Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion packages/webdecoy/src/bots/bots.test.ts
Original file line number Diff line number Diff line change
Expand Up @@ -60,7 +60,7 @@ describe('matchUserAgent', () => {

describe('registry integrity', () => {
it('carries the full generated table', () => {
expect(BOT_REGISTRY.length).toBe(168);
expect(BOT_REGISTRY.length).toBe(169);
expect(BOT_CATEGORIES).toContain('training_crawler');
expect(BOT_CATEGORIES).toContain('search_crawler');
});
Expand Down
12 changes: 12 additions & 0 deletions packages/webdecoy/src/bots/parity-vectors.generated.json
Original file line number Diff line number Diff line change
Expand Up @@ -1967,6 +1967,18 @@
"category": "archiver",
"matched": true
},
{
"userAgent": "webdecoybot",
"id": "webdecoybot",
"category": "monitoring",
"matched": true
},
{
"userAgent": "Mozilla/5.0 (compatible; webdecoybot/1.0; +http://example.com/bot)",
"id": "webdecoybot",
"category": "monitoring",
"matched": true
},
{
"userAgent": "webscrapingapi",
"id": "webscrapingapi",
Expand Down
3 changes: 2 additions & 1 deletion packages/webdecoy/src/bots/registry.generated.ts
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
* agents share User-Agent substrings, so sorting this array changes how real
* traffic is classified.
*
* 168 agents across 15 categories.
* 169 agents across 15 categories.
*/

/**
Expand Down Expand Up @@ -211,6 +211,7 @@ export const BOT_REGISTRY: readonly BotAgent[] = [
{ id: "libwww-perl", name: "libwww-perl", category: "fetcher", organization: "Perl", baseScore: 50, respectsRobots: false, uaPatterns: ["libwww-perl"] },
{ id: "lwp", name: "LWP", category: "fetcher", organization: "Perl", baseScore: 50, respectsRobots: false, uaPatterns: ["lwp-"] },
{ id: "httrack", name: "HTTrack", category: "fetcher", organization: "Open Source", baseScore: 60, respectsRobots: true, uaPatterns: ["httrack"] },
{ id: "webdecoybot", name: "WebDecoyBot", category: "monitoring", organization: "WebDecoy", baseScore: 5, respectsRobots: true, uaPatterns: ["webdecoybot"] },
{ id: "uptimerobot", name: "UptimeRobot", category: "monitoring", organization: "UptimeRobot", baseScore: 20, respectsRobots: true, uaPatterns: ["uptimerobot"] },
{ id: "pingdom", name: "Pingdom", category: "monitoring", organization: "SolarWinds", baseScore: 20, respectsRobots: true, uaPatterns: ["pingdom"] },
{ id: "statuscake", name: "StatusCake", category: "monitoring", organization: "StatusCake", baseScore: 20, respectsRobots: true, uaPatterns: ["statuscake"] },
Expand Down