Merge branch 'master' of http://git.zhiweidata.top/zhangzhiwei/media_data_crawler.git

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

@@ -93,7 +93,6 @@ public class BaiduNewsCrawlerParse extends HttpClientTemplateOK {
     public static int getBaiduNewsCount(String word, String startTime, String endTime, Proxy proxy,String cookie) throws Exception {
         try {
             String result = downloadHtml(word, startTime, endTime, proxy, "newsdy", 1,cookie);
-            System.out.println(result);
             String s = result.split("找到相关新闻")[1];
             String s1 = s.split("篇")[0];
             s1 = s1.replace(",", "").replace("约", "");

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

@@ -138,6 +138,8 @@ public class BaiduTiebaCrawlerParse extends HttpClientTemplateOK {
         if(title == null || title.length() < 1) {
             title = document.select("#j_core_title_wrap > h3").text();
         }
+        String source = null;
+        source = document.select("div.card_top.clearfix > div.card_title > a").text();
         System.out.println(title);
         for(Element element : elementes) {
             String time = null;
@@ -159,7 +161,7 @@ public class BaiduTiebaCrawlerParse extends HttpClientTemplateOK {
             }
             
             if(time != null && time.length() > 1) {
-                TiebaData tbd = new TiebaData("http://tieba.baidu.com/p/"+aid, title, time, tid, null, author, content, aid);
+                TiebaData tbd = new TiebaData("http://tieba.baidu.com/p/"+aid, title, time, tid, source, author, content, aid);
                 System.out.println(tbd.toString());
                 list.add(tbd);
             }