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
43 lines
849 B
C#
43 lines
849 B
C#
using MongoDB.Entities;
|
|
|
|
namespace PrivaPub.Models.Jobs
|
|
{
|
|
public class Job : Entity
|
|
{
|
|
public JobKind Kind { get; set; }
|
|
public JobState State { get; set; }
|
|
public string Payload { get; set; }
|
|
public string Host { get; set; }
|
|
public string DedupeKey { get; set; }
|
|
public int Attempts { get; set; }
|
|
public DateTime RunAt { get; set; } = DateTime.UtcNow;
|
|
public DateTime? LeasedUntil { get; set; }
|
|
public string LeaseOwner { get; set; }
|
|
public string LastError { get; set; }
|
|
public DateTime CreatedAt { get; set; } = DateTime.UtcNow;
|
|
public DateTime? FinishedAt { get; set; }
|
|
}
|
|
|
|
public enum JobKind
|
|
{
|
|
Deliver,
|
|
ProcessInbox,
|
|
FetchAncestors,
|
|
DescribeInstance,
|
|
PollRefresh,
|
|
PollClose,
|
|
FetchPreview,
|
|
RollupDay,
|
|
CrawlPlan,
|
|
CrawlInstance
|
|
}
|
|
|
|
public enum JobState
|
|
{
|
|
Pending,
|
|
Running,
|
|
Done,
|
|
Dead
|
|
}
|
|
}
|