snapcrawl 0.4.0 → 0.4.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a98c3d8f09eb8572a01eefb9ceb9a9b925849e4dc0eb127f9c22a8cb79a7a954
-  data.tar.gz: 649528bf60dda4bc787bcd01e1eac7b73b017aa63d6ede6ccf794b398bc8758c
+  metadata.gz: 64c0d3c62258c70417520749bdd71b7d33c8d920ec94f2dfb0aaed961310563b
+  data.tar.gz: 72ece0ddb0f5f9f2b578d4c369814507bb1b2343170d799eb27497a3c937475a
 SHA512:
-  metadata.gz: 3f447cfd3536ed826acb9f597748242313259a38fecb473a2f6b1949e98f9d579fa70a8b29b1f3d3909f34ce287336e3305de7d4f73c684fc5d8708a0436073f
-  data.tar.gz: f966675b9465bca79b004207cd9861e7fe26129d4993394ffb7f02a80deab7e206027ff2ccfa18c81cb74aee0063da3f4de1e85446c24d6ea4623e26d156f69b
+  metadata.gz: b60088e4dab7944269f76344094a6f80e6b304c0591fff2c3e9aa0e18ffac89b2a9927bf2759e7a17f9944dd925b01b342f46ec6587754ac206bf614741be0c3
+  data.tar.gz: ae1b3dda9b0339440b9f37727503ad87f1f5a71d2eadc3283250f481b9391f1d530213a05a0f5ce0adc7a1f9bd183c049c5cfc7a7fcd1b06d5286c312d8d0747

data/lib/snapcrawl/crawler.rb

@@ -6,6 +6,7 @@ require 'nokogiri'
 require 'ostruct'
 require 'pstore'
 require 'uri'
+require 'addressable/uri'
 require 'webshot'
 
 module Snapcrawl
@@ -41,7 +42,7 @@ module Snapcrawl
       FileUtils.rm @storefile if File.exist? @storefile
     end
 
-    private
+  private
 
     def crawl(url, opts={})
       url = protocolize url
@@ -190,7 +191,7 @@ module Snapcrawl
       warnings = []
 
       links.each do |link|
-        link = link.attribute('href').to_s
+        link = link.attribute('href').to_s.dup
 
         # Remove #hash
         link.gsub!(/#.+$/, '')
@@ -205,11 +206,11 @@ module Snapcrawl
 
         # Convert relative links to absolute
         begin
-          link = URI.join( @opts.base, link ).to_s
+          link = URI.join( @opts.base, link ).to_s.dup
         rescue URI::InvalidURIError
-          escaped_link = URI.escape link
+          escaped_link = Addressable::URI.encode link
           warnings << { link: link, message: "Using escaped link: #{escaped_link}" }
-          link = URI.join( @opts.base, escaped_link ).to_s
+          link = URI.join( @opts.base, escaped_link ).to_s.dup
         rescue => e
           warnings << { link: link, message: "#{e.class} #{e.message}" }
           next

data/lib/snapcrawl/version.rb

@@ -1,3 +1,3 @@
 module Snapcrawl
-  VERSION = "0.4.0"
+  VERSION = "0.4.1"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: snapcrawl
 version: !ruby/object:Gem::Version
-  version: 0.4.0
+  version: 0.4.1
 platform: ruby
 authors:
 - Danny Ben Shitrit
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2020-01-01 00:00:00.000000000 Z
+date: 2020-01-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: colsole
@@ -86,6 +86,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.17'
+- !ruby/object:Gem::Dependency
+  name: addressable
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.7'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.7'
 description: Snapcrawl is a command line utility for crawling a website and saving
   screenshots.
 email: db@dannyben.com
@@ -112,7 +126,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '2.0'
+      version: '2.3'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="