c# net爬取百度热搜

var url = "https://top.baidu.com/board?tab=realtime";//百度
using (var httpClient = new HttpClient())
{

var response = await httpClient.GetStringAsync(url);

var htmlDocument = new HtmlDocument();
htmlDocument.LoadHtml(response);
var categoryWrapNode = htmlDocument.DocumentNode.SelectNodes("//div[@class='category-wrap_iQLoo horizontal_1eKyQ']");

if (categoryWrapNode != null)
{
foreach (var div in categoryWrapNode)
{
var divA = div.SelectSingleNode(".//div[@class='c-single-text-ellipsis']");
var divB = div.SelectSingleNode(".//div[@class='hot-desc_1m_jR large_nSuFU ']");
var divC = div.SelectSingleNode(".//div[@class='hot-index_1Bl1a']");
var anchorTag = div.SelectSingleNode(".//div[@class='hot-desc_1m_jR large_nSuFU ']/a");
if (divB == null)
{
divB = div.SelectSingleNode(".//div[@class='hot-desc_1m_jR small_Uvkd3 ellipsis_DupbZ']");
}

var hrefValue = "";
if (anchorTag != null)
{
// 提取 href 属性
hrefValue = anchorTag.GetAttributeValue("href", string.Empty);
}
divB.RemoveChild(anchorTag);
string atext = divA.InnerText.Trim();
string btext = divB.InnerText.Trim();
string ctext = divC.InnerText.Trim();

}

根据这个方法制作了这个合集

http://www.cooool.live/

 

posted @   過朢  阅读(22)  评论(0编辑  收藏  举报
相关博文:
阅读排行:
· 被坑几百块钱后,我竟然真的恢复了删除的微信聊天记录!
· 没有Manus邀请码?试试免邀请码的MGX或者开源的OpenManus吧
· 【自荐】一款简洁、开源的在线白板工具 Drawnix
· 园子的第一款AI主题卫衣上架——"HELLO! HOW CAN I ASSIST YOU TODAY
· Docker 太简单,K8s 太复杂?w7panel 让容器管理更轻松!
点击右上角即可分享
微信分享提示