Scraping an Online Movie Website

Curtis Chau

已更新:六月 10, 2025

Translated

View the article in English

让我们从一个真实的网站开始另一个示例。我们将选择抓取一个电影网站。

让我们添加一个新类并将其命名为 “MovieScraper”：

现在让我们看看我们将抓取的网站：

这是我们在网站上看到的主页 HTML 的一部分：

<div id="movie-featured" class="movies-list movies-list-full tab-pane in fade active">
    <div data-movie-id="20746" class="ml-item">
        <a href="https://website.com/film/king-arthur-legend-of-the-sword-20746/">
            <span class="mli-quality">CAM</span>
            <img data-original="https://img.gocdn.online/2017/05/16/poster/2116d6719c710eabe83b377463230fbe-king-arthur-legend-of-the-sword.jpg" 
                 class="lazy thumb mli-thumb" alt="King Arthur: Legend of the Sword"
                 src="https://img.gocdn.online/2017/05/16/poster/2116d6719c710eabe83b377463230fbe-king-arthur-legend-of-the-sword.jpg" 
                 style="display: inline-block;">
            <span class="mli-info"><h2>King Arthur: Legend of the Sword</h2></span>
        </a>
    </div>
    <div data-movie-id="20724" class="ml-item">
        <a href="https://website.com/film/snatched-20724/">
            <span class="mli-quality">CAM</span>
            <img data-original="https://img.gocdn.online/2017/05/16/poster/5ef66403dc331009bdb5aa37cfe819ba-snatched.jpg" 
                 class="lazy thumb mli-thumb" alt="Snatched" 
                 src="https://img.gocdn.online/2017/05/16/poster/5ef66403dc331009bdb5aa37cfe819ba-snatched.jpg" 
                 style="display: inline-block;">
            <span class="mli-info"><h2>Snatched</h2></span>
        </a>
    </div>
</div>

<div id="movie-featured" class="movies-list movies-list-full tab-pane in fade active">
    <div data-movie-id="20746" class="ml-item">
        <a href="https://website.com/film/king-arthur-legend-of-the-sword-20746/">
            <span class="mli-quality">CAM</span>
            <img data-original="https://img.gocdn.online/2017/05/16/poster/2116d6719c710eabe83b377463230fbe-king-arthur-legend-of-the-sword.jpg" 
                 class="lazy thumb mli-thumb" alt="King Arthur: Legend of the Sword"
                 src="https://img.gocdn.online/2017/05/16/poster/2116d6719c710eabe83b377463230fbe-king-arthur-legend-of-the-sword.jpg" 
                 style="display: inline-block;">
            <span class="mli-info"><h2>King Arthur: Legend of the Sword</h2></span>
        </a>
    </div>
    <div data-movie-id="20724" class="ml-item">
        <a href="https://website.com/film/snatched-20724/">
            <span class="mli-quality">CAM</span>
            <img data-original="https://img.gocdn.online/2017/05/16/poster/5ef66403dc331009bdb5aa37cfe819ba-snatched.jpg" 
                 class="lazy thumb mli-thumb" alt="Snatched" 
                 src="https://img.gocdn.online/2017/05/16/poster/5ef66403dc331009bdb5aa37cfe819ba-snatched.jpg" 
                 style="display: inline-block;">
            <span class="mli-info"><h2>Snatched</h2></span>
        </a>
    </div>
</div>

HTML

如我们所见，我们有一个电影 ID、标题和指向详细页面的链接。

让我们开始抓取这一组数据：

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("www.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 movieId = Convert.ToInt32(div.GetAttribute("data-movie-id"));
                var link = div.Css("a")[0];
                var movieTitle = link.TextContentClean;

                // Scrape and store movie data as key-value pairs
                Scrape(new ScrapedData() 
                { 
                    { "MovieId", movieId },
                    { "MovieTitle", movieTitle }
                }, "Movie.Jsonl");
            }
        }           
    }
}

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("www.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 movieId = Convert.ToInt32(div.GetAttribute("data-movie-id"));
                var link = div.Css("a")[0];
                var movieTitle = link.TextContentClean;

                // Scrape and store movie data as key-value pairs
                Scrape(new ScrapedData() 
                { 
                    { "MovieId", movieId },
                    { "MovieTitle", movieTitle }
                }, "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("www.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 movieId = Convert.ToInt32(div.GetAttribute("data-movie-id"))
				Dim link = div.Css("a")(0)
				Dim movieTitle = link.TextContentClean

				' Scrape and store movie data as key-value pairs
				Scrape(New ScrapedData() From {
					{ "MovieId", movieId },
					{ "MovieTitle", movieTitle }
				},
				"Movie.Jsonl")
			End If
		Next div
	End Sub
End Class

$vbLabelText $csharpLabel

这段代码有什么新功能？

Working Directory 属性用于设置所有抓取数据及其相关文件的主工作目录。

让我们做更多。

如果我们需要构建将抓取数据保存在格式化对象中的类型对象该怎么办？

让我们实现一个 Movie 类来保存我们的格式化数据：

public class Movie
{
    public int Id { get; set; }
    public string Title { get; set; }
    public string URL { get; set; }
}

public class Movie
{
    public int Id { get; set; }
    public string Title { get; set; }
    public string URL { get; set; }
}

IRON VB CONVERTER ERROR developers@ironsoftware.com

$vbLabelText $csharpLabel

现在我们将更新代码：

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 : 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

$vbLabelText $csharpLabel

有新功能吗？

我们实现了一个 Movie 类来保存我们的抓取数据。
我们将电影对象传递给 Scrape 方法，它理解我们的格式并以定义的方式保存它，如下图所示：

让我们开始抓取更详细的页面。

电影页面看起来是这样的：

<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>

<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>

HTML

我们可以使用新的属性（描述、类型、演员、导演、国家、时长、IMDb 分数）来扩展我们的 Movie 类，但我们将在示例中仅使用（描述、类型、演员）。

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; }
}

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

$vbLabelText $csharpLabel

现在我们将导航到详细页面以进行抓取。

IronWebScraper 使您可以在抓取功能中添加更多，以抓取不同类型的页面格式。

正如我们在这里看到的：

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 : 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

$vbLabelText $csharpLabel

有新功能吗？