thepraandClaude Opus 5.5
4f5df743ae
Off by default (Statistics:Crawler:Enabled), as the owner decided. When it is on:
- CrawlPlan runs hourly, from StatisticsSchedule. It inserts the configured seeds and
queues up to HostsPerHour servers whose last visit is older than RevisitDays, are not
paused by the breaker and are not domain-blocked, spread across the hour.
- CrawlInstance visits one server at a time as
"PrivaPub-Stargazer/<ref> (+<base>/stargazing)":
- it reads robots.txt (RFC 9309: its own group first, then PrivaPub, then *; longest
rule wins; a 4xx allows everything; a 5xx or no answer keeps it out);
- it describes servers that only crawling ever found, through
InstanceDescriber.Describe with robots.txt as the path filter;
- it reads /api/v1/instance/peers through the new GetStringArray, which keeps what it
read from the first 1 MB instead of refusing a large list;
- it adds the names a server could ever be reached at as "crawled": DNS only,
punycode, no addresses, ports or hidden services, and the reserved test names only on
a test network. Never more than MaxNewHostsPerCrawl per visit or MaxHosts in all, and
never over a touched server.
- It reads nothing but robots.txt, NodeInfo, the instance API and the peers list.
IFederationHttp.GetText serves robots.txt, and HttpScope.Crawl carries the
User-Agent.
- /stargazing explains all this and how to keep the crawler out, says whether it is on,
and credits DB-IP. GET /clientapi/admin/statistics/crawler shows the frontier.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ELjqpznMFMNrJoJUj6K5p2
79 lines
3.5 KiB
C#
79 lines
3.5 KiB
C#
using Microsoft.AspNetCore.Authorization;
|
|
using Microsoft.AspNetCore.Mvc;
|
|
|
|
using PrivaPub.ClientModels;
|
|
using PrivaPub.Domain.Statistics;
|
|
using PrivaPub.Infrastructure.Jobs;
|
|
using PrivaPub.Infrastructure.Statistics;
|
|
using PrivaPub.Models.Jobs;
|
|
|
|
using System.Globalization;
|
|
|
|
namespace PrivaPub.Controllers.ClientToServer
|
|
{
|
|
[ApiController,
|
|
Route("clientapi/admin/statistics"),
|
|
Authorize(Policy = Policies.IsAdmin)]
|
|
public class StatisticsController : ControllerBase
|
|
{
|
|
readonly StatisticsQueries _queries;
|
|
readonly IJobQueue _queue;
|
|
readonly Microsoft.Extensions.Options.IOptionsMonitor<StatisticsOptions> _options;
|
|
|
|
public StatisticsController(StatisticsQueries queries, IJobQueue queue, Microsoft.Extensions.Options.IOptionsMonitor<StatisticsOptions> options)
|
|
{
|
|
_queries = queries;
|
|
_queue = queue;
|
|
_options = options;
|
|
}
|
|
|
|
[HttpGet, Route("/clientapi/admin/statistics/crawler")]
|
|
public async Task<IActionResult> Crawler(CancellationToken token) =>
|
|
Ok(await _queries.Crawler(_options.CurrentValue.Crawler.Enabled, _options.CurrentValue.Crawler.RevisitDays, token));
|
|
|
|
[HttpGet, Route("/clientapi/admin/statistics/overview")]
|
|
public async Task<IActionResult> Overview([FromQuery] int days = 30, CancellationToken token = default) =>
|
|
Ok(await _queries.Overview(days, token));
|
|
|
|
[HttpGet, Route("/clientapi/admin/statistics/hosts")]
|
|
public async Task<IActionResult> Hosts([FromQuery] int days = 30, [FromQuery] string sort = default, [FromQuery] string software = default,
|
|
[FromQuery] int page = 1, [FromQuery] int limit = 50, CancellationToken token = default) =>
|
|
Ok(await _queries.Hosts(days, sort, software, page, limit, token));
|
|
|
|
[HttpGet, Route("/clientapi/admin/statistics/hosts/{host}")]
|
|
public async Task<IActionResult> Host(string host, [FromQuery] int days = 90, CancellationToken token = default) =>
|
|
await _queries.Host(host, days, token) is { } found ? Ok(found) : NotFound();
|
|
|
|
[HttpGet, Route("/clientapi/admin/statistics/events")]
|
|
public async Task<IActionResult> Events([FromQuery] string host = default, [FromQuery] string channel = default, [FromQuery] string outcome = default,
|
|
[FromQuery] string reason = default, [FromQuery] DateTime? before = default, [FromQuery] int limit = 100, CancellationToken token = default) =>
|
|
Ok(await _queries.Events(host, channel, outcome, reason, before, limit, token));
|
|
|
|
[HttpGet, Route("/clientapi/admin/statistics/server")]
|
|
public async Task<IActionResult> Server([FromQuery] int days = 30, CancellationToken token = default) =>
|
|
Ok(await _queries.Server(days, token));
|
|
|
|
[HttpPost, Route("/clientapi/admin/statistics/rollups/{day}")]
|
|
public async Task<IActionResult> Rollup(string day, CancellationToken token)
|
|
{
|
|
if (!DateTime.TryParseExact(day, "yyyy-MM-dd", CultureInfo.InvariantCulture, DateTimeStyles.AdjustToUniversal | DateTimeStyles.AssumeUniversal, out var parsed)
|
|
|| parsed.Date >= DateTime.UtcNow.Date)
|
|
return BadRequest();
|
|
var job = RollupJob.For(parsed.Date, $"rollup|{day}|rerun|{DateTime.UtcNow.Ticks}");
|
|
job.RunAt = DateTime.UtcNow;
|
|
await _queue.EnqueueMany(new[] { job }, token);
|
|
return Accepted();
|
|
}
|
|
|
|
[HttpPost, Route("/clientapi/admin/statistics/hosts/{host}/describe")]
|
|
public async Task<IActionResult> Describe(string host, CancellationToken token)
|
|
{
|
|
host = Interactions.Host(host);
|
|
if (host == Interactions.Unknown)
|
|
return BadRequest();
|
|
await _queue.Enqueue(JobKind.DescribeInstance, host, host, $"describe|{host}|admin|{DateTime.UtcNow.Ticks}", token);
|
|
return Accepted();
|
|
}
|
|
}
|
|
}
|