picfisher 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: da4504372d6b3cceb6deda036fda5f51f8d46c44726ebed76636aa02c49fa4b9
-  data.tar.gz: 446d39d4044826782748ca34c5a346560d6ae5490290afeb371323976ace6b06
+  metadata.gz: d6b49dc4c4a306ff17087d90b81c875043f63062b1760eb0f481e2968b44dd66
+  data.tar.gz: 4caafb009411921cef9a4c3c60a8e231072de6a369f6b4e7a5386d636534d241
 SHA512:
-  metadata.gz: 5d2921671fd3e415c4f354ec1f0e67c62d95d3e2a470f4c1dd4db5de44169984d4ad42ee9657e246c6555f1ac18b312d05e8c9e12e37290bda3ae776b582d727
-  data.tar.gz: 7be9a0990f49777ddd3d911801d1a3ef61b69c966df20dc483b6c870c9731bf6812109bfe6af22dab5e40f000e2d3b4a523fcef2a4c9673de561787300a9e563
+  metadata.gz: 8cb50f69831f0421ec7cda95a942730ebdec12ceadc664a7c65fbba5322ee0c6315b5eefa06440041106756c3ba54c1fcad876c180abf551047b299da09fa2d7
+  data.tar.gz: 56739738de69a7e0f314815c0665018d516af93cc39451884ae8abe2ac1ba56db02a45cc4e272cab14a9bb32653fbd66e569bc0482999444702bb0ce9b2b8133

data/CHANGELOG.md

@@ -5,6 +5,14 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.2.0] - 2024-05-30
+
+### Added
+
+- Debug Level is 'info' by default
+- Error handling when image URL is not valid
+
+
 ## [0.1.0] - 2024-05-30
 
 ### Added

data/README.md

@@ -28,7 +28,7 @@ With log
 DEBUG_LEVEL=debug picfisher images.txt ~/Downloads/fished_images
 ```
 
-Accepted values for `DEBUG_LEVEL`: `debug`, `info`, `error`.
+Accepted values for `DEBUG_LEVEL`: `debug`, `info`, `error`, `silence`.
 
 ## Development
 

data/TODO.md

@@ -5,3 +5,4 @@
 - Add a progress bar for the downloading phase.
 - Allow multiple concurrent downloads. Add an extra param to decide the number, default `5`
 - Add error handling to the Downloader. Many things can be wrong when connecting to the internet.
+- Allow URLs without image extension. This requires the source urls file to have a predictable estructure. Or we request all the images and check the media type of the response.

data/lib/picfisher/downloader.rb

@@ -4,8 +4,20 @@ module PicFisher
   module Downloader
     # TODO: We need to add error handling here
     def self.download(url, output_path)
-      PicFisher::Log.debug("Downloading #{url} to #{output_path}")
+      PicFisher::Log.debug("Fishing #{url} to #{output_path}")
 
+      begin
+        _dowload(url, output_path)
+      rescue OpenURI::HTTPError => e
+        message = "Failed to fish #{url}: #{e}"
+        PicFisher::Log.error(message)
+        raise PicFisher::Error.new(message)
+      end
+    end
+
+    private
+
+    def self._dowload(url, output_path)
       io_stream = OpenURI::open_uri(url)
 
       File.open(output_path, "wb") do |f|

data/lib/picfisher/fishing_boat.rb

@@ -8,7 +8,12 @@ module PicFisher
       urls = PicFisher::URLExtractor.extract(file_to_string)
       urls.each do |url|
         sanitized_url = PicFisher::Sanitizer.sanitize_image_url(url)
-        PicFisher::Downloader.download(url, "#{output_directory_path}/#{sanitized_url}")
+
+        begin
+          PicFisher::Downloader.download(url, "#{output_directory_path}/#{sanitized_url}")
+        rescue PicFisher::Error
+          PicFisher::Log.error("Failed to fish #{url}. Skipping...")
+        end
       end
     end
   end

data/lib/picfisher/log.rb

@@ -1,19 +1,19 @@
 module PicFisher
   module Log
     def self.debug(message)
-      if ["debug"].include? ENV["DEBUG_LEVEL"]
+      if ["debug"].include? debug_level
         output(:debug, message)
       end
     end
 
     def self.info(message)
-      if ["debug", "info"].include? ENV["DEBUG_LEVEL"]
+      if ["debug", "info"].include? debug_level
         output(:info, message)
       end
     end
 
     def self.error(message)
-      if ["debug", "info", "error"].include? ENV["DEBUG_LEVEL"]
+      if ["debug", "info", "error"].include? debug_level
         output(:error, message)
       end
     end
@@ -24,5 +24,9 @@ module PicFisher
       final_message = "PicFisher [#{level.upcase}] #{message}"
       Kernel.puts(final_message)
     end
+
+    def self.debug_level
+      ENV["DEBUG_LEVEL"] || "info" # default is info
+    end
   end
 end

data/lib/picfisher/sanitizer.rb

@@ -6,7 +6,7 @@ module PicFisher
       result =
         url
           .sub(/#{filename_extension_escaped}$/, "")
-          .gsub(/[^\w\s_-]+/, "_")
+          .gsub(/[^\w\s-]+/, "_")
           .gsub(/(^|\b\s)\s+($|\s?\b)/, "\\1\\2")
           .gsub(/\s+/, "_")
 

data/lib/picfisher/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module PicFisher
-  VERSION = "0.1.0"
+  VERSION = "0.2.0"
 end

data/lib/picfisher.rb

@@ -27,7 +27,7 @@ module PicFisher
     end
 
     if !Dir.exist?(output_directory_path)
-      message = "Directory not found: #{images_file_path}"
+      message = "Directory not found: #{output_directory_path}"
       PicFisher::Log.error(message)
       raise PicFisher::Error.new(message)
     end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: picfisher
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
 - Fernando Guillen