C# 中的网络爬虫

using IronWebScraper;

namespace WebScrapingProject
{
    class MainClass
    {
        public static void Main(string [] args)
        {
            var scraper = new BlogScraper();
            scraper.Start();
        }
    }

    class BlogScraper : WebScraper
    {
        // Initialize scraper settings and make the first request
        public override void Init()
        {
            // Set logging level to show all log messages
            this.LoggingLevel = WebScraper.LogLevel.All;

            // Request the initial page to start scraping
            this.Request("https://ironpdf.com/blog/", Parse);
        }

        // Method to handle parsing of the page response
        public override void Parse(Response response)
        {
            // Loop through each blog post title link found by CSS selector
            foreach (var title_link in response.Css("h2.entry-title a"))
            {
                // Clean and extract the title text
                string strTitle = title_link.TextContentClean;

                // Store the extracted title for later use
                Scrape(new ScrapedData() { { "Title", strTitle } });
            }

            // Check if there is a link to the previous post page and if exists, follow it
            if (response.CssExists("div.prev-post > a[href]"))
            {
                // Get the URL for the next page
                var next_page = response.Css("div.prev-post > a[href]")[0].Attributes["href"];

                // Request the next page to continue scraping
                this.Request(next_page, Parse);
            }
        }
    }
}

Imports IronWebScraper

Namespace WebScrapingProject
	Friend Class MainClass
		Public Shared Sub Main(ByVal args() As String)
			Dim scraper = New BlogScraper()
			scraper.Start()
		End Sub
	End Class

	Friend Class BlogScraper
		Inherits WebScraper

		' Initialize scraper settings and make the first request
		Public Overrides Sub Init()
			' Set logging level to show all log messages
			Me.LoggingLevel = WebScraper.LogLevel.All

			' Request the initial page to start scraping
			Me.Request("https://ironpdf.com/blog/", AddressOf Parse)
		End Sub

		' Method to handle parsing of the page response
		Public Overrides Sub Parse(ByVal response As Response)
			' Loop through each blog post title link found by CSS selector
			For Each title_link In response.Css("h2.entry-title a")
				' Clean and extract the title text
				Dim strTitle As String = title_link.TextContentClean

				' Store the extracted title for later use
				Scrape(New ScrapedData() From {
					{ "Title", strTitle }
				})
			Next title_link

			' Check if there is a link to the previous post page and if exists, follow it
			If response.CssExists("div.prev-post > a[href]") Then
				' Get the URL for the next page
				Dim next_page = response.Css("div.prev-post > a[href]")(0).Attributes("href")

				' Request the next page to continue scraping
				Me.Request(next_page, AddressOf Parse)
			End If
		End Sub
	End Class
End Namespace