修复百度新闻采集问题

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

@@ -224,9 +224,10 @@ public class BaiduNewsCrawlerParse extends HttpClientTemplateOK {
 				NewsData newsData = new NewsData(link, title, source, time, content, pt, word);
 				list.add(newsData);
 				/**采集相同新闻链接**/
-				if(element.select("div.c-row").select("a.c-more_link")!=null)
+				String otherUrl = element.select("div.c-row").select("a.c-more_link").attr("href");
+				if(otherUrl!=null && !otherUrl.equals(""))
 				{
-					String otherLink = "http://news.baidu.com"+element.select("div.c-row").select("a.c-more_link").attr("href");
+					String otherLink = "http://news.baidu.com" + element.select("div.c-row").select("a.c-more_link").attr("href");
 					List<NewsData> otherDataList = getOherBaiduNewsData(otherLink, word, proxy);
 					list.addAll(otherDataList);
 					ZhiWeiTools.sleep(100);

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

@@ -103,7 +103,7 @@ public class SougouNewsCrawlerParse extends HttpClientTemplateOK {
 		//获取通用请求头
 		Map<String,String> headerMap = HeaderTool.getCommonHead();
 		//获取链接地址
-		String url = getUrl(word, mode, page);
+		String url = getMediaNewsUrl(word, mode, page);
 		headerMap.put("Host", "news.sogou.com");
 		headerMap.put("Referer", url.split("&page=")[0]+"&page="+(page-1));
 		//下载数据页面
@@ -263,7 +263,7 @@ public class SougouNewsCrawlerParse extends HttpClientTemplateOK {
 	 * @param @return 设定文件 
 	 * @return String 返回类型
 	 */
-	private static String getUrl(String word, int mode ,int page){
+	private static String getMediaNewsUrl(String word, int mode ,int page){
 		String url = null;
 		if(word!=null){
 			url = "http://news.sogou.com/news?mode="+ mode +"&media=&query="