小偷采集，有经验的猿猿应该都会做，我借此做一个回忆。
2013年我就职盛大文学，当时因文学版权、流量等问题，做了一套监控系统，用来监控当时的创世、龙空、纵横等等比较知名中文网站。对于监控，我还可以自吹一下经验满满。
当下社会，正是监控系统兴风作浪的大好时机，而且有利可图。
举例说明一下：
1、公共wifi，收集用户的部分信息，地理坐标，连接时长，搜索内容等等，通过数据分析给用户贴上标签[吃货]、[美娇娘]、[剁手党] 等等，然后将信息打包贩卖，基本能买到好几块一条呐。
2、通过采集获得大量的优秀文章，将其精修后可作为一些书籍的底稿来用，而且这些底稿可以换钱滴。
3、搜索大网站的用户信息，比如就搜索cnblogs的推荐博客博主，把他们的信息down下来，整理分析，贴上[淫才]标签，打包贩卖，至少得30块一条吧。
4、如果能有幸通过一些高级酒店的网站，搜索到一些零碎的用户信息，并将其整理、拼接、合成比较完整的用户信息，这些皇冠级用户信息拿到4S、售楼处贩卖，怎么着一条信息也得小一百吧。
...
不用再写下去了，监控能创造出巨额利益。
开始教做最简单的小偷。当然这篇小偷偷的就是cnblogs，学会了可不要乱搞，搞坏了谁负责？
java编写，需要引入绿色框的包 mysql-connector-java-5.1.13.jar，用来连接mysql数据库，如果采集信息不入库，则可以不用下载此包。
jdk1.8.0_112
黄色框内是方法：
downhtml 下载HTML内容
downImages 下载图片
GetDocument 下载博客日志
GetList 下载精华区列表
InsertMysql 博客入库
main 程序入口
蓝色框内是正则匹配式和一些配置 信息：
contectPattern 正则匹配出内容
imgPattern 正则匹配出图片
listPattern 正则匹配出精华区列表
localPath 下载的图片本地存放路径
pickFormat 精华区url Formatter
webSite 你的网站
主要结构
蓝色框总剖析
// 精选列表Formatter private static String pickFormat = "https://www.cnblogs.com/pick/%s/"; //获取图片url的正则表达式 private static Pattern imgPattern = Pattern.compile(""(?<head>http(s|))://(?<url>[^"]+).(?<tp>PNG|png|JPG|jpg|GIF|gif)""); //获取精华列表的正则表达式 private static Pattern listPattern = Pattern.compile("<div class="post_item_body">\s*<h3><a class="titlelnk" href="(?<url>[^"]+)" target="_blank">(?<title>[^<]+)</a></h3>\s*<p class="post_item_summary">\s*(<a[\s\S]+?alt=""/></a>){0,1}(?<connect>[^<]+)</p>\s*<div class="post_item_foot">\s*<a[\s\S]+?<span class="article_comment"><a[\s\S]+?class="gray">(?<ping>[^<]+)</a></span><span class="article_view"><a[\s\S]+?class="gray">(?<yue>[^<]+)</a></span></div>\s*</div>"); //获取博客内容的正则表达式 private static Pattern contectPattern = Pattern.compile("<div id="cnblogs_post_body">(?<conect>[\s\S]+?)</div><div id="MySignature"></div>"); //网站放置下载图片的路径 private static String webSite = "http://www.Website.com/loadimages/"; //本地下载图片的路径 private static String localPath = "D:\WWW\loadimages\";
DownHtml剖析
/** * 下载html * * @param url * 博客URL * @return html的内容 */ static String downhtml(String url) throws UnsupportedEncodingException, IOException{ BufferedReader br = new BufferedReader(new InputStreamReader(new URL(url).openStream(), "utf-8")); StringBuffer stringBuffer = new StringBuffer(); String read = ""; while ((read = br.readLine()) != null) { if (stringBuffer.length() == 0) { stringBuffer.append(read); } else { stringBuffer.append(" ").append(read); } } br.close(); return stringBuffer.toString(); }
DownImages剖析
/** * 下载网络图片到本地 * * @param imgUrl * 图片URL * @param imgName * 保存到本地名称 */ static void downImages(String imgUrl, String imgName) { System.out.println("downfile --> " + imgName + " " + imgUrl); try { URL url = new URL(imgUrl); URLConnection conn = url.openConnection(); conn.setConnectTimeout(10000); InputStream inStream = conn.getInputStream(); FileOutputStream fs = new FileOutputStream(imgName); int byteread = 0; byte[] buffer = new byte[1204]; while ((byteread = inStream.read(buffer)) != -1) { fs.write(buffer, 0, byteread); } fs.close(); } catch (IOException e) { System.err.println(e.getStackTrace()); } }
GetList剖析
/** * 下载精华区列表 */ static void GetList() { for (int i = 1; i < 80; i++) { try { Thread.sleep(7777); String url = String.format(pickFormat, i); //得到第一条是https://www.cnblogs.com/pick/1/ 精华区列表第一页 String html = downhtml(url);//下载精华区 Matcher listMatcher = listPattern.matcher(html);//匹配精华区列表 while (listMatcher.find()) { String title = listMatcher.group("title");//博客标题 url = listMatcher.group("url");//博客URL System.out.println(title + " " + url); GetDocument(url, title);//下载博客内容 Thread.sleep(7777); } } catch (Exception e) { System.err.println(e.getStackTrace()); } } }
GetDocument剖析
/** * 下载博客日志 */ static void GetDocument(String url, String title) { try { String html = downhtml(url);//下载博客日志 System.out.println("html.length --> " + html.length()); Matcher contectMatcher = contectPattern.matcher(html);//匹配博客内容 if (contectMatcher.find()) { String content = contectMatcher.group("conect");//获得博客内容 //图片的url去重复 HashMap<String, String> map = new HashMap<String, String>(); Matcher imgMatcher = imgPattern.matcher(content);//匹配博客图片url while (imgMatcher.find()) { String matVal = imgMatcher.group(); String webUrl = matVal.substring(1, matVal.length() - 1); if (map.containsKey(webUrl)) continue; String fileName = UUID.randomUUID().toString().replace("-", "") + "." + imgMatcher.group("tp");//保存本地随机生成图片名 String fullName = localPath + fileName;//保存图片的全路径 String webFileName = webSite + fileName;//博客内容需要转换的新图片url downImages(webUrl, fullName);//下载图片 map.put(webUrl, webFileName); try { Thread.sleep(333); } catch (InterruptedException e) { System.err.println(e.getStackTrace()); } } //将cnblogs的图片url替换成预设网站的url for (Entry<String, String> entry : map.entrySet()) { content = content.replace(entry.getKey(), entry.getValue()); } System.out.println("Match content --> " + content.substring(0, 50)); InsertMysql(title, content);//入库 } } catch (IOException e) { System.err.println(e.getStackTrace()); } }
InsertMysql剖析
//博客入库 static void InsertMysql(String title, String content) { String url = "jdbc:mysql://localhost:3306/wordpress"; String user = "root"; String password = "root"; Connection connection = null; PreparedStatement preparedStatement = null; try { Class.forName("com.mysql.jdbc.Driver"); connection = DriverManager.getConnection(url, user, password); preparedStatement = connection .prepareStatement("INSERT INTO wordpress.wp_posts " + "(post_author, " + "post_date, " + "post_date_gmt, " + "post_content, " + "post_title, " + "post_excerpt, " + "post_status, " + "comment_status, " + "ping_status, " + "post_password, " + "post_name, " + "to_ping, " + "pinged, " + "post_modified, " + "post_modified_gmt, " + "post_content_filtered, " + "post_parent, " + "guid, " + "menu_order, " + "post_type, " + "post_mime_type, " + "comment_count" + ")" + "VALUES" + "(1, " + "now(), " + "now(), " + "?, " + "?, " + "'', " + "'publish', " + "'open', " + "'open', " + "'', " + "'', " + "'', " + "'', " + "now(), " + "now(), " + "'', " + "0, " + "'', " + "0, " + "'post', " + "'', " + "0" + ");"); preparedStatement.setString(1, content); preparedStatement.setString(2, title); System.out.println(preparedStatement.executeUpdate() + " " + title); } catch (Exception e) { System.err.println(e.getStackTrace()); } finally { if (preparedStatement != null) try { preparedStatement.close(); } catch (SQLException e) { System.err.println(e.getStackTrace()); } if (connection != null) try { connection.close(); } catch (SQLException e) { System.err.println(e.getStackTrace()); } } }
完整代码（本人喜欢随性乱涂，代码基本无注释，抱歉）
import java.io.BufferedReader; import java.io.FileOutputStream; import java.io.IOException; import java.io.InputStream; import java.io.InputStreamReader; import java.io.UnsupportedEncodingException; import java.net.URL; import java.net.URLConnection; import java.util.HashMap; import java.util.Map.Entry; import java.util.UUID; import java.util.regex.Matcher; import java.util.regex.Pattern; import java.sql.Connection; import java.sql.DriverManager; import java.sql.PreparedStatement; import java.sql.SQLException; public class appCnblogsCollect { // 精选列表Formatter private static String pickFormat = "https://www.cnblogs.com/pick/%s/"; //获取图片url的正则表达式 private static Pattern imgPattern = Pattern.compile(""(?<head>http(s|))://(?<url>[^"]+).(?<tp>PNG|png|JPG|jpg|GIF|gif)""); //获取精华列表的正则表达式 private static Pattern listPattern = Pattern.compile("<div class="post_item_body">\s*<h3><a class="titlelnk" href="(?<url>[^"]+)" target="_blank">(?<title>[^<]+)</a></h3>\s*<p class="post_item_summary">\s*(<a[\s\S]+?alt=""/></a>){0,1}(?<connect>[^<]+)</p>\s*<div class="post_item_foot">\s*<a[\s\S]+?<span class="article_comment"><a[\s\S]+?class="gray">(?<ping>[^<]+)</a></span><span class="article_view"><a[\s\S]+?class="gray">(?<yue>[^<]+)</a></span></div>\s*</div>"); //获取博客内容的正则表达式 private static Pattern contectPattern = Pattern.compile("<div id="cnblogs_post_body">(?<conect>[\s\S]+?)</div><div id="MySignature"></div>"); //网站放置下载图片的路径 private static String webSite = "http://www.Website.com/loadimages/"; //本地下载图片的路径 private static String localPath = "D:\WWW\loadimages\"; public static void main(String[] args) throws Exception { GetList(); } /** * 下载精华区列表 */ static void GetList() { for (int i = 1; i < 80; i++) { try { Thread.sleep(7777); String url = String.format(pickFormat, i); //得到第一条是https://www.cnblogs.com/pick/1/ 精华区列表第一页 String html = downhtml(url);//下载精华区 Matcher listMatcher = listPattern.matcher(html); while (listMatcher.find()) { String title = listMatcher.group("title"); url = listMatcher.group("url"); System.out.println(title + " " + url); GetDocument(url, title); Thread.sleep(7777); } } catch (Exception e) { System.err.println(e.getStackTrace()); } } } /** * 下载博客日志 */ static void GetDocument(String url, String title) { try { String html = downhtml(url); System.out.println("html.length --> " + html.length()); Matcher contectMatcher = contectPattern.matcher(html); if (contectMatcher.find()) { String content = contectMatcher.group("conect"); //图片的url去重复 HashMap<String, String> map = new HashMap<String, String>(); Matcher imgMatcher = imgPattern.matcher(content); while (imgMatcher.find()) { String matVal = imgMatcher.group(); String webUrl = matVal.substring(1, matVal.length() - 1); if (map.containsKey(webUrl)) continue; String fileName = UUID.randomUUID().toString().replace("-", "") + "." + imgMatcher.group("tp"); String fullName = localPath + fileName; String webFileName = webSite + fileName; downImages(webUrl, fullName); map.put(webUrl, webFileName); try { Thread.sleep(333); } catch (InterruptedException e) { System.err.println(e.getStackTrace()); } } //将cnblogs的图片url替换成预设网站的url for (Entry<String, String> entry : map.entrySet()) { content = content.replace(entry.getKey(), entry.getValue()); } System.out.println("Match content --> " + content.substring(0, 50)); InsertMysql(title, content); } } catch (IOException e) { System.err.println(e.getStackTrace()); } } /** * 下载html * * @param url * 博客URL * @return html的内容 */ static String downhtml(String url) throws UnsupportedEncodingException, IOException{ BufferedReader br = new BufferedReader(new InputStreamReader(new URL(url).openStream(), "utf-8")); StringBuffer stringBuffer = new StringBuffer(); String read = ""; while ((read = br.readLine()) != null) { if (stringBuffer.length() == 0) { stringBuffer.append(read); } else { stringBuffer.append(" ").append(read); } } br.close(); return stringBuffer.toString(); } /** * 下载网络图片到本地 * * @param imgUrl * 图片URL * @param imgName * 保存到本地名称 */ static void downImages(String imgUrl, String imgName) { System.out.println("downfile --> " + imgName + " " + imgUrl); try { URL url = new URL(imgUrl); URLConnection conn = url.openConnection(); conn.setConnectTimeout(10000); InputStream inStream = conn.getInputStream(); FileOutputStream fs = new FileOutputStream(imgName); int byteread = 0; byte[] buffer = new byte[1204]; while ((byteread = inStream.read(buffer)) != -1) { fs.write(buffer, 0, byteread); } fs.close(); } catch (IOException e) { System.err.println(e.getStackTrace()); } } static void InsertMysql(String title, String content) { String url = "jdbc:mysql://localhost:3306/wordpress"; String user = "root"; String password = "root"; Connection connection = null; PreparedStatement preparedStatement = null; try { Class.forName("com.mysql.jdbc.Driver"); connection = DriverManager.getConnection(url, user, password); preparedStatement = connection .prepareStatement("INSERT INTO wordpress.wp_posts " + "(post_author, " + "post_date, " + "post_date_gmt, " + "post_content, " + "post_title, " + "post_excerpt, " + "post_status, " + "comment_status, " + "ping_status, " + "post_password, " + "post_name, " + "to_ping, " + "pinged, " + "post_modified, " + "post_modified_gmt, " + "post_content_filtered, " + "post_parent, " + "guid, " + "menu_order, " + "post_type, " + "post_mime_type, " + "comment_count" + ")" + "VALUES" + "(1, " + "now(), " + "now(), " + "?, " + "?, " + "'', " + "'publish', " + "'open', " + "'open', " + "'', " + "'', " + "'', " + "'', " + "now(), " + "now(), " + "'', " + "0, " + "'', " + "0, " + "'post', " + "'', " + "0" + ");"); preparedStatement.setString(1, content); preparedStatement.setString(2, title); System.out.println(preparedStatement.executeUpdate() + " " + title); } catch (Exception e) { System.err.println(e.getStackTrace()); } finally { if (preparedStatement != null) try { preparedStatement.close(); } catch (SQLException e) { System.err.println(e.getStackTrace()); } if (connection != null) try { connection.close(); } catch (SQLException e) { System.err.println(e.getStackTrace()); } } } }
以上是一个不需要用户身份验证的例子，在某些特殊的情况下，需要身份验证怎么办？不要着急，我下面还有一个例子，下面的例子是年末统计全年工作日报，而且这个工作日报还影响绩效和考核，可是，我一年没填了，从头写是不可能了，只能做个小工具，于是就有了它，随便乱弹的，看着丑就丑吧。
package ebooks; import java.text.SimpleDateFormat; import java.util.ArrayList; import java.util.Calendar; import java.util.List; import org.apache.http.HttpResponse; import org.apache.http.NameValuePair; import org.apache.http.client.entity.UrlEncodedFormEntity; import org.apache.http.client.methods.HttpPost; import org.apache.http.impl.client.DefaultHttpClient; import org.apache.http.impl.conn.PoolingClientConnectionManager; import org.apache.http.message.BasicNameValuePair; public class appTimeSheet { public static void main(String[] args) throws Exception { String username = "username"; String password = "yourpassword"; SimpleDateFormat simpleDateFormat = new SimpleDateFormat("yyyy-MM-dd hh:mm:ss"); String urlLogin = "http://10.54.11.37:8989/login"; String urlSave = "http://10.54.11.37:8989/agenda/submission/saveTimereg.json"; DefaultHttpClient client = new DefaultHttpClient(new PoolingClientConnectionManager()); HttpPost loginHttpPost = new HttpPost(urlLogin); List<NameValuePair> loginPairs = new ArrayList<NameValuePair>(); loginPairs.add(new BasicNameValuePair("username", username)); loginPairs.add(new BasicNameValuePair("password", password)); loginHttpPost.setEntity(new UrlEncodedFormEntity(loginPairs, "utf-8")); HttpResponse response = client.execute(loginHttpPost); System.out.println(response.getStatusLine()); Calendar calendar = Calendar.getInstance(); calendar.clear(); calendar.set(2017, 11, 24); long end = calendar.getTimeInMillis(); calendar.clear(); calendar.set(2017, 11, 4); for (; calendar.getTimeInMillis() < end; calendar.add(Calendar.DATE, 1)) { if (calendar.get(Calendar.DAY_OF_WEEK) == Calendar.SUNDAY || calendar.get(Calendar.DAY_OF_WEEK) == Calendar.SATURDAY) { continue; } HttpPost savePost = new HttpPost(urlSave); List<NameValuePair> savePairs = new ArrayList<NameValuePair>(); savePairs.add(new BasicNameValuePair("timereg", "监控室")); savePairs.add(new BasicNameValuePair("timereg", "研发项目")); savePairs.add(new BasicNameValuePair("timereg", "云平台智能服务技术的研究和应用")); savePairs.add(new BasicNameValuePair("timereg", "全部(共享类)")); switch (calendar.get(Calendar.DAY_OF_WEEK)) { case Calendar.MONDAY: savePairs.add(new BasicNameValuePair("timereg", "8,0,0,0,0,0,0")); System.out.println("星期一"); break; case Calendar.TUESDAY: savePairs.add(new BasicNameValuePair("timereg", "0,8,0,0,0,0,0")); System.out.println("星期二"); break; case Calendar.WEDNESDAY: savePairs.add(new BasicNameValuePair("timereg", "0,0,8,0,0,0,0")); System.out.println("星期三"); break; case Calendar.THURSDAY: savePairs.add(new BasicNameValuePair("timereg", "0,0,0,8,0,0,0")); System.out.println("星期四"); break; case Calendar.FRIDAY: savePairs.add(new BasicNameValuePair("timereg", "0,0,0,0,8,0,0")); System.out.println("星期五"); break; } savePairs.add(new BasicNameValuePair("timereg", "监控系统开发与应用")); savePairs.add(new BasicNameValuePair("timereg", "8")); savePairs .add(new BasicNameValuePair("theweek", Integer.toString(calendar.get(Calendar.WEEK_OF_YEAR) + 1))); System.out.println("第" + (calendar.get(Calendar.WEEK_OF_YEAR) + 1) + "周"); savePairs.add(new BasicNameValuePair("starttime", simpleDateFormat.format(calendar.getTime()))); System.out.println("starttime=" + simpleDateFormat.format(calendar.getTime())); savePost.setEntity(new UrlEncodedFormEntity(savePairs, "utf-8")); HttpResponse saveResponse = client.execute(savePost); System.out.println(saveResponse.getStatusLine()); System.out.println(); Thread.sleep(7777); } } }