feat: 完成yi.tool.web爬虫

This commit is contained in:
橙子
2024-06-09 00:29:53 +08:00
parent f44a099469
commit f267d820bf
11 changed files with 144 additions and 10 deletions

View File

@@ -0,0 +1,85 @@
using HtmlAgilityPack;
using Microsoft.Extensions.Caching.Distributed;
using Volo.Abp.Caching;
using Volo.Abp.DependencyInjection;
namespace Yi.Abp.Tool.Domain
{
public class NugetCrawlerManager : ITransientDependency
{
private const string NugetVersionUrl = "https://www.nuget.org/packages/Yi.Abp.Tool#versions-body-tab";
public NugetCrawlerManager(IDistributedCache<NugetResult> cache)
{
//缓存设置1分钟获取一次结果
this.NugetResult = cache.GetOrAdd("NugetResult", () =>
{
return InitData();
}, () =>
{
var options = new DistributedCacheEntryOptions();
options.AbsoluteExpiration = DateTimeOffset.Now.AddMinutes(1);
return options;
})!;
}
private HtmlDocument HtmlDoc { get; set; }
private NugetResult NugetResult { get; set; } = new NugetResult();
private NugetResult InitData()
{
NugetResult nugetResult = new NugetResult();
HtmlWeb web = new HtmlWeb();
this.HtmlDoc = web.Load(NugetVersionUrl);
nugetResult.Versions = GetVersionList();
nugetResult.DownloadNumberNumber = GetDownloadNumber();
return nugetResult;
}
public NugetResult GetNugetResult()
{
return this.NugetResult;
}
/// <summary>
/// 获取版本号列表
/// </summary>
/// <returns></returns>
private List<string> GetVersionList()
{
List<string> versions = new List<string>();
var versionDoc = HtmlDoc.DocumentNode.SelectNodes("//*[@id=\"version-history\"]/table/tbody");
var trDoc = versionDoc.First().ChildNodes.Where(x => x.Name == "tr").ToList();
foreach (var tr in trDoc)
{
var version = tr.ChildNodes.Where(x => x.Name == "td").First().ChildNodes.Where(x => x.Name == "a").First().GetAttributes("title").First().Value;
versions.Add(version);
}
return versions;
}
/// <summary>
/// 获取下载总数
/// </summary>
/// <returns></returns>
private long GetDownloadNumber()
{
var spanDoc = HtmlDoc.DocumentNode.SelectNodes("//*[@id=\"skippedToContent\"]/section/div/aside/div[1]/div[2]/div[1]/span[2]");
var downLoadNumber = spanDoc.First().InnerText;
return long.Parse(downLoadNumber);
}
}
public class NugetResult
{
public long DownloadNumberNumber { get; set; }
public List<string> Versions { get; set; }
}
}

View File

@@ -5,8 +5,13 @@
<ImplicitUsings>enable</ImplicitUsings>
<Nullable>enable</Nullable>
</PropertyGroup>
<ItemGroup>
<PackageReference Include="HtmlAgilityPack" Version="1.11.61" />
<PackageReference Include="Volo.Abp.Caching" Version="$(AbpVersion)" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\Yi.Abp.Tool.Domain.Shared\Yi.Abp.Tool.Domain.Shared.csproj" />
</ItemGroup>
</Project>