C#使用ScrapySharp快速从网页采集数据

PM> Install-Package ScrapySharp

var browser = new ScrapingBrowser();
var html = browser.DownloadString(new Uri("Http://www.cnblogs.com/"));

static IEnumerable<Htmlnode> CssSelect(this HtmlNode node, string expression);
static IEnumerable<HtmlNode> CssSelect(this IEnumerable<HtmlNode> nodes, string expression);
static IEnumerable<HtmlNode> CssSelectAncestors(this HtmlNode node, string expression);
static IEnumerable<HtmlNode> CssSelectAncestors(this IEnumerable<HtmlNode> nodes, string expression);

    var doc = new HtmlDocument();
    doc.LoadHtml(html);

    var docNode = doc.DocumentNode;

    var nodes = docNode.CssSelect(".titlelnk");
    foreach (var htmlNode in nodes)
    {
        Console.WriteLine(htmlNode.InnerText);
    }

var nodes = docNode.CssSelect(".post_item_body > h3");
var nodes = docNode.CssSelect("div#post_list").CssSelectAncestors("h3");

    html.CssSelect("div"); //all div elements
    html.CssSelect("div.content"); //all div elements with css class 'content'
    html.CssSelect("div.widget.monthlist"); //all div elements with the both css class
    html.CssSelect("#postPaging"); //all HTML elements with the id postPaging
    html.CssSelect("div#postPaging.testClass");     // all HTML elements with the id postPaging and css class testClass
    html.CssSelect("div.content > p.para");     //p elements who are direct children of div elements with css class 'content'
    html.CssSelect("input[type = text].login");     // textbox with css class login