Java实现爬取往期所有双色球开奖结果功能示例

本文实例讲述了Java实现爬取往期所有双色球开奖结果功能。分享给大家供大家参考，具体如下：

梦想还是要有的，万一实现了呢？我相信经常买双色球的朋友和我都会有一个疑问，就是往期双色球的开奖结果是什么？我钟意的这一注双色球在往期是否开过一等奖，如果开过的话，基本上可以放弃这一注了，因为历史上应该没有出现过两期双色球开奖完全一致的吧？那么往期的开奖结果是什么呢？我自己用Java写了一个简易的类，爬取所有双色球开奖结果，本来想开发安卓版本的，由于UI等需要时间准备，有缘再开发吧。

import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.zip.GZIPInputStream;
public class AllBalls {
private static StringBuffer mStringBuffer;
public static void main(String[] args) {
System.out.println("正在获取...");
mStringBuffer = new StringBuffer();
String baseUrlPrefix = "http://kaijiang.zhcw.com/zhcw/html/ssq/list_";
String baseUrlSuffix = ".html";
String homeUrl = "http://kaijiang.zhcw.com/zhcw/html/ssq/list_1.html";
String pageCountContent = getHtmlString(homeUrl);
int pageCount = getPageCount(pageCountContent);
if (pageCount > 0) {
for (int i = 1; i <= pageCount; i++) {
String url = baseUrlPrefix + i + baseUrlSuffix;
String pageContent = getHtmlString(url);
if (pageContent != null && !pageContent.equals("")) {
getOneTermContent(pageContent);
} else {
System.out.println("第" + i + "页丢失");
}
try {
Thread.sleep(1200);
} catch (Exception e) {
// TODO: handle exception
}
}
File file = new File("双色球.txt");
if (file.exists()) {
file.delete();
}
try {
FileWriter writer = new FileWriter(file);
BufferedWriter bufferedWriter = new BufferedWriter(writer);
bufferedWriter.write(mStringBuffer.toString());
bufferedWriter.close();
writer.close();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
//BufferedWriter writer = new BufferedWriter(new OutputS)
} else {
System.out.println("结果页数为0");
}
System.out.println("完成！");
}
/**
* 获取总页数
* @param result
*/
private static int getPageCount(String result) {
String regex = "\\d+\">末页";
Pattern pattern = Pattern.compile(regex);
Matcher matcher = pattern.matcher(result);
String[] splits = null;
while (matcher.find()) {
String content = matcher.group();
splits = content.split("\"");
break;
}
if (splits != null && splits.length == 2) {
String countString = splits[0];
if (countString != null && !countString.equals("")) {
return Integer.parseInt(countString);
}
}
return 0;
}
/**
* 获取网页源码
* @return
*/
private static String getHtmlString(String targetUrl) {
String content = null;
HttpURLConnection connection = null;
try {
URL url = new URL(targetUrl);
connection = (HttpURLConnection) url.openConnection();
connection.setRequestMethod("POST");
connection.setRequestProperty("User-Agent", "Mozilla/4.0 (compatible; MSIE 7.0; Windows 7)");
connection.setRequestProperty("Accept", "image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, application/x-shockwave-flash, application/vnd.ms-powerpoint, application/vnd.ms-excel, application/msword, */*");
connection.setRequestProperty("Accept-Language", "zh-cn");
connection.setRequestProperty("UA-CPU", "x86");
//为什么没有deflate呢
connection.setRequestProperty("Accept-Encoding", "gzip");
connection.setRequestProperty("Content-type", "text/html");
//keep-Alive，有什么用呢，你不是在访问网站，你是在采集。嘿嘿。减轻别人的压力，也是减轻自己。
connection.setRequestProperty("Connection", "close");
//不要用cache，用了也没有什么用，因为我们不会经常对一个链接频繁访问。（针对程序）
connection.setUseCaches(false);
connection.setConnectTimeout(6 * 1000);
connection.setReadTimeout(6 * 1000);
connection.setDoOutput(true);
connection.setDoInput(true);
connection.setRequestProperty("Charset", "utf-8");
connection.connect();
if (200 == connection.getResponseCode()) {
InputStream inputStream = null;
if (connection.getContentEncoding() != null && !connection.getContentEncoding().equals("")) {
String encode = connection.getContentEncoding().toLowerCase();
if (encode != null && !encode.equals("") && encode.indexOf("gzip") >= 0) {
inputStream = new GZIPInputStream(connection.getInputStream());
}
}
if (null == inputStream) {
inputStream = connection.getInputStream();
}
BufferedReader reader = new BufferedReader(new InputStreamReader(inputStream, "utf-8"));
StringBuilder builder = new StringBuilder();
String line = null;
while ((line = reader.readLine()) != null) {
builder.append(line).append("\n");
}
content = builder.toString();
}
} catch (Exception e) {
e.printStackTrace();
} finally {
if (connection != null) {
connection.disconnect();
}
}
return content;
}
private static void getOneTermContent(String pageContent) {
String regex = "<td align=\"center\" style=\"padding-left:10px;\">[\\s\\S]+?</em></td>";
Pattern pattern = Pattern.compile(regex);
Matcher matcher = pattern.matcher(pageContent);
while (matcher.find()) {
String oneTermContent = matcher.group();
getOneTermNumbers(oneTermContent);
}
}
private static void getOneTermNumbers(String oneTermContent) {
String regex = ">\\d+<";
Pattern pattern = Pattern.compile(regex);
Matcher matcher = pattern.matcher(oneTermContent);
while (matcher.find()) {
String content = matcher.group();
String ballNumber = content.substring(1, content.length()-1);
mStringBuffer.append(ballNumber).append(" ");
}
mStringBuffer.append("\r\n");
}
}

运行结果：

更多关于java相关内容感兴趣的读者可查看本站专题：《Java网络编程技巧总结》、《Java Socket编程技巧总结》、《Java文件与目录操作技巧汇总》、《Java数据结构与算法教程》、《Java操作DOM节点技巧总结》和《Java缓存操作技巧汇总》

希望本文所述对大家java程序设计有所帮助。

您可能感兴趣的文章:

• java实现爬取知乎用户基本信息
• 详解Java两种方式简单实现：爬取网页并且保存
• Java爬虫实现爬取京东上的手机搜索页面 HttpCliient+Jsoup
• java代理实现爬取代理IP的示例
• Java实现双色球抽奖随机算法示例
• java算法实现预测双色球中奖号码
• JAVA使用爬虫抓取网站网页内容的方法
• Java爬虫实战抓取一个网站上的全部链接
• java正则表达式简单使用和网页爬虫的制作代码
• java实现简单的爬虫之今日头条
• Java爬虫抓取视频网站下载链接