修复知乎根据用户采集用户回答死循环问题

src/main/java/com/zhiwei/media_data_crawler/crawler/ZhihuUserAnswerCrawlerParse.java

@@ -26,32 +26,41 @@ public class ZhihuUserAnswerCrawlerParse {
     private static HttpBoot httpBoot = new HttpBoot();
     
     public static List<ZhihuAnswer> getData(String userId,ProxyHolder proxy) {
+    	
         String url = "https://www.zhihu.com/api/v4/members/"+userId+"/answers?include=data%5B*%5D.is_normal%2Cadmin_closed_comment%2Creward_info%2Cis_collapsed%2Cannotation_action%2Cannotation_detail%2Ccollapse_reason%2Ccollapsed_by%2Csuggest_edit%2Ccomment_count%2Ccan_comment%2Ccontent%2Cvoteup_count%2Creshipment_settings%2Ccomment_permission%2Cmark_infos%2Ccreated_time%2Cupdated_time%2Creview_info%2Cquestion%2Cexcerpt%2Cis_labeled%2Clabel_info%2Crelationship.is_authorized%2Cvoting%2Cis_author%2Cis_thanked%2Cis_nothelp%3Bdata%5B*%5D.author.badge%5B%3F(type%3Dbest_answerer)%5D.topics&limit=20&sort_by=created&offset=";
         int page = 0;
         List<ZhihuAnswer> dataList = new ArrayList<>();
         Map<String,Object> headers = new HashMap<>();
 //        headers.put("referer", "https://www.zhihu.com/people/"+userId+"/answers");
 //        headers.put("user-agent", "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36");
-//        headers.put("cookie", "tgw_l7_route=116a747939468d99065d12a386ab1c5f; _xsrf=gn2oQ7N4G6yGOny4hc3T1TRr4kPOF4ij");
+//        headers.put("cookie", "_zap=37e196ce-6bf6-4680-9c40-a4b3dea72a47; _xsrf=g11of1WpkFPUYCJ88GRAlpty8bMnntT0; d_c0=\"ALDmEMw9Fw6PTsQcBCjppwDT8MbPGyQLkuo=|1534857872\"; __utma=51854390.1770583360.1534857893.1534857893.1534857893.1; __utmz=51854390.1534857893.1.1.utmcsr=baidu|utmccn=(organic)|utmcmd=organic; __utmv=51854390.000--|3=entry_date=20180821=1; z_c0=\"2|1:0|10:1545787952|4:z_c0|92:Mi4xbFFnaEFBQUFBQUFBc09ZUXpEMFhEaVlBQUFCZ0FsVk5NQ2dRWFFCUGxTLS1CczBSZWdDUzgyTFZOTmd4WHJISFR3|93b1755c91416a906602a708b0a451f7748cc1ff6fe5ee318fe2e7e15d30f101\"; tst=r; q_c1=3db855c272674e60bc301eae9948df45|1547635145000|1534857872000; tgw_l7_route=1b9b7363f02f3a5519d03bdf813bc914");
         while(true) {
             int count = 1;
-            try (Response response = httpBoot.syncCall(RequestUtils.wrapGet(url + page,headers), proxy)){
+            String urlNewww = url + page;
+//            System.out.println("urlNew================"+urlNewww);
+            
+            try (Response response = httpBoot.syncCall(RequestUtils.wrapGet(urlNewww,headers), proxy)){
                 String result = response.body().string();
                 JSONObject json = JSONObject.parseObject(result);
                 JSONArray jsonArray = json.getJSONArray("data");
-                for(int i =0;i < jsonArray.size();i++) {
-                    JSONObject data = jsonArray.getJSONObject(i);
-                    ZhihuAnswer za = new ZhihuAnswer();
-                    za.setFrom_url(userId);
-                    za.setTitle(data.getJSONObject("question").getString("title"));
-                    za.setAuthor(data.getJSONObject("author").getString("name"));
-                    za.setContent(data.getString("content").replaceAll("<.*?>", ""));
-                    za.setTime(new Date(data.getLong("created_time")*1000L));
-                    za.setUrl(data.getJSONObject("question").getString("url").replace("questions", "question")+"/answer/"+data.getString("id"));
-                    za.setAttitudes_count(data.getInteger("voteup_count"));
-                    za.setComment_count(data.getInteger("comment_count"));
-                    dataList.add(za);
+                if(jsonArray!=null && jsonArray.size()>0){
+                	 for(int i =0;i < jsonArray.size();i++) {
+                         JSONObject data = jsonArray.getJSONObject(i);
+                         ZhihuAnswer za = new ZhihuAnswer();
+                         za.setFrom_url(userId);
+                         za.setTitle(data.getJSONObject("question").getString("title"));
+                         za.setAuthor(data.getJSONObject("author").getString("name"));
+                         za.setContent(data.getString("content").replaceAll("<.*?>", ""));
+                         za.setTime(new Date(data.getLong("created_time")*1000L));
+                         za.setUrl(data.getJSONObject("question").getString("url").replace("questions", "question")+"/answer/"+data.getString("id"));
+                         za.setAttitudes_count(data.getInteger("voteup_count"));
+                         za.setComment_count(data.getInteger("comment_count"));
+                         dataList.add(za);
+                     }
+                }else{
+                	break;
                 }
+               
                 int total = json.getJSONObject("paging").getInteger("totals");
                 logger.info(" 知乎用户回答采集 {}  采集第 {} 条 ，一共采集到 {} 条 ，总条数 {}",userId,page,dataList.size(),total);
                 if(dataList.size() > total || page > total) {