using System;
using System.Net;
using System.Text;
using System.Text.RegularExpressions;
namespace HttpGet
{
class Class1
{
[STAThread]
static void Main(string[] args)
{
System.Net.WebClient client = new WebClient();
byte[] page = client.DownloadData("http://www.google.com");
string content = System.Text.Encoding.UTF8.GetString(page);
string regex = "href=[\\\"\\\'](http:\\/\\/|\\.\\/|\\/)?\\w+(\\.\\w+)*(\\/\\w+(\\.\\w+)?)*(\\/|\\?\\w*=\\w*(&\\w*=\\w*)*)?[\\\"\\\']";
Regex re = new Regex(regex);
MatchCollection matches = re.Matches(content);
System.Collections.IEnumerator enu = matches.GetEnumerator();
while (enu.MoveNext() && enu.Current != null)
{
Match match = (Match)(enu.Current);
Console.Write(match.Value + "\r\n");
}
}
}
}
using System;
using System.Collections.Generic;
using System.ComponentModel;
using System.Data;
using System.Drawing;
using System.Linq;
using System.Text;
using System.Windows.Forms;
using Winista.Text.HtmlParser;
using Winista.Text.HtmlParser.Lex;
using Winista.Text.HtmlParser.Util;
using Winista.Text.HtmlParser.Tags;
using Winista.Text.HtmlParser.Filters;
namespace HTMLParser
{
public partial class Form1 : Form
{
public Form1()
{
InitializeComponent();
AddUrl();
}
private void btnParser_Click(object sender, EventArgs e)
{
#region 获得网页的html
try
{
txtHtmlWhole.Text = "";
string url = CBUrl.SelectedItem.ToString().Trim();
System.Net.WebClient aWebClient = new System.Net.WebClient();
aWebClient.Encoding = System.Text.Encoding.Default;
string html = aWebClient.DownloadString(url);
txtHtmlWhole.Text = html;
}
catch (Exception ex)
{
MessageBox.Show(ex.Message);
}
#endregion
#region 分析网页html节点
Lexer lexer = new Lexer(this.txtHtmlWhole.Text);
Parser parser = new Parser(lexer);
NodeList htmlNodes = parser.Parse(null);
this.treeView1.Nodes.Clear();
this.treeView1.Nodes.Add("root");
TreeNode treeRoot = this.treeView1.Nodes[0];
for (int i = 0; i < htmlNodes.Count; i++)
{
this.RecursionHtmlNode(treeRoot, htmlNodes, false);
}
#endregion
}
private void RecursionHtmlNode(TreeNode treeNode, INode htmlNode, bool siblingRequired)
{
if (htmlNode == null || treeNode == null) return;
TreeNode current = treeNode;
TreeNode content ;
//current node
if (htmlNode is ITag)
{
ITag tag = (htmlNode as ITag);
if (!tag.IsEndTag())
{
string nodeString = tag.TagName;
if (tag.Attributes != null && tag.Attributes.Count > 0)
{
if (tag.Attributes["ID"] != null)
{
nodeString = nodeString + " { id=\"" + tag.Attributes["ID"].ToString() + "\" }";
}
if (tag.Attributes["HREF"] != null)
{
nodeString = nodeString + " { href=\"" + tag.Attributes["HREF"].ToString() + "\" }";
}
}
current = new TreeNode(nodeString);
treeNode.Nodes.Add(current);
}
}
//获取节点间的内容
if (htmlNode.Children != null && htmlNode.Children.Count > 0)
{
this.RecursionHtmlNode(current, htmlNode.FirstChild, true);
content = new TreeNode(htmlNode.FirstChild.GetText());
treeNode.Nodes.Add(content);
}
//the sibling nodes
if (siblingRequired)
{
INode sibling = htmlNode.NextSibling;
while (sibling != null)
{
this.RecursionHtmlNode(treeNode, sibling, false);
sibling = sibling.NextSibling;
}
}
}
private void AddUrl()
{
CBUrl.Items.Add("http://www.hao123.com");
CBUrl.Items.Add("http://www.sina.com");
CBUrl.Items.Add("http://www.heuet.edu.cn");
}
}
}
Uri uri = new Uri("http://www.baidu.com");
ScrapingBrowser browser1 = new ScrapingBrowser();
String htmlStr = browser1.DownloadString(uri);
HtmlAgilityPack.HtmlDocument htmlDocument = new HtmlAgilityPack.HtmlDocument();
htmlDocument.LoadHtml(htmlStr);
HtmlNode html = htmlDocument.DocumentNode;
IEnumerable<HtmlNode> nodes = html.CssSelect("div"); //all div elements
//nodes = html.CssSelect("div.content"); //all div elements with css class ‘content’
//nodes = html.CssSelect("div.widget.monthlist"); //all div elements with the both css class
//nodes = html.CssSelect("#postPaging"); //all HTML elements with the id postPaging
//nodes = html.CssSelect("div#postPaging.testClass"); // all HTML elements with the id postPaging and css class testClass
//nodes = html.CssSelect("div.content > p.para"); //p elements who are direct children of div elements with css class ‘content’
//nodes = html.CssSelect("input[type=text].login"); // textbox with css class login
//nodes = html.CssSelect("p.para").CssSelectAncestors("div.content > div.widget");
71.05 KB, 下载次数: 46, 下载积分: 金钱 -1
Dll:HtmlAgilityPack.dll + ScrapySharp.dll
欢迎光临 CSkin博客 (http://bbs.cskin.net/) | Powered by Discuz! X3.2 |