@ThreadSafe public class HttpClientDownloader extends AbstractDownloader
| 构造器和说明 |
|---|
HttpClientDownloader() |
| 限定符和类型 | 方法和说明 |
|---|---|
Page |
download(Request request,
Task task)
Downloads web pages and store in Page object.
|
protected String |
getContent(String charset,
org.apache.http.HttpResponse httpResponse) |
protected String |
getHtmlCharset(org.apache.http.HttpResponse httpResponse,
byte[] contentBytes) |
protected org.apache.http.client.methods.HttpUriRequest |
getHttpUriRequest(Request request,
Site site,
Map<String,String> headers) |
protected Page |
handleResponse(Request request,
String charset,
org.apache.http.HttpResponse httpResponse,
Task task) |
protected org.apache.http.client.methods.RequestBuilder |
selectRequestMethod(Request request) |
void |
setThread(int thread)
Tell the downloader how many threads the spider used.
|
protected boolean |
statusAccept(Set<Integer> acceptStatCode,
int statusCode) |
addToCycleRetry, download, download, onError, onSuccesspublic Page download(Request request, Task task)
Downloaderrequest - requesttask - taskpublic void setThread(int thread)
Downloaderthread - number of threadsprotected org.apache.http.client.methods.HttpUriRequest getHttpUriRequest(Request request, Site site, Map<String,String> headers)
protected org.apache.http.client.methods.RequestBuilder selectRequestMethod(Request request)
protected Page handleResponse(Request request, String charset, org.apache.http.HttpResponse httpResponse, Task task) throws IOException
IOExceptionprotected String getContent(String charset, org.apache.http.HttpResponse httpResponse) throws IOException
IOExceptionprotected String getHtmlCharset(org.apache.http.HttpResponse httpResponse, byte[] contentBytes) throws IOException
IOExceptionCopyright © 2016. All rights reserved.