搜狗修改 content解析修改

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

@@ -122,7 +122,7 @@ public class SougouNewsCrawlerParse extends HttpClientTemplateOK {
 		//获取通用请求头
 		Map<String,String> headerMap = HeaderTool.getCommonHead();
 		//获取链接地址
-		url = url + "&page" + page;
+		url = url + "&page=" + page;
 		headerMap.put("Host", "news.sogou.com");
 		headerMap.put("Referer", url);
 		//下载数据页面
@@ -189,10 +189,20 @@ public class SougouNewsCrawlerParse extends HttpClientTemplateOK {
 				}
 				if(time!=null && !time.equals("")){
 					/**文章发布时间处理**/
+				    if(time.contains("\n")){
+				        time = time.split("\n")[0];
+				    }
 					time = TimeParse.dateFormartString(TimeParse.stringFormartDate(time), "yyyy-MM-dd HH:mm:ss") ;
 				}
 				// 处理文章简介
-				content = element.select("div.news-detail").select("div.news-info").select("p.news-txt").select("span#summary_1").text();
+				if(content == null) {
+				    for(int i = 0;i < 11;i++) {
+				        content = element.select("#summary_"+i).text();
+				        if(content != null && content.length() > 0) {
+				            break;
+				        }
+				    }
+				}
 				//添加到数据集合中
 				if(title != null && !title.equals("") && source!=null && time!=null){
 					NewsData newsData = new NewsData(link, title, source, time, content, pt, word);
@@ -269,7 +279,7 @@ public class SougouNewsCrawlerParse extends HttpClientTemplateOK {
 		String url = null;
 		if(word!=null){
 			url = "http://news.sogou.com/news?mode="+ mode +"&media=&query="
-                    + URLCodeUtil.getURLEncode(word, "utf-8") + "&time=0&clusterId=&sort=1&dp=1";
+                    + URLCodeUtil.getURLEncode(word, "utf-8") + "&time=0&clusterId=&sort=1&dp=1&page="+page;
 		}
 		return url;
 	}