Scraping an Online Movie Website

Darrius Serrant

更新日期:6月 10, 2025

Translated

View the article in English

讓我們從一個現實世界的網站開始另一個例子。我們將選擇刮取一個電影網站。

讓我們添加一個新類並將其命名為“MovieScraper”：

現在讓我們看看我們將要刮取的網站：

這是我們在網站上看到的首頁 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

正如我們所見，我們有一個電影 ID、標題和指向詳細頁面的鏈接。

讓我們開始刮取這組數據：

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

這段代碼有什麼新內容？

工作目錄屬性用於設置所有刮取數據及其相關文件的主要工作目錄。

讓我們多做一些。

如果我們需要構建類型化對象以存儲格式化對象中的刮取數據怎麼辦？

讓我們實現一個Movie類，該類將保存我們的格式化數據：

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

現在我們將更新我們的代碼：

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

有什麼新內容？

我們實現了一個Movie類以保存我們的刮取數據。
我們將電影對象傳遞給Scrape方法，它了解我們的格式並以定義的方式保存它，如下圖所示：

讓我們開始刮取一個更詳細的頁面。

電影頁面看起來像這樣：

<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

我們可以用新屬性（描述、類型、演員、導演、國家、時長、IMDb 評分）擴展我們的Movie類，但我們將僅使用（描述、類型、演員）作為樣本。

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

現在我們將導航到詳細頁面進行刮取。

IronWebScraper 使您能夠為刮取功能添加更多內容，以刮取不同類型的頁面格式。

正如我們在這裡看到的：

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

有什麼新內容？