:

我觉得你想错了,亚历克斯。假设我写了一些C代码如下:

string codeBlock = "if (x == 1) Console.WriteLine(\"Hello, World!\");";

不 ,因为在格式良好的C#文件的上下文中,该文本表示 string codeBlock 正在分配变量。

<object> 和 <embed> 元素 根本不是元素

事实上,如果 HtmlAgilityPack 做 如果是HTML,使用这些元素仍然不会成功,因为在JavaScript中,它们被大量使用 \ Unescape 方法来解决这个问题)。

.

YouTubeScraper

<对象> 和 < 来自JavaScript海洋的元素。

class YouTubeScraper
{
    public HtmlNode FindObjectElement(string url)
    {
        HtmlNodeCollection scriptNodes = FindScriptNodes(url);

        for (int i = 0; i < scriptNodes.Count; ++i)
        {
            HtmlNode scriptNode = scriptNodes[i];

            string javascript = scriptNode.InnerHtml;

            int objectNodeLocation = javascript.IndexOf("<object");

            if (objectNodeLocation != -1)
            {
                string htmlStart = javascript.Substring(objectNodeLocation);

                int objectNodeEndLocation = htmlStart.IndexOf(">\" :");

                if (objectNodeEndLocation != -1)
                {
                    string finalEscapedHtml = htmlStart.Substring(0, objectNodeEndLocation + 1);

                    string unescaped = Unescape(finalEscapedHtml);

                    var objectDoc = new HtmlDocument();

                    objectDoc.LoadHtml(unescaped);

                    HtmlNode objectNode = objectDoc.GetElementbyId("movie_player");

                    return objectNode;
                }
            }
        }

        return null;
    }

    public HtmlNode FindEmbedElement(string url)
    {
        HtmlNodeCollection scriptNodes = FindScriptNodes(url);

        for (int i = 0; i < scriptNodes.Count; ++i)
        {
            HtmlNode scriptNode = scriptNodes[i];

            string javascript = scriptNode.InnerHtml;

            int approxEmbedNodeLocation = javascript.IndexOf("<\\/object>\" : \"<embed");

            if (approxEmbedNodeLocation != -1)
            {
                string htmlStart = javascript.Substring(approxEmbedNodeLocation + 15);

                int embedNodeEndLocation = htmlStart.IndexOf(">\";");

                if (embedNodeEndLocation != -1)
                {
                    string finalEscapedHtml = htmlStart.Substring(0, embedNodeEndLocation + 1);

                    string unescaped = Unescape(finalEscapedHtml);

                    var embedDoc = new HtmlDocument();

                    embedDoc.LoadHtml(unescaped);

                    HtmlNode videoEmbedNode = embedDoc.GetElementbyId("movie_player");

                    return videoEmbedNode;
                }
            }
        }

        return null;
    }

    protected HtmlNodeCollection FindScriptNodes(string url)
    {
        var doc = new HtmlDocument();

        WebRequest request = WebRequest.Create(url);
        using (var response = request.GetResponse())
        using (var stream = response.GetResponseStream())
        {
            doc.Load(stream);
        }

        HtmlNode root = doc.DocumentNode;
        HtmlNodeCollection scriptNodes = root.SelectNodes("//script");

        return scriptNodes;
    }

    static string Unescape(string htmlFromJavascript)
    {
        // The JavaScript has escaped all of its HTML using backslashes. We need
        // to reverse this.

        // DISCLAIMER: I am a TOTAL Regex n00b; I make no claims as to the robustness
        // of this code. If you could improve it, please, I beg of you to do so. Personally,
        // I tested it on a grand total of three inputs. It worked for those, at least.
        return Regex.Replace(htmlFromJavascript, @"\\(.)", UnescapeFromBeginning);
    }

    static string UnescapeFromBeginning(Match match)
    {
        string text = match.ToString();

        if (text.StartsWith("\\"))
        {
            return text.Substring(1);
        }

        return text;
    }
}

如果你感兴趣,这里有一个小演示我扔在一起(超级花哨,我知道):

class Program
{
    static void Main(string[] args)
    {
        var scraper = new YouTubeScraper();

        HtmlNode davidAfterDentistEmbedNode = scraper.FindEmbedElement("http://www.youtube.com/watch?v=txqiwrbYGrs");
        Console.WriteLine("David After Dentist:");
        Console.WriteLine(davidAfterDentistEmbedNode.OuterHtml);
        Console.WriteLine();

        HtmlNode drunkHistoryObjectNode = scraper.FindObjectElement("http://www.youtube.com/watch?v=jL68NyCSi8o");
        Console.WriteLine("Drunk History:");
        Console.WriteLine(drunkHistoryObjectNode.OuterHtml);
        Console.WriteLine();

        HtmlNode jessicaDailyAffirmationEmbedNode = scraper.FindEmbedElement("http://www.youtube.com/watch?v=qR3rK0kZFkg");
        Console.WriteLine("Jessica's Daily Affirmation:");
        Console.WriteLine(jessicaDailyAffirmationEmbedNode.OuterHtml);
        Console.WriteLine();

        HtmlNode jazzerciseObjectNode = scraper.FindObjectElement("http://www.youtube.com/watch?v=VGOO8ZhWFR4");
        Console.WriteLine("Jazzercise - Move your Boogie Body:");
        Console.WriteLine(jazzerciseObjectNode.OuterHtml);
        Console.WriteLine();

        Console.Write("Finished! Hit Enter to quit.");
        Console.ReadLine();
    }
}

为什么不改用元素的Id呢?

HtmlNode videoEmbedNode = doc.GetElementbyId("movie_player");

更新 在内部 JavaScript?这就是为什么这不起作用。(它们并不是真正要从 HtmlAgilityPack文件 ;所有这些JavaScript实际上都是 <script> <脚本> 标记的内部文本本身 从那里开始。