polite-crawler 0.3.1 → 0.4.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (28) hide show
  1. package/build/{cli-daemon-CehzGYMQ.mjs → cli-daemon-Br17snPs.mjs} +2 -2
  2. package/build/{cli-daemon-CehzGYMQ.mjs.map → cli-daemon-Br17snPs.mjs.map} +1 -1
  3. package/build/{cli-recipes-InEU5y1L.mjs → cli-recipes-Cjq6ohWH.mjs} +2 -2
  4. package/build/{cli-recipes-InEU5y1L.mjs.map → cli-recipes-Cjq6ohWH.mjs.map} +1 -1
  5. package/build/cli.mjs +7 -7
  6. package/build/{daemon-1RNbvE5p.mjs → daemon-BPswUOgu.mjs} +3 -3
  7. package/build/{daemon-1RNbvE5p.mjs.map → daemon-BPswUOgu.mjs.map} +1 -1
  8. package/build/{diff-DLyQ2mkg.mjs → diff-DuD9pinS.mjs} +2 -2
  9. package/build/{diff-DLyQ2mkg.mjs.map → diff-DuD9pinS.mjs.map} +1 -1
  10. package/build/{extract-mnKsYeaM.mjs → extract-BISJyKWN.mjs} +2 -2
  11. package/build/{extract-mnKsYeaM.mjs.map → extract-BISJyKWN.mjs.map} +1 -1
  12. package/build/index.d.mts +1 -1
  13. package/build/index.mjs +10 -10
  14. package/build/{open-CDFgV-FC.mjs → open-CsFRWOjf.mjs} +6 -6
  15. package/build/{open-CDFgV-FC.mjs.map → open-CsFRWOjf.mjs.map} +1 -1
  16. package/build/{recipe-BNjpjJ_8.mjs → recipe-30dN3orz.mjs} +3 -3
  17. package/build/{recipe-BNjpjJ_8.mjs.map → recipe-30dN3orz.mjs.map} +1 -1
  18. package/build/{recipe-product-BqDdxZxL.mjs → recipe-product-BuJ_gEwn.mjs} +4 -4
  19. package/build/{recipe-product-BqDdxZxL.mjs.map → recipe-product-BuJ_gEwn.mjs.map} +1 -1
  20. package/build/{runtime-p5WN2UAA.mjs → runtime-C2VRY89U.mjs} +2 -2
  21. package/build/{runtime-p5WN2UAA.mjs.map → runtime-C2VRY89U.mjs.map} +1 -1
  22. package/build/{version-BVrf4OJP.mjs → version-B9CUZfx5.mjs} +2 -2
  23. package/build/{version-BVrf4OJP.mjs.map → version-B9CUZfx5.mjs.map} +1 -1
  24. package/build/{wacz-BXMxWyfg.mjs → wacz-D5bvxsiM.mjs} +3 -3
  25. package/build/{wacz-BXMxWyfg.mjs.map → wacz-D5bvxsiM.mjs.map} +1 -1
  26. package/build/{warc-DmzB-FkC.mjs → warc-DsB3oP78.mjs} +2 -2
  27. package/build/{warc-DmzB-FkC.mjs.map → warc-DsB3oP78.mjs.map} +1 -1
  28. package/package.json +1 -1
package/build/index.d.mts CHANGED
@@ -3615,7 +3615,7 @@ export declare const runWatch: (runtime: CrawlRuntime, source: WatchStore | (()
3615
3615
  //#endregion
3616
3616
  //#region src/version.d.ts
3617
3617
  /** This is the version of the package. A test makes sure that it agrees with `package.json`. */
3618
- export declare const VERSION = "0.3.1";
3618
+ export declare const VERSION = "0.4.0";
3619
3619
  /** This is the product token that robots.txt rules match when an application gives no token. */
3620
3620
  export declare const DEFAULT_TOKEN = "PoliteCrawler";
3621
3621
  /** This page tells a site owner what the crawler is and how to control it. */
package/build/index.mjs CHANGED
@@ -1,21 +1,21 @@
1
1
  import { n as FileBlobStore, t as CaptureLog } from "./log-CmBWcyQm.mjs";
2
2
  import { n as RenderRefused, r as playwrightRenderer, t as NO_PLAYWRIGHT } from "./render-CKE2LILH.mjs";
3
3
  import { t as browserMissing } from "./browser-56dBBLec.mjs";
4
- import { i as durationMs, n as DEFAULT_TOKEN, r as VERSION, t as BOT_PAGE } from "./version-BVrf4OJP.mjs";
5
- import { A as DEADLINE_NOTE, F as EgressRefused, I as egressLookup, M as makeRecord, O as CAPTURE_SCHEMA, S as readPdf, T as locate, _ as archivedDocId, a as fetchPage, c as isHeldBack, d as recordOverride, f as reindex, h as archiveExtractor, i as fetchAndIndex, j as DEFAULT_SECRET_PARAMS, k as Crawler, l as isoTime, m as versionAtTime, n as HELD_BACK, o as findDocuments, p as verifyQuote, r as catchUpIndex, s as heldBackMeta, t as Extractors, u as readDocument, x as isPdf } from "./runtime-p5WN2UAA.mjs";
4
+ import { i as durationMs, n as DEFAULT_TOKEN, r as VERSION, t as BOT_PAGE } from "./version-B9CUZfx5.mjs";
5
+ import { A as DEADLINE_NOTE, F as EgressRefused, I as egressLookup, M as makeRecord, O as CAPTURE_SCHEMA, S as readPdf, T as locate, _ as archivedDocId, a as fetchPage, c as isHeldBack, d as recordOverride, f as reindex, h as archiveExtractor, i as fetchAndIndex, j as DEFAULT_SECRET_PARAMS, k as Crawler, l as isoTime, m as versionAtTime, n as HELD_BACK, o as findDocuments, p as verifyQuote, r as catchUpIndex, s as heldBackMeta, t as Extractors, u as readDocument, x as isPdf } from "./runtime-C2VRY89U.mjs";
6
6
  import { DEFAULT_POLICY, MemoryHostStateStore, VALIDATOR_MEMO, nextValidatorMemo, realClock } from "./politeness.mjs";
7
7
  import { ALLOW_ALL, decide, parseRobots } from "./robots.mjs";
8
8
  import { i as keyDirectory, n as KEY_DIRECTORY_TYPE, o as verifySignature, r as createWebBotAuthSigner, t as KEY_DIRECTORY_PATH } from "./webbotauth-Dq_dA_u3.mjs";
9
- import { A as NO_EMBEDDER, C as DISCOVER_LIMITS, D as readSitemap, E as feedDate, O as DocIndex, S as crawlSite, T as SITEMAP_LIMITS, _ as estimateTokens, b as SqliteHostStateStore, c as WatchStore, d as VectorStore, f as createHybridSearch, g as chunkTokensOf, h as chunkText, i as openCrawler, k as FAST_RANK_SHARE, l as runWatch, m as HYBRID_DEFAULTS, n as defaultUserAgent, o as WATCH_LIMITS, p as CHUNK_LIMITS, r as isMailbox, s as WATCH_SCHEMA, t as createRuntime, u as VECTORS_SCHEMA, v as fuseRanks, w as discoverSite, x as CRAWL_LIMITS, y as unitVector } from "./open-CDFgV-FC.mjs";
9
+ import { A as NO_EMBEDDER, C as DISCOVER_LIMITS, D as readSitemap, E as feedDate, O as DocIndex, S as crawlSite, T as SITEMAP_LIMITS, _ as estimateTokens, b as SqliteHostStateStore, c as WatchStore, d as VectorStore, f as createHybridSearch, g as chunkTokensOf, h as chunkText, i as openCrawler, k as FAST_RANK_SHARE, l as runWatch, m as HYBRID_DEFAULTS, n as defaultUserAgent, o as WATCH_LIMITS, p as CHUNK_LIMITS, r as isMailbox, s as WATCH_SCHEMA, t as createRuntime, u as VECTORS_SCHEMA, v as fuseRanks, w as discoverSite, x as CRAWL_LIMITS, y as unitVector } from "./open-CsFRWOjf.mjs";
10
10
  import { a as bodyEncoding, o as decodeBody, r as typesOf, t as extractPage } from "./html-Dir5QEi0.mjs";
11
- import { a as formatDiff, n as diffDocument, r as diffTexts, t as DIFF_LIMITS } from "./diff-DLyQ2mkg.mjs";
12
- import { n as checkFields, r as extractDocument, t as FIELD_KINDS } from "./extract-mnKsYeaM.mjs";
13
- import { a as readJson, i as defineRecipe, n as RESERVED_RECIPES, o as registerRecipe, s as runRecipe, t as RECIPE_LIMITS } from "./recipe-BNjpjJ_8.mjs";
14
- import { c as startDaemon, i as daemonStateFile, n as DAEMON_STATE_SCHEMA, o as readDaemonState, r as changeCommand, s as scheduleWatches, t as DAEMON_DEFAULTS } from "./daemon-1RNbvE5p.mjs";
11
+ import { a as formatDiff, n as diffDocument, r as diffTexts, t as DIFF_LIMITS } from "./diff-DuD9pinS.mjs";
12
+ import { n as checkFields, r as extractDocument, t as FIELD_KINDS } from "./extract-BISJyKWN.mjs";
13
+ import { a as readJson, i as defineRecipe, n as RESERVED_RECIPES, o as registerRecipe, s as runRecipe, t as RECIPE_LIMITS } from "./recipe-30dN3orz.mjs";
14
+ import { c as startDaemon, i as daemonStateFile, n as DAEMON_STATE_SCHEMA, o as readDaemonState, r as changeCommand, s as scheduleWatches, t as DAEMON_DEFAULTS } from "./daemon-BPswUOgu.mjs";
15
15
  import { i as ollamaEmbedder, n as OLLAMA_MODELS, r as isLoopback, t as NO_OLLAMA } from "./ollama-D1xRh3hY.mjs";
16
16
  import { n as TRANSFORMERS_MODELS, r as transformersEmbedder, t as NO_TRANSFORMERS } from "./transformers-BNiuiLxT.mjs";
17
17
  import { DAYS, compareHours, describeWeek, disagreements, fromCompact, fromSchemaOrg, fromText, toHoursWeek } from "./hours.mjs";
18
- import { a as readAmount, c as locationMatches, d as readVenue, f as venueReadingsOf, i as productOf, l as namesVenue, n as pickProduct, o as readProduct, r as pickVariant, s as VENUE_LIMITS, t as PRODUCT_LIMITS, u as rankHoursLinks } from "./recipe-product-BqDdxZxL.mjs";
19
- import { t as exportWacz } from "./wacz-BXMxWyfg.mjs";
20
- import { n as exportWarc } from "./warc-DmzB-FkC.mjs";
18
+ import { a as readAmount, c as locationMatches, d as readVenue, f as venueReadingsOf, i as productOf, l as namesVenue, n as pickProduct, o as readProduct, r as pickVariant, s as VENUE_LIMITS, t as PRODUCT_LIMITS, u as rankHoursLinks } from "./recipe-product-BuJ_gEwn.mjs";
19
+ import { t as exportWacz } from "./wacz-D5bvxsiM.mjs";
20
+ import { n as exportWarc } from "./warc-DsB3oP78.mjs";
21
21
  export { ALLOW_ALL, BOT_PAGE, CAPTURE_SCHEMA, CHUNK_LIMITS, CRAWL_LIMITS, CaptureLog, Crawler, DAEMON_DEFAULTS, DAEMON_STATE_SCHEMA, DAYS, DEADLINE_NOTE, DEFAULT_POLICY, DEFAULT_SECRET_PARAMS, DEFAULT_TOKEN, DIFF_LIMITS, DISCOVER_LIMITS, DocIndex, EgressRefused, Extractors, FAST_RANK_SHARE, FIELD_KINDS, FileBlobStore, HELD_BACK, HYBRID_DEFAULTS, KEY_DIRECTORY_PATH, KEY_DIRECTORY_TYPE, MemoryHostStateStore, NO_EMBEDDER, NO_OLLAMA, NO_PLAYWRIGHT, NO_TRANSFORMERS, OLLAMA_MODELS, PRODUCT_LIMITS, RECIPE_LIMITS, RESERVED_RECIPES, RenderRefused, SITEMAP_LIMITS, SqliteHostStateStore, TRANSFORMERS_MODELS, VALIDATOR_MEMO, VECTORS_SCHEMA, VENUE_LIMITS, VERSION, VectorStore, WATCH_LIMITS, WATCH_SCHEMA, WatchStore, archiveExtractor, archivedDocId, bodyEncoding, browserMissing, catchUpIndex, changeCommand, checkFields, chunkText, chunkTokensOf, compareHours, crawlSite, createHybridSearch, createRuntime, createWebBotAuthSigner, daemonStateFile, decide, decodeBody, defaultUserAgent, defineRecipe, describeWeek, diffDocument, diffTexts, disagreements, discoverSite, durationMs, egressLookup, estimateTokens, exportWacz, exportWarc, extractDocument, extractPage, feedDate, fetchAndIndex, fetchPage, findDocuments, formatDiff, fromCompact, fromSchemaOrg, fromText, fuseRanks, heldBackMeta, isHeldBack, isLoopback, isMailbox, isPdf, isoTime, keyDirectory, locate, locationMatches, makeRecord, namesVenue, nextValidatorMemo, ollamaEmbedder, openCrawler, parseRobots, pickProduct, pickVariant, playwrightRenderer, productOf, rankHoursLinks, readAmount, readDaemonState, readDocument, readJson, readPdf, readProduct, readSitemap, readVenue, realClock, recordOverride, registerRecipe, reindex, runRecipe, runWatch, scheduleWatches, startDaemon, toHoursWeek, transformersEmbedder, typesOf, unitVector, venueReadingsOf, verifyQuote, verifySignature, versionAtTime };
@@ -2,15 +2,15 @@ import { t as __exportAll } from "./rolldown-runtime-8H4AJuhK.mjs";
2
2
  import { n as FileBlobStore, t as CaptureLog } from "./log-CmBWcyQm.mjs";
3
3
  import { r as playwrightRenderer } from "./render-CKE2LILH.mjs";
4
4
  import { r as checkedRenderer } from "./browser-56dBBLec.mjs";
5
- import { i as durationMs, n as DEFAULT_TOKEN, r as VERSION, t as BOT_PAGE } from "./version-BVrf4OJP.mjs";
6
- import { A as DEADLINE_NOTE, C as fold, D as snippetOf, E as parseQuery, N as sha256$1, P as stableStringify, a as fetchPage, c as isHeldBack, f as reindex, i as fetchAndIndex, k as Crawler, l as isoTime, o as findDocuments, p as verifyQuote, r as catchUpIndex, t as Extractors, u as readDocument, y as archivedOf } from "./runtime-p5WN2UAA.mjs";
5
+ import { i as durationMs, n as DEFAULT_TOKEN, r as VERSION, t as BOT_PAGE } from "./version-B9CUZfx5.mjs";
6
+ import { A as DEADLINE_NOTE, C as fold, D as snippetOf, E as parseQuery, N as sha256$1, P as stableStringify, a as fetchPage, c as isHeldBack, f as reindex, i as fetchAndIndex, k as Crawler, l as isoTime, o as findDocuments, p as verifyQuote, r as catchUpIndex, t as Extractors, u as readDocument, y as archivedOf } from "./runtime-C2VRY89U.mjs";
7
7
  import { MemoryHostStateStore, nextValidatorMemo, realClock } from "./politeness.mjs";
8
8
  import { matchesPattern } from "./robots.mjs";
9
9
  import { n as canonicalUrl, r as scopeTest, t as cacheKeyOf } from "./urls-BHFeSyEK.mjs";
10
10
  import { o as decodeBody, t as extractPage } from "./html-Dir5QEi0.mjs";
11
- import { n as diffDocument, r as diffTexts } from "./diff-DLyQ2mkg.mjs";
12
- import { r as extractDocument } from "./extract-mnKsYeaM.mjs";
13
- import { o as registerRecipe } from "./recipe-BNjpjJ_8.mjs";
11
+ import { n as diffDocument, r as diffTexts } from "./diff-DuD9pinS.mjs";
12
+ import { r as extractDocument } from "./extract-BISJyKWN.mjs";
13
+ import { o as registerRecipe } from "./recipe-30dN3orz.mjs";
14
14
  import { createHash, randomUUID } from "node:crypto";
15
15
  import { dirname, join } from "node:path";
16
16
  import { existsSync, lstatSync, mkdirSync, realpathSync, statSync } from "node:fs";
@@ -4356,4 +4356,4 @@ const openCrawler = (options) => {
4356
4356
  //#endregion
4357
4357
  export { NO_EMBEDDER as A, DISCOVER_LIMITS as C, readSitemap as D, feedDate as E, DocIndex as O, crawlSite as S, SITEMAP_LIMITS as T, estimateTokens as _, open_exports as a, SqliteHostStateStore as b, WatchStore as c, VectorStore as d, createHybridSearch as f, chunkTokensOf as g, chunkText as h, openCrawler as i, FAST_RANK_SHARE as k, runWatch as l, HYBRID_DEFAULTS as m, defaultUserAgent as n, WATCH_LIMITS as o, CHUNK_LIMITS as p, isMailbox as r, WATCH_SCHEMA as s, createRuntime as t, VECTORS_SCHEMA as u, fuseRanks as v, discoverSite as w, CRAWL_LIMITS as x, unitVector as y };
4358
4358
 
4359
- //# sourceMappingURL=open-CDFgV-FC.mjs.map
4359
+ //# sourceMappingURL=open-CsFRWOjf.mjs.map