hydrafetch 0.1.1 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 35ac08607d9ee8ca889a20a004a731c7209f6073fff19bb0b03f2fe81c43727b
-  data.tar.gz: 43d69727dfe8f80e5568b7aaac052ef0f26c7d794a613676034c523a2fd1b32b
+  metadata.gz: d895f580349c33641dc5f853c8d4c0ee46fa54bf55cf7edcb50093e47997bdf5
+  data.tar.gz: 10d8ea933dbd6c8091a616780711e248881c7ba6a83cff3eda0de11d1b122cfd
 SHA512:
-  metadata.gz: 911787510a48aeca53334e2091d76cb6eb011cce68f7138fed1b861cc5eb6d23732a45d3dc82184016bda179cd23f97372bc18aea07a4ef34a48a43ab73e96b5
-  data.tar.gz: 77475fd922ba15a0d68d62868b8fc20fa22c385ab37ff2d225a256e8d4a01fcc7f3e80101885c55d9183a6ee6adca681692b2206f6b47bce887b8959e2aa70da
+  metadata.gz: b30cee276a93de1f569d53daa0fb039d6fc68d1804b680e31f7f29a76dc7b16ab206527aa10d68eda922c5eb48e526d825d6f6931986d1195bdadece5e46fc70
+  data.tar.gz: bac4bf2d4499fc4773bccfe2d59f7441f3f1f38cce49af9bfa971f806638b3d55db97297097a9081b7699f3f3c430f3f839f88a25a88d208ec9bc88f672ae656

data/README.md

@@ -31,7 +31,7 @@ page = hf.scrape("https://example.com/article")
 puts page["markdown"]
 ```
 
-Create a key at [app.hydrafetch.com](https://app.hydrafetch.com). The constructor reads `HYDRAFETCH_API_KEY` when no key is passed.
+Copy your key from [app.hydrafetch.com](https://app.hydrafetch.com). The constructor reads `HYDRAFETCH_API_KEY` when no key is passed.
 
 Responses are plain hashes with string keys. Option names are camelCase because they are passed to the API unchanged; client options such as `poll_interval:` and `job_timeout:` are snake_case.
 
@@ -126,10 +126,27 @@ end
 hf.brand("stripe.com")                             # logos, colours, fonts, socials
 hf.logo("stripe.com", theme: "dark", type: "icon") # one asset
 hf.styleguide("stripe.com")                        # computed design system
+hf.styleguide("https://stripe.com/pricing", maxAge: 0) # one page, read fresh
 ```
 
 For logos in a browser use [`@hydrafetch/client-sdk`](https://github.com/Hydrafetch/client-sdk) with a publishable key. Those bill against logo pulls rather than credits.
 
+## Rating results
+
+Tell us when a result was wrong, so it gets looked at. It is free, and rating the same request again replaces the earlier rating.
+
+```ruby
+hf.scrape("https://stripe.com/pricing")
+hf.rate_result("bad",
+               request_id: hf.last_request_id,
+               reasons: ["missing_content"],
+               note: "The enterprise tier is missing")
+
+hf.rate_result("good", url: "https://stripe.com/pricing") # by URL, last 24 hours
+```
+
+Reasons are `missing_content`, `wrong_content`, `blocked`, `slow`, `formatting` and `other`.
+
 ## Error handling
 
 All failures raise `Hydrafetch::Error`, carrying the API's error code, HTTP status and request id.
@@ -181,13 +198,14 @@ hf = Hydrafetch::Client.new("hf_...",
 | `extract(urls, **options)` | hash with `"results"` | 5 per URL |
 | `brand(domain)` | brand hash | 5 |
 | `logo(domain, **options)` | logo hash | 1 |
-| `styleguide(domain)` | design system hash | 10 |
+| `styleguide(domain_or_url, **options)` | design system hash | 10 |
 | `screenshot(url, **options)` | screenshot hash | 5 |
 | `images(url)`, `links(url)` | page assets | 1 |
 | `crawl(url, **options)` | job hash, polled to completion | 1 per page |
 | `batch(urls, **options)` | job hash, polled to completion | 1 per page |
 | `start_crawl`, `start_batch` | job id `String` | 1 per page |
 | `crawl_status(id)`, `batch_status(id)` | job hash | free |
+| `rate_result(rating, request_id:, url:, reasons:, note:)` | rating hash | free |
 
 Failed requests are not billed. Pricing does not vary with page difficulty, so there is no render, stealth or proxy option to set.
 

data/lib/hydrafetch/client.rb

@@ -11,7 +11,7 @@ module Hydrafetch
     DEFAULT_MAX_RETRIES = 2
     TERMINAL_STATUSES = %w[completed failed cancelled].freeze
 
-    attr_reader :base_url
+    attr_reader :base_url, :last_request_id
 
     def initialize(api_key = nil, base_url: DEFAULT_BASE_URL, timeout: DEFAULT_TIMEOUT,
                    max_retries: DEFAULT_MAX_RETRIES)
@@ -32,6 +32,16 @@ module Hydrafetch
       post("/v1/web/scrape", { url: url }.merge(compact(options)))
     end
 
+    def rate_result(rating, request_id: nil, url: nil, reasons: nil, note: nil)
+      if request_id.nil? && url.nil?
+        raise Error.new("Pass request_id: or url: to say which result you are rating.",
+                        code: "VALIDATION_ERROR", status: 400)
+      end
+
+      post("/v1/web/feedback", compact(requestId: request_id, url: url, rating: rating,
+                                        reasons: reasons, note: note))
+    end
+
     def markdown(url, **options)
       scrape(url, formats: ["markdown"], **options)["markdown"]
     end
@@ -57,8 +67,9 @@ module Hydrafetch
       get("/v1/web/brand/logo", { domain: domain }.merge(compact(options)))
     end
 
-    def styleguide(domain)
-      get("/v1/web/styleguide", domain: domain)
+    def styleguide(domain_or_url, **options)
+      key = domain_or_url.match?(%r{\Ahttps?://}i) ? :url : :domain
+      get("/v1/web/styleguide", { key => domain_or_url }.merge(compact(options)))
     end
 
     def screenshot(url, **options)
@@ -161,6 +172,7 @@ module Hydrafetch
         end
 
         res = http_for(uri).request(req)
+        @last_request_id = res["x-request-id"] || @last_request_id
         unwrap(res)
       rescue Error => e
         raise unless e.retryable? && attempt < @max_retries

data/lib/hydrafetch/version.rb

@@ -1,3 +1,3 @@
 module Hydrafetch
-  VERSION = "0.1.1".freeze
+  VERSION = "0.3.0".freeze
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: hydrafetch
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.3.0
 platform: ruby
 authors:
 - Hydrafetch
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-08-21 00:00:00.000000000 Z
+date: 2026-10-21 00:00:00.000000000 Z
 dependencies: []
 description: Turn any URL into clean Markdown and structured data. Scrape, map, search,
   extract, brand and bulk crawl through one API.