我想尝试将我的音乐文件按类型划分为文件夹，为了方便起见，我用 c# 编写代码。我需要的信息位于 google 页面 html 代码的这个 div 类中 \'...

我想尝试将我的音乐文件按类型划分到文件夹中，为了方便起见，我用 c# 编写代码。我需要的信息位于 google 页面 \'xGj8Mb\' 的 html 代码的这个 div 类中，但使用标准 c# 方法以及 AngleSharp 库，我无法访问此信息，并且它不会保存太多其他信息。我使用 Jsoup 库用 Java 重写了相同的代码，它从页面中获取所有信息。下面我报告了我用于进行此实验的代码，既使用了 AngleSharp 也使用了标准方法。

使用标准方法编码

public class Program {
private static async Task Main(string[] args) {
    const string folderPath = @"C:\Users\chris\Desktop\Attilio\ATTILIO MUSIC";
    if (!Directory.Exists(folderPath)) {
        Console.Error.WriteLine("DOES NOT EXIST");
        return;
    }

    var archive = Directory.GetFiles(folderPath);
    foreach (var entry in archive) {
        // Check if the file is not a directory and has the .mp3 or .wav extension
        var fileName = entry.Split(folderPath + @"\")[1];
        //Console.WriteLine(fileName);

        SearchOnInternet(fileName);
        return;
    }

    Console.WriteLine($"Number: {archive.Length}");
}

private static void SearchOnInternet(string fileName) {
    // Split to remove the extension from the file name
    if (fileName.EndsWith(".mp3"))
        fileName = fileName.Split(".mp3")[0];
    else if (fileName.EndsWith(".wav"))
        fileName = fileName.Split(".wav")[0];

    // Conversion for the search
    var fileNameAsUrl = Uri.EscapeDataString(fileName);
    Console.WriteLine(fileNameAsUrl);
    var url =
        $"https://www.google.com/search?q={fileNameAsUrl}";

    // Search
    using (var client = new HttpClient()) {
        var response = client.GetAsync(url);
        if (response.Result.IsSuccessStatusCode) {
            var responseBody = response.Result.Content.ReadAsStringAsync();

            // Save page
            var outputPath = @"C:\Users\chris\Documents\Universita\Programmi\C#\FileAura\FileAuraServer\Search";
            if (!Directory.Exists(outputPath))
                Directory.CreateDirectory(outputPath);
            File.WriteAllText(
                @$"{outputPath}\{fileName}.html",
                responseBody.Result);
        }
    }
}

}

使用 AngleSharp 的代码

private static async void SearchOnInternet(string fileName) {
    // Split to remove the extension from the file name
    if (fileName.EndsWith(".mp3"))
        fileName = fileName.Split(".mp3")[0];
    else if (fileName.EndsWith(".wav"))
        fileName = fileName.Split(".wav")[0];

    // Conversion for the search
    var fileNameAsUrl = Uri.EscapeDataString(fileName);
    var googleSearchUrl =
        $"https://www.google.com/search?q={fileNameAsUrl}";

    // Create an HttpClient to send the request
    using var httpClient = new HttpClient();

    // Send a GET request to Google
    var response = await httpClient.GetAsync(googleSearchUrl);

    // Ensure the request was successful
    response.EnsureSuccessStatusCode();

    // Get the response content as a string
    var responseContent = await response.Content.ReadAsStringAsync();

    // Save the HTML content to a file
    string filePath = "output.html";
    await File.WriteAllTextAsync(filePath, responseContent);

    Console.WriteLine($"The HTML content has been saved to {filePath}");

    // Configure AngleSharp to parse the HTML
    var context = BrowsingContext.New(Configuration.Default);
    var parser = context.GetService<IHtmlParser>();
    var document = await parser.ParseDocumentAsync(responseContent);

    // Example: extract the title of the search results page
    var title = document.Title;
    Console.WriteLine("Title: " + title);

    // Example: extract the search results
    var results = document.QuerySelectorAll("h3"); // <h3> elements contain the titles of the search results

    foreach (var result in results)
    {
        Console.WriteLine(result.TextContent);
    }
}

• anglesharp