universal-parcel-scraper 0.861.0-main.4621 → 0.862.1-main.4625

package/README.md

@@ -13,7 +13,7 @@ The engine behind [Peek](https://peektracker.com) ([GitHub](https://github.com/p
 [![License: Apache-2.0](https://img.shields.io/badge/core-Apache--2.0-blue.svg)](LICENSE)
 
 <!-- GENERATED:summary -->
-**3,500+ carriers** through **658 dedicated adapters** and **5 universal fallbacks**
+**3,500+ carriers** through **661 dedicated adapters** and **5 universal fallbacks**
 
 <sub>1045 catalog entries · 145 countries represented</sub>
 <!-- /GENERATED:summary -->
@@ -163,7 +163,7 @@ the command line's `track --source ParcelsApp` does the same.
 <!-- GENERATED:stages -->
 <img src="docs/assets/stages.svg" alt="DHL: Die Sendung wurde in das Zustellfahrzeug geladen.; Mondial Relay: En cours de livraison; Correios Brazil: Objeto saiu para entrega ao destinatário; Correos Express: EN REPARTO; Yamato Transport: 配達中; La Poste / Colissimo: DISTOU. All are filed under out_for_delivery." width="760">
 
-The carrier folders record 17,879 such statuses, each filed under one stage.
+The carrier folders record 17,895 such statuses, each filed under one stage.
 <!-- /GENERATED:stages -->
 
 Wording nobody recorded yet goes through a classifier that reads seven European languages.

package/data/catalog.json

@@ -11611,7 +11611,9 @@
     "timezone": "Asia/Manila",
     "tracking": {
       "mode": "automatic",
-      "adapter": "universal"
+      "adapter": "consegnia",
+      "recognitionRank": 57,
+      "localClocks": true
     },
     "canaryUrl": "https://clc-express.com/",
     "trackingUrlTemplate": "https://clc-express.com/track-delivery?awb={trackingNumber}",
@@ -18128,7 +18130,9 @@
     "timezone": "Asia/Kuala_Lumpur",
     "tracking": {
       "mode": "automatic",
-      "adapter": "universal"
+      "adapter": "fmx",
+      "recognitionRank": 147,
+      "localClocks": true
     },
     "canaryUrl": "https://www.fmx.asia/",
     "trackingUrlTemplate": "https://www.fmx.asia/result_detail.php?p=1&conno={trackingNumber}",
@@ -20577,7 +20581,9 @@
     "timezone": "Asia/Manila",
     "tracking": {
       "mode": "automatic",
-      "adapter": "universal"
+      "adapter": "hitch",
+      "recognitionRank": 117,
+      "localClocks": true
     },
     "canaryUrl": "https://hitch.com.ph/",
     "trackingUrlTemplate": "https://hitch.com.ph/tracking?no={trackingNumber}",

package/data/coverage-summary.json

@@ -1,6 +1,6 @@
 {
   "catalog": 1045,
-  "activeAdapters": 658,
+  "activeAdapters": 661,
   "countries": 145,
   "referenceCarriers": 100,
   "comparison": {

package/data/detection-golden.json

@@ -87063,6 +87063,9 @@
     "confidence": "low",
     "candidates": [
       "fmx"
+    ],
+    "asked": [
+      "fmx"
     ]
   },
   {
@@ -87071,6 +87074,9 @@
     "confidence": "low",
     "candidates": [
       "fmx"
+    ],
+    "asked": [
+      "fmx"
     ]
   },
   {
@@ -87079,6 +87085,9 @@
     "confidence": "low",
     "candidates": [
       "fmx"
+    ],
+    "asked": [
+      "fmx"
     ]
   },
   {
@@ -100584,6 +100593,9 @@
     "confidence": "low",
     "candidates": [
       "hitch"
+    ],
+    "asked": [
+      "hitch"
     ]
   },
   {
@@ -100592,6 +100604,9 @@
     "confidence": "low",
     "candidates": [
       "hitch"
+    ],
+    "asked": [
+      "hitch"
     ]
   },
   {
@@ -100600,6 +100615,9 @@
     "confidence": "low",
     "candidates": [
       "hitch"
+    ],
+    "asked": [
+      "hitch"
     ]
   },
   {
@@ -100608,6 +100626,9 @@
     "confidence": "low",
     "candidates": [
       "hitch"
+    ],
+    "asked": [
+      "hitch"
     ]
   },
   {
@@ -100616,6 +100637,9 @@
     "confidence": "low",
     "candidates": [
       "hitch"
+    ],
+    "asked": [
+      "hitch"
     ]
   },
   {
@@ -100624,6 +100648,9 @@
     "confidence": "low",
     "candidates": [
       "hitch"
+    ],
+    "asked": [
+      "hitch"
     ]
   },
   {
@@ -100632,6 +100659,9 @@
     "confidence": "low",
     "candidates": [
       "hitch"
+    ],
+    "asked": [
+      "hitch"
     ]
   },
   {
@@ -100640,6 +100670,9 @@
     "confidence": "low",
     "candidates": [
       "hitch"
+    ],
+    "asked": [
+      "hitch"
     ]
   },
   {
@@ -100648,6 +100681,9 @@
     "confidence": "low",
     "candidates": [
       "hitch"
+    ],
+    "asked": [
+      "hitch"
     ]
   },
   {

package/dist/browser/scraper.js

@@ -9243,7 +9243,9 @@ var tt = {
 		timezone: "Asia/Manila",
 		tracking: {
 			mode: "automatic",
-			adapter: "universal"
+			adapter: "consegnia",
+			recognitionRank: 57,
+			localClocks: !0
 		},
 		canaryUrl: "https://clc-express.com/",
 		trackingUrlTemplate: "https://clc-express.com/track-delivery?awb={trackingNumber}",
@@ -14105,7 +14107,9 @@ var tt = {
 		timezone: "Asia/Kuala_Lumpur",
 		tracking: {
 			mode: "automatic",
-			adapter: "universal"
+			adapter: "fmx",
+			recognitionRank: 147,
+			localClocks: !0
 		},
 		canaryUrl: "https://www.fmx.asia/",
 		trackingUrlTemplate: "https://www.fmx.asia/result_detail.php?p=1&conno={trackingNumber}",
@@ -15930,7 +15934,9 @@ var tt = {
 		timezone: "Asia/Manila",
 		tracking: {
 			mode: "automatic",
-			adapter: "universal"
+			adapter: "hitch",
+			recognitionRank: 117,
+			localClocks: !0
 		},
 		canaryUrl: "https://hitch.com.ph/",
 		trackingUrlTemplate: "https://hitch.com.ph/tracking?no={trackingNumber}",
@@ -39169,6 +39175,7 @@ var ed = {
 	"closer-logistics": 849,
 	"colis-prive": 740,
 	"connect-couriers": 831,
+	consegnia: 57,
 	coordinadora: 973,
 	"copa-courier": 773,
 	corre: 587,
@@ -39259,6 +39266,7 @@ var ed = {
 	fleetex: 571,
 	fleetoptics: 763,
 	flippost: 568,
+	fmx: 147,
 	"forward-air": 755,
 	"forza-delivery": 633,
 	"four-px": 570,
@@ -39301,6 +39309,7 @@ var ed = {
 	hermes: 602,
 	"hermes-at": 876,
 	"hermes-de": 840,
+	hitch: 117,
 	"houng-ah-loun": 637,
 	hovership: 687,
 	"hr-parcel": 887,

package/dist/carriers/amazon-shipping/adapter.js

@@ -6,7 +6,7 @@ import { ChallengeError, IndeterminateError, InvalidInputError, NotFoundError, S
 import { listsNewestFirst } from '../../core/result/order.js';
 import { cleanScalar, decodeText, fetchBounded, parseJsonBytes, userAgentOf } from '../../core/transport/index.js';
 import { isRecord } from '../../core/types.js';
-import { classifyStatus, statusKey } from './status.js';
+import { classifyStatus, DELAYED, statusKey } from './status.js';
 const PROVIDER = 'Amazon Shipping';
 const DEFAULT_TIMEOUT_MS = 15_000;
 const MAX_RESPONSE_BYTES = 2_000_000;
@@ -266,7 +266,10 @@ export function parseAmazonShippingTrackingResponse(payload, zone = 'Europe/Pari
     // that had just left their pickup site and went on being scanned for another day.
     const unscannedDelivery = current.stage === 'delivered' && latestKnown !== undefined
         && !parsedEvents.some((item) => item.classified.stage === 'delivered');
-    const active = current.status !== 'unknown' && !echoesNewest && !unscannedDelivery ? current : latestKnown?.classified;
+    // A delay moves nothing: a parcel whose scans show only its label keeps that stage, with the delay as its text.
+    const unmovedDelay = current === DELAYED && latestKnown?.classified.stage === 'registered';
+    const active = unmovedDelay ? { ...latestKnown.classified, description: DELAYED.description }
+        : current.status !== 'unknown' && !echoesNewest && !unscannedDelivery ? current : latestKnown?.classified;
     if (!active) {
         throw new SchemaError(PROVIDER, 'Amazon Shipping returned incomplete tracking details');
     }

package/dist/carriers/amazon-shipping/status.d.ts

@@ -20,6 +20,8 @@ export interface ClassifiedStatus {
     description: string;
 }
 export declare const UNKNOWN_STATUS: ClassifiedStatus;
+/** A late delivery: no exception, and no movement of its own. */
+export declare const DELAYED: ClassifiedStatus;
 /** Fold any provider signal into the comparison key: lower case, letters and digits only. */
 export declare function statusKey(value: unknown): string;
 /** Classify one or more provider signals; the first matching rule wins. */

package/dist/carriers/amazon-shipping/status.js

@@ -3,6 +3,12 @@ export const UNKNOWN_STATUS = {
     stage: 'in_transit',
     description: 'Amazon Shipping update',
 };
+/** A late delivery: no exception, and no movement of its own. */
+export const DELAYED = {
+    status: 'in_transit',
+    stage: 'in_transit',
+    description: 'Delivery delayed',
+};
 /** Fold any provider signal into the comparison key: lower case, letters and digits only. */
 export function statusKey(value) {
     if (typeof value !== 'string' && typeof value !== 'number')
@@ -48,9 +54,8 @@ export function classifyStatus(...values) {
     ])) {
         return { status: 'exception', stage: 'failed_attempt', description: 'Delivery issue' };
     }
-    if (includesAny(key, ['delayed', 'late'])) {
-        return { status: 'in_transit', stage: 'in_transit', description: 'Delivery delayed' };
-    }
+    if (includesAny(key, ['delayed', 'late']))
+        return DELAYED;
     if (includesAny(key, ['delivered'])) {
         return { status: 'delivered', stage: 'delivered', description: 'Delivered' };
     }

package/dist/carriers/consegnia/adapter.d.ts

@@ -0,0 +1,17 @@
+import { type AdapterFactory, type TrackingContext } from '../../core/adapter/index.js';
+import type { CarrierResult } from '../../core/result/index.js';
+import { type StepRecorder } from '../../core/telemetry/index.js';
+/** The tracking page, which opens the session its lookup needs and carries the session's token. */
+export declare const CONSEGNIA_PAGE = "https://clc-express.com/track-delivery";
+/** The lookup the tracking page's script posts the number to. */
+export declare const CONSEGNIA_LOOKUP = "https://clc-express.com/track-delivery-result";
+export declare class ConsegniaTracker {
+    private readonly options;
+    constructor(options?: {
+        fetcher?: typeof fetch;
+        recorder?: StepRecorder;
+        userAgent?: string;
+    });
+    fetch(raw: string, context?: TrackingContext): Promise<CarrierResult>;
+}
+export declare const adapter: AdapterFactory;

package/dist/carriers/consegnia/adapter.js

@@ -0,0 +1,107 @@
+import { accepted, recognizeFromLookup } from '../../core/adapter/index.js';
+import { ChallengeError, IndeterminateError, NotFoundError, SchemaError, TransportError } from '../../core/errors/index.js';
+import { runSteps } from '../../core/runner/index.js';
+import { firstAttemptMs, networkRetryStep } from '../../core/runner/networkRetry.js';
+import { NOOP_RECORDER } from '../../core/telemetry/index.js';
+import { decodeText, fetchBounded, userAgentOf } from '../../core/transport/index.js';
+import { CARRIER, CONSEGNIA_MAX_BYTES, consegniaJson, consegniaToken, isBlockPage, isUnknownShipment, normalizeConsegniaNumber, parseConsegnia, PROVIDER, } from './parser.js';
+const ORIGIN = 'https://clc-express.com';
+/** The tracking page, which opens the session its lookup needs and carries the session's token. */
+export const CONSEGNIA_PAGE = `${ORIGIN}/track-delivery`;
+/** The lookup the tracking page's script posts the number to. */
+export const CONSEGNIA_LOOKUP = `${ORIGIN}/track-delivery-result`;
+const REDIRECTS = [301, 302, 303, 307, 308];
+// The lookup answers an unknown number with its own HTTP 404; any other is a missing route.
+const GONE = [404, 410];
+// Laravel's refusal of a token or session it did not issue, or one that expired.
+const REFUSED_SESSION = 419;
+const COOKIE_NAME = /^[A-Za-z0-9!#$%&'*+.^_`|~-]{1,128}$/;
+const COOKIE_VALUE = /^[^\s;,]{1,4096}$/;
+const MAX_COOKIES = 8;
+const DEFAULT_BUDGET_MS = 15_000;
+/**
+ * The cookies the tracking page sets, as the lookup sends them back: Laravel's
+ * session, its token cookie and the site's own. Null without the session.
+ */
+function sessionCookies(response) {
+    const pairs = [];
+    for (const header of response.headers.getSetCookie()) {
+        const pair = header.split(';', 1)[0].trim();
+        const separator = pair.indexOf('=');
+        const name = pair.slice(0, separator);
+        if (separator > 0 && COOKIE_NAME.test(name) && COOKIE_VALUE.test(pair.slice(separator + 1)) && pairs.length < MAX_COOKIES)
+            pairs.push(pair);
+    }
+    return pairs.some((pair) => /^[^=]+_session=/.test(pair)) ? pairs.join('; ') : null;
+}
+export class ConsegniaTracker {
+    options;
+    constructor(options = {}) {
+        this.options = options;
+    }
+    async fetch(raw, context = {}) {
+        const number = normalizeConsegniaNumber(raw);
+        const userAgent = userAgentOf(this.options.userAgent);
+        // One attempt opens a session on the tracking page and posts the number with its token, as the page's script does.
+        const attempt = async (signal, timeoutMs) => {
+            const deadline = performance.now() + timeoutMs;
+            // A request left without time fails as a timeout, which the retry can recover.
+            const left = () => Math.max(1, Math.floor(deadline - performance.now()));
+            const page = await fetchBounded(CONSEGNIA_PAGE, { method: 'GET', signal, headers: {
+                    Accept: 'text/html,application/xhtml+xml', 'User-Agent': userAgent,
+                } }, { provider: PROVIDER, timeoutMs: left(), maxBytes: CONSEGNIA_MAX_BYTES, redirect: 'manual',
+                allowHttpStatuses: [...REDIRECTS, ...GONE, 403], fetcher: this.options.fetcher });
+            if (page.response.status === 403)
+                throw new ChallengeError(PROVIDER, 'Consegnia refused its tracking page', { status: 403 });
+            if (page.response.status !== 200) {
+                throw new TransportError(PROVIDER, 'Consegnia tracking page is unavailable', { status: page.response.status });
+            }
+            const html = decodeText(page.bytes);
+            const token = consegniaToken(html);
+            if (!token) {
+                if (isBlockPage(html))
+                    throw new ChallengeError(PROVIDER, 'Consegnia answered the tracking page with a browser check');
+                throw new SchemaError(PROVIDER, 'Consegnia tracking page carries no lookup token');
+            }
+            const cookie = sessionCookies(page.response);
+            if (!cookie)
+                throw new SchemaError(PROVIDER, 'Consegnia tracking page opened no session');
+            const lookup = await fetchBounded(CONSEGNIA_LOOKUP, { method: 'POST', signal, headers: {
+                    Accept: 'application/json, text/javascript, */*; q=0.01', 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
+                    'User-Agent': userAgent, Cookie: cookie, 'X-Requested-With': 'XMLHttpRequest', Origin: ORIGIN, Referer: CONSEGNIA_PAGE,
+                }, body: new URLSearchParams({ _token: token, awb_number: number }).toString() }, { provider: PROVIDER, timeoutMs: left(),
+                maxBytes: CONSEGNIA_MAX_BYTES, redirect: 'manual', allowHttpStatuses: [...REDIRECTS, ...GONE, 403, REFUSED_SESSION],
+                fetcher: this.options.fetcher });
+            const { status } = lookup.response;
+            const body = decodeText(lookup.bytes).replace(/^\uFEFF/, '').trim();
+            if (REDIRECTS.includes(status) || status === 410)
+                throw new TransportError(PROVIDER, 'Consegnia tracking lookup is unavailable', { status });
+            if (status === 403)
+                throw new ChallengeError(PROVIDER, 'Consegnia refused the lookup', { status });
+            // The session the page just opened was refused: it says nothing about the shipment.
+            if (status === REFUSED_SESSION)
+                throw new IndeterminateError(PROVIDER, 'Consegnia refused the tracking page’s session', { status });
+            if (status === 404) {
+                if (isUnknownShipment(body))
+                    throw new NotFoundError(PROVIDER);
+                throw new TransportError(PROVIDER, 'Consegnia tracking lookup is unavailable', { status });
+            }
+            return parseConsegnia(consegniaJson(body), number);
+        };
+        // An attempt that fails to reach Consegnia, or hangs, gets one more in a new
+        // session: the first gets half of the budget, so the retry fits in the rest.
+        return runSteps({ carrier: CARRIER, budgetMs: context.budgetMs ?? DEFAULT_BUDGET_MS, signal: context.signal,
+            recorder: this.options.recorder ?? NOOP_RECORDER }, [
+            { id: 'direct', run: ({ signal, remainingMs }) => attempt(signal, firstAttemptMs(remainingMs)) },
+            networkRetryStep(({ signal, remainingMs }) => attempt(signal, remainingMs)),
+        ]);
+    }
+}
+export const adapter = (environment) => {
+    const tracker = new ConsegniaTracker({ fetcher: environment.fetcher, recorder: environment.recorder, userAgent: environment.userAgent });
+    return {
+        id: CARRIER, recordsSteps: true, steps: ['direct', 'retry'],
+        track: (input, context) => tracker.fetch(input.number, context),
+        recognize: (number, context) => recognizeFromLookup(() => tracker.fetch(number, context), () => accepted(() => normalizeConsegniaNumber(number))),
+    };
+};

package/dist/carriers/consegnia/carrier.json

@@ -18,18 +18,49 @@
   "timezone": "Asia/Manila",
   "tracking": {
     "mode": "automatic",
-    "adapter": "universal",
-    "steps": []
+    "adapter": "consegnia",
+    "steps": [
+      "direct",
+      "retry"
+    ],
+    "recognition": {
+      "rank": 57
+    },
+    "localClocks": true
   },
-  "capabilities": [],
+  "capabilities": [
+    "history"
+  ],
   "portal": {
     "url": "https://clc-express.com/track-delivery?awb={trackingNumber}",
     "searchUrl": "https://clc-express.com/track-delivery",
     "canaryUrl": "https://clc-express.com/",
-    "shows": [],
-    "scraped": [],
-    "discarded": [],
-    "unavailable": []
+    "shows": [
+      "status",
+      "history",
+      "failed_delivery_reason",
+      "awb_date",
+      "delivered_at"
+    ],
+    "scraped": [
+      "status",
+      "history",
+      "failed_delivery_reason"
+    ],
+    "discarded": [
+      "awb_date",
+      "delivered_at"
+    ],
+    "unavailable": [
+      "location",
+      "eta",
+      "offset_timestamps",
+      "provider_code",
+      "weight",
+      "sender_name",
+      "recipient_name",
+      "proof_of_delivery"
+    ]
   },
   "links": [
     {

package/dist/carriers/consegnia/parser.d.ts

@@ -0,0 +1,29 @@
+import type { CarrierResult } from '../../core/result/index.js';
+export declare const PROVIDER = "Consegnia Logistics";
+export declare const CARRIER = "consegnia";
+export declare const CONSEGNIA_MAX_BYTES: number;
+/** A number for Consegnia's tracker: CLC and nine digits. */
+export declare function normalizeConsegniaNumber(raw: string): string;
+/** A firewall or bot-check page in place of the tracking page or the lookup's JSON. */
+export declare function isBlockPage(body: string): boolean;
+/** The token the tracking page's form sends with a number, or null when the page has none. */
+export declare function consegniaToken(html: string): string | null;
+/**
+ * The lookup's reply for one number, `{ success, data: { html } }`: a fragment
+ * its server renders with the number, the current status, the last update, the
+ * booking day, the delivery clock once delivered, and the history, newest
+ * first, each row a status, the reason for a failed delivery and a wall clock
+ * to the minute with no zone. It names no person, place or phone number.
+ *
+ * The fragment must carry the whole number asked. The delivery clock is not
+ * read: a delivered parcel's newest row gives it, and it has no zone either.
+ */
+export declare function parseConsegnia(payload: unknown, raw: string): CarrierResult;
+/**
+ * The lookup's answer to a number it does not hold: HTTP 404 with `success`
+ * false and its message. The message does not quote the number. Any other 404
+ * is a missing route.
+ */
+export declare function isUnknownShipment(body: string): boolean;
+/** The lookup's reply as JSON, or the reason it is not one. */
+export declare function consegniaJson(body: string): unknown;