标签:根据 level eth encoding package tno tor title width
参考:
GitHub:https://github.com/zzzprojects/html-agility-pack/releases
官网:https://html-agility-pack.net/
https://www.nuget.org/packages/HtmlAgilityPack/
HtmlAgilityPack(以下简称HAP)是一个基于.Net的、第三方免费开源的微型类库,主要用于在服务器端解析html文档。
HtmlAgilityPack为网页提供了标准的DOM API和XPath导航 。使用WebBrowser和HttpWebRequest下载的网页可以用Html Agility Pack来解析。
Xpath表达式的参考文档可见:https://www.cnblogs.com/springsnow/p/11810458.html#_label0
HtmlAgilityPack中的HtmlNode类与XmlNode类差不多,HtmlDocument类与XmlDocument类差不多。
参考:https://www.cnblogs.com/springsnow/p/12883050.html
下面来看看该类提供功能。
下面是几个简单使用说明:
1、获取网页title:
doc.DocumentNode.SelectSingleNode("//title").InnerText;//XPath中:“//title”表示所有title节点。SelectSingleNode用于获取满足条件的唯一的节点。
2、获取所有的超链接:
doc.DocumentNode.Descendants("a")
3、获取name为kw的input,也就是相当于getElementsByName():
var kwBox = doc.DocumentNode.SelectSingleNode("//input[@name=‘kw‘]");
示例:
private void Form1_Load(object sender, EventArgs e) { List<Result> list = new List<Result>(); HtmlWeb htmlWeb = new HtmlWeb(); htmlWeb.OverrideEncoding = Encoding.UTF8;//编码,这里网上有些很多写法都不正确 HtmlAgilityPack.HtmlDocument htmlDoc = htmlWeb.Load(@http://www.cnblogs.com/); //选择博客园首页文章列表 htmlDoc.DocumentNode.SelectNodes("//div[@id=‘post_list‘]/div[@class=‘post_item‘]").//双斜杠“//”表示从跟节点开始查找 AsParallel().ToList().ForEach(ac => { //抓取图片,因为有空的,所以拿变量存起来 HtmlNode node = ac.SelectSingleNode(".//p[@class=‘post_item_summary‘]/a/img"); list.Add(new Result { url = ac.SelectSingleNode(".//a[@class=‘titlelnk‘]").Attributes["href"].Value, title = ac.SelectSingleNode(".//a[@class=‘titlelnk‘]").InnerText, //图片如果为空,显示默认图片 img = node == null ? "http ://www.cnblogs.com//Content/img/avatar.png" : node.Attributes["src"].Value, content = ac.SelectSingleNode(".//p[@class=‘post_item_summary‘]").InnerText }); }); foreach (Result item in list) { this.listBox1.Items.Add(item.title); } }
/// <summary> /// 页面抓取结果 /// </summary> public class Result { /// <summary> /// 链接 /// </summary> public string url { get; set; } /// <summary> /// 标题 /// </summary> public string title { get; set; } /// <summary> /// 头像地址 /// </summary> public string img { get; set; } /// <summary> /// 正文内容 /// </summary> public string content { get; set; } }
示例2:下载微软文档
using HtmlAgilityPack; using System; using System.Collections.Generic; using System.IO; using System.Text; namespace ConsoleApp4 { internal class Program { private static void Main(string[] args) { //网页地址: string Url = "https://docs.microsoft.com/zh-cn/aspnet/mvc/overview/getting-started/getting-started-with-ef-using-mvc/implementing-inheritance-with-the-entity-framework-in-an-asp-net-mvc-application"; List<string> list = new List<string>(); ; HtmlWeb htmlWeb = new HtmlWeb(); htmlWeb.OverrideEncoding = Encoding.UTF8; HtmlDocument htmlDoc = htmlWeb.Load(Url); HtmlNode node = htmlDoc.DocumentNode.SelectSingleNode("//main[@id=‘main‘]"); //去掉英文翻译 var a = node.SelectNodes("//span[@class=‘sxs-lookup‘]"); foreach (HtmlNode b in a) { b.Remove(); } string src = ""; //图片相对路径改成绝对路径 var imgNode = node.SelectNodes("//img[@data-linktype=‘relative-path‘]"); foreach (HtmlNode node1 in imgNode) { src = node1.GetAttributeValue("src", ""); var url = new Uri(htmlWeb.ResponseUri, src); node1.SetAttributeValue("src", url.AbsoluteUri); } //链接路径转换 var hrefNode = node.SelectNodes("//a[@data-linktype=‘relative-path‘]|//a[@data-linktype=‘absolute-path‘]"); foreach (HtmlNode node1 in hrefNode) { src = node1.GetAttributeValue("href", ""); var url = new Uri(htmlWeb.ResponseUri, src); node1.SetAttributeValue("href", url.AbsoluteUri); } //找到所有的H2标签,然后加上顺序。 var h2Node = node.SelectNodes("//h2"); var arr = new string[] { "一", "二", "三", "四", "五", "六", "七", "八", "九", "十", "十一", "十二", "十三", "十四", "十五", "十六", "十七", "十八", "十九", "二十" }; if (h2Node != null) { for (int i = 0; i < h2Node.Count; i++) { h2Node[i].InnerHtml = arr[i] + "、" + h2Node[i].InnerHtml; //找到所有的H3标签,然后加上顺序。 var h3Node = h2Node[i].SelectNodes("following-sibling::h2|following-sibling::h3"); if (h3Node is null) break; for (int j = 0; j < h3Node.Count; j++) { if (h3Node[j].Name == "h2") break; else h3Node[j].InnerHtml = (j + 1) + "、" + h3Node[j].InnerHtml; } } } HtmlNode myNOde = htmlDoc.CreateElement("div"); //去掉前面无用的部分 var OK = node.SelectNodes("nav[1]/following-sibling::*"); myNOde.AppendChildren(OK); //添加原文连接: HtmlNode nodeOriUrl = htmlDoc.CreateElement("p"); nodeOriUrl.InnerHtml = "原文:<a href=‘" + htmlWeb.ResponseUri + "‘>" + htmlWeb.ResponseUri + "</a>"; myNOde.PrependChild(nodeOriUrl); //写入到本地文件 TextWriter wr = new StreamWriter(@"aa.html"); myNOde.WriteTo(wr); wr.Close(); } } }
Hazz为HTMLAgilityPack实现CSS选择器。它基于Fizzler,一个通用的CSS选择器解析器和生成器库。
Hazz以前称为Fizzler.Systems.HtmlAgilityPack。
// Load the document using HTMLAgilityPack as normal var html = new HtmlDocument(); html.LoadHtml(@" <html> <head></head> <body> <div> <p class=‘content‘>Fizzler</p> <p>CSS Selector Engine</p></div> </body> </html>"); // Fizzler for HtmlAgilityPack is implemented as the // QuerySelectorAll extension method on HtmlNode var document = html.DocumentNode; // yields: [<p class="content">Fizzler</p>] document.QuerySelectorAll(".content"); // yields: [<p class="content">Fizzler</p>,<p>CSS Selector Engine</p>] document.QuerySelectorAll("p"); // yields empty sequence document.QuerySelectorAll("body>p"); // yields [<p class="content">Fizzler</p>,<p>CSS Selector Engine</p>] document.QuerySelectorAll("body p"); // yields [<p class="content">Fizzler</p>] document.QuerySelectorAll("p:first-child");
C#爬虫(04):HtmlAgilityPack解析html文档
标签:根据 level eth encoding package tno tor title width
原文地址:https://www.cnblogs.com/springsnow/p/13278283.html