Commit bb73a9c6 by yangchen

知乎 链接拼接 修改

parent 9df9a7ca
...@@ -49,6 +49,8 @@ public class ZhihuAnwserCrawlerParse { ...@@ -49,6 +49,8 @@ public class ZhihuAnwserCrawlerParse {
}else{ }else{
more = false; more = false;
} }
}else {
more = false;
} }
//单线程采集避免被封休眠8s //单线程采集避免被封休眠8s
ZhiWeiTools.sleep(8000); ZhiWeiTools.sleep(8000);
...@@ -137,7 +139,7 @@ public class ZhihuAnwserCrawlerParse { ...@@ -137,7 +139,7 @@ public class ZhihuAnwserCrawlerParse {
Date time = new Date(answerJson.getLong("created_time")*1000); Date time = new Date(answerJson.getLong("created_time")*1000);
if(time.after(endDate)){ if(time.after(endDate)){
String answerId = answerJson.getString("id"); String answerId = answerJson.getString("id");
String link = from_url+"/answers/" + answerId; String link = from_url+"/answer/" + answerId;
String author = answerJson.getJSONObject("author").getString("name"); String author = answerJson.getJSONObject("author").getString("name");
String authorUrl = "https://www.zhihu.com/people/"+answerJson.getJSONObject("author").getString("url_token"); String authorUrl = "https://www.zhihu.com/people/"+answerJson.getJSONObject("author").getString("url_token");
String content = ZhiWeiTools.delHTMLTag(answerJson.getString("content")); String content = ZhiWeiTools.delHTMLTag(answerJson.getString("content"));
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment