snapcrawl 0.2.7 → 0.2.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7c2f0d180ff2e9b9cdeed900ceb8b3ccb7bbdbe2ca4f6312b22e913189e73902
-  data.tar.gz: fd1ff5e8abadde31e0bebf702e3ac589a88e5e79e54857a10078cc1e793d80bf
+  metadata.gz: 2500895cfd465dd633ac9650fc702f87b684ae4a81aa2feb979a16fad17bedc2
+  data.tar.gz: 042f0e14f8139d3b33bdd0061731c7973f7c445e57e2c474d32c3b226d333acb
 SHA512:
-  metadata.gz: 9c9462ca2fe28a1fa4b93462104f609dbc9608f5dec191767f81401a00283bdf030026e5e94c6394594beafbf35800fe68ec137fa6131fe09cd59de07ae0e4ee
-  data.tar.gz: ade326042ed804293b56451c6f7cd204ba0b8d4c86d15d5d1b51323ef7401c4529b7e4d67b25e1ca6c09cf6b1ca1bfd2d667f4a3d2647813f4b9f98ba9d393df
+  metadata.gz: 7603f985467c47f26b5bbf8c3cebf5654de708d0f7039c0268b4c4824089c259c17b687be482ed3e5813f44fef2274407542c76e3291f064aed1b06c2af1837a
+  data.tar.gz: 3246ea728fa90fc65da1732964492da9383ae0c99a47746d1194f5c991b2efadd333c69478e2c97fd99274acb47fc38773285a53c9fd5505e7a605af08f58cf2

data/README.md

@@ -1,6 +1,7 @@
 Snapcrawl - crawl a website and take screenshots
 ==================================================
 
+[![Build Status](https://travis-ci.com/DannyBen/snapcrawl.svg?branch=master)](https://travis-ci.com/DannyBen/snapcrawl)
 [![Gem Version](https://badge.fury.io/rb/snapcrawl.svg)](http://badge.fury.io/rb/snapcrawl)
 [![Code Climate](https://codeclimate.com/github/DannyBen/snapcrawl/badges/gpa.svg)](https://codeclimate.com/github/DannyBen/snapcrawl)
 
@@ -56,22 +57,41 @@ Usage
     Snapcrawl
     
     Usage:
-      snapcrawl go <url> [options]
+      snapcrawl go URL [options]
       snapcrawl -h | --help 
       snapcrawl -v | --version
     
     Options:
-      -f --folder <path>     Where to save screenshots [default: snaps]
-      -a --age <n>           Number of seconds to consider screenshots fresh
-                             [default: 86400]
-      -d --depth <n>         Number of levels to crawl [default: 1]
-      -W --width <n>         Screen width in pixels [default: 1280]
-      -H --height <n>        Screen height in pixels. Use 0 to capture the full 
-                             page [default: 0]
-      -s --selector <s>      CSS selector to capture
-      -o --only <regex>      Include only URLs that match <regex>
-      -h --help              Show this screen
-      -v --version           Show version
+      -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
@@ -80,18 +100,8 @@ Usage
       snapcrawl go example.com -W360 -H480
       snapcrawl go example.com --selector "#main-content"
       snapcrawl go example.com --only "products|collections"
-
----
-
-Notes
---------------------------------------------------
-
-If a URL cannot be found, Snapcrawl will report to stderr. 
-You can create a report by running
-
-    $ snapcrawl go example.com 2> err.txt
-
-
+      snapcrawl go example.com --name "screenshot-%{url}"
+      snapcrawl go example.com --name "`date +%Y%m%d`_%{url}"
 
 ---
 

data/lib/snapcrawl/crawler.rb

@@ -35,7 +35,7 @@ module Snapcrawl
     def execute(args)
       raise MissingPhantomJS unless command_exist? "phantomjs"
       raise MissingImageMagick unless command_exist? "convert"
-      crawl args['<url>'].dup, opts_from_args(args)
+      crawl args['URL'].dup, opts_from_args(args)
     end
 
     def clear_cache
@@ -51,7 +51,8 @@ module Snapcrawl
         depth: 1,
         age: 86400,
         folder: 'snaps',
-        base: url, 
+        name: '%{url}',
+        base: url,
       }
       urls = [protocolize(url)]
 
@@ -155,7 +156,7 @@ module Snapcrawl
 
     # Return proper image path for a UR
     def image_path_for(url)
-      "#{@opts.folder}/#{handelize(url)}.png"
+      "#{@opts.folder}/#{@opts.name}.png" % { url: handelize(url) }
     end
 
     # Add protocol to a URL if neeed
@@ -214,7 +215,7 @@ module Snapcrawl
 
     def opts_from_args(args)
       opts = {}
-      %w[folder selector only].each do |opt|
+      %w[folder name selector only].each do |opt|
         opts[opt.to_sym] = args["--#{opt}"] if args["--#{opt}"]
       end
 

data/lib/snapcrawl/templates/docopt.txt

@@ -1,22 +1,41 @@
 Snapcrawl
 
 Usage:
-  snapcrawl go <url> [options]
+  snapcrawl go URL [options]
   snapcrawl -h | --help 
   snapcrawl -v | --version
 
 Options:
-  -f --folder <path>     Where to save screenshots [default: snaps]
-  -a --age <n>           Number of seconds to consider screenshots fresh
-                         [default: 86400]
-  -d --depth <n>         Number of levels to crawl [default: 1]
-  -W --width <n>         Screen width in pixels [default: 1280]
-  -H --height <n>        Screen height in pixels. Use 0 to capture the full 
-                         page [default: 0]
-  -s --selector <s>      CSS selector to capture
-  -o --only <regex>      Include only URLs that match <regex>
-  -h --help              Show this screen
-  -v --version           Show version
+  -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
@@ -25,3 +44,5 @@ Examples:
   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}"

data/lib/snapcrawl/version.rb

@@ -1,3 +1,3 @@
 module Snapcrawl
-  VERSION = "0.2.7"
+  VERSION = "0.2.8"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: snapcrawl
 version: !ruby/object:Gem::Version
-  version: 0.2.7
+  version: 0.2.8
 platform: ruby
 authors:
 - Danny Ben Shitrit
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-06-13 00:00:00.000000000 Z
+date: 2019-06-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: colsole