import org.apache.poi.openxml4j.exceptions.InvalidFormatException;
import org.apache.poi.ss.usermodel.*;
import org.apache.poi.xssf.usermodel.ListAutoNumber;
import org.apache.poi.xssf.usermodel.XSSFWorkbook;
import org.jsoup.HttpStatusException;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import java.io.EOFException;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;

public class Main3 {
    public static void main(String[] args) throws IOException, InvalidFormatException {
        List<String> list = new ArrayList<>();
        // Load the Excel file
        String excelFilePath = "E:\\desktop\\ziyi\\ci.xlsx";
        Workbook workbook = new XSSFWorkbook(new File(excelFilePath));
        Sheet sheet = workbook.getSheetAt(0); // assuming you want the first sheet
        for (Row row : sheet) {
            Cell cell = row.getCell(0); // get the first column
            String keyword = cell.getStringCellValue();

            // Replace the keyword in the URL
            String url = "https://hanyu.baidu.com/s?wd="+keyword+"&ptype=zici&from=poem#detailmean";
//            Document document = Jsoup.parse(new URL(url),300000);
            Document document = null;
            try {
                document = Jsoup.connect(url).userAgent("Mozilla/5.0").timeout(30000).get();
                // 在此处添加你的解析代码...
            } catch (HttpStatusException e) {
                System.out.println("HTTP error fetching URL: " + e.getUrl());
            } catch (IOException e) {
                System.out.println("Error in connecting to URL: " + e.getMessage());
            }
            Element element = null;
            try{
                element = document.getElementById("detailmean-wrapper");
            }catch (Exception e){
                System.out.println(keyword+"没有基本字义");
            }
            Element element2 = document.getElementById("basicmean-wrapper");
//            System.out.println(element2);
            //字义
            Cell outputCell1 = row.createCell(1);
            if(!keyword.equals("百度") && element2 != null){
                String html = "";
                try {
                    html = element.toString();
                }catch (Exception e){

                    html = element2.toString();
                }
                Document parse = Jsoup.parse(html);
                Element div = parse.getElementsByTag("div").first();
//            System.out.println(div);
                if (div != null) {
                    Element element1 = div.getElementsByClass("tab-content").first();
//                System.out.println(element1);
                    if(element1 != null){
                        outputCell1.setCellValue(element1.text());
                    }else {
                        System.out.println("没有字义"+keyword);
                        list.add(keyword);
                    }
                }else {
                    System.out.println("没有字义"+keyword);
                    list.add(keyword);
                }

                // Print a message to the console
                System.out.println("Successfully parsed and wrote keyword: " + keyword);
            }else {
                System.out.println("百度一下，我没有");
                outputCell1.setCellValue("百度");
                System.out.println(keyword);
            }
        }

        System.out.println(list);
        // Save the changes to a new file
        String outputExcelFilePath = "E:\\desktop\\ziyi\\ci001.xlsx";
        try (FileOutputStream outputStream = new FileOutputStream(outputExcelFilePath)) {
            workbook.write(outputStream);
        }

        workbook.close();
    }
}