c# - C# 使用递归从完整 url 中检索父子 url
问题描述
我需要您帮助从完整 URL 获取父子 URL 列表,可能是递归使用。例如,下面是平面结构中的 URL。我必须用子结构的内部级别以父子形式解析。
- https://domain/UrlA/UrlA_L1/UrlA_L1_L2
- https://domain/UrlA/UrlA_L1/UrlA2_L1_L2
- https://domain/UrlB/UrlB_L1/UrlB_L1_L2
- https://domain/UrlC/UrlC_L1/UrlC_L1_L2
- https://domain/UrlD/UrlD_L1/UrlD_L1_L2/UrlD_L1_L2_L3
- https://domain/UrlE/UrlE_L1/UrlE_L1_L2/UrlE_L1_L2_L3
- https://domain/UrlF/UrlF_L1/UrlF_L1_L2/UrlF_L1_L2_L3
进入具有子父关系的 URL 列表。
public class HtmlSiteMap
{
public string Url { get; set; }
public string PageTitle { get; set; }
public int UrlLevel { get; set; }
public List<HtmlSiteMap> Childrens { get; set; }
}
我的预期输出
{
Url: https://domain/UrlA,
PageTitle : UrlA,
UrlLevel : 0 ,
Childrens : {
Url : https://domain/UrlA/UrlA_L1,
PageTitle : UrlA_L1,
UrlLevel : 1,
Childrens : {
Url : https://domain/UrlA/UrlA_L1/UrlA_L1_L2,
PageTitle : UrlA_L1_L2,
UrlLevel : 2,
Childrens : null
},
{
Url : https://domain/UrlA/UrlA_L1/UrlA2_L1_L2,
PageTitle : UrlA2_L1_L2,
UrlLevel : 2,
Childrens : null
}
},
Url: https://domain/UrlB,
PageTitle : UrlB,
UrlLevel : 0 ,
Childrens : {
Url : https://domain/UrlB/UrlB_L1,
PageTitle : UrlB_L1,
UrlLevel : 1,
Childrens : {
Url : https://domain/UrlB/UrlB_L1/UrlB_L1_L2,
PageTitle : UrlB_L1_L2,
UrlLevel : 2,
Childrens : null
}
}
.................
.................
..................
}
我试图通过拆分和递归来实现。但无法得到结果。您的帮助将不胜感激。
解决方案
基本版本(没有错误处理)可能如下所示:
static void Main(string[] args)
{
var input = new List<string>
{
"https://domain/UrlA/",
"https://domain/UrlA/UrlA_L1/",
"https://domain/UrlA/UrlA_L1/UrlA_L1_L2",
"https://domain/UrlA/UrlA_L1/UrlA2_L1_L2",
"https://domain/UrlB",
"https://domain/UrlB/UrlB_L1",
"https://domain/UrlB/UrlB_L1/UrlB_L1_L2",
"https://domain/UrlC/UrlC_L1/UrlC_L1_L2",
"https://domain/UrlD/UrlD_L1/UrlD_L1_L2/UrlD_L1_L2_L3",
"https://domain/UrlE/UrlE_L1/UrlE_L1_L2/UrlE_L1_L2_L3",
"https://domain/UrlF/UrlF_L1/UrlF_L1_L2/UrlF_L1_L2_L3"
};
var output = new List<HtmlSiteMap>();
foreach (var url in input)
{
var parts = url.Split(@"/", StringSplitOptions.RemoveEmptyEntries);
var current = new HtmlSiteMap
{
Url = url,
PageTitle = parts[^1]
};
var parentName = parts[^2];
static HtmlSiteMap FindParent(List<HtmlSiteMap> score, string name)
{
foreach (var item in score)
{
if (item.PageTitle == name)
{
return item;
}
var inChild = FindParent(item.Childrens, name);
if (inChild != null)
{
return inChild;
}
}
return null;
}
var parent = FindParent(output, parentName);
if (parent == null)
{
current.UrlLevel = 1;
output.Add(current);
}
else
{
current.UrlLevel = parent.UrlLevel + 1;
parent.Childrens.Add(current);
}
}
foreach (var current in output)
{
Console.WriteLine(current.ToString());
}
Console.ReadLine();
}
public class HtmlSiteMap
{
public string Url { get; set; }
public string PageTitle { get; set; }
public int UrlLevel { get; set; }
public List<HtmlSiteMap> Children { get; set; }
public HtmlSiteMap()
{
Children = new List<HtmlSiteMap>();
}
public override string ToString()
{
var shift = new string(' ', UrlLevel);
var sb = new StringBuilder();
sb.AppendLine(shift + $"Url: {Url},");
sb.AppendLine(shift + $"PageTitle: {PageTitle},");
sb.AppendLine(shift + $"UrlLevel: {UrlLevel},");
sb.AppendLine(shift + "Children:");
if (Children.Count == 0)
{
sb.AppendLine(shift + "-");
}
else
{
foreach (var child in Children)
{
sb.AppendLine(child.ToString());
}
}
return sb.ToString();
}
}