java爬取诛仙

	String indexUrl = "https://www.qu.la/book/116/92229.html";
		//创建一个输出流,将爬到的小说以txt形式保存在硬盘
		BufferedWriter bw = new BufferedWriter(new OutputStreamWriter(new FileOutputStream("D://诛仙"+".txt")));
		while (true) {
			//2. 发送请求, 获取数据
			//2.1 创建httpClient对象
			CloseableHttpClient httpClient = HttpClients.createDefault();

			//2.2 设置请求方式
			HttpGet httpGet = new HttpGet(indexUrl);
			//2.3 设置请求参数 和请求头
			httpGet.setHeader("User-Agent",
					"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36");

			//2.4 发送请求, 获取响应
			CloseableHttpResponse response = httpClient.execute(httpGet);
			//2.5 获取数据

			String html = EntityUtils.toString(response.getEntity(), "UTF-8");

			//3. 解析数据:
			Document document2 = Jsoup.parse(html);
			//获得本章的章节名称 并输出到文本中
			Elements chapterName = document2.select("h1");
			System.err.println(chapterName.text());

			
			bw.write(chapterName.text());
			bw.newLine();
			bw.flush();

			//获得本章的小说内容 并输出到文本中
			Elements pEl = document2.select("#content");
			for (Element p : pEl) {
				System.err.println("p.text():"+p.text());
				bw.write(p.text());
				//System.out.println(p.text());
				bw.newLine();
				bw.flush();
			}

			//下一章内容:

			Element aEl = document2.select(".bottem2>a[href*=html]").last();
			System.err.println(aEl);
			System.err.println("aEl:"+aEl);
			if (aEl == null) {
				break;
			}
			if(document2.select(".bottem2>a[href*=html]").size()<2) {
				break;
			}
			String nextUrl = aEl.attr("href");
			System.err.println(nextUrl);
			indexUrl = "https://www.qu.la/book/116/" + nextUrl;
			System.out.println(indexUrl);
//			//4. 关闭httpClient对象
			httpClient.close();
		}