- package test;
- import java.io.BufferedReader;
- import java.io.IOException;
- import java.io.InputStreamReader;
- import org.jsoup.Jsoup;
- import org.jsoup.nodes.Document;
- import org.jsoup.nodes.Element;
- import org.jsoup.select.Elements;
- public class QiuShiBaiKe {
- private static int currentPage;
- private static String split = "++++++++++++++++++++++++";
- public static void main(String[] args) throws IOException {
- System.out.println("Please input the page:");
- BufferedReader buff = new BufferedReader(new InputStreamReader(
- System.in));
- int index = 0;
- String temp;
- while (true) {
- temp = buff.readLine();
- index = toInt(temp);
- if (index == 0) {
- System.out.println("默认加载第" + (++currentPage) + "页\\n" + split);
- } else {
- currentPage = index;
- System.out.println("加载第" + currentPage + "页\\n" + split);
- }
- System.out.println(getUrl(currentPage));
- }
- }
- private static int toInt(String dd) {
- try {
- return Integer.parseInt(dd);
- } catch (NumberFormatException e) {
- return 0;
- }
- }
- private static String getUrl(int page) {
- StringBuffer sb = new StringBuffer();
- try {
- String url = "http://www.qiushibaike.com/month/page/" + page
- + "?s=4595690&slow";
- Document doc = Jsoup
- .connect(url)
- .timeout(60000)
- .userAgent(
- "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:23.0) Gecko/20100101 Firefox/23.0")
- .get();
- Elements newsHeadlines = doc.select("div.content");
- for (Element e : newsHeadlines) {
- sb.append(changeLine(e.text()));
- sb.append("\\n").append(split).append("\\n");
- }
- } catch (Exception e) {
- e.printStackTrace();
- }
- return sb.toString();
- }
- private static String changeLine(String line) {
- StringBuffer sb = new StringBuffer(line);
- for (int i = 0; i < line.length() / 60; i++) {
- sb.insert((i + 1) * 60, "\\n");
- }
- return sb.toString();
- }
- }
- //该片段来自于http://www.codesnippet.cn/detail/0112201411102.html
来源: http://www.codesnippet.cn/detail/0112201411102.html