Zhihu.java
import java.util.ArrayList; import java.util.regex.Matcher; import java.util.regex.Pattern; public class Zhihu { public String question;// 问题 public String questionDescription;// 问题描述 public String zhihuUrl;// 网页链接 public ArrayList<String> answers;// 存储所有回答的数组 // 构造方法初始化数据 public Zhihu(String url) { // 初始化属性 question = ""; questionDescription = ""; zhihuUrl = ""; answers = new ArrayList<String>(); // 判断url是否合法 if (getRealUrl(url)) { System.out.println("正在抓取" + zhihuUrl); // 根据url获取该问答的细节 String content = Spider.SendGet(zhihuUrl); Pattern pattern; Matcher matcher; // 匹配标题 pattern = Pattern.compile("zh-question-title.+?<h2.+?>(.+?)</h2>"); matcher = pattern.matcher(content); if (matcher.find()) { question = matcher.group(1); } // 匹配描述 pattern = Pattern .compile("zh-question-detail.+?<div.+?>(.*?)</div>"); matcher = pattern.matcher(content); if (matcher.find()) { questionDescription = matcher.group(1); } // 匹配答案 pattern = Pattern.compile("/answer/content.+?<div.+?>(.*?)</div>"); matcher = pattern.matcher(content); boolean isFind = matcher.find(); while (isFind) { answers.add(matcher.group(1)); isFind = matcher.find(); } } } // 根据自己的url抓取自己的问题和描述和答案 public boolean getAll() { return true; } // 处理url boolean getRealUrl(String url) { // 将http://www.zhihu.com/question/22355264/answer/21102139 // 转化成http://www.zhihu.com/question/22355264 // 否则不变 Pattern pattern = Pattern.compile("question/(.*?)/"); Matcher matcher = pattern.matcher(url); if (matcher.find()) { zhihuUrl = "http://www.zhihu.com/question/" + matcher.group(1); } else { return false; } return true; } @Override public String toString() { return "问题:" + question + "\n" + "描述:" + questionDescription + "\n" + "链接:" + zhihuUrl + "\n回答:" + answers.size() + "\n"; } }
Spider.java
import java.io.BufferedReader; import java.io.InputStreamReader; import java.net.URL; import java.net.URLConnection; import java.util.ArrayList; import java.util.regex.Matcher; import java.util.regex.Pattern; public class Spider { static String SendGet(String url) { // 定义一个字符串用来存储网页内容 String result = ""; // 定义一个缓冲字符输入流 BufferedReader in = null; try { // 将string转成url对象 URL realUrl = new URL(url); // 初始化一个链接到那个url的连接 URLConnection connection = realUrl.openConnection(); // 开始实际的连接 connection.connect(); // 初始化 BufferedReader输入流来读取URL的响应 in = new BufferedReader(new InputStreamReader( connection.getInputStream(), "UTF-8")); // 用来临时存储抓取到的每一行的数据 String line; while ((line = in.readLine()) != null) { // 遍历抓取到的每一行并将其存储到result里面 result += line; } } catch (Exception e) { System.out.println("发送GET请求出现异常!" + e); e.printStackTrace(); } // 使用finally来关闭输入流 finally { try { if (in != null) { in.close(); } } catch (Exception e2) { e2.printStackTrace(); } } return result; } // 获取所有的编辑推荐的知乎内容 static ArrayList<Zhihu> GetRecommendations(String content) { // 预定义一个ArrayList来存储结果 ArrayList<Zhihu> results = new ArrayList<Zhihu>(); // 用来匹配url,也就是问题的链接 Pattern pattern = Pattern .compile("<h2>.+?question_link.+?href=\"(.+?)\".+?</h2>"); Matcher matcher = pattern.matcher(content); // 是否存在匹配成功的对象 Boolean isFind = matcher.find(); while (isFind) { // 定义一个知乎对象来存储抓取到的信息 Zhihu zhihuTemp = new Zhihu(matcher.group(1)); // 添加成功匹配的结果 results.add(zhihuTemp); // 继续查找下一个匹配对象 isFind = matcher.find(); } return results; } }
위는 Zhihu 답변(2)을 처음부터 잡기 위해 Java Zhihu 크롤러를 작성하는 내용입니다. 관련 내용은 PHP 중국어 홈페이지(www.php.cn)를 주목해주세요!