贴吧采集修改

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

@@ -117,29 +117,12 @@ public class BaiduTiebaCrawlerParse extends HttpClientTemplateOK {
             String content = null;
             String author = null;
             String tid = null;
-            System.out.println("-------------------------");
-//            System.out.println(element.toString());
             author = element.select("li.d_name").select("a").text();
             content = element.select("div.p_content_nameplate").select("cc").select("div.clearfix").text();
             if(content == null ||content.length() < 1) {
                 content = element.select("div.j_d_post_content").text();
             }
-            if(time == null || time.length() < 1) {
-                time = element.select("span.tail-info").text();
-                if(time.contains("楼")) {
-                    time = time.split("楼")[1].trim();
-                }
-            }
-            if(time == null || time.trim().length() < 1) {
-            
-                Pattern pa = Pattern.compile("date&quot;:&quot;(.*?)&quot");
-                Matcher ma = pa.matcher(element.toString());
-                while(ma.find()) {
-                    time = ma.group(0);
-                    time = time.split("date&quot;:&quot;")[1].split("&quot")[0];
-                    break;
-                }
-            }
+            time = getTime(element);
             Pattern pa2 = Pattern.compile("post_id&quot(.*?),&quot");
             Matcher ma2 = pa2.matcher(element.toString());
             while(ma2.find()) {
@@ -163,6 +146,33 @@ public class BaiduTiebaCrawlerParse extends HttpClientTemplateOK {
     }
 	
 	/**
+	 * 
+	 * @Description 百度贴吧获取时间
+	 * @param element
+	 * @return
+	 */
+	private static String getTime(Element element) {
+	    String time = null;
+	    if(time == null || time.length() < 1) {
+            time = element.select("span.tail-info").text();
+            if(time.contains("楼")) {
+                time = time.split("楼")[1].trim();
+            }
+        }
+        if(time == null || time.trim().length() < 1) {
+        
+            Pattern pa = Pattern.compile("date&quot;:&quot;(.*?)&quot");
+            Matcher ma = pa.matcher(element.toString());
+            while(ma.find()) {
+                time = ma.group(0);
+                time = time.split("date&quot;:&quot;")[1].split("&quot")[0];
+                break;
+            }
+        }
+        return time;
+	}
+
+    /**
      * @Title: downloadHtml 
      * @author hero 
      * @Description: 下載百度貼吧具体页面数据