\{).*?(?=\\}\\))")); JSONObject job=JSONObject.parseObject("{"+zzee(page.getWebResponse().getContentAsString(),"(?<=\\(\\{).*?(?=\\}\\))")+"}").getJSONObject("data");
//System.out.println("job:"+job);
String job0=job.getString("song");
//System.out.println("job0"+job0);
job=JSON.parseObject(job0);
JSONArray list=job.getJSONArray("list");
//System.out.println("list:"+list);
for(int i=0;i<list.size();i++){
id1=list.getJSONObject(i).getString("mid");
//System.out.println("id1"+id1);
id2=list.getJSONObject(i).getString("file");
//System.out.println("id"+id2);
id2="C400"+JSONObject.parseObject(id2).getString("media_mid")+".m4a";
//System.out.println("id"+id2);
name1=list.getJSONObject(i).getString("title");
name2=list.getJSONObject(i).getString("singer");
//System.out.println(name2);
JSONArray name=JSON.parseArray(name2);
//System.out.println("job4:"+name);
name2=name.getJSONObject(0).getString("name");
//System.out.println(name.getJSONObject(0).getString("name")); /*String detailUrl="https://c.y.qq.com/v8/fcg-bin/fcg_play_single_song.fcg?"
+ "songmid="+id1
+ "&tpl=yqq_song_detail&format=jsonp&callback=getOneSongInfoCallback&g_tk=5381&jsonpCallback=getOneSongInfoCallback&loginUin=0&hostUin=0&format=jsonp&inCharset=utf8&outCharset=utf-8¬ice=0&platform=yqq&needNewCode=0"
;
Page page2=webClient.getPage(detailUrl);
//System.out.println(page2);
String b="{"+zzee(page2.getWebResponse().getContentAsString(),"(?<=\\(\\{).*?(?=\\}\\))")+"}";
//System.out.println("b"+b);
JSONObject job1=JSONObject.parseObject("{"+zzee(page2.getWebResponse().getContentAsString(),"(?<=\\(\\{).*?(?=\\}\\))")+"}").getJSONObject("url");
System.out.println("job1:"+job1);
String job2=job1.getString(id2); System.out.println("job2"+job2);*/
String url1="https://c.y.qq.com/base/fcgi-bin/fcg_music_express_mobile3.fcg?g_tk=5381&jsonpCallback=MusicJsonCallback32651599216689386&loginUin=0&hostUin=0&format=json&inCharset=utf8&outCharset=utf-8¬ice=0&platform=yqq&needNewCode=0&cid=205361747&callback=MusicJsonCallback32651599216689386&uin=0"
+"&songmid="+id1
+"&filename="+id2
+"&guid=2241489759";
;
Page page2=webClient.getPage(url1);
//System.out.println("page2"+page2);
JSONObject job2=JSONObject.parseObject("{"+zzee(page2.getWebResponse().getContentAsString(),"(?<=\\(\\{).*?(?=\\}\\))")+"}").getJSONObject("data");
//System.out.println("标题:"+job2.getString("items"));
String job3=job2.getString("items");
JSONArray job4=JSON.parseArray(job3);
//System.out.println("job4:"+job4);
//System.out.println(job4.getJSONObject(0).getString("vkey"));
url ="http://dl.stream.qqmusic.qq.com/"+id2+"?vkey="+job4.getJSONObject(0).getString("vkey")+"&guid=2241489759&uin=0&fromtag=66";
System.out.println("name:"+name1+"--"+name2);
System.out.println("url:"+url); download();
} } catch (Exception e) {
e.printStackTrace();
}
return name; }
private static String zzee(String str, String zz) {
String list = null;
Pattern p = Pattern.compile(zz);
Matcher m = p.matcher(str);
while (m.find()) {
list = m.group();
} return list;
}
private static void download() throws IOException{
FileOutputStream outputStream = null;
InputStream inputStream = null;
BufferedInputStream bis = null;
String outImage = name1+"--"+name2+ ".mp3";
URL imgUrl = new URL(url);//获取输入流
inputStream = imgUrl.openConnection().getInputStream();
//将输入流信息放入缓冲流提升读写速度
bis = new BufferedInputStream(inputStream);
//读取字节娄
byte[] buf = new byte[1024];
//生成文件
outputStream = new FileOutputStream("f://"+ outImage);
int size = 0;
//边读边写
while ((size = bis.read(buf)) != -1) {
outputStream.write(buf, 0, size);
}
//刷新文件流
outputStream.flush();
}
public static void main(String[] args) {
WebClient webClient=getWebClient(false);
getMp3Url(webClient);
}
}
运行结果:
相比之下,酷狗音乐相对好爬一些,QQ音乐有些繁琐。。。