网易云评论 爬虫 java_网易云音乐资源爬取（登录+评论）

如何爬取网易云音乐的评论呢？

1.文本以华晨宇的《我的滑板鞋2016》为例

2.使用浏览器的工具，查找获取评论的url

3.不难发现，此API是通过POST请求获得我们想要的评论信息的，需要POST的参数有params和encSecKey，网易为了反爬虫，加密了这2个参数，不过不要紧，下面有加密过程

4.POST请求成功后，会得到一个JSON字符串，里面就包含了各种评论信息

5.下面就用JAVA来实现评论的获取

AES加密工具类

import java.util.Base64;

import javax.crypto.Cipher;

import javax.crypto.spec.IvParameterSpec;

import javax.crypto.spec.SecretKeySpec;

public class EncryptTools {

//AES加密

public static String encrypt(String text, String secKey) throws Exception {

byte[] raw = secKey.getBytes();

SecretKeySpec skeySpec = new SecretKeySpec(raw, "AES");

// "算法/模式/补码方式"

Cipher cipher = Cipher.getInstance("AES/CBC/PKCS5Padding");

// 使用CBC模式，需要一个向量iv，可增加加密算法的强度

IvParameterSpec iv = new IvParameterSpec("0102030405060708".getBytes());

cipher.init(Cipher.ENCRYPT_MODE, skeySpec, iv);

byte[] encrypted = cipher.doFinal(text.getBytes());

return Base64.getEncoder().encodeToString(encrypted);

}

//字符填充

public static String zfill(String result, int n) {

if (result.length() >= n) {

result = result.substring(result.length() - n, result.length());

} else {

StringBuilder stringBuilder = new StringBuilder();

for (int i = n; i > result.length(); i--) {

stringBuilder.append("0");

}

stringBuilder.append(result);

result = stringBuilder.toString();

}

return result;

}

}

评论获取

public void commentAPI() throws Exception {

//私钥，随机16位字符串(自己可改)

String secKey = "cd859f54539b24b7";

String text = "{\"username\": \"\", \"rememberLogin\": \"true\", \"password\": \"\"}";

String modulus = "00e0b509f6259df8642dbc35662901477df22677ec152b5ff68ace615bb7b725152b3ab17a876aea8a5aa76d2e417629ec4ee341f56135fccf695280104e0312ecbda92557c93870114af6c9d05c4f7f0c3685b7a46bee255932575cce10b424d813cfe4875d3e82047b97ddef52741d546b8e289dc6935b3ece0462db0a22b8e7";

String nonce = "0CoJUm6Qyw8W8jud";

String pubKey = "010001";

//2次AES加密，得到params

String params = EncryptTools.encrypt(EncryptTools.encrypt(text, nonce), secKey);

StringBuffer stringBuffer = new StringBuffer(secKey);

//逆置私钥

secKey = stringBuffer.reverse().toString();

String hex = Hex.encodeHexString(secKey.getBytes());

BigInteger bigInteger1 = new BigInteger(hex, 16);

BigInteger bigInteger2 = new BigInteger(pubKey, 16);

BigInteger bigInteger3 = new BigInteger(modulus, 16);

//RSA加密计算

BigInteger bigInteger4 = bigInteger1.pow(bigInteger2.intValue()).remainder(bigInteger3);

String encSecKey= Hex.encodeHexString(bigInteger4.toByteArray());

//字符填充

encSecKey= EncryptTools.zfill(encSecKey, 256);

//评论获取

Document document = Jsoup.connect("http://music.163.com/weapi/v1/resource/comments/R_SO_4_437859519/").cookie("appver", "1.5.0.75771")

.header("Referer", "http://music.163.com/").data("params", params).data("encSecKey", encSecKey)

.ignoreContentType(true).post();

System.out.println("评论：" + document.text());

}

那么如何登录网易云音乐呢？

1.查找登录的API地址(在浏览器登录一次，在network中查看url)

Paste_Image.png

2.查看登录时post需要提交的参数

Paste_Image.png

3.是不是很熟悉？和刚才获取评论的时候一样，该如何做呢？看看下面的示例代码

在上面AES加密工具类中添加MD5加密方法

public static String md5(String pwd) {

try {

MessageDigest digest = MessageDigest.getInstance("md5");

byte[] bs = digest.digest(pwd.getBytes());

String hexString = "";

for (byte b : bs) {

int temp = b & 255;

if (temp < 16 && temp >= 0) {

hexString = hexString + "0" + Integer.toHexString(temp);

} else {

hexString = hexString + Integer.toHexString(temp);

}

}

return hexString;

} catch (NoSuchAlgorithmException e) {

e.printStackTrace();

}

return "";

}

登录请求

public void loginAPI(String username, String password) throws Exception {

password = EncryptTools.md5(password);

// 私钥，随机16位字符串(自己可改)

String secKey = "cd859f54539b24b7";

String text = "{\"username\": \"" + username + "\", \"rememberLogin\": \"true\", \"password\": \"" + password

+ "\"}";

String modulus = "00e0b509f6259df8642dbc35662901477df22677ec152b5ff68ace615bb7b725152b3ab17a876aea8a5aa76d2e417629ec4ee341f56135fccf695280104e0312ecbda92557c93870114af6c9d05c4f7f0c3685b7a46bee255932575cce10b424d813cfe4875d3e82047b97ddef52741d546b8e289dc6935b3ece0462db0a22b8e7";

String nonce = "0CoJUm6Qyw8W8jud";

String pubKey = "010001";

// 2次AES加密，得到params

String params = EncryptTools.encrypt(EncryptTools.encrypt(text, nonce), secKey);

StringBuffer stringBuffer = new StringBuffer(secKey);

// 逆置私钥

secKey = stringBuffer.reverse().toString();

String hex = Hex.encodeHexString(secKey.getBytes());

BigInteger bigInteger1 = new BigInteger(hex, 16);

BigInteger bigInteger2 = new BigInteger(pubKey, 16);

BigInteger bigInteger3 = new BigInteger(modulus, 16);

// RSA加密计算

BigInteger bigInteger4 = bigInteger1.pow(bigInteger2.intValue()).remainder(bigInteger3);

String encSecKey = Hex.encodeHexString(bigInteger4.toByteArray());

// 字符填充

encSecKey = EncryptTools.zfill(encSecKey, 256);

// 登录请求

Document document = Jsoup.connect("http://music.163.com/weapi/login/").cookie("appver", "1.5.0.75771")

.header("Referer", "http://music.163.com/").data("params", params).data("encSecKey", encSecKey)

.ignoreContentType(true).post();

System.out.println("登录结果：" + document.text());

}

参考资料