使用 C## 和 IronWebScraper 抓取在线电影网站。

public class MovieScraper : WebScraper
{
    public override void Init()
    {
        // Initialize scraper settings
        License.LicenseKey = "LicenseKey";
        this.LoggingLevel = WebScraper.LogLevel.All;
        this.WorkingDirectory = AppSetting.GetAppRoot() + @"\MovieSample\Output\";

        // Request homepage content for scraping
        this.Request("https://domain/", Parse);
    }

    public override void Parse(Response response)
    {
        // Iterate over each movie div within the featured movie section
        foreach (var div in response.Css("#movie-featured > div"))
        {
            if (div.Attributes["class"] != "clearfix")
            {
                var movie = new Movie
                {
                    Id = Convert.ToInt32(div.GetAttribute("data-movie-id"))
                };

                var link = div.Css("a")[0];
                movie.Title = link.TextContentClean;
                movie.URL = link.Attributes["href"];

                // Request detailed page
                this.Request(movie.URL, ParseDetails, new MetaData() { { "movie", movie } });
            }
        }           
    }

    public void ParseDetails(Response response)
    {
        // Retrieve movie object from metadata
        var movie = response.MetaData.Get<Movie>("movie");
        var div = response.Css("div.mvic-desc")[0];

        // Extract description
        movie.Description = div.Css("div.desc")[0].TextContentClean;

        // Extract genres
        movie.Genre = new List<string>(); // Initialize genre list
        foreach(var genre in div.Css("div > p > a"))
        {
            movie.Genre.Add(genre.TextContentClean);
        }

        // Extract actors
        movie.Actor = new List<string>(); // Initialize actor list
        foreach (var actor in div.Css("div > p:nth-child(2) > a"))
        {
            movie.Actor.Add(actor.TextContentClean);
        }

        // Scrape and store detailed movie data
        Scrape(movie, "Movie.Jsonl");
    }
}

Public Class MovieScraper
	Inherits WebScraper

	Public Overrides Sub Init()
		' Initialize scraper settings
		License.LicenseKey = "LicenseKey"
		Me.LoggingLevel = WebScraper.LogLevel.All
		Me.WorkingDirectory = AppSetting.GetAppRoot() & "\MovieSample\Output\"

		' Request homepage content for scraping
		Me.Request("https://domain/", AddressOf Parse)
	End Sub

	Public Overrides Sub Parse(ByVal response As Response)
		' Iterate over each movie div within the featured movie section
		For Each div In response.Css("#movie-featured > div")
			If div.Attributes("class") <> "clearfix" Then
				Dim movie As New Movie With {.Id = Convert.ToInt32(div.GetAttribute("data-movie-id"))}

				Dim link = div.Css("a")(0)
				movie.Title = link.TextContentClean
				movie.URL = link.Attributes("href")

				' Request detailed page
				Me.Request(movie.URL, AddressOf ParseDetails, New MetaData() From {
					{ "movie", movie }
				})
			End If
		Next div
	End Sub

	Public Sub ParseDetails(ByVal response As Response)
		' Retrieve movie object from metadata
		Dim movie = response.MetaData.Get(Of Movie)("movie")
		Dim div = response.Css("div.mvic-desc")(0)

		' Extract description
		movie.Description = div.Css("div.desc")(0).TextContentClean

		' Extract genres
		movie.Genre = New List(Of String)() ' Initialize genre list
		For Each genre In div.Css("div > p > a")
			movie.Genre.Add(genre.TextContentClean)
		Next genre

		' Extract actors
		movie.Actor = New List(Of String)() ' Initialize actor list
		For Each actor In div.Css("div > p:nth-child(2) > a")
			movie.Actor.Add(actor.TextContentClean)
		Next actor

		' Scrape and store detailed movie data
		Scrape(movie, "Movie.Jsonl")
	End Sub
End Class