增加zaker客户端获取

src/main/java/com/zhiwei/source_forward/crawler/MediaSelfSourceCrawler.java

@@ -93,28 +93,50 @@ public class MediaSelfSourceCrawler {
             map.put("referer", url);
         }
         map.put("Connection", "close");
-        Request request = RequestUtils.wrapGet(url, map);
-        counter.add();
-        
-        httpBoot.asyncCall(request, ProxyHolder.NAT_HEAVY_PROXY).whenComplete((rs,ex) -> {
-            try {
-                if (Objects.isNull(ex)) {
-                    try {
-                        parseHtml(rs.body().string(), attr, callback);
-                    } catch (Exception e) {
-                        logger.error("解析出错", e);
+        url = dealUrl(url);
+        if(Objects.nonNull(url)) {
+            Request request = RequestUtils.wrapGet(url, map);
+            counter.add();
+            
+            httpBoot.asyncCall(request, ProxyHolder.NAT_HEAVY_PROXY).whenComplete((rs,ex) -> {
+                try {
+                    if (Objects.isNull(ex)) {
+                        try {
+                            parseHtml(rs.body().string(), attr, callback);
+                        } catch (Exception e) {
+                            logger.error("解析出错", e);
+                        }
+                    } else {
+                        logger.info("{} 搜索结果访问失败: {}", request.url().url(),ex);
                     }
-                } else {
-                    logger.info("{} 搜索结果访问失败: {}", request.url().url(),ex);
+                } finally {
+                    counter.done();
                 }
-            } finally {
-                counter.done();
-            }
-        });
+            });
+        }
         return counter;
     }
     
     /**
+     ** 链接处理 
+     * @param url
+     * @return
+     * @return String
+     */
+    private String dealUrl(String url) {
+        try {
+            if(url.startsWith("http")) {
+                if(url.contains("wap.peopleapp.com/article")) {
+                    return "https://app.peopleapp.com/WapApi/610/ArtInfoApi/getInfoUp?id=" + url.split("article")[1].split("/")[1];
+                }
+                return url;
+            }
+        } catch (Exception e) {
+        }
+        return null;
+    }
+    
+    /**
      * 
      * @Description 解析文章获取相关数据
      * @param response

src/main/java/com/zhiwei/source_forward/run/MediaSelfSource.java

@@ -32,7 +32,7 @@ public class MediaSelfSource {
     public static void main(String[] args) {
         ProxyFactory.init("zookeeper://192.168.0.11:2181?backup=192.168.0.30:2181,192.168.0.35:2181", "local", GroupType.PROVIDER, 10000002L);
         List<String> urlList = new ArrayList<>();
-        urlList.add("https://www.360kuai.com/pc/922e4596800e5ef0a?cota=3&kuai_so=1&sign=360_e39369d1&refer_scene=so_3");
+        urlList.add("http://app.myzaker.com/news/article.php?pk=5dbef675b15ec03075727503");
         List<MediaSelfSourceBean> u = MediaSelfSource.getMediaSelfSource(urlList);
         for(MediaSelfSourceBean b : u) {
             System.out.println(b.toString());

src/main/java/com/zhiwei/source_forward/util/MatchSource.java

@@ -439,7 +439,13 @@ public class MatchSource {
 				if(source!=null && source.length()>1){
 					source = "百度百家-" + source;
 				}
-			}else if(url.contains("yidianzixun.com")){
+			}else if(url.contains("app.myzaker.com")){
+                // zaker客户端
+                source = document.select("#tpl_author").first().text().trim();
+                if(source!=null && source.length()>1){
+                    source = "zaker客户端-" + source;
+                }
+            }else if(url.contains("yidianzixun.com")){
 				//一点资讯
 				if(html.contains("related_wemedia")){
 					source = html.split("media_name\":\"")[1].split("\",\"")[0].trim();
@@ -462,6 +468,13 @@ public class MatchSource {
                 if(Objects.nonNull(source) && !source.isEmpty()){
                     source = "it时代网-" + source;
                 }
+            }else if(url.contains("wap.peopleapp.com")){
+                // 人民日报客户端
+                JSONObject json = JSONObject.parseObject(html);
+                source = json.getJSONObject("data").getString("authors");
+                if(Objects.nonNull(source) && !source.isEmpty()){
+                    source = "人民日报客户端-" + source;
+                }
             }else if(url.contains("guancha.cn")){
                 // 风闻社区
                 source = document.select("div.main-tow > div.box-left > div.article-content > div:nth-child(3) > div.user-main > h4 > a").text();