使用httpclient实现免费的google翻译api

时间:2021-05-19

由於Google translate API要收錢 ,因此想了一個偷機的方法

1. 用HttpClient發送一個request給http://translate.google.com

2. 再用Jsoup來parse html, 並取出翻譯後的文字

复制代码 代码如下:
/**
* Copyright (c) blackbear, Inc All Rights Reserved.
*/
package org.bb.util.i18n;

import java.io.InputStream;
import java.net.URLEncoder;
import java.text.MessageFormat;

import org.apache.commons.io.IOUtils;

import org.bb.util.net.http.HttpClientUtil;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;

/**
* TranslateUtil
*
* <pre>翻譯工具
* PS: 透過google translate
* </pre>
*
* @author catty
* @version 1.0, Created on 2011/9/2
*/
public class TranslateUtil {

protected static final String URL_TEMPLATE = "http://translate.google.com/?langpair={0}&text={1}";
protected static final String ID_RESULTBOX = "result_box";
protected static final String ENCODING = "UTF-8";

protected static final String AUTO = "auto"; // google自動判斷來源語系
protected static final String TAIWAN = "zh-TW"; // 繁中
protected static final String CHINA = "zh-CN"; // 簡中
protected static final String ENGLISH = "en"; // 英
protected static final String JAPAN = "ja"; // 日

/**
* <pre>Google翻譯
* PS: 交由google自動判斷來源語系
* </pre>
*
* @param text
* @param target_lang 目標語系
* @return
* @throws Exception
*/
public static String translate(final String text, final String target_lang) throws Exception {
return translate(text, AUTO, target_lang);
}

/**
* <pre>Google翻譯</pre>
*
* @param text
* @param src_lang 來源語系
* @param target_lang 目標語系
* @return
* @throws Exception
*/
public static String translate(final String text, final String src_lang, final String target_lang)
throws Exception {
InputStream is = null;
Document doc = null;
Element ele = null;
try {
// create URL string
String url = MessageFormat.format(URL_TEMPLATE,
URLEncoder.encode(src_lang + "|" + target_lang, ENCODING),
URLEncoder.encode(text, ENCODING));

// connect & download html
is = HttpClientUtil.downloadAsStream(url);

// parse html by Jsoup
doc = Jsoup.parse(is, ENCODING, "");
ele = doc.getElementById(ID_RESULTBOX);
String result = ele.text();
return result;

} finally {
IOUtils.closeQuietly(is);
is = null;
doc = null;
ele = null;
}
}

/**
* <pre>Google翻譯: 簡中-->繁中</pre>
*
* @param text
* @return
* @throws Exception
*/
public static String cn2tw(final String text) throws Exception {
return translate(text, CHINA, TAIWAN);
}

/**
* <pre>Google翻譯: 繁中-->簡中</pre>
*
* @param text
* @return
* @throws Exception
*/
public static String tw2cn(final String text) throws Exception {
return translate(text, TAIWAN, CHINA);
}

/**
* <pre>Google翻譯: 英文-->繁中</pre>
*
* @param text
* @return
* @throws Exception
*/
public static String en2tw(final String text) throws Exception {
return translate(text, ENGLISH, TAIWAN);
}

/**
* <pre>Google翻譯: 繁中-->英文</pre>
*
* @param text
* @return
* @throws Exception
*/
public static String tw2en(final String text) throws Exception {
return translate(text, TAIWAN, ENGLISH);
}

/**
* <pre>Google翻譯: 日文-->繁中</pre>
*
* @param text
* @return
* @throws Exception
*/
public static String jp2tw(final String text) throws Exception {
return translate(text, JAPAN, TAIWAN);
}

/**
* <pre>Google翻譯: 繁中-->日</pre>
*
* @param text
* @return
* @throws Exception
*/
public static String tw2jp(final String text) throws Exception {
return translate(text, TAIWAN, JAPAN);
}
}

HttpClientUtil.java

复制代码 代码如下:
/**
* Copyright (c) Blackbear, Inc All Rights Reserved.
*/
package org.bb.util.net.http;

import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.util.Map;

import org.apache.commons.io.IOUtils;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.http.HttpEntity;
import org.apache.http.HttpResponse;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.client.methods.HttpRequestBase;
import org.apache.http.conn.scheme.PlainSocketFactory;
import org.apache.http.conn.scheme.Scheme;
import org.apache.http.conn.scheme.SchemeRegistry;
import org.apache.http.conn.ssl.SSLSocketFactory;
import org.apache.http.entity.BufferedHttpEntity;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.impl.conn.tsccm.ThreadSafeClientConnManager;
import org.apache.http.params.BasicHttpParams;

/**
* PostUtil.java
*
* @author catty
* @version 1.0, Created on 2008/2/20
*/
public class HttpClientUtil {

protected static Log log = LogFactory.getLog(HttpClientUtil.class);
protected static HttpClient httpclient = null;
protected static int maxTotal = 200;
protected static int maxPerRoute = 20;
protected static String userAgent = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.77 Safari/535.7";

static {
if (httpclient == null) {
// ~~~~~~~~~~~~~~~~~~~~
// create httpclient
// ~~~~~~~~~~~~~~~~~~~~
SchemeRegistry reg = new SchemeRegistry();
reg.register(new Scheme("http", 80, PlainSocketFactory.getSocketFactory()));
reg.register(new Scheme("https", 443, SSLSocketFactory.getSocketFactory()));
ThreadSafeClientConnManager cm = new ThreadSafeClientConnManager(reg);
cm.setMaxTotal(maxTotal);
cm.setDefaultMaxPerRoute(maxPerRoute);
httpclient = new DefaultHttpClient(cm);
}
}

/**
* <pre>下載後回傳Inputstream</pre>
*
* @param url
* @return
* @throws Exception
*/
public static InputStream downloadAsStream(String url) throws Exception {
InputStream is = (InputStream) download(url, null, null, false);
return is;
}

/**
* <pre>下載後儲存到File</pre>
*
* @param url
* @param saveFile
* @throws Exception
*/
public static void download(String url, File saveFile) throws Exception {
download(url, saveFile, null, false);
}

/**
* <pre>下載</pre>
*
* @param url
* @param saveFile
* @param params
* @param isPost
* @return 如果saveFile==null則回傳inputstream, 否則回傳saveFile
* @throws Exception
*/
public static Object download(final String url, final File saveFile, final Map<String, String> params,
final boolean isPost) throws Exception {

boolean saveToFile = saveFile != null;

// check dir exist ??
if (saveToFile && saveFile.getParentFile().exists() == false) {
saveFile.getParentFile().mkdirs();
}

Exception err = null;
HttpRequestBase request = null;
HttpResponse response = null;
HttpEntity entity = null;
FileOutputStream fos = null;
Object result = null;

try {
// create request
if (isPost) {
request = new HttpPost(url);
} else {
request = new HttpGet(url);
}

// add header & params
addHeaderAndParams(request, params);

// connect
response = httpclient.execute(request);
entity = response.getEntity();
entity = new BufferedHttpEntity(entity);

// get result
if (saveToFile) {// save to disk
fos = new FileOutputStream(saveFile);
IOUtils.copy(entity.getContent(), fos);
result = saveFile;
} else { // warp to inpustream
result = new BufferedInputStream(entity.getContent());
}

} catch (Exception e) {
err = e;
} finally {

// close
IOUtils.closeQuietly(fos);

// clear
request = null;
response = null;
entity = null;

if (err != null) {
throw err;
}

return result;
}

}

protected static void addHeaderAndParams(final HttpRequestBase request, final Map<String, String> params) {
// add default header
request.addHeader("User-Agent", userAgent);

// add params
if (params != null) {

// map --> HttpParams
BasicHttpParams myParams = new BasicHttpParams();
for (String key : params.keySet()) {
myParams.setParameter(key, params.get(key));
}

request.setParams(myParams);
}
}

public static HttpClient getHttpclient() {
return httpclient;
}

public static void setHttpclient(HttpClient httpclient) {
HttpClientUtil.httpclient = httpclient;
}

public static int getMaxTotal() {
return maxTotal;
}

public static void setMaxTotal(int maxTotal) {
HttpClientUtil.maxTotal = maxTotal;
}

public static int getMaxPerRoute() {
return maxPerRoute;
}

public static void setMaxPerRoute(int maxPerRoute) {
HttpClientUtil.maxPerRoute = maxPerRoute;
}

public static String getUserAgent() {
return userAgent;
}

public static void setUserAgent(String userAgent) {
HttpClientUtil.userAgent = userAgent;
}
}

声明:本页内容来源网络,仅供用户参考;我单位不保证亦不表示资料全面及准确无误,也不保证亦不表示这些资料为最新信息,如因任何原因,本网内容或者用户因倚赖本网内容造成任何损失或损害,我单位将不会负任何法律责任。如涉及版权问题,请提交至online#300.cn邮箱联系删除。

相关文章