清华大佬耗费三个月吐血整理的几百G的资源,免费分享!....>>>
可以用于处理HTTP GET请求,POST请求,过滤HTML代码等
import java.io.BufferedReader; import java.io.DataOutputStream; import java.io.InputStreamReader; import java.net.HttpURLConnection; import java.net.URL; import java.util.regex.Pattern; /** * Http操作辅助工具 * * Get和Post两者在传递参数方式上有差异 * * 1、Get: 把参数附加到url上,比如URL="http://www.abc.com?name=123&age=18" * 2、Post:请求的url不变,但在content中加入参数,如 content="name=123&age=18",然后把content加入到post中 * */ public class HttpTool { /** * GET请求数据 * @param get_url url地址 * @param content key=value形式 * @return 返回结果 * @throws Exception */ public String sendGetData(String get_url, String content) throws Exception { String result = ""; URL getUrl = null; BufferedReader reader = null; String lines = ""; HttpURLConnection connection = null; try { if (content != null && !content.equals("")) get_url = get_url + "?" + content; //get_url = get_url + "?" + URLEncoder.encode(content, "utf-8"); getUrl = new URL(get_url); connection = (HttpURLConnection) getUrl.openConnection(); connection.connect(); // 取得输入流,并使用Reader读取 reader = new BufferedReader(new InputStreamReader(connection .getInputStream(), "utf-8"));// 设置编码 while ((lines = reader.readLine()) != null) { result = result + lines; } return result; } catch (Exception e) { throw e; } finally { if (reader != null) { reader.close(); reader = null; } connection.disconnect(); } } /** * @param POST_URL url地址 * @param content key=value形式 * @return 返回结果 * @throws Exception */ public String sendPostData(String POST_URL, String content) throws Exception { HttpURLConnection connection=null; DataOutputStream out=null; BufferedReader reader=null; String line = ""; String result=""; try { URL postUrl = new URL(POST_URL); connection= (HttpURLConnection) postUrl.openConnection(); connection.setDoOutput(true);//Let the run-time system (RTS) know that we want input connection.setDoInput(true);//we want to do output. connection.setRequestMethod("POST"); connection.setUseCaches(false);// Post 请求不能使用缓存 connection.setInstanceFollowRedirects(true); connection.setRequestProperty("Content-Type",//Specify the header content type. "application/x-www-form-urlencoded"); connection.connect(); out = new DataOutputStream(connection.getOutputStream()); // Send POST output. // DataOutputStream.writeBytes将字符串中的16位的unicode字符变为utf-8的字符形式写道流里 //content = URLEncoder.encode(content, "utf-8"); out.writeBytes(content); /** * 如果url中带有多个key-value参数对,则采用下面的方式写到content中 * 正文内容其实跟get的URL中'?'后的参数字符串一致 * String content = "name=" + URLEncoder.encode ("Hitesh Agrawal") + "&profession=" + URLEncoder.encode ("Software Engineer"); out.flush(); out.close(); */ //获取结果 reader = new BufferedReader(new InputStreamReader( connection.getInputStream(), "utf-8"));// 设置编码 while ((line = reader.readLine()) != null) { result=result+line; } return result; } catch (Exception e) { throw e; }finally { if(out!=null) { out.close(); out=null; } if(reader!=null) { reader.close(); reader=null; } connection.disconnect(); } } /* * 过滤掉html里不安全的标签,不允许用户输入这些符号 */ public static String htmlFilter(String inputString) { //return inputString; String htmlStr = inputString; // 含html标签的字符串 String textStr = ""; java.util.regex.Pattern p_script; java.util.regex.Matcher m_script; try { String regEx_script = "<[s]*?(script|style)[^>]*?>[sS]*?<[s]*?/[s]*?(script|style)[s]*?>"; String regEx_onevent="on[^s]+=s*"; String regEx_hrefjs="href=javascript:"; String regEx_iframe="<[s]*?(iframe|frameset)[^>]*?>[sS]*?<[s]*?/[s]*?(iframe|frameset)[s]*?>"; String regEx_link="<[s]*?link[^>]*?/>"; htmlStr = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE).matcher(htmlStr).replaceAll(""); htmlStr=Pattern.compile(regEx_onevent, Pattern.CASE_INSENSITIVE).matcher(htmlStr).replaceAll(""); htmlStr=Pattern.compile(regEx_hrefjs, Pattern.CASE_INSENSITIVE).matcher(htmlStr).replaceAll(""); htmlStr=Pattern.compile(regEx_iframe, Pattern.CASE_INSENSITIVE).matcher(htmlStr).replaceAll(""); htmlStr=Pattern.compile(regEx_link, Pattern.CASE_INSENSITIVE).matcher(htmlStr).replaceAll(""); //p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE); // m_html = p_html.matcher(htmlStr); // htmlStr = m_html.replaceAll(""); // 过滤html标签 textStr = htmlStr; } catch (Exception e) { System.err.println("Html2Text: " + e.getMessage()); } return textStr; } public static void main(String[] args){ HttpTool ht = new HttpTool(); try { ht.sendGetData("http://www.baidu.com", ""); } catch (Exception e) { // TODO Auto-generated catch block e.printStackTrace(); } } }