snapcrawl 0.3.1 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d5c46ba3f4a171eb59bbc9afa6eca7327c8ef1964268bb63f407354201bb553b
-  data.tar.gz: beff7935a00a34edf97207f443a0a8a1b7e4734a6149f3b60fc6c625030a1be2
+  metadata.gz: a98c3d8f09eb8572a01eefb9ceb9a9b925849e4dc0eb127f9c22a8cb79a7a954
+  data.tar.gz: 649528bf60dda4bc787bcd01e1eac7b73b017aa63d6ede6ccf794b398bc8758c
 SHA512:
-  metadata.gz: 6e72274c6fa25d0b397bfd20fd676f0f8c83abb1d493610d58d091af4bdab700614ed8530aeaa75bea89c4c754a9fbea25feec669a62cdfb79d759c296d530ef
-  data.tar.gz: 349670f9155d5dae148c77af37f9aab2c6b334c560d73b48ca09a8fe10c15b485daee015082ac76c1698f0aa2d313bccbd747560d731f64738f8c94a801e2b4d
+  metadata.gz: 3f447cfd3536ed826acb9f597748242313259a38fecb473a2f6b1949e98f9d579fa70a8b29b1f3d3909f34ce287336e3305de7d4f73c684fc5d8708a0436073f
+  data.tar.gz: f966675b9465bca79b004207cd9861e7fe26129d4993394ffb7f02a80deab7e206027ff2ccfa18c81cb74aee0063da3f4de1e85446c24d6ea4623e26d156f69b

data/README.md

@@ -14,7 +14,7 @@ screenshots.
 Features
 --------------------------------------------------
 
-- Crawls a website to any given depth and save screenshots
+- Crawls a website to any given depth and saves screenshots
 - Can capture the full length of the page
 - Can use a specific resolution for screenshots
 - Skips capturing if the screenshot was already saved recently
@@ -34,11 +34,15 @@ Docker Image
 You can run Snapcrawl by using this docker image (which contains all the
 necessary prerequisites):
 
-    $ docker pull dannyben/snapcrawl
+```
+$ docker pull dannyben/snapcrawl
+```
 
 Then you can use it like this:
 
-    $ docker run --rm -it dannyben/snapcrawl --help
+```
+$ docker run --rm -it dannyben/snapcrawl --help
+```
 
 For more information refer to the [docker-snapcrawl][3] repository.
 
@@ -46,65 +50,71 @@ For more information refer to the [docker-snapcrawl][3] repository.
 Install
 --------------------------------------------------
 
-	$ gem install snapcrawl
+```
+$ gem install snapcrawl
+```
 
 
 Usage
 --------------------------------------------------
 
-	$ snapcrawl --help
-
-    Snapcrawl
-    
-    Usage:
-      snapcrawl go URL [options]
-      snapcrawl -h | --help 
-      snapcrawl -v | --version
-    
-    Options:
-      -f, --folder PATH
-        Where to save screenshots [default: snaps]
-    
-      -n, --name TEMPLATE
-        Filename template. Include the string '%{url}' anywhere in the name to 
-        use the captured URL in the filename [default: %{url}]
-    
-      -a, --age SECONDS
-        Number of seconds to consider screenshots fresh [default: 86400]
-    
-      -d, --depth LEVELS
-        Number of levels to crawl [default: 1]
-    
-      -W, --width PIXELS
-        Screen width in pixels [default: 1280]
-    
-      -H, --height PIXELS
-        Screen height in pixels. Use 0 to capture the full page [default: 0]
-    
-      -s, --selector SELECTOR
-        CSS selector to capture
-    
-      -o, --only REGEX
-        Include only URLs that match REGEX
-    
-      -h, --help
-        Show this screen
-    
-      -v, --version
-        Show version number
-    
-    Examples:
-      snapcrawl go example.com
-      snapcrawl go example.com -d2 -fscreens
-      snapcrawl go example.com -d2 > out.txt 2> err.txt &
-      snapcrawl go example.com -W360 -H480
-      snapcrawl go example.com --selector "#main-content"
-      snapcrawl go example.com --only "products|collections"
-      snapcrawl go example.com --name "screenshot-%{url}"
-      snapcrawl go example.com --name "`date +%Y%m%d`_%{url}"
+```
+$ snapcrawl --help
+
+Snapcrawl
+
+Usage:
+  snapcrawl URL [options]
+  snapcrawl -h | --help 
+  snapcrawl -v | --version
+
+Options:
+  -f, --folder PATH
+    Where to save screenshots [default: snaps]
+
+  -n, --name TEMPLATE
+    Filename template. Include the string '%{url}' anywhere in the name to 
+    use the captured URL in the filename [default: %{url}]
+
+  -a, --age SECONDS
+    Number of seconds to consider screenshots fresh [default: 86400]
+
+  -d, --depth LEVELS
+    Number of levels to crawl [default: 1]
+
+  -W, --width PIXELS
+    Screen width in pixels [default: 1280]
+
+  -H, --height PIXELS
+    Screen height in pixels. Use 0 to capture the full page [default: 0]
+
+  -s, --selector SELECTOR
+    CSS selector to capture
+
+  -o, --only REGEX
+    Include only URLs that match REGEX
+
+  -h, --help
+    Show this screen
+
+  -v, --version
+    Show version number
+
+Examples:
+  snapcrawl example.com
+  snapcrawl example.com -d2 -fscreens
+  snapcrawl example.com -d2 > out.txt 2> err.txt &
+  snapcrawl example.com -W360 -H480
+  snapcrawl example.com --selector "#main-content"
+  snapcrawl example.com --only "products|collections"
+  snapcrawl example.com --name "screenshot-%{url}"
+  snapcrawl example.com --name "`date +%Y%m%d`_%{url}"
+```
 
 ---
 
 [1]: http://phantomjs.org/download.html
 [2]: https://imagemagick.org/script/download.php
 [3]: https://github.com/DannyBen/docker-snapcrawl
+
+

data/lib/snapcrawl/crawler.rb

@@ -15,10 +15,8 @@ module Snapcrawl
   class MissingImageMagick < StandardError; end
 
   class Crawler
-    def self.instance
-      @@instance ||= self.new
-    end
-
+    include Singleton
+    
     def initialize
       @storefile  = "snapcrawl.pstore"
       @store      = PStore.new(@storefile)
@@ -256,11 +254,11 @@ module Snapcrawl
     # prints some output to stdout, this is why we override $stdout for
     # the duration of the run.
     def hide_output
-      $keep_stdout, $keep_stderr = $stdout, $stderr
+      keep_stdout, keep_stderr = $stdout, $stderr
       $stdout, $stderr = StringIO.new, StringIO.new
       yield
     ensure
-      $stdout, $stderr = $keep_stdout, $keep_stderr
+      $stdout, $stderr = keep_stdout, keep_stderr
     end
   end
 end

data/lib/snapcrawl/templates/docopt.txt

@@ -1,7 +1,7 @@
 Snapcrawl
 
 Usage:
-  snapcrawl go URL [options]
+  snapcrawl URL [options]
   snapcrawl -h | --help 
   snapcrawl -v | --version
 
@@ -38,11 +38,11 @@ Options:
     Show version number
 
 Examples:
-  snapcrawl go example.com
-  snapcrawl go example.com -d2 -fscreens
-  snapcrawl go example.com -d2 > out.txt 2> err.txt &
-  snapcrawl go example.com -W360 -H480
-  snapcrawl go example.com --selector "#main-content"
-  snapcrawl go example.com --only "products|collections"
-  snapcrawl go example.com --name "screenshot-%{url}"
-  snapcrawl go example.com --name "`date +%Y%m%d`_%{url}"
+  snapcrawl example.com
+  snapcrawl example.com -d2 -fscreens
+  snapcrawl example.com -d2 > out.txt 2> err.txt &
+  snapcrawl example.com -W360 -H480
+  snapcrawl example.com --selector "#main-content"
+  snapcrawl example.com --only "products|collections"
+  snapcrawl example.com --name "screenshot-%{url}"
+  snapcrawl example.com --name "`date +%Y%m%d`_%{url}"

data/lib/snapcrawl/version.rb

@@ -1,3 +1,3 @@
 module Snapcrawl
-  VERSION = "0.3.1"
+  VERSION = "0.4.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: snapcrawl
 version: !ruby/object:Gem::Version
-  version: 0.3.1
+  version: 0.4.0
 platform: ruby
 authors:
 - Danny Ben Shitrit
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-09-11 00:00:00.000000000 Z
+date: 2020-01-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: colsole
@@ -119,7 +119,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.4
+rubygems_version: 3.0.3
 signing_key: 
 specification_version: 4
 summary: Crawl a website and take screenshots (CLI + Library)