HttpsURLConnection 安全传输(HTTPS--Secure Hypertext Transfer Protocol-安全超文本传输协议)
HttpsURLConnection 扩展 HttpURLConnection,支持各种特定于 https 功能。此类使用 HostnameVerifier 和 SSLSocketFactory。为这两个类都定义了默认实现。但是,可以根据每个类(静态的)或每个实例来替换该实现。所有新 HttpsURLConnection 实例在创建时将被分配“默认的”静态值,通过在连接前调用每个实例适当的 set 方法可以重写这些值
在URL前加https://前缀表明是用SSL加密的。 你的电脑与服务器之间收发的信息传输将更加安全。
Web服务器启用SSL需要获得一个服务器证书并将该证书与要使用SSL的服务器绑定。
http和https使用的是完全不同的连接方式,用的端口也不一样,前者是80,后者是443。http的连接很简单,是无状态的,...
HTTPS协议是由SSL+HTTP协议构建的可进行加密传输、身份认证的网络协议
要比http协议安全
以下摘自: http://www.zimbio.com/member/kinggod03/articles/HImNQwJm-Lp/
终于完成了博客备份的程序,自己一直想做的事情算是完成了。发扬怀疑一切的精神,真不放心把自己的帐号告诉其他的公司,让他们来备份。闲来无事,也为了让我玩实况累的发软的手体验一下敲代码的感觉,专心的做完了这个备份博客的程序。总共有300多行,功能其实也很简单,就是把每篇文章的网页保存起来 ,但第一次做这种网络程序,很多都要学习。下面列出几点收获:
1,登陆需要使用SSL协议,似乎封装的太好了——只是把代码烤过来,很简单,现在也没懂是啥意思
2,使用Cookie。登录之后究竟用什么保存SessionID,头疼了很长时间。用IE进行登陆,把Cookie设成“提示”,于是所有的暗箱操作都见了阳光。这时才知道,几乎每个网页都会用Cookie存些东西,哪还有隐私。百度是必须用Cookie的,否则就无法登陆。这样有些过分了,应该提供一个选择。得到Cookie值后需要把“PASSPORTRETRYSTRING=deleted;”去掉,这个字段应该是用于防止重复提交的。如果不去掉,相当于没有登陆。去掉之后的Cookie值(主要是BDUUSS和BDUID)可以发送到服务器,这样就以登陆用户的身份查看博客了。
3,对于HTML代码应该可以用XML的方式来处理,不过我没有那个耐心,就用字符串的替代查找来实现了,效率不好,可以改进。
4,连接那部分代码借鉴了Google提供的博客访问的源代码,受益匪浅。百度没有相应的API,要不然我也不用这么麻烦。
5,还有许多细节的东西,比如文件读写啦。
6,看HTML代码真是头大!!!
为了取得信任我就把源代码贴出来,这也是我不愿意用那些商业软件的原因。商业软件,赚钱是最主要的,他不信任我,我也不信任他。而我,只不过图个安心和方便。
在URL前加https://前缀表明是用SSL加密的。 你的电脑与服务器之间收发的信息传输将更加安全。
Web服务器启用SSL需要获得一个服务器证书并将该证书与要使用SSL的服务器绑定。
http和https使用的是完全不同的连接方式,用的端口也不一样,前者是80,后者是443。http的连接很简单,是无状态的,...
HTTPS协议是由SSL+HTTP协议构建的可进行加密传输、身份认证的网络协议
要比http协议安全
package
com.yixun.wap;
import java.io. * ;
import java.net. * ;
import java.security. * ;
import java.security.cert. * ;
import javax.net.ssl. * ;
public class HttpsURLConnectionTest {
private String url = "https://esales.the9.com/esa/DealerLogin.php?txt_sLogin=andysmile234&pas_sPwd=343211&userstatus=1";
private myX509TrustManager xtm = new myX509TrustManager();
private myHostnameVerifier hnv = new myHostnameVerifier();
public HttpsURLConnectionTest() {
SSLContext sslContext = null;
try {
sslContext = SSLContext.getInstance("TLS"); //或SSL
X509TrustManager[] xtmArray = new X509TrustManager[] {xtm};
sslContext.init(null, xtmArray, new java.security.SecureRandom());
} catch (GeneralSecurityException e) {
e.printStackTrace();
}
if (sslContext != null) {
HttpsURLConnection.setDefaultSSLSocketFactory(sslContext.getSocketFactory());
}
HttpsURLConnection.setDefaultHostnameVerifier(hnv);
}
public void run() {
HttpsURLConnection urlCon = null;
try {
urlCon = (HttpsURLConnection)(new URL(url)).openConnection();
urlCon.setDoOutput(true);
urlCon.setRequestMethod("POST");
urlCon.setRequestProperty("Content-Length", "1024");
urlCon.setUseCaches(false);
urlCon.setDoInput(true);
urlCon.getOutputStream().write("request content".getBytes("gbk"));
urlCon.getOutputStream().flush();
urlCon.getOutputStream().close();
BufferedReader in = new BufferedReader(new InputStreamReader(urlCon.getInputStream()));
String line;
while ((line = in.readLine()) != null) {
System.out.println(line);
}
// 增加自己的代码
} catch (MalformedURLException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
} catch (Exception e) {
e.printStackTrace();
}
}
public static void main(String[] args) {
HttpsURLConnectionTest httpsTest = new HttpsURLConnectionTest();
httpsTest.run();
}
}
/** */ /**
* 重写三个方法
* @author Administrator
*
*/
class myX509TrustManager implements X509TrustManager {
public void checkClientTrusted(X509Certificate[] chain, String authType) {
}
public void checkServerTrusted(X509Certificate[] chain, String authType) {
System.out.println("cert: " + chain[0].toString() + ", authType: " + authType);
}
public X509Certificate[] getAcceptedIssuers() {
return null;
}
}
/** */ /**
* 重写一个方法
* @author Administrator
*
*/
class myHostnameVerifier implements HostnameVerifier {
public boolean verify(String hostname, SSLSession session) {
System.out.println("Warning: URL Host: " + hostname + " vs. " + session.getPeerHost());
return true;
}
}
import java.io. * ;
import java.net. * ;
import java.security. * ;
import java.security.cert. * ;
import javax.net.ssl. * ;
public class HttpsURLConnectionTest {
private String url = "https://esales.the9.com/esa/DealerLogin.php?txt_sLogin=andysmile234&pas_sPwd=343211&userstatus=1";
private myX509TrustManager xtm = new myX509TrustManager();
private myHostnameVerifier hnv = new myHostnameVerifier();
public HttpsURLConnectionTest() {
SSLContext sslContext = null;
try {
sslContext = SSLContext.getInstance("TLS"); //或SSL
X509TrustManager[] xtmArray = new X509TrustManager[] {xtm};
sslContext.init(null, xtmArray, new java.security.SecureRandom());
} catch (GeneralSecurityException e) {
e.printStackTrace();
}
if (sslContext != null) {
HttpsURLConnection.setDefaultSSLSocketFactory(sslContext.getSocketFactory());
}
HttpsURLConnection.setDefaultHostnameVerifier(hnv);
}
public void run() {
HttpsURLConnection urlCon = null;
try {
urlCon = (HttpsURLConnection)(new URL(url)).openConnection();
urlCon.setDoOutput(true);
urlCon.setRequestMethod("POST");
urlCon.setRequestProperty("Content-Length", "1024");
urlCon.setUseCaches(false);
urlCon.setDoInput(true);
urlCon.getOutputStream().write("request content".getBytes("gbk"));
urlCon.getOutputStream().flush();
urlCon.getOutputStream().close();
BufferedReader in = new BufferedReader(new InputStreamReader(urlCon.getInputStream()));
String line;
while ((line = in.readLine()) != null) {
System.out.println(line);
}
// 增加自己的代码
} catch (MalformedURLException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
} catch (Exception e) {
e.printStackTrace();
}
}
public static void main(String[] args) {
HttpsURLConnectionTest httpsTest = new HttpsURLConnectionTest();
httpsTest.run();
}
}
/** */ /**
* 重写三个方法
* @author Administrator
*
*/
class myX509TrustManager implements X509TrustManager {
public void checkClientTrusted(X509Certificate[] chain, String authType) {
}
public void checkServerTrusted(X509Certificate[] chain, String authType) {
System.out.println("cert: " + chain[0].toString() + ", authType: " + authType);
}
public X509Certificate[] getAcceptedIssuers() {
return null;
}
}
/** */ /**
* 重写一个方法
* @author Administrator
*
*/
class myHostnameVerifier implements HostnameVerifier {
public boolean verify(String hostname, SSLSession session) {
System.out.println("Warning: URL Host: " + hostname + " vs. " + session.getPeerHost());
return true;
}
}
以下摘自: http://www.zimbio.com/member/kinggod03/articles/HImNQwJm-Lp/
终于完成了博客备份的程序,自己一直想做的事情算是完成了。发扬怀疑一切的精神,真不放心把自己的帐号告诉其他的公司,让他们来备份。闲来无事,也为了让我玩实况累的发软的手体验一下敲代码的感觉,专心的做完了这个备份博客的程序。总共有300多行,功能其实也很简单,就是把每篇文章的网页保存起来 ,但第一次做这种网络程序,很多都要学习。下面列出几点收获:
1,登陆需要使用SSL协议,似乎封装的太好了——只是把代码烤过来,很简单,现在也没懂是啥意思
2,使用Cookie。登录之后究竟用什么保存SessionID,头疼了很长时间。用IE进行登陆,把Cookie设成“提示”,于是所有的暗箱操作都见了阳光。这时才知道,几乎每个网页都会用Cookie存些东西,哪还有隐私。百度是必须用Cookie的,否则就无法登陆。这样有些过分了,应该提供一个选择。得到Cookie值后需要把“PASSPORTRETRYSTRING=deleted;”去掉,这个字段应该是用于防止重复提交的。如果不去掉,相当于没有登陆。去掉之后的Cookie值(主要是BDUUSS和BDUID)可以发送到服务器,这样就以登陆用户的身份查看博客了。
3,对于HTML代码应该可以用XML的方式来处理,不过我没有那个耐心,就用字符串的替代查找来实现了,效率不好,可以改进。
4,连接那部分代码借鉴了Google提供的博客访问的源代码,受益匪浅。百度没有相应的API,要不然我也不用这么麻烦。
5,还有许多细节的东西,比如文件读写啦。
6,看HTML代码真是头大!!!
为了取得信任我就把源代码贴出来,这也是我不愿意用那些商业软件的原因。商业软件,赚钱是最主要的,他不信任我,我也不信任他。而我,只不过图个安心和方便。
package
com.yixun.wap;
/** */ /**
* 本程序可用于备份百度空间的文章。
* 18 hours costed.
* niuys.
* 2007.7.11
*/
import java.io. * ;
import java.net. * ;
import java.security.GeneralSecurityException;
import java.security.cert.X509Certificate;
import java.util. * ;
import javax.net.ssl.HostnameVerifier;
import javax.net.ssl.HttpsURLConnection;
import javax.net.ssl.SSLContext;
import javax.net.ssl.SSLSession;
import javax.net.ssl.X509TrustManager;
public class OpticalBackup {
// 把博客信息应编码
private String urlString = "https://passport.baidu.com/?login";
// 保存的目录
private String saveDir = "L:\\blogBackup";
// 博客的根路径
private String spaceRoot = "http://hi.baidu.com/niuys/blog/index/";
private String articleURLHead = "/niuys/blog/item/";
// parameters needed to log in.
Map parameters = new HashMap();
// 建立连接需要使用cookie提供的sessionID.
String cookieVal = null;
// Create an anonymous class to trust all certificates.
// This is bad style, you should create a separate class.
private X509TrustManager xtm = new X509TrustManager() {
public void checkClientTrusted(X509Certificate[] chain, String authType) {
}
public void checkServerTrusted(X509Certificate[] chain, String authType) {
// System.out.println("cert: " + chain[0].toString() + ", authType:
// "
// + authType);
}
public X509Certificate[] getAcceptedIssuers() {
return null;
}
};
// Create an class to trust all hosts
private HostnameVerifier hnv = new HostnameVerifier() {
public boolean verify(String hostname, SSLSession session) {
// System.out.println("hostname: " + hostname);
return true;
}
};
// In this function we configure our system with a less stringent
// hostname verifier and X509 trust manager. This code is
// executed once, and calls the static methods of HttpsURLConnection
public OpticalBackup() {
// The parameters needed to log on.
parameters.put("username", "保密");
parameters.put("password", "保密");
parameters.put("Submit", " 登录 ");
parameters.put("tpl", "sp");
parameters.put("tpl_reg", "sp");
parameters.put("u", "http://www.baidu.com/");
// check the saveDir
File dir = new File(saveDir);
if (!dir.exists()) {
dir.mkdir();
}
// Initialize the TLS SSLContext with
// our TrustManager
SSLContext sslContext = null;
try {
sslContext = SSLContext.getInstance("TLS");
X509TrustManager[] xtmArray = new X509TrustManager[] {xtm};
sslContext.init(null, xtmArray, new java.security.SecureRandom());
} catch (GeneralSecurityException e) {
// Print out some error message and deal with this exception
e.printStackTrace();
}
// Set the default SocketFactory and HostnameVerifier
// for javax.net.ssl.HttpsURLConnection
if (sslContext != null) {
HttpsURLConnection.setDefaultSSLSocketFactory(sslContext.getSocketFactory());
}
HttpsURLConnection.setDefaultHostnameVerifier(hnv);
}
// the whole process
public void run() {
try {
URL url = new URL(urlString);
HttpURLConnection urlConnection = (HttpURLConnection) url.openConnection();
// Set properties of the connection
urlConnection.setDoInput(true);
urlConnection.setDoOutput(true);
urlConnection.setUseCaches(false);
urlConnection.setRequestProperty("Content-Type", "application/x-www-form-urlencoded");
// Form the POST parameters
StringBuilder content = new StringBuilder();
boolean first = true;
Set set = parameters.entrySet();
Iterator iterator = set.iterator();
Map.Entry parameter = (Map.Entry) iterator.next();
try {
while (parameter != null) {
if (!first) {
content.append("&");
}
content.append(URLEncoder.encode((String) parameter.getKey(), "UTF-8")).append("=");
content.append(URLEncoder.encode((String) parameter.getValue(), "UTF-8"));
first = false;
parameter = (Map.Entry) iterator.next();
}
} catch (NoSuchElementException e) {
e.printStackTrace();
}
// send the POST request to server
OutputStream outputStream = null;
try {
outputStream = urlConnection.getOutputStream();
outputStream.write(content.toString().getBytes("utf-8"));
outputStream.flush();
} finally {
if (outputStream != null) {
outputStream.close();
}
}
// Retrieve the output
InputStream inputStream = null;
StringBuilder outputBuilder = new StringBuilder();
try {
int responseCode = urlConnection.getResponseCode();
if (responseCode == HttpURLConnection.HTTP_OK) {
inputStream = urlConnection.getInputStream();
} else {
inputStream = urlConnection.getErrorStream();
}
String string;
if (inputStream != null) {
BufferedReader reader = new BufferedReader(new InputStreamReader(inputStream));
while (null != (string = reader.readLine())) {
outputBuilder.append(string).append('\n');
}
}
// get the cookie value in the header filelds
Map map = urlConnection.getHeaderFields();
Collection collection = map.values();
Object[] values = collection.toArray();
// values[4].toString() is nedded .Otherwise,an exception
// throws. Direct class cast is forbidded.
cookieVal = (String) values[4].toString();
// "replaceAll()" requests that if "[" exits, "]" is nedded
// too.This is the diffrence from "replace()".
cookieVal = cookieVal.replace(']', ' ').replace("[PASSPORTRETRYSTRING=deleted; expires=Mon, 01 Jan 1970 00:00:00 GMT; path=/;", "");// remedy the first key from cookie
} finally {
if (inputStream != null) {
inputStream.close();
}
}
// find all the URLs of the articles you write.
ArrayList pageURLs = findLinkers();
// save all the articles
for (int i = 0; i < pageURLs.size(); i++) {
savePage((String) pageURLs.get(i));
}
} catch (Exception e) {
e.printStackTrace();
}
}
// save the article with the URL
private void savePage(String pageURL) {
try {
// create the file to accept the output.The file's name is a part of
// the URL
File pageFile = new File(saveDir + "\\" + pageURL.substring(36));
// 增量备份
if (pageFile.exists())
return;
FileWriter fw = new FileWriter(pageFile);
// create the connection to the server,and get the results.
URL url = new URL(pageURL);
String content = getContentFromURL(url);
// write the contents to the file.
fw.write(content);
// flush the contents in the buffer.Without
// it,the file's content may be not completed.
fw.flush();
fw.close();
} catch (Exception e) {
e.printStackTrace();
}
}
// find all the articles' URL from the html code accepted from the server
private ArrayList findLinkers() {
// the index of the articles
int i = 0;
ArrayList linkers = new ArrayList();
URL url = null;
try {
while (true) {
url = new URL(spaceRoot + i);
System.out.println("url==" + url);
i++;// next index
// get the content from server
String content = getContentFromURL(url);
// Analyze the content.
ArrayList temp = getLinkerFromContent(content);
if (temp.isEmpty())// no article url exists
return linkers;
linkers.addAll(temp);// combine the URLs
}
} catch (Exception e) {
e.printStackTrace();
}
return linkers;
}
private ArrayList getLinkerFromContent(String content) {
ArrayList linkerArray = new ArrayList();
String linker = null;
// The article's URL begins with "/niuys/blog/item/"
int index = content.indexOf(articleURLHead);
if (content.indexOf("暂无文章") > 0) {// 超过页数时会返回包含“暂无文章”的页,end
return linkerArray;
}
// deal with the content
while (index > 0) {
// get the whole URL
linker = content.substring(index, index + 46);
content = content.replace(linker, "");
index = content.indexOf(articleURLHead);
linker = "http://hi.baidu.com" + linker;
linkerArray.add(linker);
System.out.println("linker==" + linker);
}
return linkerArray;
}
private String getContentFromURL(URL url) throws Exception {
HttpURLConnection urlConnection = (HttpURLConnection) url.openConnection();
// Set properties of the connection
urlConnection.setDoInput(true);
urlConnection.setDoOutput(true);
urlConnection.setUseCaches(false);
urlConnection.setRequestProperty("Content-Type", "application/x-www-form-urlencoded");
urlConnection.addRequestProperty("Cookie", cookieVal);
// Retrieve the output
InputStream inputStream = null;
StringBuilder outputBuilder = new StringBuilder();
int responseCode = urlConnection.getResponseCode();
if (responseCode == HttpURLConnection.HTTP_OK) {
inputStream = urlConnection.getInputStream();
} else {
inputStream = urlConnection.getErrorStream();
}
String string;
if (inputStream != null) {
BufferedReader reader = new BufferedReader(new InputStreamReader(inputStream));
while (null != (string = reader.readLine())) {
outputBuilder.append(string).append('\n');
}
inputStream.close();
return outputBuilder.toString();
}
return "";
}
public static void main(String[] args) {
OpticalBackup backup = new OpticalBackup();
backup.run();
}
}
/** */ /**
* 本程序可用于备份百度空间的文章。
* 18 hours costed.
* niuys.
* 2007.7.11
*/
import java.io. * ;
import java.net. * ;
import java.security.GeneralSecurityException;
import java.security.cert.X509Certificate;
import java.util. * ;
import javax.net.ssl.HostnameVerifier;
import javax.net.ssl.HttpsURLConnection;
import javax.net.ssl.SSLContext;
import javax.net.ssl.SSLSession;
import javax.net.ssl.X509TrustManager;
public class OpticalBackup {
// 把博客信息应编码
private String urlString = "https://passport.baidu.com/?login";
// 保存的目录
private String saveDir = "L:\\blogBackup";
// 博客的根路径
private String spaceRoot = "http://hi.baidu.com/niuys/blog/index/";
private String articleURLHead = "/niuys/blog/item/";
// parameters needed to log in.
Map parameters = new HashMap();
// 建立连接需要使用cookie提供的sessionID.
String cookieVal = null;
// Create an anonymous class to trust all certificates.
// This is bad style, you should create a separate class.
private X509TrustManager xtm = new X509TrustManager() {
public void checkClientTrusted(X509Certificate[] chain, String authType) {
}
public void checkServerTrusted(X509Certificate[] chain, String authType) {
// System.out.println("cert: " + chain[0].toString() + ", authType:
// "
// + authType);
}
public X509Certificate[] getAcceptedIssuers() {
return null;
}
};
// Create an class to trust all hosts
private HostnameVerifier hnv = new HostnameVerifier() {
public boolean verify(String hostname, SSLSession session) {
// System.out.println("hostname: " + hostname);
return true;
}
};
// In this function we configure our system with a less stringent
// hostname verifier and X509 trust manager. This code is
// executed once, and calls the static methods of HttpsURLConnection
public OpticalBackup() {
// The parameters needed to log on.
parameters.put("username", "保密");
parameters.put("password", "保密");
parameters.put("Submit", " 登录 ");
parameters.put("tpl", "sp");
parameters.put("tpl_reg", "sp");
parameters.put("u", "http://www.baidu.com/");
// check the saveDir
File dir = new File(saveDir);
if (!dir.exists()) {
dir.mkdir();
}
// Initialize the TLS SSLContext with
// our TrustManager
SSLContext sslContext = null;
try {
sslContext = SSLContext.getInstance("TLS");
X509TrustManager[] xtmArray = new X509TrustManager[] {xtm};
sslContext.init(null, xtmArray, new java.security.SecureRandom());
} catch (GeneralSecurityException e) {
// Print out some error message and deal with this exception
e.printStackTrace();
}
// Set the default SocketFactory and HostnameVerifier
// for javax.net.ssl.HttpsURLConnection
if (sslContext != null) {
HttpsURLConnection.setDefaultSSLSocketFactory(sslContext.getSocketFactory());
}
HttpsURLConnection.setDefaultHostnameVerifier(hnv);
}
// the whole process
public void run() {
try {
URL url = new URL(urlString);
HttpURLConnection urlConnection = (HttpURLConnection) url.openConnection();
// Set properties of the connection
urlConnection.setDoInput(true);
urlConnection.setDoOutput(true);
urlConnection.setUseCaches(false);
urlConnection.setRequestProperty("Content-Type", "application/x-www-form-urlencoded");
// Form the POST parameters
StringBuilder content = new StringBuilder();
boolean first = true;
Set set = parameters.entrySet();
Iterator iterator = set.iterator();
Map.Entry parameter = (Map.Entry) iterator.next();
try {
while (parameter != null) {
if (!first) {
content.append("&");
}
content.append(URLEncoder.encode((String) parameter.getKey(), "UTF-8")).append("=");
content.append(URLEncoder.encode((String) parameter.getValue(), "UTF-8"));
first = false;
parameter = (Map.Entry) iterator.next();
}
} catch (NoSuchElementException e) {
e.printStackTrace();
}
// send the POST request to server
OutputStream outputStream = null;
try {
outputStream = urlConnection.getOutputStream();
outputStream.write(content.toString().getBytes("utf-8"));
outputStream.flush();
} finally {
if (outputStream != null) {
outputStream.close();
}
}
// Retrieve the output
InputStream inputStream = null;
StringBuilder outputBuilder = new StringBuilder();
try {
int responseCode = urlConnection.getResponseCode();
if (responseCode == HttpURLConnection.HTTP_OK) {
inputStream = urlConnection.getInputStream();
} else {
inputStream = urlConnection.getErrorStream();
}
String string;
if (inputStream != null) {
BufferedReader reader = new BufferedReader(new InputStreamReader(inputStream));
while (null != (string = reader.readLine())) {
outputBuilder.append(string).append('\n');
}
}
// get the cookie value in the header filelds
Map map = urlConnection.getHeaderFields();
Collection collection = map.values();
Object[] values = collection.toArray();
// values[4].toString() is nedded .Otherwise,an exception
// throws. Direct class cast is forbidded.
cookieVal = (String) values[4].toString();
// "replaceAll()" requests that if "[" exits, "]" is nedded
// too.This is the diffrence from "replace()".
cookieVal = cookieVal.replace(']', ' ').replace("[PASSPORTRETRYSTRING=deleted; expires=Mon, 01 Jan 1970 00:00:00 GMT; path=/;", "");// remedy the first key from cookie
} finally {
if (inputStream != null) {
inputStream.close();
}
}
// find all the URLs of the articles you write.
ArrayList pageURLs = findLinkers();
// save all the articles
for (int i = 0; i < pageURLs.size(); i++) {
savePage((String) pageURLs.get(i));
}
} catch (Exception e) {
e.printStackTrace();
}
}
// save the article with the URL
private void savePage(String pageURL) {
try {
// create the file to accept the output.The file's name is a part of
// the URL
File pageFile = new File(saveDir + "\\" + pageURL.substring(36));
// 增量备份
if (pageFile.exists())
return;
FileWriter fw = new FileWriter(pageFile);
// create the connection to the server,and get the results.
URL url = new URL(pageURL);
String content = getContentFromURL(url);
// write the contents to the file.
fw.write(content);
// flush the contents in the buffer.Without
// it,the file's content may be not completed.
fw.flush();
fw.close();
} catch (Exception e) {
e.printStackTrace();
}
}
// find all the articles' URL from the html code accepted from the server
private ArrayList findLinkers() {
// the index of the articles
int i = 0;
ArrayList linkers = new ArrayList();
URL url = null;
try {
while (true) {
url = new URL(spaceRoot + i);
System.out.println("url==" + url);
i++;// next index
// get the content from server
String content = getContentFromURL(url);
// Analyze the content.
ArrayList temp = getLinkerFromContent(content);
if (temp.isEmpty())// no article url exists
return linkers;
linkers.addAll(temp);// combine the URLs
}
} catch (Exception e) {
e.printStackTrace();
}
return linkers;
}
private ArrayList getLinkerFromContent(String content) {
ArrayList linkerArray = new ArrayList();
String linker = null;
// The article's URL begins with "/niuys/blog/item/"
int index = content.indexOf(articleURLHead);
if (content.indexOf("暂无文章") > 0) {// 超过页数时会返回包含“暂无文章”的页,end
return linkerArray;
}
// deal with the content
while (index > 0) {
// get the whole URL
linker = content.substring(index, index + 46);
content = content.replace(linker, "");
index = content.indexOf(articleURLHead);
linker = "http://hi.baidu.com" + linker;
linkerArray.add(linker);
System.out.println("linker==" + linker);
}
return linkerArray;
}
private String getContentFromURL(URL url) throws Exception {
HttpURLConnection urlConnection = (HttpURLConnection) url.openConnection();
// Set properties of the connection
urlConnection.setDoInput(true);
urlConnection.setDoOutput(true);
urlConnection.setUseCaches(false);
urlConnection.setRequestProperty("Content-Type", "application/x-www-form-urlencoded");
urlConnection.addRequestProperty("Cookie", cookieVal);
// Retrieve the output
InputStream inputStream = null;
StringBuilder outputBuilder = new StringBuilder();
int responseCode = urlConnection.getResponseCode();
if (responseCode == HttpURLConnection.HTTP_OK) {
inputStream = urlConnection.getInputStream();
} else {
inputStream = urlConnection.getErrorStream();
}
String string;
if (inputStream != null) {
BufferedReader reader = new BufferedReader(new InputStreamReader(inputStream));
while (null != (string = reader.readLine())) {
outputBuilder.append(string).append('\n');
}
inputStream.close();
return outputBuilder.toString();
}
return "";
}
public static void main(String[] args) {
OpticalBackup backup = new OpticalBackup();
backup.run();
}
}
http://www.blogjava.net/jzone/articles/307329.html