Question

我有一点腌渍。我想在网站上抓取一系列图片。我知道如何做到这一点，但我必须过滤出图像的位置。

例如我想要在id为“theseImages”的div标签中抓取图像，但在另一个div标签中还有另一组图像，其ID为“notTheseImages”。将每个标记循环到带有标签“img”的HtmlElementCollection中会忽略div，因为它还会从“notTheseImages”中获取图像。

有没有办法在检查这些图像在div标签中的位置时循环显示图像？

Answer 1

这可以帮助您选择当前的HTML，也许可以用于未来的场景：）

protected HtmlElement[] GetElementsByParent(HtmlDocument document, HtmlElement baseElement = null, params string[] singleSelectors)
{
    if (singleSelectors == null || singleSelectors.Length == 0)
    {
        throw new Exception("Please give at least 1 selector!");
    }
    IList<HtmlElement> result = new List<HtmlElement>();
    bool last = singleSelectors.Length == 1;
    string singleSelector = singleSelectors[0];
    if (string.IsNullOrWhiteSpace(singleSelector) || string.IsNullOrWhiteSpace(singleSelector.Trim()))
    {
        return null;
    }
    singleSelector = singleSelector.Trim();
    if (singleSelector.StartsWith("#"))
    {
        var item = document.GetElementById(singleSelector.Substring(1));
        if (item == null)
        {
            return null;
        }
        if (last)
        {
            result.Add(item);
        }
        else
        {
            var results = GetElementsByParent(document, item, singleSelectors.Skip(1).ToArray());
            if (results != null && results.Length > 0)
            {
                foreach (var res in results)
                {
                    result.Add(res);
                }
            }
        }
    }
    else if (singleSelector.StartsWith("."))
    {
        if (baseElement == null)
        {
            baseElement = document.Body;
        }
        foreach (HtmlElement child in baseElement.Children)
        {
            string cls;
            if (!string.IsNullOrWhiteSpace((cls = child.GetAttribute("class"))))
            {
                if (cls.Split(' ').Contains(singleSelector.Substring(1)))
                {
                    if (last)
                    {
                        result.Add(child);
                    }
                    else
                    {
                        var results = GetElementsByParent(document, child, singleSelectors.Skip(1).ToArray());
                        if (results != null && results.Length > 0)
                        {
                            foreach (var res in results)
                            {
                                result.Add(res);
                            }
                        }
                    }
                }
            }
        }
    }
    else
    {
        HtmlElementCollection elements = null;

        if (baseElement != null)
        {
            elements = baseElement.GetElementsByTagName(singleSelector);
        }
        else
        {
            elements = document.GetElementsByTagName(singleSelector);
        }
        foreach (HtmlElement item in elements)
        {
            if (last)
            {
                result.Add(item);
            }
            else
            {
                var results = GetElementsByParent(document, item, singleSelectors.Skip(1).ToArray());
                if (results != null && results.Length > 0)
                {
                    foreach (var res in results)
                    {
                        result.Add(res);
                    }
                }
            }
        }
    }
    return result.ToArray();
}

private void webBrowser1_DocumentCompleted(object sender, WebBrowserDocumentCompletedEventArgs e)
{
    // here we can query
    var result = GetElementsByParent(webBrowser1.Document, null, "#theseImages", "img");
}

结果将包含#theseImages

下的图像

请注意，GetElementsByParent是相当未经测试的，我只是根据您的用例测试它，它似乎没问题。

一旦确定文档已完成，请不要忘记启动查询;）

标记中的C＃HTML标记

1 个答案: