coelacanth 0.6.1 → 0.7.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 94493e66b4aae51d1790f03eb89c95d2ec1861b9d150c1001bba7554a1b37ab7
-  data.tar.gz: acdd939524543ec62740e153774c44f5fcdee11d30a9bd5ca4e6bcabe2f65398
+  metadata.gz: f1bc84d97135234e0e80586a789381ea2e10785c66fac0bebe21375205489ef3
+  data.tar.gz: fdbea80d5c55c1059aedc568ec593121517cf0cbcf55d145fbe123c121b66c2a
 SHA512:
-  metadata.gz: 05b8789bd0bf8a23cb678b9f17349a403c0f1e7017903dea14ae13dbea1df1204a3a5cdd184c70e86e0d7366dce67cabbbd528846c2c498953088c1309830421
-  data.tar.gz: 047d1acabd38e890579947bd7311178ab0197089acd0185d5dbfa0628bbe6a5ad003c330e786c2d82d44fbada5b3ed13882178b50cba86c74ed2e2e12a527199
+  metadata.gz: 37165c8087b6119d7cd9ce3517bfd12b1c5f52c8c27b7c4eab12351f47034d46b2e86c7fe72820e6b425e02e7f643494e74766995805d1052469fdfaec7f47f2
+  data.tar.gz: d45c1d607c7e35f938ca6fc3658ec082020fcdcfb6888c2a60a7e080e508c7430eedcf9f7eddcf78dad2320f3dfae2803de975d8de9f7cbfb66282944547c5f1

data/CHANGELOG.md

@@ -4,11 +4,8 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [v0.6.1] - 2026-06-15
-### :bug: Bug Fixes
-- [`f387ef9`](https://github.com/slidict/coelacanth/commit/f387ef997e0c383458a4fd0384f74883fcb63f37) - Update gem-push.yml *(commit by [@abechan1](https://github.com/abechan1))*
-
+## [v0.7.0] - 2026-07-08
 ### :wrench: Chores
-- [`4ad8456`](https://github.com/slidict/coelacanth/commit/4ad8456deba3aea4e6eea8836d6bdf728fbbdb70) - Bump version to 0.6.1 *(commit by [@abechan1](https://github.com/abechan1))*
+- [`ab6d634`](https://github.com/slidict/coelacanth/commit/ab6d634abbc5f954b4b9861e19e3420ee034fd77) - bump version to 0.7.0 *(commit by [@abechan1](https://github.com/abechan1))*
 
-[v0.6.1]: https://github.com/slidict/coelacanth/compare/v0.6.0...v0.6.1
+[v0.7.0]: https://github.com/slidict/coelacanth/compare/v0.6.1...v0.7.0

data/README.md

@@ -32,6 +32,7 @@ it into contemporary ingestion stacks without bespoke glue code.
   multi-byte sources.
 - **Screenshot capture** – Fetches full-page PNGs via a configurable browser client so you can archive visual context alongside
   the extracted text.
+- **PDF generation** – Renders any URL to PDF through Ferrum so you can persist printer-friendly snapshots of source pages.
 - **Redirect resolution** – Follows HTTP redirects and long redirect chains to guarantee the extractor works on the final
   landing page.
 - **Configurable HTTP headers** – Inject custom headers (user agent, authorization, etc.) into the remote browser session for
@@ -82,6 +83,9 @@ result[:extraction] # => article metadata and body markdown
 result[:dom]        # => Oga DOM representation for downstream processing
 result[:screenshot] # => PNG screenshot as a binary string
 result[:response]   # => HTTP status, headers, and final URL
+
+pdf = Coelacanth.pdf("https://example.com/article")
+File.binwrite("article.pdf", pdf)
 ```
 
 # Plain-text morphology
@@ -181,6 +185,8 @@ development:
 - **Gotenberg client** – Set `client: "gotenberg"` to capture screenshots through Gotenberg's Chromium URL screenshot
   endpoint. Configure `gotenberg.url`, request timeouts, an optional `wait_delay`, an optional screenshot `user_agent`,
   and optional `extra_http_headers`.
+- **PDF generation** – `Coelacanth.pdf(url)` renders the URL with the Ferrum client and returns the generated PDF as a binary
+  string. Configure `remote_client` with a Chrome-compatible WebSocket endpoint before using this helper.
 - **Eyecatch image extraction** – Representative images are discovered automatically by checking Open Graph/Twitter metadata,
   Schema.org JSON-LD payloads, and high-signal `<img>` elements (hero/cover images, large dimensions, etc.). No manual XPath
   maintenance is required.

data/lib/coelacanth/client/base.rb

@@ -23,5 +23,9 @@ module Coelacanth::Client
     def get_screenshot
       raise "Must be implemented in subclass"
     end
+
+    def get_pdf
+      raise "Must be implemented in subclass"
+    end
   end
 end

data/lib/coelacanth/client/ferrum.rb

@@ -29,6 +29,13 @@ module Coelacanth::Client
       raise sanitized_remote_client_error(e)
     end
 
+    def get_pdf
+      wait_for_network_idle
+      remote_client.pdf
+    rescue => e
+      raise sanitized_remote_client_error(e)
+    end
+
     private
 
     def sanitized_remote_client_error(error)

data/lib/coelacanth/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Coelacanth
-  VERSION = "0.6.1"
+  VERSION = "0.7.0"
 end

data/lib/coelacanth.rb

@@ -48,6 +48,10 @@ module Coelacanth
     }
   end
 
+  def self.pdf(url)
+    Client::Ferrum.new(url).get_pdf
+  end
+
   def self.client_class_for(client_name)
     case client_name
     when "screenshot_one"

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: coelacanth
 version: !ruby/object:Gem::Version
-  version: 0.6.1
+  version: 0.7.0
 platform: ruby
 authors:
 - Yusuke