Question

所以，我正在看的html数据是：

<A HREF="/data/client/Action.log">Action.log</A><br>  6/8/2015  3:45 PM

由此我需要提取Action.log的实例，

我的问题是我已经完成了大量的正则表达式教程，我似乎仍然无法通过大脑提取模式来提取它。我想我对正则表达式缺乏一些基本的理解，但任何帮助都会受到赞赏。

编辑：

internal string[] ParseFolderIndex_Alpha(string url, WebDirectory directory)
    {
        try
        {
            HttpWebRequest request = (HttpWebRequest)WebRequest.Create(url);
            request.Timeout = 3 * 60 * 1000;
            request.KeepAlive = true;

            HttpWebResponse response = (HttpWebResponse)request.GetResponse();

            if (response.StatusCode == HttpStatusCode.OK)
            {
                List<string> fileLocations = new List<string>(); string line;
                using (StreamReader reader = new StreamReader(response.GetResponseStream()))
                {
                    while ((line = reader.ReadLine()) != null)
                    {
                        int index = line.IndexOf("<a href=");
                        if (index >= 0)
                        {
                            string[] segments = line.Substring(index).Split('\"');

                            ///Can Parse File Size Here: Add todo
                            if (!segments[1].Contains("/"))
                            {
                                fileLocations.Add(segments[1]);
                                UI.UpdatePatchNotes("Web File Found: " + segments[1]);

                                UI.UpdateProgressBar();
                            }

                            else
                            {
                                if (segments[1] != @"../")
                                {
                                    directory.SubDirectories.Add(new WebDirectory(url + segments[1], this));
                                    UI.UpdatePatchNotes("Web Directory Found: " + segments[1].Replace("/", string.Empty));
                                }
                            }
                        }
                        else if (line.Contains("</pre")) break;
                    }
                }

                response.Dispose(); /// After ((line = reader.ReadLine()) != null)
                return fileLocations.ToArray<string>();
            }

            else return new string[0]; /// !(HttpStatusCode.OK)
        }

        catch (Exception e)
        {
            LogHandler.LogErrors(e.ToString(), this);
            LogHandler.LogErrors(url, this);
            return null;
        }
    }

这就是我在做的，问题是我改变了服务器并且html IIS显示的是不同的所以我必须制作新的逻辑。

修改/ 结论：

首先，对不起，我甚至提到正则表达式：P其次，每个平台都必须根据环境单独处理。

这就是我目前收集文件名的方式。

internal string[] ParseFolderIndex(string url, WebDirectory directory)
        {
            try
            {
                HttpWebRequest request = (HttpWebRequest)WebRequest.Create(url);
                request.Timeout = 3 * 60 * 1000;
                request.KeepAlive = true;

                HttpWebResponse response = (HttpWebResponse)request.GetResponse();
                bool endMet = false;
                if (response.StatusCode == HttpStatusCode.OK)
                {
                    List<string> fileLocations = new List<string>(); string line;
                    using (StreamReader reader = new StreamReader(response.GetResponseStream()))
                    {
                        while (!endMet)
                        {
                            line = reader.ReadLine();
                            if (line != null && line != "" && line.IndexOf("</A>") >= 0)
                            {
                                if (line.Contains("</html>")) endMet = true;
                                string[] segments = line.Replace("\\", "").Split('\"');
                                List<string> paths = new List<string>();
                                List<string> files = new List<string>();
                                for (int i = 0; i < segments.Length; i++)
                                {
                                    if (!segments[i].Contains('<'))
                                        paths.Add(segments[i]);
                                }

                                paths.RemoveAt(0);

                                foreach (String s in paths)
                                {
                                    string[] secondarySegments = s.Split('/');
                                    if (s.Contains(".") || s.Contains("Verinfo"))
                                        files.Add(secondarySegments[secondarySegments.Length - 1]);
                                    else
                                    {
                                        directory.SubDirectories.Add(new WebDirectory
                                            (url + "/" + secondarySegments[secondarySegments.Length - 2], this));
                                        UI.UpdatePatchNotes("Web Directory Found: " + secondarySegments[secondarySegments.Length - 2]);
                                    }

                                }

                                foreach (String s in files)
                                {
                                    if (!String.IsNullOrEmpty(s) && !s.Contains('%'))
                                    {
                                        fileLocations.Add(s);
                                        UI.UpdatePatchNotes("Web File Found: " + s);

                                        UI.UpdateProgressBar();
                                    }
                                }

                                if (line.Contains("</pre")) break;
                            }
                        }
                    }

                    response.Dispose(); /// After ((line = reader.ReadLine()) != null)
                    return fileLocations.ToArray<string>();
                }

                else return new string[0]; /// !(HttpStatusCode.OK)
            }

            catch (Exception e)
            {
                LogHandler.LogErrors(e.ToString(), this);
                LogHandler.LogErrors(url, this);
                return null;
            }
        }

Answer 1

尝试匹配以下模式：

<A HREF="(?<url>.*)">

然后从匹配结果中获取名为url的组。

工作示例：https://regex101.com/r/hW8iH6/1

Answer 2

正则表达式是矫枉过正。它太重了，考虑到字符串的格式总是一样的，你会发现使用拆分和子串更容易调试和维护。

 class Program {
    static void Main(string[] args) {

        String s = "<A HREF=\"/data/client/Action.log\">Action.log</A><br>  6/8/2015  3:45 PM ";

        String[] t = s.Split('"');

        String fileName = String.Empty;

        //To get the entire file name and path....
        fileName = t[1].Substring(0, (t[1].Length));

        //To get just the file name (Action.log in this case)....
        fileName = t[1].Substring(0, (t[1].Length)).Split('/').Last();
    }
}

Answer 3

string text = @"<A HREF=""/data/client/Action.log"">Action.log</A><br>  6/8/2015  3:45 PM";

            var match = Regex.Match(text, @"^<A HREF=\""\/data\/client\/.*\.log\"">(.*)</A>.*$");
            var result = match.Groups[1].Value;

尝试http://regexr.com/或Regexbuddy！

通过url提取文件的正则表达式模式？

3 个答案: