static void Main(string[] args)
{
WebClient client = new WebClient();
client.Encoding = System.Text.Encoding.UTF8;
var html = client.DownloadString("https://blog.csdn.net/czjnoe/article/details/106600070");
NSoup.Nodes.Document doc = NSoup.NSoupClient.Parse(html);
//根据标签名获取节点
NSoup.Select.Elements metaElements = doc.GetElementsByTag("meta");
foreach (var item in metaElements)
{
}
//根据id获取节点
NSoup.Nodes.Element headClassElements = doc.GetElementById("head");
//根据class获取节点
var headIdElements = doc.GetElementsByClass("fm").ToList();
foreach (var item in headIdElements)
{
}
//根据属性名称获取节点
List <Element> attributeNameElements = doc.GetElementsByAttribute("class").ToList();
//根据属性值获取节点
List <Element> attributeValueElements = doc.GetElementsByAttributeValue("id", "su").ToList();
//根据jQuery选择器获取节点
var selectElments = doc.Select("#head").ToList();
}
private void timAuto_Tick(object sender, EventArgs e)
{
String cPageHtml = geckoWebBrowser1.Text;
Document doc = NSoupClient.Parse(cPageHtml);
Elements rs = doc.Select(this.txtMatch.Text);
for (int i = 0; i < rs.Count; i++)
{
NSoup.Nodes.Element rowKey = rs[i];
String cUrl = rowKey.Attr(this.txtAttr.Text);
log4net.WriteLogFile(cUrl);
}
}
private void download2()
{
// 下载地址
string url = textBox1.Text;
string html = getHtml(url);
NSoup.Nodes.Document d = NSoup.NSoupClient.Parse(html);
//获取标题
String title = d.GetElementsByClass("tit").First.GetElementsByTag("h1").Text;
//如果没有标题就用毫秒数
title = (title != null && !title.Equals(""))?title:DateTime.Now.ToUniversalTime().Ticks + "";
NSoup.Nodes.Element el = d.GetElementById("vlink_1");
NSoup.Select.Elements es = el.GetElementsByTag("li");
richTextBox1.Text = "";
foreach (var e in es)
{
string subHtml = getHtml("http://www.ting56.com" + e.GetElementsByTag("a").Attr("href"));
Document d1 = NSoup.NSoupClient.Parse(subHtml);
Match mc = Regex.Match(subHtml, "FonHen_JieMa\\('([0-9,*]*)'\\)");
//获取加密url
string miwen = mc.Groups[1].Value;
string[] tArr = Regex.Split(miwen, "\\*", RegexOptions.IgnoreCase);
int n = tArr.Length;
string s = "";
for (int i = 0; i < n; i++)
{
if (!tArr[i].Equals(""))
{
s += (char)int.Parse(tArr[i]);
}
}
//下载地址
string downUrl = Regex.Split(s, "\\&", RegexOptions.IgnoreCase)[0];
//文件扩展名
string downFileExt = Regex.Split(s, "\\&", RegexOptions.IgnoreCase)[2];
string path = textBox2.Text + "\\" + title + "\\";
string fileName = e.Text();
string localFile = path + fileName + downFileExt;
// MessageBox.Show(localFile);
richTextBox1.AppendText("开始下载 " + fileName + "\n\r" + downUrl + "\n\r");
//用线程执行下载
// Thread oGetArgThread = new Thread(new ThreadStart(HttpDownload));
// oGetArgThread.IsBackground = true;
// oGetArgThread.Start();
// DownFile hd = new DownFile();
// hd.downUrl=downUrl;
// hd.localFile=localFile;
// DownFile df = new DownFile(downUrl,localFile);
// ThreadPool.QueueUserWorkItem(new WaitCallback(df.HttpDownload));
// Thread oGetArgThread = new Thread(new ThreadStart(hd.HttpDownload));
// oGetArgThread.IsBackground = true;
// oGetArgThread.Start();
HttpDownload(downUrl, localFile);
}
// MessageBox.Show(title);
}