1.修复搜狗新闻无限死循环问题

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

@@ -406,7 +406,7 @@ public class BaiduNewsCrawlerParse extends HttpClientTemplateOK {
 		return list;
 	}
 	
-	
+	@SuppressWarnings("unchecked")
 	public static List<NewsData> getOherBaiduNewsDataByTitle(String url, String word, Proxy proxy) throws Exception{
 		List<NewsData> list = new ArrayList<NewsData>();
 		int page = 0;

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

@@ -49,7 +49,7 @@ public class SougouNewsCrawlerParse extends HttpClientTemplateOK {
 			 }
 			 String htmlBody = downloadHtml(word, 1, proxy, page);
 			 if(htmlBody != null && !htmlBody.equals("")){
-				 Map<String,Object> dataMap = analysisData(htmlBody, proxy, word);
+				 Map<String,Object> dataMap = analysisData(htmlBody, proxy, word, "normal");
 				 List<NewsData> dataList = (List<NewsData>)dataMap.get("data");
 				 list.addAll(dataList);
 				 more = (Boolean)dataMap.get("more");
@@ -67,7 +67,7 @@ public class SougouNewsCrawlerParse extends HttpClientTemplateOK {
 	public static Map<String,Object> getSougouNewsData(String word, Proxy proxy, int page) throws Exception{
 		String htmlBody = downloadHtml(word, 1, proxy, page);
 		 if(htmlBody != null && !htmlBody.equals("")){
-			 return analysisData(htmlBody, proxy, word);
+			 return analysisData(htmlBody, proxy, word, "normal");
 		 }
 		 return null;
 	}
@@ -85,7 +85,7 @@ public class SougouNewsCrawlerParse extends HttpClientTemplateOK {
 			 }
 			 String htmlBody = downloadHtml(word, 2, proxy, page);
 			 if(htmlBody != null){
-				 Map<String,Object> dataMap = analysisData(htmlBody, proxy, word);
+				 Map<String,Object> dataMap = analysisData(htmlBody, proxy, word, "normal");
 				 List<NewsData> dataList = (List<NewsData>)dataMap.get("data");
 				 list.addAll(dataList);
 				 more = (Boolean)dataMap.get("more");
@@ -168,7 +168,7 @@ public class SougouNewsCrawlerParse extends HttpClientTemplateOK {
 	 * @param @return 设定文件 
 	 * @return Map<String,Object> 返回类型
 	 */
-	private static Map<String,Object> analysisData(String htmlBody, Proxy proxy, String word) throws Exception{
+	private static Map<String,Object> analysisData(String htmlBody, Proxy proxy, String word, String type) throws Exception{
 		Map<String,Object> resultMap = new HashMap<String,Object>();
 		List<NewsData> list = new ArrayList<NewsData>();
 		boolean more = true;
@@ -228,6 +228,7 @@ public class SougouNewsCrawlerParse extends HttpClientTemplateOK {
 					logger.info("搜狗新闻数据:{}", newsData);
 					list.add(newsData);
 				}
+				if(!type.equals("other")){
 					/**采集相同新闻链接**/
 					String otherUrl = element.select("div.news-detail").select("div.news-info").select("p.news-txt").select("a#news_similar").attr("href");
 					if(otherUrl!=null && !otherUrl.equals(""))
@@ -236,9 +237,10 @@ public class SougouNewsCrawlerParse extends HttpClientTemplateOK {
 						List<NewsData> otherDataList = getOherSougouNewsData(otherLink, word, proxy);
 						list.addAll(otherDataList);
 					}
+				}
 			} catch (Exception e) {
-				e.printStackTrace();
-//				logger.error("搜狗新闻数据解析时出现问题，问题为:{}", e.fillInStackTrace());
+//				e.printStackTrace();
+				logger.error("搜狗新闻数据解析时出现问题，问题为:{}", e.fillInStackTrace());
 				continue;
 			}
 		}
@@ -271,7 +273,7 @@ public class SougouNewsCrawlerParse extends HttpClientTemplateOK {
 			 }
 			 String htmlBody = downloadHtml(url, proxy, page);
 			 if(htmlBody != null){
-				Map<String,Object> dataMap = analysisData(htmlBody, null, word);
+				Map<String,Object> dataMap = analysisData(htmlBody, null, word, "other");
 				List<NewsData> dataList = (List<NewsData>)dataMap.get("data");
 				 list.addAll(dataList);
 				 more = (Boolean)dataMap.get("more");