crawlora 1.8.0.pre.sdk.1 → 1.8.0.pre.sdk.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 36129f7e8b7350f03f729c2145128e62df5bab95b7967fe4aae514d1fb49f735
-  data.tar.gz: 44db68771843957454b0949081084e01549b5e93cca878dc664d30f6d72e0bb1
+  metadata.gz: a055f6f58608503ed3b6e3aeaee2df8c354e3a3dd545ee0c0d1a78f426751fdf
+  data.tar.gz: ec2164216f5226fcd2478ec9b2ef6145e56b6f09a2d6ede5bcf8626a263cf936
 SHA512:
-  metadata.gz: 14142688a8258cf40bec98657e14512e507dc207db2db3ed0dbb19ca7c9c21dd3eb676262666d2b072803c143414a09a891813cbf04c9a27a931deb52ce78d73
-  data.tar.gz: '034489ae31a54225aef9a4d2f82ac03e37f5c3288af4b33ba253f130a4f413f47bca9eaa3130c800b646d46c71f23625947c3629d2bac04aa1d50ee4f5a30ae0'
+  metadata.gz: c915cda57689bdd0708f50f54a432af81938fe0cbbba731d6b2cc3e0995d604e7dae7507410455a68795fd9890a3b69c53153576f74b9bdd65bb6aa61dbe8628
+  data.tar.gz: 360e1bb791ab1cea375d31514fd8fe6a8214f254b4114c2eb7e7e6e60e087be70acaeaabbefd85dfeb7b0d1c85cb15050cad07a1c37d7c82f4c76e98d7c1ab8a

data/CHANGELOG.md

@@ -1,5 +1,15 @@
 # Changelog
 
+## v1.8.0-sdk.2
+
+- Regenerated from the public API contract (499 operations, unchanged). Enriches
+  the Web `antibot-check` diagnostic response with additional fields:
+  `block_reason`, `block_detail`, `auth_required`, `captcha_type`,
+  `captcha_types`, `captcha_mode`, `confidence_score`, `custom_vm`, and
+  `vm_vendor`.
+- Clarified the `google-search` and datasets `google-map-businesses/search`
+  endpoint descriptions (wording only; no behavior change).
+
 ## v1.8.0-sdk.1
 
 - Added two new platforms, regenerated from the public API contract (now 499

data/lib/crawlora/version.rb

@@ -5,5 +5,5 @@ module Crawlora
   # as the Go/Java/PHP SDKs). RubyGems treats it as a prerelease and normalizes
   # the published gem version (the `-` becomes `.pre.`, e.g. `1.5.0.pre.sdk.N`).
   # Bumped across all SDK repos by the API repo's tools/sdkgen/bump_version.py.
-  VERSION = "1.8.0-sdk.1"
+  VERSION = "1.8.0-sdk.2"
 end

data/openapi/public.json

@@ -485,10 +485,25 @@
     },
     "antibot.Protection": {
       "properties": {
+        "captcha_mode": {
+          "type": "string"
+        },
+        "captcha_type": {
+          "description": "CaptchaType / CaptchaMode sub-classify a kind=captcha detection\n(e.g. recaptcha_v3 / score, turnstile / managed).",
+          "type": "string"
+        },
         "confidence": {
           "description": "low | medium | high",
           "type": "string"
         },
+        "confidence_score": {
+          "description": "ConfidenceScore is the numeric (0-100) additive confidence over this\ndetection's own evidence (Wappalyzer-style); Confidence is its bucketed label.",
+          "type": "integer"
+        },
+        "custom_vm": {
+          "description": "CustomVM marks the proprietary signed-payload / closed-VM class (Kasada,\nF5 Shape, TikTok) whose anti-bot is a closed in-browser bytecode VM rather\nthan generic transport detection; VMVendor names it.",
+          "type": "boolean"
+        },
         "evidence": {
           "items": {
             "type": "string"
@@ -501,6 +516,9 @@
         },
         "vendor": {
           "type": "string"
+        },
+        "vm_vendor": {
+          "type": "string"
         }
       },
       "type": "object"
@@ -542,10 +560,35 @@
     },
     "antibot.Verdict": {
       "properties": {
+        "auth_required": {
+          "type": "boolean"
+        },
+        "block_detail": {
+          "type": "string"
+        },
+        "block_reason": {
+          "description": "BlockReason is WHY the representative request was blocked (or \"ok\"):\nok | bot_challenge | captcha_required | rate_limited | ip_blocked |\ngeo_blocked | auth_required | payment_required | service_unavailable |\nforbidden | other | unreachable. Different reasons call for different fixes\n(rotate IPs vs run a browser vs log in), so they are surfaced distinctly.",
+          "type": "string"
+        },
+        "captcha_types": {
+          "description": "CaptchaTypes lists the distinct CAPTCHA types detected (e.g. recaptcha_v3,\nturnstile) for easy aggregation.",
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
         "coverage": {
           "description": "Coverage is `full` when every transport tier ran, or `partial` when some\nwere skipped (e.g. browser sidecars unconfigured in this environment), in\nwhich case a \"blocked\" verdict may understate what a browser could do.",
           "type": "string"
         },
+        "custom_vm": {
+          "description": "CustomVM / VMVendor are set when any detected protection is the proprietary\nclosed-VM class (Kasada / F5 Shape / TikTok).",
+          "type": "boolean"
+        },
+        "detection_confidence_score": {
+          "description": "ConfidenceScore is the strongest detection's numeric confidence (0-100), or\n0 when nothing was detected (confidence describes a detection, not a negative).",
+          "type": "integer"
+        },
         "difficulty_band": {
           "$ref": "#/definitions/antibot.Band"
         },
@@ -556,6 +599,10 @@
         "easiest_working_transport": {
           "type": "string"
         },
+        "enforcement": {
+          "description": "Enforcement separates a managed vendor actively challenging/blocking us from\none merely sitting in front as passive CDN/edge:\nopen | passive_edge | active_challenge | active_block.",
+          "type": "string"
+        },
         "gated_layers": {
           "description": "GatedLayers names the anti-bot detection layers that block a plain client,\nderived empirically from which probe tiers were rejected: `tls` (a plain\nHTTP client's TLS/header fingerprint was rejected, but browser-impersonation\nor a browser got through), `js` (HTTP transports failed; JavaScript\nrendering / a real browser was required), `behavior` (a plain headless\nbrowser was also rejected; an anti-detect/stealth browser was needed).",
           "items": {
@@ -581,6 +628,9 @@
         "recommended_profile": {
           "type": "string"
         },
+        "retry_after": {
+          "type": "string"
+        },
         "scrapeable": {
           "type": "boolean"
         },
@@ -592,6 +642,9 @@
         },
         "url": {
           "type": "string"
+        },
+        "vm_vendor": {
+          "type": "string"
         }
       },
       "type": "object"
@@ -43442,7 +43495,7 @@
         "consumes": [
           "application/json"
         ],
-        "description": "Fetches a domain's homepage and extracts a normalized brand profile (title, description, colors, logos, backdrops, socials, links, and any schema.org organization data). Enrichment-only fields that are not present in the page markup are returned as null.",
+        "description": "Fetches a domain's homepage and Web App Manifest and extracts a normalized brand profile (title, description, brand colors normalized to hex, logos and icons ranked best-first, backdrops, socials, links, and any schema.org organization data). Enrichment-only fields that are not present in the page markup are returned as null.",
         "operationId": "brand-retrieve",
         "parameters": [
           {
@@ -47200,7 +47253,7 @@
         "consumes": [
           "application/json"
         ],
-        "description": "Searches Google Maps business records stored in Elasticsearch. Sort enum: `relevance`, `updated_at_desc`, `rating_desc`, `review_count_desc`, `distance_asc`.",
+        "description": "Searches Google Maps business records stored in a search index. Sort enum: `relevance`, `updated_at_desc`, `rating_desc`, `review_count_desc`, `distance_asc`.",
         "operationId": "datasets-google-map-businesses-search",
         "parameters": [
           {
@@ -47896,8 +47949,8 @@
               "$ref": "#/definitions/app.Response"
             }
           },
-          "429": {
-            "description": "Too Many Requests",
+          "502": {
+            "description": "Bad Gateway",
             "schema": {
               "$ref": "#/definitions/app.Response"
             }
@@ -47995,8 +48048,8 @@
               "$ref": "#/definitions/app.Response"
             }
           },
-          "429": {
-            "description": "Too Many Requests",
+          "502": {
+            "description": "Bad Gateway",
             "schema": {
               "$ref": "#/definitions/app.Response"
             }
@@ -48128,8 +48181,8 @@
               "$ref": "#/definitions/app.Response"
             }
           },
-          "429": {
-            "description": "Too Many Requests",
+          "502": {
+            "description": "Bad Gateway",
             "schema": {
               "$ref": "#/definitions/app.Response"
             }
@@ -49588,7 +49641,7 @@
         "consumes": [
           "application/json"
         ],
-        "description": "Returns normalized Google web search results. Results are fetched through gost-egressing browser backends that race several concurrent renders per request (in-render gost fan-out) and return the first clean result, with stale-cache fallback when available. The endpoint returns 503 when Google serves a challenge page or unusable HTML. Rate limit is enforced at 1 request per second, and if the limit is exceeded a 429 status code is returned with rate limit headers.",
+        "description": "Returns normalized Google web search results. Results are fetched through proxied browser renderers that race several concurrent renders per request and return the first clean result, with stale-cache fallback when available. The endpoint returns 503 when Google serves a challenge page or unusable HTML. Rate limit is enforced at 1 request per second, and if the limit is exceeded a 429 status code is returned with rate limit headers.",
         "operationId": "google-search",
         "parameters": [
           {

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: crawlora
 version: !ruby/object:Gem::Version
-  version: 1.8.0.pre.sdk.1
+  version: 1.8.0.pre.sdk.2
 platform: ruby
 authors:
 - Crawlora
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-06-11 00:00:00.000000000 Z
+date: 2026-06-14 00:00:00.000000000 Z
 dependencies: []
 description: 'Crawlora is a web-scraping API for structured public web data — search,
   marketplace, social, finance, media, reviews, and geodata — without running your