apache httpclient 4 學習和例子
阿新 • • 發佈：2019-02-20
package com.eecn.warehouse.api.action; import java.util.regex.Matcher; import java.util.regex.Pattern; import org.apache.http.Header; import org.apache.http.HttpEntity; import org.apache.http.HttpHost; import org.apache.http.HttpResponse; import org.apache.http.HttpStatus; import org.apache.http.client.HttpClient; import org.apache.http.client.methods.HttpGet; import org.apache.http.entity.ContentType; import org.apache.http.impl.client.DefaultHttpClient; import org.apache.http.util.EntityUtils; public class HttpTest { public final static void main(String[] args) throws Exception { // 初始化，此處建構函式就與3.1中不同 HttpClient httpclient = new DefaultHttpClient(); HttpHost targetHost = new HttpHost("www.google.com.hk"); //HttpGet httpget = new HttpGet("http://www.apache.org/"); HttpGet httpget = new HttpGet("/"); // 檢視預設request頭部資訊 System.out.println("Accept-Charset:" + httpget.getFirstHeader("Accept-Charset")); // 以下這條如果不加會發現無論你設定Accept-Charset為gbk還是utf-8，他都會預設返回gb2312（本例針對google.cn來說） httpget.setHeader("User-Agent", "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9.1.2)"); // 用逗號分隔顯示可以同時接受多種編碼 httpget.setHeader("Accept-Language", "zh-cn,zh;q=0.5"); httpget.setHeader("Accept-Charset", "GB2312,utf-8;q=0.7,*;q=0.7"); // 驗證頭部資訊設定生效 System.out.println("Accept-Charset:" + httpget.getFirstHeader("Accept-Charset").getValue()); // Execute HTTP request System.out.println("executing request " + httpget.getURI()); HttpResponse response = httpclient.execute(targetHost, httpget); //HttpResponse response = httpclient.execute(httpget); System.out.println("----------------------------------------"); System.out.println("Location: " + response.getLastHeader("Location")); System.out.println(response.getStatusLine().getStatusCode()); System.out.println(response.getLastHeader("Content-Type")); System.out.println(response.getLastHeader("Content-Length")); System.out.println("----------------------------------------"); // 判斷頁面返回狀態判斷是否進行轉向抓取新連結 int statusCode = response.getStatusLine().getStatusCode(); if ((statusCode == HttpStatus.SC_MOVED_PERMANENTLY) || (statusCode == HttpStatus.SC_MOVED_TEMPORARILY) || (statusCode == HttpStatus.SC_SEE_OTHER) || (statusCode == HttpStatus.SC_TEMPORARY_REDIRECT)) { // 此處重定向處理 此處還未驗證 String newUri = response.getLastHeader("Location").getValue(); httpclient = new DefaultHttpClient(); httpget = new HttpGet(newUri); response = httpclient.execute(httpget); } // Get hold of the response entity HttpEntity entity = response.getEntity(); // 檢視所有返回頭部資訊 Header headers[] = response.getAllHeaders(); int ii = 0; while (ii < headers.length) { System.out.println(headers[ii].getName() + ": " + headers[ii].getValue()); ++ii; } // If the response does not enclose an entity, there is no need // to bother about connection release if (entity != null) { // 將原始碼流儲存在一個byte陣列當中，因為可能需要兩次用到該流， byte[] bytes = EntityUtils.toByteArray(entity); String charSet = ""; // 如果頭部Content-Type中包含了編碼資訊，那麼我們可以直接在此處獲取 charSet = ContentType.getOrDefault(entity).getCharset().name(); System.out.println("In header: " + charSet); // 如果頭部中沒有，那麼我們需要 檢視頁面原始碼，這個方法雖然不能說完全正確，因為有些粗糙的網頁編碼者沒有在頁面中寫頭部編碼資訊 if (charSet == "") { String regEx = "(?=<meta).*?(?<=charset=[\\'|\\\"]?)([[a-z]|[A-Z]|[0-9]|-]*)"; Pattern p = Pattern.compile(regEx, Pattern.CASE_INSENSITIVE); Matcher m = p.matcher(new String(bytes)); // 預設編碼轉成字串，因為我們的匹配中無中文，所以串中可能的亂碼對我們沒有影響 boolean result = m.find(); System.out.println(result); if (m.groupCount() == 1) { charSet = m.group(1); } else { charSet = ""; } } System.out.println("Last get: " + charSet); // 至此，我們可以將原byte陣列按照正常編碼專成字串輸出（如果找到了編碼的話） System.out.println("Encoding string is: " + new String(bytes, charSet)); } httpclient.getConnectionManager().shutdown(); } }
下面是也是一個例子：
public static String sendRequest(String[] reqXml) { HttpPost httpPost = null; String rspXml = null; try { // 構造HttpClient的例項 HttpClient httpClient = new DefaultHttpClient(); // 設定連線超時 httpClient.getParams().setIntParameter(HttpConnectionParams.CONNECTION_TIMEOUT, 10000); httpClient.getParams().setIntParameter(HttpConnectionParams.SO_TIMEOUT, 20000); httpClient.getParams().setParameter(CoreProtocolPNames.HTTP_CONTENT_CHARSET, "UTF-8"); httpPost = new HttpPost(ApiAction.SERVER_URL); //httpPost.setHeader(HTTP.CONTENT_TYPE, "charset=UTF-8"); httpPost.setHeader(HTTP.CONTENT_ENCODING, "UTF-8"); httpPost.setHeader(HTTP.USER_AGENT, "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9.1.2)"); // 用逗號分隔顯示可以同時接受多種編碼 httpPost.setHeader("Accept-Language", "zh-cn,zh;q=0.5"); httpPost.setHeader("Accept-Charset", "UTF-8;q=0.7,*;q=0.7"); //引數 List<NameValuePair> nameValuePairList = new ArrayList<NameValuePair>(); nameValuePairList.add(new BasicNameValuePair("xml", reqXml[0])); nameValuePairList.add(new BasicNameValuePair("signature", reqXml[1])); // 將引數加入到請求方法中 HttpEntity httpEntity = new UrlEncodedFormEntity(nameValuePairList, "UTF-8"); httpPost.setEntity(httpEntity); // 傳送連線 HttpResponse httpResponse = httpClient.execute(httpPost); HttpEntity rspHttpEntity = httpResponse.getEntity(); int statusCode = httpResponse.getStatusLine().getStatusCode(); if (statusCode == HttpStatus.SC_OK) { rspXml = IOUtils.toString(rspHttpEntity.getContent()); LOGGER.info("響應XML：" + rspXml); } else { LOGGER.error("http client 錯誤。錯誤碼[" + statusCode + "]"); } return rspXml; } catch (Exception e) { LOGGER.error("http client invoke error.", e); return null; } finally { if (httpPost != null) { httpPost.releaseConnection(); } } }