jsoup爬取驾考题库

た入场券 2022-01-21 01:51 319阅读 0赞

为了课程设计准备数据，爬取驾考的题库，包括题目、选项、答案、解析、图片

**模型：Question **

@Entity
    public class Question {
        private int id;
        private Integer num;
        private String type;
        private String chapter;
        private String question;
        private String options;
        private String answer;
        private String analysis;
        private String picpath;
        private String picurl;
    ...
    }

目标网址：[https://www.ybjk.com/tiku/02dec.htm][https_www.ybjk.com_tiku_02dec.htm]

public void getInfo(QuestionService questionService) throws IOException {
            //1: 科目一 4: 科目四
            String url = "";
            String subject = "";
            url = "https://www.ybjk.com/tiku/02dec.htm";
            subject = "1";
    //        url = "https://www.ybjk.com/tiku/d704f.htm";
    //        subject = "4";
            int i = 1;
            while (!url.equals("")) {
                Document document = Jsoup.connect(url).timeout(4000).userAgent("Mozilla").get();
                String num = "";
                String type = "";
                String chapter = "";
                String question = "";
                String option = "";
                String answer = "";
                String analysis = "";
                String picpath = "";
                String picurl = "";
                //序号
                num = new Integer(i++).toString();
                //章节
                chapter = document.select(".h_Nav a").get(3).text();
                //题目
                question = document.selectFirst("#WinContent div strong a").text();
                //正确答案
                answer = document.selectFirst("#WinContent div ul li i u").text();
                //分析本题类型
                if (answer.equals("对") || answer.equals("错")) {
                    //判断题 0代表科目一
                    type = subject +":judge";
                } else if (answer.length() == 1) {
                    //单选题
                    type = subject + ":one";
                } else {
                    //多选题
                    type = subject + ":more";
                }
                //选择题选项
                if (type.equals(subject + ":one") || type.equals(subject + ":more")) {
                    //选项option
                    Elements elements = document.select("#WinContent div ul li");
                    int f = 0;
                    for (Element element : elements) {
                        if (f++ < 4) {
                            option += element.text() + ":";
                        }
                    }
                } else {
                    //判断题
                    option = "对:错";
                }
                //题目解析
                analysis = document.select("#NoteContent p").get(1).text();
                //图片
                Element picElement = document.selectFirst("#WinContent div div img.min");
                if (picElement != null) {
                    picurl = "https:" + picElement.attr("src");
                    writePicTo("H:/dirver_image/", subject + "_" + num + ".gif", picurl);
                } else {
                    picpath = "0";
                    picurl = "0";
                }
                System.out.println("题号: " + num);
                System.out.println("类型: " + type);
                System.out.println("章节: " + chapter);
                System.out.println("题目: " + question);
                System.out.println("选项: " + option);
                System.out.println("答案: " + answer);
                System.out.println("题解: " + analysis);
                System.out.println("图片: " + picurl);
                System.out.println("图片本地地址: " + picpath);
    
                Question question1 = new Question();
                question1.setNum(Integer.parseInt(num));
                question1.setType(type);
                question1.setChapter(chapter);
                question1.setQuestion(question);
                question1.setOptions(option);
                question1.setAnswer(answer);
                question1.setAnalysis(analysis);
                question1.setPicpath(picpath);
                question1.setPicurl(picurl);
                //保存
                questionService.add(question1);
                //下一题url
                url = "https://www.ybjk.com" + document.select("#WinContent div table tr td a").last().attr("href");
                System.out.println("url: " + url);
            }
        }
    
    
        //爬图片 path:输出路径 name:图片名(含后缀名) url:图片地址
        private void writePicTo(String path, String name, String url) {
            URL urlConn = null;
            URLConnection connection = null;
            InputStream is = null;
            OutputStream os = null;
            try {
                urlConn = new URL(url);
                //打开网址连接
                connection = urlConn.openConnection();
                //获取连接中的数据流
                is = connection.getInputStream();
                //设置输出流
                os = new FileOutputStream(new File(path + name));
                System.out.println("保存图片到: " + path + name);
                //将输入流中的数据输出到输出流中
                byte[] b = new byte[1024];
                int count = 0;
                while((count=is.read(b))!=-1){
                    os.write(b,0,count);
                }
            } catch (MalformedURLException e) {
                e.printStackTrace();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }

[https_www.ybjk.com_tiku_02dec.htm]: https://www.ybjk.com/tiku/02dec.htm