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://website.com/", 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"];

                // Scrape and store movie object
                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://website.com/", 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")

				' Scrape and store movie object
				Scrape(movie, "Movie.Jsonl")
			End If
		Next div
	End Sub
End Class

<div class="mvi-content">
    <div class="thumb mvic-thumb" 
         style="background-image: url(https://img.gocdn.online/2017/04/28/poster/5a08e94ba02118f22dc30f298c603210-guardians-of-the-galaxy-vol-2.jpg);"></div>
    <div class="mvic-desc">
        <h3>Guardians of the Galaxy Vol. 2</h3>        
        <div class="desc">
            Set to the backdrop of Awesome Mixtape #2, Marvel's Guardians of the Galaxy Vol. 2 continues the team's adventures as they travel throughout the cosmos to help Peter Quill learn more about his true parentage.
        </div>
        <div class="mvic-info">
            <div class="mvici-left">
                <p>
                    <strong>Genre: </strong>
                    <a href="https://Domain/genre/action/" title="Action">Action</a>,
                    <a href="https://Domain/genre/adventure/" title="Adventure">Adventure</a>,
                    <a href="https://Domain/genre/sci-fi/" title="Sci-Fi">Sci-Fi</a>
                </p>
                <p>
                    <strong>Actor: </strong>
                    <a target="_blank" href="https://Domain/actor/chris-pratt" title="Chris Pratt">Chris Pratt</a>,
                    <a target="_blank" href="https://Domain/actor/-zoe-saldana" title="Zoe Saldana">Zoe Saldana</a>,
                    <a target="_blank" href="https://Domain/actor/-dave-bautista-" title="Dave Bautista">Dave Bautista</a>
                </p>
                <p>
                    <strong>Director: </strong>
                    <a href="#" title="James Gunn">James Gunn</a>
                </p>
                <p>
                    <strong>Country: </strong>
                    <a href="https://Domain/country/us" title="United States">United States</a>
                </p>
            </div>
            <div class="mvici-right">
                <p><strong>Duration:</strong> 136 min</p>
                <p><strong>Quality:</strong> <span class="quality">CAM</span></p>
                <p><strong>Release:</strong> 2017</p>
                <p><strong>IMDb:</strong> 8.3</p>
            </div>
            <div class="clearfix"></div>
        </div>
        <div class="clearfix"></div>
    </div>
    <div class="clearfix"></div>
</div>

using System.Collections.Generic;

public class Movie
{
    public int Id { get; set; }
    public string Title { get; set; }
    public string URL { get; set; }
    public string Description { get; set; }
    public List<string> Genre { get; set; }
    public List<string> Actor { get; set; }
}

Imports System.Collections.Generic

Public Class Movie
	Public Property Id() As Integer
	Public Property Title() As String
	Public Property URL() As String
	Public Property Description() As String
	Public Property Genre() As List(Of String)
	Public Property Actor() As List(Of String)
End Class

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