java导入163联系人
2013-11-14 11:58
267 查看
现在在许多SNS中都有导入邮箱联系人的功能,以下的代码功能就是如何取得163邮箱账号的联系人
更多的导入联系人代码,可在此处下载:http://code.google.com/p/jcontactfetcher/
首先是工具类
1.CommonUtil类,现在只有初始化log4j方法
[java] view
plaincopy
package org.gc.contact.util;
import java.io.IOException;
import java.io.InputStream;
import java.util.Properties;
import org.apache.log4j.PropertyConfigurator;
public final class CommonUtil {
static {
initLog4J();
}
private CommonUtil() {}
private static void initLog4J() {
InputStream in = CommonUtil.class.getResourceAsStream("/log4j.properties");
Properties props = new Properties();
try {
props.load(in);
PropertyConfigurator.configure(props);
} catch(IOException ex) {
System.out.println("Log4JLogger Create Exception:/n" + ex.getMessage());
}
}
}
2.EncodingUtil类,编码相关
[java] view
plaincopy
package org.gc.contact.util;
public class EncodingUtil {
public static final String DEFAULT_ENCODING = "UTF-8";
private EncodingUtil() {}
}
3.RegexpUtil类,正则表达式工具
[java] view
plaincopy
package org.gc.contact.util;
import java.util.regex.Pattern;
public final class RegexpUtil {
private static final String REGEXP_FORM_INPUT_VALUE = "<//s*input(?://s+.*)*//s+value=/"?([^//s/"]*)/"?";
private static final String REGEXP_HOST_FROM_URI = "http://([^/]+)/.*";
private static final String REGEXP_JS_REDIRECTION = "location//.replace//(/"(.+)/"//)";
private static final Pattern PATTERN_FORM_INPUT_VALUE = Pattern.compile(REGEXP_FORM_INPUT_VALUE);
private static final Pattern PATTERN_HOST_FROM_URI = Pattern.compile(REGEXP_HOST_FROM_URI);
private static final Pattern PATTERN_JS_REDIRECTION = Pattern.compile(REGEXP_JS_REDIRECTION);
private RegexpUtil() {}
public static Pattern getFormInputValueRegexp() {
return PATTERN_FORM_INPUT_VALUE;
}
public static Pattern getHostFromURIRegexp() {
return PATTERN_HOST_FROM_URI;
}
public static Pattern getJSRedirectionRegexp() {
return PATTERN_JS_REDIRECTION;
}
}
接着是实体类
4.联系人类
[java] view
plaincopy
package org.gc.contact.model;
import java.io.Serializable;
public class ContactInfo implements Serializable {
private static final long serialVersionUID = 5530203198421462152L;
private final String username;
private final String address; //email & qq etc.
public ContactInfo(String username, String address) {
this.username = username;
this.address = address;
}
public String getUsername() {
return username;
}
public String getAddress() {
return address;
}
public String toString() {
return "[" + username + "," + address + "]";
}
}
异常类
5.错误消息
[java] view
plaincopy
package org.gc.contact.exception;
public final class ExceptionMessage {
public static final String PROTOCOL_MSG = "Don't find a match; may be the regular expression error, may be the protocol changed.";
private ExceptionMessage() {}
}
6.HttpBrowserException,浏览器异常
[java] view
plaincopy
package org.gc.contact.exception;
@SuppressWarnings("serial")
public class HttpBrowserException extends Exception {
public HttpBrowserException() {
super();
}
public HttpBrowserException(String error) {
super(error);
}
public HttpBrowserException(Throwable t) {
super(t);
}
public HttpBrowserException(String error, Throwable t) {
super(error, t);
}
}
7.HttpServerException,服务器异常
[java] view
plaincopy
package org.gc.contact.exception;
@SuppressWarnings("serial")
public class HttpServerException extends Exception {
public HttpServerException() {
super();
}
public HttpServerException(String error) {
super(error);
}
public HttpServerException(Throwable t) {
super(t);
}
public HttpServerException(String error, Throwable t) {
super(error, t);
}
}
8.ProtocolException,协议异常
[java] view
plaincopy
package org.gc.contact.exception;
@SuppressWarnings("serial")
public class ProtocolException extends Exception {
public ProtocolException() {
super();
}
public ProtocolException(Throwable t) {
super(t);
}
public ProtocolException(String error) {
super(error);
}
public ProtocolException(String error, Throwable t) {
super(error, t);
}
}
核心类
9.HttpBrowser类,模拟浏览器的类,有get,post行为
[java] view
plaincopy
package org.gc.contact.http;
import java.io.IOException;
import java.util.Date;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.apache.commons.httpclient.Cookie;
import org.apache.commons.httpclient.Header;
import org.apache.commons.httpclient.HttpClient;
import org.apache.commons.httpclient.HttpException;
import org.apache.commons.httpclient.HttpMethod;
import org.apache.commons.httpclient.HttpStatus;
import org.apache.commons.httpclient.NameValuePair;
import org.apache.commons.httpclient.URIException;
import org.apache.commons.httpclient.cookie.CookiePolicy;
import org.apache.commons.httpclient.methods.GetMethod;
import org.apache.commons.httpclient.methods.PostMethod;
import org.apache.commons.httpclient.params.HttpMethodParams;
import org.apache.commons.httpclient.protocol.Protocol;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.gc.contact.exception.ExceptionMessage;
import org.gc.contact.exception.HttpBrowserException;
import org.gc.contact.exception.HttpServerException;
import org.gc.contact.util.EncodingUtil;
import org.gc.contact.util.RegexpUtil;
@SuppressWarnings("deprecation")
public class HttpBrowser {
static {
SSLUtilities.trustAllHttpsCertificates();
SSLUtilities.trustAllHostnames();
Protocol myhttps = new Protocol("https", new SSLFactory (), 443);
Protocol.registerProtocol("https", myhttps);
}
private static final Log logger = LogFactory.getLog(HttpBrowser.class);
private HttpClient httpClient;
protected String encoding;
protected int bufferLength = 4096;
protected String lastVisitUrl;
public HttpBrowser() {
this(EncodingUtil.DEFAULT_ENCODING);
}
public HttpBrowser(String encoding) {
this.encoding = encoding;
httpClient = new HttpClient();
httpClient.getParams().setCookiePolicy(CookiePolicy.BROWSER_COMPATIBILITY);
httpClient.getParams().setParameter(HttpMethodParams.HTTP_CONTENT_CHARSET, encoding);
httpClient.getParams().setParameter(HttpMethodParams.SINGLE_COOKIE_HEADER, true);
}
//----------- callable methods -------------//
public HttpResponse doGet(String url) throws HttpBrowserException, HttpServerException {
return doGet(url, "");
}
public HttpResponse doGet(String url, String referer) throws HttpBrowserException, HttpServerException {
try {
GetMethod getMethod = new GetMethod(url);
setHttpRequestHeader(getMethod);
if (referer != null && referer.trim().length() != 0) {
getMethod.setRequestHeader("Referer", referer);
}
logHttpGetRequest(getMethod);
int status =httpClient.executeMethod(getMethod);
String strResp = getMethod.getResponseBodyAsString();
byte[] byteResp = getMethod.getResponseBody();
String respEnc = getResponseEncoding(getMethod);
logHttpResponse(getMethod, strResp);
getMethod.releaseConnection();
//http:301,302,303,307
if (status == HttpStatus.SC_MOVED_PERMANENTLY ||
status == HttpStatus.SC_MOVED_TEMPORARILY ||
status == HttpStatus.SC_SEE_OTHER ||
status == HttpStatus.SC_TEMPORARY_REDIRECT) {
Header locationHeader = getMethod.getResponseHeader("Location");
String location = locationHeader.getValue();
if (logger.isDebugEnabled()) {
logger.debug("Redirect To Location = " + location);
}
if (location.startsWith("http")) {
return doGet(location);
} else {
return doGet("http://" + getResponseHost(getMethod) + location);
}
} else if (status == HttpStatus.SC_OK) { //http:200
return new HttpResponse(getMethod.getURI().toString(), byteResp, respEnc);
} else {
throw new HttpServerException("Server Exception[code=" + status + "]");
}
} catch (HttpException e) {
throw new HttpBrowserException(e);
} catch (IOException e) {
throw new HttpBrowserException(e);
}
}
public HttpResponse doPost(String url, NameValuePair[] params) throws HttpBrowserException, HttpServerException {
return doPost(url, params, "");
}
public HttpResponse doPost(String url, NameValuePair[] params, String referer) throws HttpBrowserException, HttpServerException {
try {
PostMethod postMethod = new PostMethod(url);
setHttpRequestHeader(postMethod);
if (referer != null && referer.trim().length() != 0) {
postMethod.setRequestHeader("Referer", referer);
}
postMethod.setRequestHeader("Content-Type", "application/x-www-form-urlencoded");
postMethod.setRequestBody(params);
logHttpPostRequest(postMethod);
int status = httpClient.executeMethod(postMethod);
String strResp = postMethod.getResponseBodyAsString();
byte[] byteResp = postMethod.getResponseBody();
String respEnc = getResponseEncoding(postMethod);
logHttpResponse(postMethod, strResp);
postMethod.releaseConnection();
//http:301,302,303,307
if (status == HttpStatus.SC_MOVED_PERMANENTLY ||
status == HttpStatus.SC_MOVED_TEMPORARILY ||
status == HttpStatus.SC_SEE_OTHER ||
status == HttpStatus.SC_TEMPORARY_REDIRECT) {
Header locationHeader = postMethod.getResponseHeader("Location");
String location = locationHeader.getValue();
if (logger.isDebugEnabled()) {
logger.debug("Redirect To Location = " + location);
}
if (location.startsWith("http")) {
return doGet(location);
} else {
return doGet("http://" + getResponseHost(postMethod) + location);
}
} else if (status == HttpStatus.SC_OK) { //http:200
return new HttpResponse(postMethod.getURI().toString(), byteResp, respEnc);
} else {
throw new HttpServerException("Server Exception[code=" + status + "]");
}
} catch (HttpException e) {
throw new HttpBrowserException(e);
} catch (IOException e) {
throw new HttpBrowserException(e);
}
}
public Cookie[] getCurrentCookies() {
Cookie[] cookies = httpClient.getState().getCookies();
return cookies;
}
protected void setHttpRequestHeader(HttpMethod method) {
method.setRequestHeader("Accept",
"text/html,application/xhtml+xml,application/xml,application/json,image/jpeg,image/gif,*/*");
method.setRequestHeader("Accept-Language", "zh-cn");
method.setRequestHeader(
"User-Agent",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9.0.3) Gecko/2008092417 Firefox/3.0.3");
method.setRequestHeader("Accept-Charset", encoding);
method.setRequestHeader("Keep-Alive", "300");
method.setRequestHeader("Connection", "Keep-Alive");
method.setRequestHeader("Cache-Control", "no-cache");
}
//------------- log methods ----------------//
private void logHttpGetRequest(HttpMethod method) {
try {
if (logger.isDebugEnabled()) {
logger.debug("/n/n============= HTTP Request Start =============");
logger.debug("HTTP Get Request URL ==>/n" + method.getURI().toString());
logger.debug("HTTP Get Request Headers ==>/n" + getHttpRequestHeader(method));
logger.debug("HTTP Get Request Cookies ==>/n" + getHttpCookie());
logger.debug("HTTP Get Request QueryString ==>/n" + method.getQueryString());
logger.debug("============= HTTP Request End =============/n/n");
}
} catch (URIException e) {
logger.error(e);
}
}
private void logHttpPostRequest(PostMethod method) {
try {
if (logger.isDebugEnabled()) {
logger.debug("/n/n============= HTTP Request Start =============");
logger.debug("HTTP Post Request URL ==>/n" + method.getURI().toString());
logger.debug("HTTP Post Request Headers ==>/n" + getHttpRequestHeader(method));
logger.debug("HTTP Post Request Cookies ==>/n" + getHttpCookie());
logger.debug("HTTP Post Request QueryString ==>/n" + method.getQueryString());
logger.debug("HTTP Post Request Body ==>/n" + getHttpRequestBody(method));
logger.debug("============= HTTP Request End =============/n/n");
}
} catch (URIException e) {
logger.error("URIException", e);
}
}
private void logHttpResponse(HttpMethod method, String strResp) {
try {
if (logger.isDebugEnabled()) {
logger.debug("/n/n============= HTTP Response Start =============");
logger.debug("HTTP Response URL ==>/n" + method.getURI().toString());
logger.debug("HTTP Response Headers ==>/n" + getHttpResponseHeader(method));
logger.debug("HTTP Response Cookies ==>/n" + getHttpCookie());
logger.debug("HTTP Response Body ==>/n" + strResp);
logger.debug("============= HTTP Response End =============/n/n");
}
} catch (URIException e) {
logger.error("URIException", e);
}
}
//---------- util methods -------------//
private String getResponseEncoding(HttpMethod method) {
Header header = method.getResponseHeader("Content-Type");
String encoding = EncodingUtil.DEFAULT_ENCODING;
if (header != null) {
if (logger.isDebugEnabled()) {
logger.debug("Content-Type=" + header.getValue());
}
if (header != null) {
String value = header.getValue();
int idx1 = value.indexOf("charset=");
if (idx1 > -1) {
encoding = value.substring(idx1 + 8);
if (logger.isDebugEnabled()) {
logger.debug("Response Encoding=" + encoding);
}
}
}
}
return encoding;
}
private String getResponseHost(HttpMethod method) {
try {
Pattern p = RegexpUtil.getHostFromURIRegexp();
String url = method.getURI().toString();
Matcher matcher = p.matcher(url);
if (!matcher.find()) {
String msg = ExceptionMessage.PROTOCOL_MSG + "[Type=ResponseHost,Regexp=" + p.pattern() + "]";
logger.error(msg);
}
if (logger.isDebugEnabled()) {
logger.debug("Host=" + matcher.group(1));
}
return matcher.group(1);
} catch (Exception e) {
logger.error(e);
}
return "";
}
private String getHttpRequestBody(PostMethod method) {
StringBuilder strBody = new StringBuilder();
NameValuePair[] pairs = method.getParameters();
for (NameValuePair pair : pairs) {
String name = pair.getName();
String value = pair.getValue();
strBody.append(name + "=" + value + ";");
}
return strBody.toString();
}
private String getHttpCookie() {
StringBuilder strHeader = new StringBuilder();
Cookie[] cookies = httpClient.getState().getCookies();
for (Cookie cookie : cookies) {
String domain = cookie.getDomain();
String path = cookie.getPath();
String name = cookie.getName();
String value = cookie.getValue();
Date expired = cookie.getExpiryDate();
boolean isSecure = cookie.getSecure();
strHeader.append("domain=" + domain + ";");
strHeader.append("path=" + path + ";");
strHeader.append(name + "=" + value + ";");
if (expired != null) {
strHeader.append("expired=" + expired.toGMTString() + ";");
}
strHeader.append("isSecure=" + isSecure+ "/n");
}
return strHeader.toString();
}
private String getHttpRequestHeader(HttpMethod method) {
StringBuilder strHeader = new StringBuilder();
Header[] headers = method.getRequestHeaders();
for (Header header : headers) {
String name = header.getName();
String value = header.getValue();
strHeader.append(name + "=" + value + ";");
}
return strHeader.toString();
}
private String getHttpResponseHeader(HttpMethod method) {
StringBuilder strHeader = new StringBuilder();
Header[] headers = method.getResponseHeaders();
for (Header header : headers) {
String name = header.getName();
String value = header.getValue();
strHeader.append(name + "=" + value + ";");
}
return strHeader.toString();
}
}
10.HttpResponse类,http的回复结果类
[java] view
plaincopy
package org.gc.contact.http;
import java.io.ByteArrayInputStream;
import java.io.InputStream;
import java.io.UnsupportedEncodingException;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.gc.contact.util.EncodingUtil;
public class HttpResponse {
private static final Log logger = LogFactory.getLog(HttpResponse.class);
private final String responseUrl;
private final byte[] bodyAsBytes;
private final String encoding;
public HttpResponse(String responseUrl, byte[] bodyAsBytes) {
this(responseUrl, bodyAsBytes, EncodingUtil.DEFAULT_ENCODING);
}
public HttpResponse(String responseUrl, byte[] bodyAsBytes, String encoding) {
this.responseUrl = responseUrl;
this.bodyAsBytes = bodyAsBytes;
this.encoding = encoding;
}
public String getResponseUrl() {
return responseUrl;
}
public String getBodyAsString() {
try {
if (logger.isDebugEnabled()) {
logger.debug("Convert Encoding=" + encoding);
}
return new String(bodyAsBytes, encoding);
} catch (UnsupportedEncodingException e) {
logger.error("Encoding Error[encoding=" + encoding + "]", e);
try {
return new String(bodyAsBytes, EncodingUtil.DEFAULT_ENCODING);
} catch (UnsupportedEncodingException e1) {
logger.error("Encoding Error[encoding=" + EncodingUtil.DEFAULT_ENCODING + "]", e);
return new String(bodyAsBytes);
}
}
}
public byte[] getBodyAsBytes() {
return bodyAsBytes;
}
public InputStream getBodyAsStream() {
return new ByteArrayInputStream(bodyAsBytes);
}
}
11.SSLFactory类,用于https
[java] view
plaincopy
package org.gc.contact.http;
import java.io.IOException;
import java.net.InetAddress;
import java.net.InetSocketAddress;
import java.net.Socket;
import java.net.SocketAddress;
import java.net.UnknownHostException;
import java.security.KeyManagementException;
import java.security.NoSuchAlgorithmException;
import java.security.cert.CertificateException;
import java.security.cert.X509Certificate;
import javax.net.SocketFactory;
import javax.net.ssl.SSLContext;
import javax.net.ssl.TrustManager;
import javax.net.ssl.X509TrustManager;
import org.apache.commons.httpclient.ConnectTimeoutException;
import org.apache.commons.httpclient.params.HttpConnectionParams;
import org.apache.commons.httpclient.protocol.SecureProtocolSocketFactory;
public class SSLFactory implements SecureProtocolSocketFactory {
static {
System.out.println(">>>> SSLFactory Init <<<<");
}
private SSLContext sslcontext = null;
private SSLContext createSSLContext() {
SSLContext sslcontext=null;
try {
sslcontext = SSLContext.getInstance("SSL");
sslcontext.init(null, new TrustManager[]{new TrustAnyTrustManager()}, new java.security.SecureRandom());
} catch (NoSuchAlgorithmException e) {
e.printStackTrace();
} catch (KeyManagementException e) {
e.printStackTrace();
}
return sslcontext;
}
private SSLContext getSSLContext() {
if (this.sslcontext == null) {
this.sslcontext = createSSLContext();
}
return this.sslcontext;
}
public Socket createSocket(Socket socket, String host, int port, boolean autoClose)
throws IOException, UnknownHostException {
return getSSLContext().getSocketFactory().createSocket(
socket,
host,
port,
autoClose
);
}
public Socket createSocket(String host, int port) throws IOException,
UnknownHostException {
return getSSLContext().getSocketFactory().createSocket(
host,
port
);
}
public Socket createSocket(String host, int port, InetAddress clientHost, int clientPort)
throws IOException, UnknownHostException {
return getSSLContext().getSocketFactory().createSocket(host, port, clientHost, clientPort);
}
public Socket createSocket(String host, int port, InetAddress localAddress,
int localPort, HttpConnectionParams params) throws IOException,
UnknownHostException, ConnectTimeoutException {
if (params == null) {
throw new IllegalArgumentException("Parameters may not be null");
}
int timeout = params.getConnectionTimeout();
SocketFactory socketfactory = getSSLContext().getSocketFactory();
if (timeout == 0) {
return socketfactory.createSocket(host, port, localAddress, localPort);
} else {
Socket socket = socketfactory.createSocket();
SocketAddress localaddr = new InetSocketAddress(localAddress, localPort);
SocketAddress remoteaddr = new InetSocketAddress(host, port);
socket.bind(localaddr);
socket.connect(remoteaddr, timeout);
return socket;
}
}
private static class TrustAnyTrustManager implements X509TrustManager {
public void checkClientTrusted(X509Certificate[] chain, String authType) throws CertificateException {
}
public void checkServerTrusted(X509Certificate[] chain, String authType) throws CertificateException {
}
public X509Certificate[] getAcceptedIssuers() {
return new X509Certificate[]{};
}
}
}
12.SSLUtilities类,用于https
[java] view
plaincopy
package org.gc.contact.http;
import java.security.GeneralSecurityException;
import java.security.SecureRandom;
import java.security.cert.X509Certificate;
import javax.net.ssl.HostnameVerifier;
import javax.net.ssl.HttpsURLConnection;
import javax.net.ssl.SSLContext;
import javax.net.ssl.TrustManager;
import javax.net.ssl.X509TrustManager;
/**
* This class provide various static methods that relax X509 certificate and
* hostname verification while using the SSL over the HTTP protocol.
*
* @author Francis Labrie
*/
public final class SSLUtilities {
/**
* Hostname verifier for the Sun's deprecated API.
*
* @deprecated see {@link #_hostnameVerifier}.
*/
private static com.sun.net.ssl.HostnameVerifier __hostnameVerifier;
/**
* Thrust managers for the Sun's deprecated API.
*
* @deprecated see {@link #_trustManagers}.
*/
private static com.sun.net.ssl.TrustManager[] __trustManagers;
/**
* Hostname verifier.
*/
private static HostnameVerifier _hostnameVerifier;
/**
* Thrust managers.
*/
private static TrustManager[] _trustManagers;
/**
* Set the default Hostname Verifier to an instance of a fake class that
* trust all hostnames. This method uses the old deprecated API from the
* com.sun.ssl package.
*
* @deprecated see {@link #_trustAllHostnames()}.
*/
private static void __trustAllHostnames() {
// Create a trust manager that does not validate certificate chains
if (__hostnameVerifier == null) {
__hostnameVerifier = new _FakeHostnameVerifier();
} // if
// Install the all-trusting host name verifier
com.sun.net.ssl.HttpsURLConnection
.setDefaultHostnameVerifier(__hostnameVerifier);
} // __trustAllHttpsCertificates
/**
* Set the default X509 Trust Manager to an instance of a fake class that
* trust all certificates, even the self-signed ones. This method uses the
* old deprecated API from the com.sun.ssl package.
*
* @deprecated see {@link #_trustAllHttpsCertificates()}.
*/
private static void __trustAllHttpsCertificates() {
com.sun.net.ssl.SSLContext context;
// Create a trust manager that does not validate certificate chains
if (__trustManagers == null) {
__trustManagers = new com.sun.net.ssl.TrustManager[] { new _FakeX509TrustManager() };
} // if
// Install the all-trusting trust manager
try {
context = com.sun.net.ssl.SSLContext.getInstance("SSL");
context.init(null, __trustManagers, new SecureRandom());
} catch (GeneralSecurityException gse) {
throw new IllegalStateException(gse.getMessage());
} // catch
com.sun.net.ssl.HttpsURLConnection.setDefaultSSLSocketFactory(context
.getSocketFactory());
} // __trustAllHttpsCertificates
/**
* Return true if the protocol handler property java. protocol.handler.pkgs
* is set to the Sun's com.sun.net.ssl. internal.www.protocol deprecated
* one, false otherwise.
*
* @return true if the protocol handler property is set to the Sun's
* deprecated one, false otherwise.
*/
private static boolean isDeprecatedSSLProtocol() {
return ("com.sun.net.ssl.internal.www.protocol".equals(System
.getProperty("java.protocol.handler.pkgs")));
} // isDeprecatedSSLProtocol
/**
* Set the default Hostname Verifier to an instance of a fake class that
* trust all hostnames.
*/
private static void _trustAllHostnames() {
// Create a trust manager that does not validate certificate chains
if (_hostnameVerifier == null) {
_hostnameVerifier = new FakeHostnameVerifier();
} // if
// Install the all-trusting host name verifier:
HttpsURLConnection.setDefaultHostnameVerifier(_hostnameVerifier);
} // _trustAllHttpsCertificates
/**
* Set the default X509 Trust Manager to an instance of a fake class that
* trust all certificates, even the self-signed ones.
*/
private static void _trustAllHttpsCertificates() {
SSLContext context;
// Create a trust manager that does not validate certificate chains
if (_trustManagers == null) {
_trustManagers = new TrustManager[] { new FakeX509TrustManager() };
} // if
// Install the all-trusting trust manager:
try {
context = SSLContext.getInstance("SSL");
context.init(null, _trustManagers, new SecureRandom());
} catch (GeneralSecurityException gse) {
throw new IllegalStateException(gse.getMessage());
} // catch
HttpsURLConnection.setDefaultSSLSocketFactory(context
.getSocketFactory());
} // _trustAllHttpsCertificates
/**
* Set the default Hostname Verifier to an instance of a fake class that
* trust all hostnames.
*/
public static void trustAllHostnames() {
// Is the deprecated protocol setted?
if (isDeprecatedSSLProtocol()) {
__trustAllHostnames();
} else {
_trustAllHostnames();
} // else
} // trustAllHostnames
/**
* Set the default X509 Trust Manager to an instance of a fake class that
* trust all certificates, even the self-signed ones.
*/
public static void trustAllHttpsCertificates() {
// Is the deprecated protocol setted?
if (isDeprecatedSSLProtocol()) {
__trustAllHttpsCertificates();
} else {
_trustAllHttpsCertificates();
} // else
} // trustAllHttpsCertificates
/**
* This class implements a fake hostname verificator, trusting any host
* name. This class uses the old deprecated API from the com.sun. ssl
* package.
*
* @author Francis Labrie
*
* @deprecated see {@link SSLUtilities.FakeHostnameVerifier}.
*/
public static class _FakeHostnameVerifier implements
com.sun.net.ssl.HostnameVerifier {
/**
* Always return true, indicating that the host name is an acceptable
* match with the server's authentication scheme.
*
* @param hostname
* the host name.
* @param session
* the SSL session used on the connection to host.
* @return the true boolean value indicating the host name is trusted.
*/
public boolean verify(String hostname, String session) {
return (true);
} // verify
} // _FakeHostnameVerifier
/**
* This class allow any X509 certificates to be used to authenticate the
* remote side of a secure socket, including self-signed certificates. This
* class uses the old deprecated API from the com.sun.ssl package.
*
* @author Francis Labrie
*
* @deprecated see {@link SSLUtilities.FakeX509TrustManager}.
*/
public static class _FakeX509TrustManager implements
com.sun.net.ssl.X509TrustManager {
/**
* Empty array of certificate authority certificates.
*/
private static final X509Certificate[] _AcceptedIssuers = new X509Certificate[] {};
/**
* Always return true, trusting for client SSL chain peer certificate
* chain.
*
* @param chain
* the peer certificate chain.
* @return the true boolean value indicating the chain is trusted.
*/
public boolean isClientTrusted(X509Certificate[] chain) {
return (true);
} // checkClientTrusted
/**
* Always return true, trusting for server SSL chain peer certificate
* chain.
*
* @param chain
* the peer certificate chain.
* @return the true boolean value indicating the chain is trusted.
*/
public boolean isServerTrusted(X509Certificate[] chain) {
return (true);
} // checkServerTrusted
/**
* Return an empty array of certificate authority certificates which are
* trusted for authenticating peers.
*
* @return a empty array of issuer certificates.
*/
public X509Certificate[] getAcceptedIssuers() {
return (_AcceptedIssuers);
} // getAcceptedIssuers
} // _FakeX509TrustManager
/**
* This class implements a fake hostname verificator, trusting any host
* name.
*
* @author Francis Labrie
*/
public static class FakeHostnameVerifier implements HostnameVerifier {
/**
* Always return true, indicating that the host name is an acceptable
* match with the server's authentication scheme.
*
* @param hostname
* the host name.
* @param session
* the SSL session used on the connection to host.
* @return the true boolean value indicating the host name is trusted.
*/
public boolean verify(String hostname, javax.net.ssl.SSLSession session) {
return (true);
} // verify
} // FakeHostnameVerifier
/**
* This class allow any X509 certificates to be used to authenticate the
* remote side of a secure socket, including self-signed certificates.
*
* @author Francis Labrie
*/
public static class FakeX509TrustManager implements X509TrustManager {
/**
* Empty array of certificate authority certificates.
*/
private static final X509Certificate[] _AcceptedIssuers = new X509Certificate[] {};
/**
* Always trust for client SSL chain peer certificate chain with any
* authType authentication types.
*
* @param chain
* the peer certificate chain.
* @param authType
* the authentication type based on the client certificate.
*/
public void checkClientTrusted(X509Certificate[] chain, String authType) {
} // checkClientTrusted
/**
* Always trust for server SSL chain peer certificate chain with any
* authType exchange algorithm types.
*
* @param chain
* the peer certificate chain.
* @param authType
* the key exchange algorithm used.
*/
public void checkServerTrusted(X509Certificate[] chain, String authType) {
} // checkServerTrusted
/**
* Return an empty array of certificate authority certificates which are
* trusted for authenticating peers.
*
* @return a empty array of issuer certificates.
*/
public X509Certificate[] getAcceptedIssuers() {
return (_AcceptedIssuers);
} // getAcceptedIssuers
} // FakeX509TrustManager
} // SSLUtilities
下面就是取得联系人的过程了
13.IContactFetcher接口
[java] view
plaincopy
package org.gc.contact.fetcher;
import java.util.List;
import org.gc.contact.exception.HttpBrowserException;
import org.gc.contact.exception.HttpServerException;
import org.gc.contact.exception.ProtocolException;
import org.gc.contact.model.ContactInfo;
public interface IContactFetcher {
void doLogin() throws HttpBrowserException, HttpServerException, ProtocolException;
List<ContactInfo> fetchContactInfo() throws HttpBrowserException, HttpServerException, ProtocolException;
}
14.AbstractContactFetcher类
[java] view
plaincopy
package org.gc.contact.fetcher;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.gc.contact.exception.ExceptionMessage;
import org.gc.contact.exception.ProtocolException;
import org.gc.contact.http.HttpBrowser;
import org.gc.contact.util.RegexpUtil;
public abstract class AbstractContactFetcher implements IContactFetcher {
protected final Log logger = LogFactory.getLog(getClass());
protected final HttpBrowser browser;
protected String username;
protected String password;
public AbstractContactFetcher(String username, String password) {
this.username = username;
this.password = password;
browser = new HttpBrowser();
}
protected String getJSRedirection(String htmlContent) throws ProtocolException {
Pattern p = RegexpUtil.getJSRedirectionRegexp();
Matcher matcher = p.matcher(htmlContent);
if (!matcher.find()) {
String msg = ExceptionMessage.PROTOCOL_MSG + "[Type=JSRedirection,Regexp=" + p.pattern() + "]";
logger.error(msg);
throw new ProtocolException(msg);
}
if (logger.isDebugEnabled()) {
logger.debug("Redirection URL = " + matcher.group(1));
}
return matcher.group(1);
}
protected String getFormInputValue(String name, String htmlContent) throws ProtocolException {
Pattern p = RegexpUtil.getFormInputValueRegexp();
int index = htmlContent.indexOf(name);
int prePos = index - 400 > 0 ? index - 400 : 0;
int postPos = index + 400 < htmlContent.length() ? index + 400 : htmlContent.length();
int start = htmlContent.substring(prePos, index).lastIndexOf("<input") + prePos;
int end = htmlContent.substring(index, postPos).indexOf(">") + index;
String htmlInput = htmlContent.substring(start, end + 1);
if (logger.isDebugEnabled()) {
logger.debug("HtmlInput=" + htmlInput);
}
Matcher matcher = p.matcher(htmlInput);
if (!matcher.find()) {
String msg = ExceptionMessage.PROTOCOL_MSG + "[Type=FormInputValue,Regexp=" + p.pattern() + "]";
logger.error(msg);
throw new ProtocolException(msg);
}
if (logger.isDebugEnabled()) {
logger.debug("Name = " + name + ";value = " + matcher.group(1));
}
return matcher.group(1);
}
protected String getHost(String url) throws ProtocolException {
Pattern p = RegexpUtil.getHostFromURIRegexp();
Matcher matcher = p.matcher(url);
if (!matcher.find()) {
String msg = ExceptionMessage.PROTOCOL_MSG + "[Type=Host,Regexp=" + p.pattern() + "]";
logger.error(msg);
throw new ProtocolException(msg);
}
if (logger.isDebugEnabled()) {
logger.debug("Host = " + matcher.group(1));
}
return matcher.group(1);
}
protected List<String> getValue(Pattern p, String htmlContent) throws ProtocolException {
List<String> data = new ArrayList<String>();
Matcher matcher = p.matcher(htmlContent);
while (matcher.find()) {
try {
data.add(matcher.group(1));
if (logger.isDebugEnabled()) {
logger.debug("Matched String=" + matcher.group(1));
}
} catch (Exception e) {
String msg = ExceptionMessage.PROTOCOL_MSG + "[Type=getValue,Regexp=" + p.pattern() + "]";
logger.error(msg);
throw new ProtocolException(msg);
}
}
if (data.size() == 0) {
String msg = ExceptionMessage.PROTOCOL_MSG + "[Type=getValue,Regexp=" + p.pattern() + "]";
logger.warn(msg);
}
return data;
}
}
15.取163的联系人
[java] view
plaincopy
package org.gc.contact.fetcher;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Pattern;
import org.apache.commons.httpclient.NameValuePair;
import org.gc.contact.exception.HttpBrowserException;
import org.gc.contact.exception.HttpServerException;
import org.gc.contact.exception.ProtocolException;
import org.gc.contact.http.HttpResponse;
import org.gc.contact.model.ContactInfo;
/**
* @163.com邮箱取地址本过程
* 1. loginUrl
* 2. window.location.replace("url")
* 3. fetch address list
*
*/
public class Mail163ContactFetcher extends AbstractContactFetcher {
private final String loginUrl = "http://reg.163.com/login.jsp?type=1&product=mail163&url=http://entry.mail.163.com/coremail/fcg/ntesdoor2?lightweight%3D1%26verifycookie%3D1%26language%3D-1%26style%3D35";
/**
* fetch url
* http://g1a61.mail.163.com/jy3/address/addrlist.jsp?sid=SBmtqsXXQmCXunRFLtXXXfowbRxMPUUX&gid=all
*/
private String fetchUrl;
private final String REGEXP_USER = "<td class=/"Ibx_Td_addrName/"><a href="/" mce_href="/""addrdetail.jsp//?sid=.+&gid=all/" title=/".+/">(.+)</a></td>";
private final String REGEXP_EMAIL = "<td class=/"Ibx_Td_addrEmail/"><a href="/" mce_href="/""addrdetail.jsp//?sid=.+&gid=all/" title=/".+/">(.+)</a></td>";
private final Pattern PATTERN_USER = Pattern.compile(REGEXP_USER);
private final Pattern PATTERN_EMAIL = Pattern.compile(REGEXP_EMAIL);
public Mail163ContactFetcher(String username, String password) {
super(username, password);
}
@Override
public void doLogin() throws HttpBrowserException, HttpServerException, ProtocolException {
NameValuePair[] loginParams = makeLoginParams();
HttpResponse redirectPage = browser.doPost(loginUrl, loginParams);
String redirectUrl = getJSRedirection(redirectPage.getBodyAsString());
HttpResponse mainPage = browser.doGet(redirectUrl);
fetchUrl = mainPage.getResponseUrl();
}
@Override
public List<ContactInfo> fetchContactInfo() throws HttpBrowserException, HttpServerException, ProtocolException {
List<ContactInfo> contacts = new ArrayList<ContactInfo>();
String contactUrl = fetchUrl.replace("main.jsp", "address/addrlist.jsp");
contactUrl += "&gid=all";
HttpResponse contactPage = browser.doGet(contactUrl);
String html = contactPage.getBodyAsString();
//为了匹配,每个td一行
html = html.replace("</td>", "</td>/n");
List<String> username = getValue(PATTERN_USER, html);
List<String> email = getValue(PATTERN_EMAIL, html);
for (int i = 0; i < username.size(); i++) {
contacts.add(new ContactInfo(username.get(i), email.get(i)));
}
return contacts;
}
private NameValuePair[] makeLoginParams() {
return new NameValuePair[] {
new NameValuePair("username", username),
new NameValuePair("password", password)
};
}
}
更多的导入联系人代码,可在此处下载:http://code.google.com/p/jcontactfetcher/
首先是工具类
1.CommonUtil类,现在只有初始化log4j方法
[java] view
plaincopy
package org.gc.contact.util;
import java.io.IOException;
import java.io.InputStream;
import java.util.Properties;
import org.apache.log4j.PropertyConfigurator;
public final class CommonUtil {
static {
initLog4J();
}
private CommonUtil() {}
private static void initLog4J() {
InputStream in = CommonUtil.class.getResourceAsStream("/log4j.properties");
Properties props = new Properties();
try {
props.load(in);
PropertyConfigurator.configure(props);
} catch(IOException ex) {
System.out.println("Log4JLogger Create Exception:/n" + ex.getMessage());
}
}
}
2.EncodingUtil类,编码相关
[java] view
plaincopy
package org.gc.contact.util;
public class EncodingUtil {
public static final String DEFAULT_ENCODING = "UTF-8";
private EncodingUtil() {}
}
3.RegexpUtil类,正则表达式工具
[java] view
plaincopy
package org.gc.contact.util;
import java.util.regex.Pattern;
public final class RegexpUtil {
private static final String REGEXP_FORM_INPUT_VALUE = "<//s*input(?://s+.*)*//s+value=/"?([^//s/"]*)/"?";
private static final String REGEXP_HOST_FROM_URI = "http://([^/]+)/.*";
private static final String REGEXP_JS_REDIRECTION = "location//.replace//(/"(.+)/"//)";
private static final Pattern PATTERN_FORM_INPUT_VALUE = Pattern.compile(REGEXP_FORM_INPUT_VALUE);
private static final Pattern PATTERN_HOST_FROM_URI = Pattern.compile(REGEXP_HOST_FROM_URI);
private static final Pattern PATTERN_JS_REDIRECTION = Pattern.compile(REGEXP_JS_REDIRECTION);
private RegexpUtil() {}
public static Pattern getFormInputValueRegexp() {
return PATTERN_FORM_INPUT_VALUE;
}
public static Pattern getHostFromURIRegexp() {
return PATTERN_HOST_FROM_URI;
}
public static Pattern getJSRedirectionRegexp() {
return PATTERN_JS_REDIRECTION;
}
}
接着是实体类
4.联系人类
[java] view
plaincopy
package org.gc.contact.model;
import java.io.Serializable;
public class ContactInfo implements Serializable {
private static final long serialVersionUID = 5530203198421462152L;
private final String username;
private final String address; //email & qq etc.
public ContactInfo(String username, String address) {
this.username = username;
this.address = address;
}
public String getUsername() {
return username;
}
public String getAddress() {
return address;
}
public String toString() {
return "[" + username + "," + address + "]";
}
}
异常类
5.错误消息
[java] view
plaincopy
package org.gc.contact.exception;
public final class ExceptionMessage {
public static final String PROTOCOL_MSG = "Don't find a match; may be the regular expression error, may be the protocol changed.";
private ExceptionMessage() {}
}
6.HttpBrowserException,浏览器异常
[java] view
plaincopy
package org.gc.contact.exception;
@SuppressWarnings("serial")
public class HttpBrowserException extends Exception {
public HttpBrowserException() {
super();
}
public HttpBrowserException(String error) {
super(error);
}
public HttpBrowserException(Throwable t) {
super(t);
}
public HttpBrowserException(String error, Throwable t) {
super(error, t);
}
}
7.HttpServerException,服务器异常
[java] view
plaincopy
package org.gc.contact.exception;
@SuppressWarnings("serial")
public class HttpServerException extends Exception {
public HttpServerException() {
super();
}
public HttpServerException(String error) {
super(error);
}
public HttpServerException(Throwable t) {
super(t);
}
public HttpServerException(String error, Throwable t) {
super(error, t);
}
}
8.ProtocolException,协议异常
[java] view
plaincopy
package org.gc.contact.exception;
@SuppressWarnings("serial")
public class ProtocolException extends Exception {
public ProtocolException() {
super();
}
public ProtocolException(Throwable t) {
super(t);
}
public ProtocolException(String error) {
super(error);
}
public ProtocolException(String error, Throwable t) {
super(error, t);
}
}
核心类
9.HttpBrowser类,模拟浏览器的类,有get,post行为
[java] view
plaincopy
package org.gc.contact.http;
import java.io.IOException;
import java.util.Date;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.apache.commons.httpclient.Cookie;
import org.apache.commons.httpclient.Header;
import org.apache.commons.httpclient.HttpClient;
import org.apache.commons.httpclient.HttpException;
import org.apache.commons.httpclient.HttpMethod;
import org.apache.commons.httpclient.HttpStatus;
import org.apache.commons.httpclient.NameValuePair;
import org.apache.commons.httpclient.URIException;
import org.apache.commons.httpclient.cookie.CookiePolicy;
import org.apache.commons.httpclient.methods.GetMethod;
import org.apache.commons.httpclient.methods.PostMethod;
import org.apache.commons.httpclient.params.HttpMethodParams;
import org.apache.commons.httpclient.protocol.Protocol;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.gc.contact.exception.ExceptionMessage;
import org.gc.contact.exception.HttpBrowserException;
import org.gc.contact.exception.HttpServerException;
import org.gc.contact.util.EncodingUtil;
import org.gc.contact.util.RegexpUtil;
@SuppressWarnings("deprecation")
public class HttpBrowser {
static {
SSLUtilities.trustAllHttpsCertificates();
SSLUtilities.trustAllHostnames();
Protocol myhttps = new Protocol("https", new SSLFactory (), 443);
Protocol.registerProtocol("https", myhttps);
}
private static final Log logger = LogFactory.getLog(HttpBrowser.class);
private HttpClient httpClient;
protected String encoding;
protected int bufferLength = 4096;
protected String lastVisitUrl;
public HttpBrowser() {
this(EncodingUtil.DEFAULT_ENCODING);
}
public HttpBrowser(String encoding) {
this.encoding = encoding;
httpClient = new HttpClient();
httpClient.getParams().setCookiePolicy(CookiePolicy.BROWSER_COMPATIBILITY);
httpClient.getParams().setParameter(HttpMethodParams.HTTP_CONTENT_CHARSET, encoding);
httpClient.getParams().setParameter(HttpMethodParams.SINGLE_COOKIE_HEADER, true);
}
//----------- callable methods -------------//
public HttpResponse doGet(String url) throws HttpBrowserException, HttpServerException {
return doGet(url, "");
}
public HttpResponse doGet(String url, String referer) throws HttpBrowserException, HttpServerException {
try {
GetMethod getMethod = new GetMethod(url);
setHttpRequestHeader(getMethod);
if (referer != null && referer.trim().length() != 0) {
getMethod.setRequestHeader("Referer", referer);
}
logHttpGetRequest(getMethod);
int status =httpClient.executeMethod(getMethod);
String strResp = getMethod.getResponseBodyAsString();
byte[] byteResp = getMethod.getResponseBody();
String respEnc = getResponseEncoding(getMethod);
logHttpResponse(getMethod, strResp);
getMethod.releaseConnection();
//http:301,302,303,307
if (status == HttpStatus.SC_MOVED_PERMANENTLY ||
status == HttpStatus.SC_MOVED_TEMPORARILY ||
status == HttpStatus.SC_SEE_OTHER ||
status == HttpStatus.SC_TEMPORARY_REDIRECT) {
Header locationHeader = getMethod.getResponseHeader("Location");
String location = locationHeader.getValue();
if (logger.isDebugEnabled()) {
logger.debug("Redirect To Location = " + location);
}
if (location.startsWith("http")) {
return doGet(location);
} else {
return doGet("http://" + getResponseHost(getMethod) + location);
}
} else if (status == HttpStatus.SC_OK) { //http:200
return new HttpResponse(getMethod.getURI().toString(), byteResp, respEnc);
} else {
throw new HttpServerException("Server Exception[code=" + status + "]");
}
} catch (HttpException e) {
throw new HttpBrowserException(e);
} catch (IOException e) {
throw new HttpBrowserException(e);
}
}
public HttpResponse doPost(String url, NameValuePair[] params) throws HttpBrowserException, HttpServerException {
return doPost(url, params, "");
}
public HttpResponse doPost(String url, NameValuePair[] params, String referer) throws HttpBrowserException, HttpServerException {
try {
PostMethod postMethod = new PostMethod(url);
setHttpRequestHeader(postMethod);
if (referer != null && referer.trim().length() != 0) {
postMethod.setRequestHeader("Referer", referer);
}
postMethod.setRequestHeader("Content-Type", "application/x-www-form-urlencoded");
postMethod.setRequestBody(params);
logHttpPostRequest(postMethod);
int status = httpClient.executeMethod(postMethod);
String strResp = postMethod.getResponseBodyAsString();
byte[] byteResp = postMethod.getResponseBody();
String respEnc = getResponseEncoding(postMethod);
logHttpResponse(postMethod, strResp);
postMethod.releaseConnection();
//http:301,302,303,307
if (status == HttpStatus.SC_MOVED_PERMANENTLY ||
status == HttpStatus.SC_MOVED_TEMPORARILY ||
status == HttpStatus.SC_SEE_OTHER ||
status == HttpStatus.SC_TEMPORARY_REDIRECT) {
Header locationHeader = postMethod.getResponseHeader("Location");
String location = locationHeader.getValue();
if (logger.isDebugEnabled()) {
logger.debug("Redirect To Location = " + location);
}
if (location.startsWith("http")) {
return doGet(location);
} else {
return doGet("http://" + getResponseHost(postMethod) + location);
}
} else if (status == HttpStatus.SC_OK) { //http:200
return new HttpResponse(postMethod.getURI().toString(), byteResp, respEnc);
} else {
throw new HttpServerException("Server Exception[code=" + status + "]");
}
} catch (HttpException e) {
throw new HttpBrowserException(e);
} catch (IOException e) {
throw new HttpBrowserException(e);
}
}
public Cookie[] getCurrentCookies() {
Cookie[] cookies = httpClient.getState().getCookies();
return cookies;
}
protected void setHttpRequestHeader(HttpMethod method) {
method.setRequestHeader("Accept",
"text/html,application/xhtml+xml,application/xml,application/json,image/jpeg,image/gif,*/*");
method.setRequestHeader("Accept-Language", "zh-cn");
method.setRequestHeader(
"User-Agent",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9.0.3) Gecko/2008092417 Firefox/3.0.3");
method.setRequestHeader("Accept-Charset", encoding);
method.setRequestHeader("Keep-Alive", "300");
method.setRequestHeader("Connection", "Keep-Alive");
method.setRequestHeader("Cache-Control", "no-cache");
}
//------------- log methods ----------------//
private void logHttpGetRequest(HttpMethod method) {
try {
if (logger.isDebugEnabled()) {
logger.debug("/n/n============= HTTP Request Start =============");
logger.debug("HTTP Get Request URL ==>/n" + method.getURI().toString());
logger.debug("HTTP Get Request Headers ==>/n" + getHttpRequestHeader(method));
logger.debug("HTTP Get Request Cookies ==>/n" + getHttpCookie());
logger.debug("HTTP Get Request QueryString ==>/n" + method.getQueryString());
logger.debug("============= HTTP Request End =============/n/n");
}
} catch (URIException e) {
logger.error(e);
}
}
private void logHttpPostRequest(PostMethod method) {
try {
if (logger.isDebugEnabled()) {
logger.debug("/n/n============= HTTP Request Start =============");
logger.debug("HTTP Post Request URL ==>/n" + method.getURI().toString());
logger.debug("HTTP Post Request Headers ==>/n" + getHttpRequestHeader(method));
logger.debug("HTTP Post Request Cookies ==>/n" + getHttpCookie());
logger.debug("HTTP Post Request QueryString ==>/n" + method.getQueryString());
logger.debug("HTTP Post Request Body ==>/n" + getHttpRequestBody(method));
logger.debug("============= HTTP Request End =============/n/n");
}
} catch (URIException e) {
logger.error("URIException", e);
}
}
private void logHttpResponse(HttpMethod method, String strResp) {
try {
if (logger.isDebugEnabled()) {
logger.debug("/n/n============= HTTP Response Start =============");
logger.debug("HTTP Response URL ==>/n" + method.getURI().toString());
logger.debug("HTTP Response Headers ==>/n" + getHttpResponseHeader(method));
logger.debug("HTTP Response Cookies ==>/n" + getHttpCookie());
logger.debug("HTTP Response Body ==>/n" + strResp);
logger.debug("============= HTTP Response End =============/n/n");
}
} catch (URIException e) {
logger.error("URIException", e);
}
}
//---------- util methods -------------//
private String getResponseEncoding(HttpMethod method) {
Header header = method.getResponseHeader("Content-Type");
String encoding = EncodingUtil.DEFAULT_ENCODING;
if (header != null) {
if (logger.isDebugEnabled()) {
logger.debug("Content-Type=" + header.getValue());
}
if (header != null) {
String value = header.getValue();
int idx1 = value.indexOf("charset=");
if (idx1 > -1) {
encoding = value.substring(idx1 + 8);
if (logger.isDebugEnabled()) {
logger.debug("Response Encoding=" + encoding);
}
}
}
}
return encoding;
}
private String getResponseHost(HttpMethod method) {
try {
Pattern p = RegexpUtil.getHostFromURIRegexp();
String url = method.getURI().toString();
Matcher matcher = p.matcher(url);
if (!matcher.find()) {
String msg = ExceptionMessage.PROTOCOL_MSG + "[Type=ResponseHost,Regexp=" + p.pattern() + "]";
logger.error(msg);
}
if (logger.isDebugEnabled()) {
logger.debug("Host=" + matcher.group(1));
}
return matcher.group(1);
} catch (Exception e) {
logger.error(e);
}
return "";
}
private String getHttpRequestBody(PostMethod method) {
StringBuilder strBody = new StringBuilder();
NameValuePair[] pairs = method.getParameters();
for (NameValuePair pair : pairs) {
String name = pair.getName();
String value = pair.getValue();
strBody.append(name + "=" + value + ";");
}
return strBody.toString();
}
private String getHttpCookie() {
StringBuilder strHeader = new StringBuilder();
Cookie[] cookies = httpClient.getState().getCookies();
for (Cookie cookie : cookies) {
String domain = cookie.getDomain();
String path = cookie.getPath();
String name = cookie.getName();
String value = cookie.getValue();
Date expired = cookie.getExpiryDate();
boolean isSecure = cookie.getSecure();
strHeader.append("domain=" + domain + ";");
strHeader.append("path=" + path + ";");
strHeader.append(name + "=" + value + ";");
if (expired != null) {
strHeader.append("expired=" + expired.toGMTString() + ";");
}
strHeader.append("isSecure=" + isSecure+ "/n");
}
return strHeader.toString();
}
private String getHttpRequestHeader(HttpMethod method) {
StringBuilder strHeader = new StringBuilder();
Header[] headers = method.getRequestHeaders();
for (Header header : headers) {
String name = header.getName();
String value = header.getValue();
strHeader.append(name + "=" + value + ";");
}
return strHeader.toString();
}
private String getHttpResponseHeader(HttpMethod method) {
StringBuilder strHeader = new StringBuilder();
Header[] headers = method.getResponseHeaders();
for (Header header : headers) {
String name = header.getName();
String value = header.getValue();
strHeader.append(name + "=" + value + ";");
}
return strHeader.toString();
}
}
10.HttpResponse类,http的回复结果类
[java] view
plaincopy
package org.gc.contact.http;
import java.io.ByteArrayInputStream;
import java.io.InputStream;
import java.io.UnsupportedEncodingException;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.gc.contact.util.EncodingUtil;
public class HttpResponse {
private static final Log logger = LogFactory.getLog(HttpResponse.class);
private final String responseUrl;
private final byte[] bodyAsBytes;
private final String encoding;
public HttpResponse(String responseUrl, byte[] bodyAsBytes) {
this(responseUrl, bodyAsBytes, EncodingUtil.DEFAULT_ENCODING);
}
public HttpResponse(String responseUrl, byte[] bodyAsBytes, String encoding) {
this.responseUrl = responseUrl;
this.bodyAsBytes = bodyAsBytes;
this.encoding = encoding;
}
public String getResponseUrl() {
return responseUrl;
}
public String getBodyAsString() {
try {
if (logger.isDebugEnabled()) {
logger.debug("Convert Encoding=" + encoding);
}
return new String(bodyAsBytes, encoding);
} catch (UnsupportedEncodingException e) {
logger.error("Encoding Error[encoding=" + encoding + "]", e);
try {
return new String(bodyAsBytes, EncodingUtil.DEFAULT_ENCODING);
} catch (UnsupportedEncodingException e1) {
logger.error("Encoding Error[encoding=" + EncodingUtil.DEFAULT_ENCODING + "]", e);
return new String(bodyAsBytes);
}
}
}
public byte[] getBodyAsBytes() {
return bodyAsBytes;
}
public InputStream getBodyAsStream() {
return new ByteArrayInputStream(bodyAsBytes);
}
}
11.SSLFactory类,用于https
[java] view
plaincopy
package org.gc.contact.http;
import java.io.IOException;
import java.net.InetAddress;
import java.net.InetSocketAddress;
import java.net.Socket;
import java.net.SocketAddress;
import java.net.UnknownHostException;
import java.security.KeyManagementException;
import java.security.NoSuchAlgorithmException;
import java.security.cert.CertificateException;
import java.security.cert.X509Certificate;
import javax.net.SocketFactory;
import javax.net.ssl.SSLContext;
import javax.net.ssl.TrustManager;
import javax.net.ssl.X509TrustManager;
import org.apache.commons.httpclient.ConnectTimeoutException;
import org.apache.commons.httpclient.params.HttpConnectionParams;
import org.apache.commons.httpclient.protocol.SecureProtocolSocketFactory;
public class SSLFactory implements SecureProtocolSocketFactory {
static {
System.out.println(">>>> SSLFactory Init <<<<");
}
private SSLContext sslcontext = null;
private SSLContext createSSLContext() {
SSLContext sslcontext=null;
try {
sslcontext = SSLContext.getInstance("SSL");
sslcontext.init(null, new TrustManager[]{new TrustAnyTrustManager()}, new java.security.SecureRandom());
} catch (NoSuchAlgorithmException e) {
e.printStackTrace();
} catch (KeyManagementException e) {
e.printStackTrace();
}
return sslcontext;
}
private SSLContext getSSLContext() {
if (this.sslcontext == null) {
this.sslcontext = createSSLContext();
}
return this.sslcontext;
}
public Socket createSocket(Socket socket, String host, int port, boolean autoClose)
throws IOException, UnknownHostException {
return getSSLContext().getSocketFactory().createSocket(
socket,
host,
port,
autoClose
);
}
public Socket createSocket(String host, int port) throws IOException,
UnknownHostException {
return getSSLContext().getSocketFactory().createSocket(
host,
port
);
}
public Socket createSocket(String host, int port, InetAddress clientHost, int clientPort)
throws IOException, UnknownHostException {
return getSSLContext().getSocketFactory().createSocket(host, port, clientHost, clientPort);
}
public Socket createSocket(String host, int port, InetAddress localAddress,
int localPort, HttpConnectionParams params) throws IOException,
UnknownHostException, ConnectTimeoutException {
if (params == null) {
throw new IllegalArgumentException("Parameters may not be null");
}
int timeout = params.getConnectionTimeout();
SocketFactory socketfactory = getSSLContext().getSocketFactory();
if (timeout == 0) {
return socketfactory.createSocket(host, port, localAddress, localPort);
} else {
Socket socket = socketfactory.createSocket();
SocketAddress localaddr = new InetSocketAddress(localAddress, localPort);
SocketAddress remoteaddr = new InetSocketAddress(host, port);
socket.bind(localaddr);
socket.connect(remoteaddr, timeout);
return socket;
}
}
private static class TrustAnyTrustManager implements X509TrustManager {
public void checkClientTrusted(X509Certificate[] chain, String authType) throws CertificateException {
}
public void checkServerTrusted(X509Certificate[] chain, String authType) throws CertificateException {
}
public X509Certificate[] getAcceptedIssuers() {
return new X509Certificate[]{};
}
}
}
12.SSLUtilities类,用于https
[java] view
plaincopy
package org.gc.contact.http;
import java.security.GeneralSecurityException;
import java.security.SecureRandom;
import java.security.cert.X509Certificate;
import javax.net.ssl.HostnameVerifier;
import javax.net.ssl.HttpsURLConnection;
import javax.net.ssl.SSLContext;
import javax.net.ssl.TrustManager;
import javax.net.ssl.X509TrustManager;
/**
* This class provide various static methods that relax X509 certificate and
* hostname verification while using the SSL over the HTTP protocol.
*
* @author Francis Labrie
*/
public final class SSLUtilities {
/**
* Hostname verifier for the Sun's deprecated API.
*
* @deprecated see {@link #_hostnameVerifier}.
*/
private static com.sun.net.ssl.HostnameVerifier __hostnameVerifier;
/**
* Thrust managers for the Sun's deprecated API.
*
* @deprecated see {@link #_trustManagers}.
*/
private static com.sun.net.ssl.TrustManager[] __trustManagers;
/**
* Hostname verifier.
*/
private static HostnameVerifier _hostnameVerifier;
/**
* Thrust managers.
*/
private static TrustManager[] _trustManagers;
/**
* Set the default Hostname Verifier to an instance of a fake class that
* trust all hostnames. This method uses the old deprecated API from the
* com.sun.ssl package.
*
* @deprecated see {@link #_trustAllHostnames()}.
*/
private static void __trustAllHostnames() {
// Create a trust manager that does not validate certificate chains
if (__hostnameVerifier == null) {
__hostnameVerifier = new _FakeHostnameVerifier();
} // if
// Install the all-trusting host name verifier
com.sun.net.ssl.HttpsURLConnection
.setDefaultHostnameVerifier(__hostnameVerifier);
} // __trustAllHttpsCertificates
/**
* Set the default X509 Trust Manager to an instance of a fake class that
* trust all certificates, even the self-signed ones. This method uses the
* old deprecated API from the com.sun.ssl package.
*
* @deprecated see {@link #_trustAllHttpsCertificates()}.
*/
private static void __trustAllHttpsCertificates() {
com.sun.net.ssl.SSLContext context;
// Create a trust manager that does not validate certificate chains
if (__trustManagers == null) {
__trustManagers = new com.sun.net.ssl.TrustManager[] { new _FakeX509TrustManager() };
} // if
// Install the all-trusting trust manager
try {
context = com.sun.net.ssl.SSLContext.getInstance("SSL");
context.init(null, __trustManagers, new SecureRandom());
} catch (GeneralSecurityException gse) {
throw new IllegalStateException(gse.getMessage());
} // catch
com.sun.net.ssl.HttpsURLConnection.setDefaultSSLSocketFactory(context
.getSocketFactory());
} // __trustAllHttpsCertificates
/**
* Return true if the protocol handler property java. protocol.handler.pkgs
* is set to the Sun's com.sun.net.ssl. internal.www.protocol deprecated
* one, false otherwise.
*
* @return true if the protocol handler property is set to the Sun's
* deprecated one, false otherwise.
*/
private static boolean isDeprecatedSSLProtocol() {
return ("com.sun.net.ssl.internal.www.protocol".equals(System
.getProperty("java.protocol.handler.pkgs")));
} // isDeprecatedSSLProtocol
/**
* Set the default Hostname Verifier to an instance of a fake class that
* trust all hostnames.
*/
private static void _trustAllHostnames() {
// Create a trust manager that does not validate certificate chains
if (_hostnameVerifier == null) {
_hostnameVerifier = new FakeHostnameVerifier();
} // if
// Install the all-trusting host name verifier:
HttpsURLConnection.setDefaultHostnameVerifier(_hostnameVerifier);
} // _trustAllHttpsCertificates
/**
* Set the default X509 Trust Manager to an instance of a fake class that
* trust all certificates, even the self-signed ones.
*/
private static void _trustAllHttpsCertificates() {
SSLContext context;
// Create a trust manager that does not validate certificate chains
if (_trustManagers == null) {
_trustManagers = new TrustManager[] { new FakeX509TrustManager() };
} // if
// Install the all-trusting trust manager:
try {
context = SSLContext.getInstance("SSL");
context.init(null, _trustManagers, new SecureRandom());
} catch (GeneralSecurityException gse) {
throw new IllegalStateException(gse.getMessage());
} // catch
HttpsURLConnection.setDefaultSSLSocketFactory(context
.getSocketFactory());
} // _trustAllHttpsCertificates
/**
* Set the default Hostname Verifier to an instance of a fake class that
* trust all hostnames.
*/
public static void trustAllHostnames() {
// Is the deprecated protocol setted?
if (isDeprecatedSSLProtocol()) {
__trustAllHostnames();
} else {
_trustAllHostnames();
} // else
} // trustAllHostnames
/**
* Set the default X509 Trust Manager to an instance of a fake class that
* trust all certificates, even the self-signed ones.
*/
public static void trustAllHttpsCertificates() {
// Is the deprecated protocol setted?
if (isDeprecatedSSLProtocol()) {
__trustAllHttpsCertificates();
} else {
_trustAllHttpsCertificates();
} // else
} // trustAllHttpsCertificates
/**
* This class implements a fake hostname verificator, trusting any host
* name. This class uses the old deprecated API from the com.sun. ssl
* package.
*
* @author Francis Labrie
*
* @deprecated see {@link SSLUtilities.FakeHostnameVerifier}.
*/
public static class _FakeHostnameVerifier implements
com.sun.net.ssl.HostnameVerifier {
/**
* Always return true, indicating that the host name is an acceptable
* match with the server's authentication scheme.
*
* @param hostname
* the host name.
* @param session
* the SSL session used on the connection to host.
* @return the true boolean value indicating the host name is trusted.
*/
public boolean verify(String hostname, String session) {
return (true);
} // verify
} // _FakeHostnameVerifier
/**
* This class allow any X509 certificates to be used to authenticate the
* remote side of a secure socket, including self-signed certificates. This
* class uses the old deprecated API from the com.sun.ssl package.
*
* @author Francis Labrie
*
* @deprecated see {@link SSLUtilities.FakeX509TrustManager}.
*/
public static class _FakeX509TrustManager implements
com.sun.net.ssl.X509TrustManager {
/**
* Empty array of certificate authority certificates.
*/
private static final X509Certificate[] _AcceptedIssuers = new X509Certificate[] {};
/**
* Always return true, trusting for client SSL chain peer certificate
* chain.
*
* @param chain
* the peer certificate chain.
* @return the true boolean value indicating the chain is trusted.
*/
public boolean isClientTrusted(X509Certificate[] chain) {
return (true);
} // checkClientTrusted
/**
* Always return true, trusting for server SSL chain peer certificate
* chain.
*
* @param chain
* the peer certificate chain.
* @return the true boolean value indicating the chain is trusted.
*/
public boolean isServerTrusted(X509Certificate[] chain) {
return (true);
} // checkServerTrusted
/**
* Return an empty array of certificate authority certificates which are
* trusted for authenticating peers.
*
* @return a empty array of issuer certificates.
*/
public X509Certificate[] getAcceptedIssuers() {
return (_AcceptedIssuers);
} // getAcceptedIssuers
} // _FakeX509TrustManager
/**
* This class implements a fake hostname verificator, trusting any host
* name.
*
* @author Francis Labrie
*/
public static class FakeHostnameVerifier implements HostnameVerifier {
/**
* Always return true, indicating that the host name is an acceptable
* match with the server's authentication scheme.
*
* @param hostname
* the host name.
* @param session
* the SSL session used on the connection to host.
* @return the true boolean value indicating the host name is trusted.
*/
public boolean verify(String hostname, javax.net.ssl.SSLSession session) {
return (true);
} // verify
} // FakeHostnameVerifier
/**
* This class allow any X509 certificates to be used to authenticate the
* remote side of a secure socket, including self-signed certificates.
*
* @author Francis Labrie
*/
public static class FakeX509TrustManager implements X509TrustManager {
/**
* Empty array of certificate authority certificates.
*/
private static final X509Certificate[] _AcceptedIssuers = new X509Certificate[] {};
/**
* Always trust for client SSL chain peer certificate chain with any
* authType authentication types.
*
* @param chain
* the peer certificate chain.
* @param authType
* the authentication type based on the client certificate.
*/
public void checkClientTrusted(X509Certificate[] chain, String authType) {
} // checkClientTrusted
/**
* Always trust for server SSL chain peer certificate chain with any
* authType exchange algorithm types.
*
* @param chain
* the peer certificate chain.
* @param authType
* the key exchange algorithm used.
*/
public void checkServerTrusted(X509Certificate[] chain, String authType) {
} // checkServerTrusted
/**
* Return an empty array of certificate authority certificates which are
* trusted for authenticating peers.
*
* @return a empty array of issuer certificates.
*/
public X509Certificate[] getAcceptedIssuers() {
return (_AcceptedIssuers);
} // getAcceptedIssuers
} // FakeX509TrustManager
} // SSLUtilities
下面就是取得联系人的过程了
13.IContactFetcher接口
[java] view
plaincopy
package org.gc.contact.fetcher;
import java.util.List;
import org.gc.contact.exception.HttpBrowserException;
import org.gc.contact.exception.HttpServerException;
import org.gc.contact.exception.ProtocolException;
import org.gc.contact.model.ContactInfo;
public interface IContactFetcher {
void doLogin() throws HttpBrowserException, HttpServerException, ProtocolException;
List<ContactInfo> fetchContactInfo() throws HttpBrowserException, HttpServerException, ProtocolException;
}
14.AbstractContactFetcher类
[java] view
plaincopy
package org.gc.contact.fetcher;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.gc.contact.exception.ExceptionMessage;
import org.gc.contact.exception.ProtocolException;
import org.gc.contact.http.HttpBrowser;
import org.gc.contact.util.RegexpUtil;
public abstract class AbstractContactFetcher implements IContactFetcher {
protected final Log logger = LogFactory.getLog(getClass());
protected final HttpBrowser browser;
protected String username;
protected String password;
public AbstractContactFetcher(String username, String password) {
this.username = username;
this.password = password;
browser = new HttpBrowser();
}
protected String getJSRedirection(String htmlContent) throws ProtocolException {
Pattern p = RegexpUtil.getJSRedirectionRegexp();
Matcher matcher = p.matcher(htmlContent);
if (!matcher.find()) {
String msg = ExceptionMessage.PROTOCOL_MSG + "[Type=JSRedirection,Regexp=" + p.pattern() + "]";
logger.error(msg);
throw new ProtocolException(msg);
}
if (logger.isDebugEnabled()) {
logger.debug("Redirection URL = " + matcher.group(1));
}
return matcher.group(1);
}
protected String getFormInputValue(String name, String htmlContent) throws ProtocolException {
Pattern p = RegexpUtil.getFormInputValueRegexp();
int index = htmlContent.indexOf(name);
int prePos = index - 400 > 0 ? index - 400 : 0;
int postPos = index + 400 < htmlContent.length() ? index + 400 : htmlContent.length();
int start = htmlContent.substring(prePos, index).lastIndexOf("<input") + prePos;
int end = htmlContent.substring(index, postPos).indexOf(">") + index;
String htmlInput = htmlContent.substring(start, end + 1);
if (logger.isDebugEnabled()) {
logger.debug("HtmlInput=" + htmlInput);
}
Matcher matcher = p.matcher(htmlInput);
if (!matcher.find()) {
String msg = ExceptionMessage.PROTOCOL_MSG + "[Type=FormInputValue,Regexp=" + p.pattern() + "]";
logger.error(msg);
throw new ProtocolException(msg);
}
if (logger.isDebugEnabled()) {
logger.debug("Name = " + name + ";value = " + matcher.group(1));
}
return matcher.group(1);
}
protected String getHost(String url) throws ProtocolException {
Pattern p = RegexpUtil.getHostFromURIRegexp();
Matcher matcher = p.matcher(url);
if (!matcher.find()) {
String msg = ExceptionMessage.PROTOCOL_MSG + "[Type=Host,Regexp=" + p.pattern() + "]";
logger.error(msg);
throw new ProtocolException(msg);
}
if (logger.isDebugEnabled()) {
logger.debug("Host = " + matcher.group(1));
}
return matcher.group(1);
}
protected List<String> getValue(Pattern p, String htmlContent) throws ProtocolException {
List<String> data = new ArrayList<String>();
Matcher matcher = p.matcher(htmlContent);
while (matcher.find()) {
try {
data.add(matcher.group(1));
if (logger.isDebugEnabled()) {
logger.debug("Matched String=" + matcher.group(1));
}
} catch (Exception e) {
String msg = ExceptionMessage.PROTOCOL_MSG + "[Type=getValue,Regexp=" + p.pattern() + "]";
logger.error(msg);
throw new ProtocolException(msg);
}
}
if (data.size() == 0) {
String msg = ExceptionMessage.PROTOCOL_MSG + "[Type=getValue,Regexp=" + p.pattern() + "]";
logger.warn(msg);
}
return data;
}
}
15.取163的联系人
[java] view
plaincopy
package org.gc.contact.fetcher;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Pattern;
import org.apache.commons.httpclient.NameValuePair;
import org.gc.contact.exception.HttpBrowserException;
import org.gc.contact.exception.HttpServerException;
import org.gc.contact.exception.ProtocolException;
import org.gc.contact.http.HttpResponse;
import org.gc.contact.model.ContactInfo;
/**
* @163.com邮箱取地址本过程
* 1. loginUrl
* 2. window.location.replace("url")
* 3. fetch address list
*
*/
public class Mail163ContactFetcher extends AbstractContactFetcher {
private final String loginUrl = "http://reg.163.com/login.jsp?type=1&product=mail163&url=http://entry.mail.163.com/coremail/fcg/ntesdoor2?lightweight%3D1%26verifycookie%3D1%26language%3D-1%26style%3D35";
/**
* fetch url
* http://g1a61.mail.163.com/jy3/address/addrlist.jsp?sid=SBmtqsXXQmCXunRFLtXXXfowbRxMPUUX&gid=all
*/
private String fetchUrl;
private final String REGEXP_USER = "<td class=/"Ibx_Td_addrName/"><a href="/" mce_href="/""addrdetail.jsp//?sid=.+&gid=all/" title=/".+/">(.+)</a></td>";
private final String REGEXP_EMAIL = "<td class=/"Ibx_Td_addrEmail/"><a href="/" mce_href="/""addrdetail.jsp//?sid=.+&gid=all/" title=/".+/">(.+)</a></td>";
private final Pattern PATTERN_USER = Pattern.compile(REGEXP_USER);
private final Pattern PATTERN_EMAIL = Pattern.compile(REGEXP_EMAIL);
public Mail163ContactFetcher(String username, String password) {
super(username, password);
}
@Override
public void doLogin() throws HttpBrowserException, HttpServerException, ProtocolException {
NameValuePair[] loginParams = makeLoginParams();
HttpResponse redirectPage = browser.doPost(loginUrl, loginParams);
String redirectUrl = getJSRedirection(redirectPage.getBodyAsString());
HttpResponse mainPage = browser.doGet(redirectUrl);
fetchUrl = mainPage.getResponseUrl();
}
@Override
public List<ContactInfo> fetchContactInfo() throws HttpBrowserException, HttpServerException, ProtocolException {
List<ContactInfo> contacts = new ArrayList<ContactInfo>();
String contactUrl = fetchUrl.replace("main.jsp", "address/addrlist.jsp");
contactUrl += "&gid=all";
HttpResponse contactPage = browser.doGet(contactUrl);
String html = contactPage.getBodyAsString();
//为了匹配,每个td一行
html = html.replace("</td>", "</td>/n");
List<String> username = getValue(PATTERN_USER, html);
List<String> email = getValue(PATTERN_EMAIL, html);
for (int i = 0; i < username.size(); i++) {
contacts.add(new ContactInfo(username.get(i), email.get(i)));
}
return contacts;
}
private NameValuePair[] makeLoginParams() {
return new NameValuePair[] {
new NameValuePair("username", username),
new NameValuePair("password", password)
};
}
}
相关文章推荐
- 导入msn和邮箱联系人列表——向大家推荐contact-list-java调用
- 黑马程序员——【Java高新技术】——JDK1.5新特性:静态导入、可变参数、增强型for循环、自动装箱拆箱、枚举
- excel导入导出--Java
- java 导入xls文件
- JAVA实现excel表格导出,(IDEA 导入jar包操作)
- eclipse导入java项目出现多处错误解决方案
- java导入/导出excel表
- java处理emoji,导入mysql
- 【JavaWeb开发】使用java实现简单的Excel文件的导入与导出(POI)
- eclipse导入项目,java文件中文乱码
- Java不写文件,LOAD DATA LOCAL INFILE大批量导入数据到MySQL的实现
- java excel打包成zip 导入zip先解压
- java使用POI操作excel文件,实现批量导出,和导入
- java的poi技术读取和导入Excel
- java导入导出excel操作(jxl)
- GitHub中Java项目导入eclipse报错selection cannot be launched
- sqluldr2全量数据库导入导出和java-java语言介入(3)
- Java类型信息与用反射机制编写通用的Excel导入导出
- 将安全证书导入到java的cacerts证书库
- java对AD域的密码修改!!证书导入!!!