添加360新闻采集今日头条

pom.xml

@@ -66,7 +66,7 @@
 		<dependency>
 			<groupId>com.zhiwei</groupId>
 			<artifactId>zhiweiTools</artifactId>
-			<version>0.0.6-SNAPSHOT</version>
+			<version>0.0.7-SNAPSHOT</version>
 		</dependency>
 	</dependencies>
 </project>
\ No newline at end of file

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

@@ -165,7 +165,6 @@ public class BaiduNewsCrawlerParse extends HttpClientTemplateOK {
 		Map<String, String> headerMap = HeaderTool.getCommonHead();
 		// 获取链接地址
 		String url = getUrl(word, startTime, endTime, tn, page);
-		System.out.println(url);
 		headerMap.put("Host", "news.baidu.com");
 		headerMap.put("Referer", url);
 		// 下载数据页面
@@ -286,6 +285,7 @@ public class BaiduNewsCrawlerParse extends HttpClientTemplateOK {
 					ZhiWeiTools.sleep(100);
 				}
 			} catch (Exception e) {
+				System.out.println("soureAndtime======"+soureAndtime);
 				e.printStackTrace();
 				logger.error("百度新闻数据解析时出现问题，问题为:{}", e.fillInStackTrace());
 				continue;

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

 package com.zhiwei.media_data_crawler.crawler;
 
-import java.io.IOException;
 import java.net.Proxy;
 import java.util.ArrayList;
 import java.util.HashMap;
@@ -124,18 +123,18 @@ public class SoNewsCrawlerParse extends HttpClientTemplateOK {
 	 * @param @return 设定文件 
 	 * @return String 返回类型
 	 */
-	private static String downloadHtml(String word, String tn, Proxy proxy, int page)throws IOException {
+	private static String downloadHtml(String word, String tn, Proxy proxy, int page)throws Exception {
 		// 获取通用请求头
 		Map<String, String> headerMap = HeaderTool.getCommonHead();
 		// 获取链接地址
 		String url = getUrl(word, tn, page);
-		headerMap.put("Host", "news.baidu.com");
+		headerMap.put("Host", "www.so.com");
 		headerMap.put("Referer", url);
 		// 下载数据页面
 		for (int i = 1; i <= 3; i++) {
 			try {
 				return get(url, proxy, headerMap);
-			} catch (IOException e) {
+			} catch (Exception e) {
 				logger.error("获取360新闻数据时出现问题,问题为：{}", e.fillInStackTrace());
 				if(i==3){
 					throw e;

src/main/java/com/zhiwei/media_data_crawler/data/DataCrawler.java

@@ -6,6 +6,7 @@ import java.util.List;
 import com.zhiwei.media_data_crawler.crawler.BaiduNewsCrawlerParse;
 import com.zhiwei.media_data_crawler.crawler.BaiduTiebaCrawlerParse;
 import com.zhiwei.media_data_crawler.crawler.DoubanCrawlerParse;
+import com.zhiwei.media_data_crawler.crawler.SoCrawlerParse;
 import com.zhiwei.media_data_crawler.crawler.SoNewsCrawlerParse;
 import com.zhiwei.media_data_crawler.crawler.SougouNewsCrawlerParse;
 import com.zhiwei.media_data_crawler.crawler.SougouZhihuCrawlerParse;
@@ -20,10 +21,6 @@ public class DataCrawler {
 
 	public static Long sleepTime;
 
-	public void setSleepTime(Long sleepTime) {
-		DataCrawler.sleepTime = sleepTime;
-	}
-
 	/**
 	 * 
 	 * @Title: getBaiduNewsData
@@ -278,4 +275,26 @@ public class DataCrawler {
 		}
 	}
 	
+
+	/**
+	 * 根据域名匹配数据来源
+	 * @Title: getSoData 
+	 * @author hero 
+	 * @param @param word
+	 * @param @param site
+	 * @param @param time
+	 * @param @param proxy
+	 * @param @return 设定文件 
+	 * @return List<NewsData> 返回类型
+	 */
+	public static List<NewsData> getSoData(String word, String site, String time, Proxy proxy) {
+		try {
+			return SoCrawlerParse.getSoData(word, site, time, proxy);
+		} catch (Exception e) {
+			e.printStackTrace();
+			return null;
+		}
+	}
+	
+	
 }

src/main/java/com/zhiwei/media_data_crawler/entity/NewsData.java

@@ -18,10 +18,10 @@ public class NewsData implements Serializable{
 	private String time;       //文章时间
 	private String content;   //文章简介
 	private String pt;       //采集来源
+	private String user_id;  //用户id
 	private String word;      //采集关键词
 	
 	
-	
 	public NewsData() {}
 	
 	
@@ -36,6 +36,18 @@ public class NewsData implements Serializable{
 		this.word = word;
 	}
 	
+	public NewsData(String url, String title, String source, String time
+			,String content, String pt, String word,String user_id) {
+		this.url = url;
+		this.title = title;
+		this.source = source;
+		this.time = time;
+		this.content = content;
+		this.pt = pt;
+		this.word = word;
+		this.user_id = user_id;
+	}
+	
 	@Override
 	public String toString(){
 		return "new NewsData["
@@ -46,6 +58,7 @@ public class NewsData implements Serializable{
 				+ ", content = " + content
 				+ ", pt = " + pt
 				+ ", word = " + word
+				+ ", user_id = " + user_id
 				+ "]";
 	}
 	
@@ -94,4 +107,12 @@ public class NewsData implements Serializable{
 		this.word = word;
 	}
 	
+	public String getUser_id() {
+		return user_id;
+	}
+
+	public void setUser_id(String user_id) {
+		this.user_id = user_id;
+	}
+	
 }

src/test/java/com/zhiwei/media_data_crawler/test/DataCrawlerTest.java

@@ -46,6 +46,12 @@ public class DataCrawlerTest {
 //			List<DouBanData> list = DataCrawler.getDouBanData(word, type, proxy);
 			
 			
+			List<NewsData> list = DataCrawler.getSoData("京东", "www.toutiao.com", "d", proxy);
+			for(NewsData newsData : list) {
+				System.out.println(newsData);
+			}
+			
+			
 		} catch (Exception e) {
 			// TODO Auto-generated catch block
 			e.printStackTrace();