抓取線上電影網站

Translated

View the article in English

讓我們從一個真實世界的網站開始另一個例子。我們將選擇抓取一個電影網站。

讓我們新增一個類別並命名為「MovieScraper」：

現在讓我們來看看我們將要抓取的網站：

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，我們有電影 ID、標題和詳細頁面的鏈接。

讓我們開始抓取這組數據：

public class MovieScraper : WebScraper
{
    public override void Init()
    {
        License.LicenseKey = "LicenseKey";
        this.LoggingLevel = WebScraper.LogLevel.All;
        this.WorkingDirectory = AppSetting.GetAppRoot() + @"\MovieSample\Output\";
        this.Request("www.website.com", Parse);
    }
    public override void Parse(Response response)
    {
        foreach (var Divs in response.Css("#movie-featured > div"))
        {
            if (Divs.Attributes ["class"] != "clearfix")
            {
                var MovieId = Divs.GetAttribute("data-movie-id");
                var link = Divs.Css("a")[0];
                var MovieTitle = link.TextContentClean;
                Scrape(new ScrapedData() { { "MovieId", MovieId }, { "MovieTitle", MovieTitle } }, "Movie.Jsonl");
            }
        }           
    }
}

public class MovieScraper : WebScraper
{
    public override void Init()
    {
        License.LicenseKey = "LicenseKey";
        this.LoggingLevel = WebScraper.LogLevel.All;
        this.WorkingDirectory = AppSetting.GetAppRoot() + @"\MovieSample\Output\";
        this.Request("www.website.com", Parse);
    }
    public override void Parse(Response response)
    {
        foreach (var Divs in response.Css("#movie-featured > div"))
        {
            if (Divs.Attributes ["class"] != "clearfix")
            {
                var MovieId = Divs.GetAttribute("data-movie-id");
                var link = Divs.Css("a")[0];
                var MovieTitle = link.TextContentClean;
                Scrape(new ScrapedData() { { "MovieId", MovieId }, { "MovieTitle", MovieTitle } }, "Movie.Jsonl");
            }
        }           
    }
}

Public Class MovieScraper
	Inherits WebScraper

	Public Overrides Sub Init()
		License.LicenseKey = "LicenseKey"
		Me.LoggingLevel = WebScraper.LogLevel.All
		Me.WorkingDirectory = AppSetting.GetAppRoot() & "\MovieSample\Output\"
		Me.Request("www.website.com", AddressOf Parse)
	End Sub
	Public Overrides Sub Parse(ByVal response As Response)
		For Each Divs In response.Css("#movie-featured > div")
			If Divs.Attributes ("class") <> "clearfix" Then
				Dim MovieId = Divs.GetAttribute("data-movie-id")
				Dim link = Divs.Css("a")(0)
				Dim MovieTitle = link.TextContentClean
				Scrape(New ScrapedData() From {
					{ "MovieId", MovieId },
					{ "MovieTitle", MovieTitle }
				},
				"Movie.Jsonl")
			End If
		Next Divs
	End Sub
End Class

VB C#

這段代碼有什麼新變化？

工作目錄屬性用於設置所有抓取數據及其相關文件的主要工作目錄。

讓我們做得更多。

如果我們需要構建類型化對象以保存格式化對象中的抓取數據，該怎麼辦？

讓我們實現一個電影類，用來存放我們格式化的數據：

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; }

}

Public Class Movie
	Public Property Id() As Integer
	Public Property Title() As String
	Public Property URL() As String

End Class

VB C#

現在我們將更新我們的代碼：

public class MovieScraper : WebScraper
{
    public override void Init()
    {
        License.LicenseKey = "LicenseKey";
        this.LoggingLevel = WebScraper.LogLevel.All;
        this.WorkingDirectory = AppSetting.GetAppRoot() + @"\MovieSample\Output\";
        this.Request("https://website.com/", Parse);
    }
    public override void Parse(Response response)
    {
        foreach (var Divs in response.Css("#movie-featured > div"))
        {
            if (Divs.Attributes ["class"] != "clearfix")
            {
                var movie = new Movie();
                movie.Id = Convert.ToInt32( Divs.GetAttribute("data-movie-id"));
                var link = Divs.Css("a")[0];
                movie.Title = link.TextContentClean;
                movie.URL = link.Attributes ["href"];
                Scrape(movie, "Movie.Jsonl");
            }
        }
    }
}

public class MovieScraper : WebScraper
{
    public override void Init()
    {
        License.LicenseKey = "LicenseKey";
        this.LoggingLevel = WebScraper.LogLevel.All;
        this.WorkingDirectory = AppSetting.GetAppRoot() + @"\MovieSample\Output\";
        this.Request("https://website.com/", Parse);
    }
    public override void Parse(Response response)
    {
        foreach (var Divs in response.Css("#movie-featured > div"))
        {
            if (Divs.Attributes ["class"] != "clearfix")
            {
                var movie = new Movie();
                movie.Id = Convert.ToInt32( Divs.GetAttribute("data-movie-id"));
                var link = Divs.Css("a")[0];
                movie.Title = link.TextContentClean;
                movie.URL = link.Attributes ["href"];
                Scrape(movie, "Movie.Jsonl");
            }
        }
    }
}

Public Class MovieScraper
	Inherits WebScraper

	Public Overrides Sub Init()
		License.LicenseKey = "LicenseKey"
		Me.LoggingLevel = WebScraper.LogLevel.All
		Me.WorkingDirectory = AppSetting.GetAppRoot() & "\MovieSample\Output\"
		Me.Request("https://website.com/", AddressOf Parse)
	End Sub
	Public Overrides Sub Parse(ByVal response As Response)
		For Each Divs In response.Css("#movie-featured > div")
			If Divs.Attributes ("class") <> "clearfix" Then
				Dim movie As New Movie()
				movie.Id = Convert.ToInt32(Divs.GetAttribute("data-movie-id"))
				Dim link = Divs.Css("a")(0)
				movie.Title = link.TextContentClean
				movie.URL = link.Attributes ("href")
				Scrape(movie, "Movie.Jsonl")
			End If
		Next Divs
	End Sub
End Class

VB C#

有什麼新消息？

我們實現Movie Class來保存我們抓取的數據
我們將電影對象傳遞給 Scrape 方法，它了解我們的格式並以我們在此處看到的已定義格式保存：
讓我們開始抓取更詳細的頁面。

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

我們可以為我們的電影類別擴展新的屬性(描述, 類型, 演員, 導演, 國家, 片長, IMDB 評分)但我們將使用(描述, 類型, 演員)僅供我們的範例使用。

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; }

}

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; }

}

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

VB C#

現在我們將導航到詳細頁面進行抓取。

IronWebScraper 讓您可以增加更多抓取功能，以抓取不同類型的頁面格式。

如我們在此所見:

public class MovieScraper : WebScraper
{
    public override void Init()
    {
        License.LicenseKey = "LicenseKey";
        this.LoggingLevel = WebScraper.LogLevel.All;
        this.WorkingDirectory = AppSetting.GetAppRoot() + @"\MovieSample\Output\";
        this.Request("https://domain/", Parse);
    }
    public override void Parse(Response response)
    {
        foreach (var Divs in response.Css("#movie-featured > div"))
        {
            if (Divs.Attributes ["class"] != "clearfix")
            {
                var movie = new Movie();
                movie.Id = Convert.ToInt32( Divs.GetAttribute("data-movie-id"));
                var link = Divs.Css("a")[0];
                movie.Title = link.TextContentClean;
                movie.URL = link.Attributes ["href"];
                this.Request(movie.URL, ParseDetails, new MetaData() { { "movie", movie } });// to scrap Detailed Page
            }
        }           
    }
    public void ParseDetails(Response response)
    {
        var movie = response.MetaData.Get<Movie>("movie");
        var Div = response.Css("div.mvic-desc")[0];
        movie.Description = Div.Css("div.desc")[0].TextContentClean;
        foreach(var Genre in Div.Css("div > p > a"))
        {
            movie.Genre.Add(Genre.TextContentClean);
        }
        foreach (var Actor in Div.Css("div > p:nth-child(2) > a"))
        {
            movie.Actor.Add(Actor.TextContentClean);
        }
        Scrape(movie, "Movie.Jsonl");
    }
}

public class MovieScraper : WebScraper
{
    public override void Init()
    {
        License.LicenseKey = "LicenseKey";
        this.LoggingLevel = WebScraper.LogLevel.All;
        this.WorkingDirectory = AppSetting.GetAppRoot() + @"\MovieSample\Output\";
        this.Request("https://domain/", Parse);
    }
    public override void Parse(Response response)
    {
        foreach (var Divs in response.Css("#movie-featured > div"))
        {
            if (Divs.Attributes ["class"] != "clearfix")
            {
                var movie = new Movie();
                movie.Id = Convert.ToInt32( Divs.GetAttribute("data-movie-id"));
                var link = Divs.Css("a")[0];
                movie.Title = link.TextContentClean;
                movie.URL = link.Attributes ["href"];
                this.Request(movie.URL, ParseDetails, new MetaData() { { "movie", movie } });// to scrap Detailed Page
            }
        }           
    }
    public void ParseDetails(Response response)
    {
        var movie = response.MetaData.Get<Movie>("movie");
        var Div = response.Css("div.mvic-desc")[0];
        movie.Description = Div.Css("div.desc")[0].TextContentClean;
        foreach(var Genre in Div.Css("div > p > a"))
        {
            movie.Genre.Add(Genre.TextContentClean);
        }
        foreach (var Actor in Div.Css("div > p:nth-child(2) > a"))
        {
            movie.Actor.Add(Actor.TextContentClean);
        }
        Scrape(movie, "Movie.Jsonl");
    }
}

Public Class MovieScraper
	Inherits WebScraper

	Public Overrides Sub Init()
		License.LicenseKey = "LicenseKey"
		Me.LoggingLevel = WebScraper.LogLevel.All
		Me.WorkingDirectory = AppSetting.GetAppRoot() & "\MovieSample\Output\"
		Me.Request("https://domain/", AddressOf Parse)
	End Sub
	Public Overrides Sub Parse(ByVal response As Response)
		For Each Divs In response.Css("#movie-featured > div")
			If Divs.Attributes ("class") <> "clearfix" Then
				Dim movie As New Movie()
				movie.Id = Convert.ToInt32(Divs.GetAttribute("data-movie-id"))
				Dim link = Divs.Css("a")(0)
				movie.Title = link.TextContentClean
				movie.URL = link.Attributes ("href")
				Me.Request(movie.URL, AddressOf ParseDetails, New MetaData() From {
					{ "movie", movie }
				}) ' to scrap Detailed Page
			End If
		Next Divs
	End Sub
	Public Sub ParseDetails(ByVal response As Response)
		Dim movie = response.MetaData.Get(Of Movie)("movie")
		Dim Div = response.Css("div.mvic-desc")(0)
		movie.Description = Div.Css("div.desc")(0).TextContentClean
		For Each Genre In Div.Css("div > p > a")
			movie.Genre.Add(Genre.TextContentClean)
		Next Genre
		For Each Actor In Div.Css("div > p:nth-child(2) > a")
			movie.Actor.Add(Actor.TextContentClean)
		Next Actor
		Scrape(movie, "Movie.Jsonl")
	End Sub
End Class

VB C#

有什麼新消息？