我需要将一个pdf文件从网络服务器下载到我的电脑并将其保存在本地。
我使用Httpclient连接到webserver并获取内容正文：
HttpEntity entity=response.getEntity();
InputStream in=entity.getContent();
String stream = CharStreams.toString(new InputStreamReader(in));
int size=stream.length();
System.out.println("stringa html page LENGTH:"+stream.length());
System.out.println(stream);
SaveToFile(stream);
然后我将内容保存在文件中：
//check CRLF (i don't know if i need to to this)
String[] fix=stream.split("\r\n");
File file=new File("C:\\Users\\augusto\\Desktop\\progetti web\\test\\test2.pdf");
PrintWriter out = new PrintWriter(new FileWriter(file));
for (int i = 0; i < fix.length; i++) {
out.print(fix[i]);
out.print("\n");
}
out.close();
我还尝试直接将String内容保存到文件中：
OutputStream out=new FileOutputStream("pathPdfFile");
out.write(stream.getBytes());
out.close();
但结果总是一样的：我可以打开pdf文件，但我只能看到白页。错误是围绕pdf流和endstream charset编码？ stream和endStream之间的pdf内容是否需要以其他方式进行操作？
希望这有助于避免对我想做的事情产生一些误解：
这是我的登录信息（完美运行）：
public static void postForm(){
String cookie="";
try {
System.out.println("POSTFORM ###################################");
String postURL = "http://login.libero.it/logincheck.php";
HttpPost post = new HttpPost(postURL);
post.setHeader("User-Agent", "Chrome/14.0.835.202");
post.setHeader("Referer","http://login.libero.it/?layout=m&service_id=m_mail&ret_url=http://m.mailbeta.libero.it/m/wmm/auth/check");
if(cookieVector.size()>0){
for(int i=0;i<cookieVector.size();i++){
cookie=cookie+cookieVector.elementAt(i).toString().replace("Set-Cookie:", "")+";";
}
post.setHeader("Cookie",cookie);
}
//System.out.println("sequenza cookie post:"+cookie);
List<NameValuePair> params = new ArrayList<NameValuePair>();
params.add(new BasicNameValuePair("SERVICE_ID", "m_mail"));
params.add(new BasicNameValuePair("LAYOUT", "m"));
params.add(new BasicNameValuePair("DEVICE", ""));
params.add(new BasicNameValuePair("RET_URL","http://m.mailbeta.libero.it/m/wmm/auth/check"));
params.add(new BasicNameValuePair("LOGINID", "secret"));
params.add(new BasicNameValuePair("PASSWORD", "secret"));
UrlEncodedFormEntity ent = new UrlEncodedFormEntity(params,HTTP.UTF_8);
System.out.println("stringa urlPost:"+ent.toString());
post.setEntity(ent);
HttpResponse responsePOST = client.execute(post);
System.out.println("Response postForm: " + responsePOST.getStatusLine());
Header[] allHeaders = responsePOST.getAllHeaders();
String location = "";
for (Header header : allHeaders) {
if("location".equalsIgnoreCase(header.getName())) location = header.getValue();
responsePOST.addHeader(header.getName(), header.getValue());
}
cookieVector.clear();
Header[] headerx=responsePOST.getHeaders("Set-Cookie");
System.out.println("array header:"+headerx.length);
for(int i=0;i<headerx.length;i++){
System.out.println("restituito cookie POST:"+headerx[i].getValue());
cookieVector.add(headerx[i]);
//System.out.println("cookie trovato POST:"+cookieVector.elementAt(i));
}
//System.out.println("inseriti"+cookieVector.size()+""+"elements");
//HttpEntity resEntity = responsePOST.getEntity();
// populate redirect information in response
//CONTROLLO ESITO LOGIN
if(location.contains("https://login.libero.it/logincheck.php")){
loginError=1;
}
System.out.println("Redirecting to: " + location);
//EntityUtils.consume(resEntity);
responsePOST.getEntity().consumeContent();
System.out.println("torno a GET:"+"url:"+location+"cookieVector size:"+cookieVector.size());
get(location,"http://login.libero.it/logincheck.php");
} catch (IOException ex) {
Logger.getLogger(LiberoLoginNew.class.getName()).log(Level.SEVERE, null, ex);
}
}
登录后，我可以访问文件的链接（pdf，image，doc，exc。）。在这种情况下，我们以pdf文件为例：
public static void httpConnection(String url,String referer,String cookieAuth){
try {
String location="";
String cookie="";
HttpResponse response;
HttpGet get;
HttpEntity respEntity;
Referer=referer;
System.out.println("HTTPCONNECTION ################################");
System.out.println("connessione a:"+url+"............");
get = new HttpGet(url);
if(referer.length()>0){
//httpget.setHeader("Referer",referer );
}
if(attachmentURL.size()==0){
get.setHeader("User-Agent", "Chrome/14.0.835.202");
}else{
get.setHeader("Accept-charset", "UTF-8");
get.setHeader("Content-type", "application/pdf");
}
if(cookieVector.size()>0){
System.out.println("iserisco cookie da vector");
for(int i=0;i<cookieVector.size();i++){
cookie=cookie+cookieVector.elementAt(i).toString().replace("Set-Cookie:", "")+";";
}
get.setHeader("Cookie", cookie);
}else if(cookieAuth.length()>0){
System.out.println("inserisco cookieAuth....");
System.out.println("valore cookieSession:"+cookieAuth);
get.setHeader("Cookie",cookieAuth.replace("Set-Cookie:", "")+";");
}
response = client.execute(get);
cookieVector.clear();//reset cookie
System.out.println("home get: " + response.getStatusLine());
Header[] headery=response.getAllHeaders();
for(int j=0;j<headery.length;j++){
System.out.println(headery[j].getName()+" "+" VALUE:"+" "+headery[j].getValue());
}
Header[] headerx=response.getHeaders("Set-Cookie");
System.out.println("array header:"+headerx.length);
System.out.print("httpconnection SERVER HEADERS ###############");
for(int i=0;i<headerx.length;i++){
if("location".equalsIgnoreCase(headerx[i].getName())){
location = headerx[i].getValue();
//ResponseGET.addHeader(headerx[i].getName(), header.getValue());
}
//System.out.println(headerx[i].getValue());
cookieVector.add(headerx[i]);
}
//STREAM CONTENT BODY
HttpEntity entity2=response.getEntity();
InputStream in=entity2.getContent(); <==THIS IS THE WAY I GET STREAM RESPONSE
if(attachmentURL.size()>0){
saveAttachment(in);//SAVE FILE <==
}else{
from(in,htmlpage);//Parse and grab: message title,subject,attachments. If attachments are found then come back here and execute the method saveAttachment.
in.close();
}
} catch (IOException ex) {
Logger.getLogger(LiberoLoginNew.class.getName()).log(Level.SEVERE, null, ex);
}
}
方法httpConnection有效，我可以下载文件!!
服务器响应：
Date VALUE: Fri, 18 Nov 2011 13:09:46 GMT
Server VALUE: Apache/2.2.21 (Unix) mod_jk/1.2.23
Set-Cookie VALUE: MST_PVP=tiQZO3nbl9_5f_OQXtJP32YiqQx_5f_kSh6F6Io7r3xS; Domain=m.libero.it; Path=/
Content-Type VALUE: application/octet-stream
Expires VALUE: Fri, 18 Nov 2011 15:09:46 GMT
Transfer-Encoding VALUE: chunked
回复正文的例子：
%PDF-1.7
1 0 obj % entry point
<<
/Type /Catalog
/Pages 2 0 R
＆GT; endobj
2 0 obj
<<
/Type /Pages
/MediaBox [ 0 0 200 200 ]
/Count 1
/Kids [ 3 0 R ]
>>
endobj
3 0 obj
<<
/Type /Page
/Parent 2 0 R
/Resources <<
/Font <<
/F1 4 0 R
>>
>>
/Contents 5 0 R
>>
endobj
4 0 obj
<<
/Type /Font
/Subtype /Type1
/BaseFont /Times-Roman
>>
endobj
5 0 obj % page content
<<
/Length 44
>>
stream
BT
70 50 TD
/F1 12 Tf
(Hello, world!) Tj
ET
endstream
endobj
xref
0 6
0000000000 65535 f
0000000010 00000 n
0000000079 00000 n
0000000173 00000 n
0000000301 00000 n
0000000380 00000 n
trailer
<<
/Size 6
/Root 1 0 R
>>
startxref
492
%%EOF
现在，让我们从这里开始。 请你告诉我在将文件保存到文件中需要做些什么？
＃＃＃＃＃＃＃＃＃＃＃ 解决了：要从Stream数据本地保存文件，尊重二进制数据性质，我确实喜欢这样：
public void saveFile(InputStream is){
try {
DataOutputStream out = new DataOutputStream(new BufferedOutputStream(new FileOutputStream(new File("test.pdf"))));
int c;
while((c = is.read()) != -1) {
out.writeByte(c);
}
out.close();
is.close();
}catch(IOException e) {
System.err.println("Error Writing/Reading Streams.");
}
}
如果你想要一个更有效的方法，你可以使用java.IOUtils并且这样做：
public void saveFile(InputStream is){
OutputStream os=new FileOutputStream(new File("test.pdf"));
byte[] bytes = IOUtils.toByteArray(is);
os.write(bytes);
os.close();
}
答案 0 :(得分：9)
从不 将二进制数据存储到String。
从不 使用PrintWriter获取二进制数据。
从不 逐行写入二进制文件。
我不想苛刻或不礼貌，但这三个永远不得不扎根于你的脑海！ ：）
有关如何下载二进制文件的示例，您可以看到this page。我不喜欢这个例子，因为它将整个文档缓存在内存中（如果它的大小为5GB会发生什么？）但你可以从这开始。 ：）
答案 1 :(得分：7)
使用apache FileUtils。我用一个小的PDF和一个60兆的JAR尝试了它。效果很好！
import java.io.File;
import java.io.IOException;
import java.net.URL;
import org.apache.commons.io.FileUtils;
String uri = "http://localhost:8080/PMInstaller/f1.pdf";
URL url = new URL(uri);
File destination = new File("f1.pdf");
FileUtils.copyURLToFile(url, destination);
答案 2 :(得分：3)
你不能只拿这个链接吗？
public static void downloadFile(URL from, File to, boolean overwrite) throws Exception {
if (to.exists()) {
if (!overwrite)
throw new Exception("File " + to.getAbsolutePath() + " exists already.");
if (!to.delete())
throw new Exception("Cannot delete the file " + to.getAbsolutePath() + ".");
}
int lengthTotal = 0;
try {
HttpURLConnection content = (HttpURLConnection) from.openConnection();
lengthTotal = content.getContentLength();
} catch (Exception e) {
lengthTotal = -1;
}
int lengthSoFar = 0;
InputStream is = from.openStream();
FileOutputStream fos = new FileOutputStream(to);
int lastUpdate = 0;
int c;
while ((c = is.read()) != -1) {
fos.write(c);
}
is.close();
fos.close();
}
答案 3 :(得分：0)
让jsoup努力将响应下载为字节。
Response response= Jsoup.connect(location)
.ignoreContentType(true)
.userAgent("Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:25.0) Gecko/20100101 Firefox/25.0")
.referrer("http://www.google.com")
.timeout(12000)
.execute();
使用apache commons FileUtil。
写入字节FileUtils.writeByteArrayToFile(new File(path), response.bodyAsBytes());