Commit 2f6f9a6f by leiliangliang

知乎热搜标签采集程序更新

parent 472d0d4f
...@@ -189,7 +189,7 @@ public class ZhihuHotSearchCrawler { ...@@ -189,7 +189,7 @@ public class ZhihuHotSearchCrawler {
//获取标签 //获取标签
String label = ""; String label = "";
Elements select = document.select("div.QuestionHeader-topics").select("div.css-1gomreu"); Elements select = document.select("div.QuestionHeader-topics").select("div.css-1gomreu");
String substring = htmlBody.substring(htmlBody.indexOf("initialState") - 2, htmlBody.indexOf("subAppName") + 19); String substring = htmlBody.substring(htmlBody.indexOf("initialState") - 2, htmlBody.indexOf("spanName") + 25);
JSONObject jsonObject = JSONObject.parseObject(substring); JSONObject jsonObject = JSONObject.parseObject(substring);
String detail= jsonObject.getJSONObject("initialState").getJSONObject("entities").getJSONObject("questions").getJSONObject(id).getString("detail"); String detail= jsonObject.getJSONObject("initialState").getJSONObject("entities").getJSONObject("questions").getJSONObject(id).getString("detail");
String topicLead = DelTagsUtil.getTextFromHtml(detail); String topicLead = DelTagsUtil.getTextFromHtml(detail);
......
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