微信正文获取修改

src/main/java/com/zhiwei/source_forward/crawler/UrlLiveCrawler.java

@@ -60,7 +60,7 @@ public class UrlLiveCrawler {
         logger.info("当前处理 URL: {}", url);
         Request request = HttpRequestBuilder.newGetRequest(url, null);
         counter.increase();
-        HttpBoot.asyncCall(request, ProxyClientUtil.getNATProxy(), false).addListeners(future -> {
+        HttpBoot.asyncCall(request, ProxyClientUtil.getNATProxy(), false,false).addListeners(future -> {
             if (future.isSuccess()) {
                 Response response = future.result();
                 try {

src/main/java/com/zhiwei/source_forward/run/ContentMatch.java

@@ -55,6 +55,15 @@ public class ContentMatch {
         return dataList;
     }
     
+    public static void main(String[] args) {
+        List<String> urlList = new ArrayList<>();
+        urlList.add("https://mp.weixin.qq.com/s?src=11&timestamp=1535449515&ver=1088&signature=9kByOydse2KaausR0FP5HoQpSeSXs097LR-akxhJxfCV*onfJuoWkznZ8UEk5OfFox4aVzDqx0n0xwbtTm6KUzPpNz2desfNiQ4Uevp4LaTSyoH3OKysG2qxy2jisojb&new=1");
+        List<ContentBean> l = getContentMatch(urlList);
+        for(ContentBean cb : l) {
+            System.out.println(cb.toString());
+        }
+    }
+    
     static class ContentMatchCrawlerThread extends Thread{
 
       private static List<ContentBean> getContentMatch(List<String> urlList){

src/main/java/com/zhiwei/source_forward/util/MatchContent.java

@@ -29,8 +29,12 @@ public class MatchContent {
 	public static String matchContent(String url,String html) {
 		String content = null;
 		try {
-			Document document = Jsoup.parse(html);
-			content = mathchContent(html, document);
+		    Document document = Jsoup.parse(html);
+		    if(url.contains("weixin.qq.com")) {
+		        content = matchContentWeixin(document);
+		    }else {
+		        content = mathchContent(html, document);
+		    }
 			return content;
 		} catch (Exception e) {
 			logger.debug("获取全文失败",e.fillInStackTrace());
@@ -39,8 +43,18 @@ public class MatchContent {
 		return content;
 	}
 	
-	
 	/**
+	 * 
+	 * @Description 微信文本获取
+	 * @param html
+	 * @return
+	 */
+	private static String matchContentWeixin(Document document) {
+        return document.select("div.rich_media_content").text();
+    }
+
+
+    /**
 	 * @Title: mathchContent 
 	 * @author hero 
 	 * @Description: 匹配正文数据