使用Java爬取網站：http://www.shicimingju.com的小說內容

代碼詳解
1.在本地創建存儲位置
2.編寫正則表達式
3.循環獲取內容
4.把內容存入文件夾中
5.判斷成功或失敗

效果演示

代碼展示

package text;import java.io.BufferedReader;import java.io.BufferedWriter;import java.io.File;import java.io.FileOutputStream;import java.io.InputStreamReader;import java.io.OutputStreamWriter;import java.net.URL;import java.util.regex.Matcher;import java.util.regex.Pattern;public class text {public static void main(String[] args) {//創建文件存放內容File file = new File("D:\\Text\\text.txt");//正則表達式String regex_content = "<p.*?>(.*?)</p>";String regex_title = "<title>(.*?)</title>";Pattern p_content = Pattern.compile(regex_content);Pattern p_title = Pattern.compile(regex_title);Matcher m_content;Matcher m_title;//循環獲取內容for (int i = 1; i <= 120; i++) {System.out.println("第" + i + "章開始下載。。。");try {URL url = new URL("http://www.shicimingju.com/book/sanguoyanyi/" + i+ ".html");BufferedReader reader = new BufferedReader(new InputStreamReader(url.openStream(), "utf8"));String str = null;BufferedWriter writer = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(file, true)));while ((str = reader.readLine()) != null) {m_title = p_title.matcher(str.toString());m_content = p_content.matcher(str.toString());boolean isEx = m_title.find();if (isEx) {String title = m_title.group();title = title.replace("<title>", "").replace("</title>", "");System.out.println(title);writer.write("第" + i + "章：" + title + "\n");}while (m_content.find()) {String content = m_content.group();content = content.replace("<p>", "").replace("</p>", "").replace("&nbsp;", "").replace("?", "");//存內容writer.write(content + "\n");}}System.out.println("第" + i + "章下載完成.........");writer.write("\n\n");writer.close();reader.close();} catch (Exception e) {System.out.println("很遺憾，本次下載失敗！！！");e.printStackTrace();}}}}

了解更多關注我喲！！！

總結

以上是生活随笔為你收集整理的java爬取小说的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。