url_fetcher 1.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: a0720abc5e87d7a504fb8d25c58cec2675fe2e6c
+  data.tar.gz: 93bb4aeffae265ce2acd95e84584b7d28ebd6f5f
+SHA512:
+  metadata.gz: 2a9d32727ad820eb13f494b70e242cbe7f81b751da46d4c53d91055ea4e43dde090bc3eb25fdb5f447f6484d819abb21e875e31592df4ff54e1c0b5c1b5b54ef
+  data.tar.gz: b61ae8d4f664273bf63a1deaa7a8d19025ed9acc74db06a8a92e5181869e4d40b60c1e1a8280ea93327f59c74d7d3b73b4f457f06bf375d063ffdce3497ee814

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/.rspec

@@ -0,0 +1,2 @@
+--color
+--format progress

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in url_fetcher.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2014 WHI, Inc.
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,30 @@
+# UrlFetcher
+
+This gem provides a class that will fetch a URL response and save the body to a Tempfile. This can be useful if you are fetching large HTTP objects so you don't need to read them into memory all at once. The response body is exposed as a stream.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'url_fetcher'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install url_fetcher
+
+## Usage
+
+response = UrlFetcher.new("http://example.com/large_file")
+response.body # Returns a stream to a the body from a Tempfile on disk.
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1,18 @@
+require "bundler/gem_tasks"
+
+desc 'Default: run unit tests.'
+task :default => :test
+
+desc 'RVM likes to call it tests'
+task :tests => :test
+
+begin
+  require 'rspec'
+  require 'rspec/core/rake_task'
+  desc 'Run the unit tests'
+  RSpec::Core::RakeTask.new(:test)
+rescue LoadError
+  task :test do
+    STDERR.puts "You must have rspec 2.0 installed to run the tests"
+  end
+end

data/VERSION

@@ -0,0 +1 @@
+1.0.1

data/lib/url_fetcher.rb

@@ -0,0 +1,105 @@
+require "net/http"
+require "open-uri"
+require "tempfile"
+
+# This class will fetch the contents of a URL and store them in a Tempfile. The
+# results are exposed as a stream so you don't need to read potentialy huge responses
+# into memory all at once.
+class UrlFetcher
+  MEGABYTE = 1048576
+  
+  attr_reader :url
+
+  # Create a fetcher for the specified URL.
+  #
+  # Options include (default in parentheses):
+  # * :unlink (true) - Automatically delete the Tempfile. The stream will still be open, but will not be accessible from any other process.
+  # * :follow_redirects (true) - Automatically follow redirects instead of returning the redirect response.
+  # * :method (:get) - HTTP method to use to fetch the URL.
+  # * :max_size (10 megabytes)- The maximum size in bytes that should be fetched.
+  # * :open_timeout (10) - Time in seconds to wait for a connection to be established.
+  # * :read_timeout (20) - Time in seconds to wait for reading the HTTP response.
+  def initialize(url, options = {}, &redirect_hook)
+    @url = url
+    @redirect_hook = redirect_hook
+    options = default_options.merge(options)
+    @response = fetch_response(@url, options)
+  end
+
+  # Return an open stream to the downloaded URL.
+  def body
+    @response.body if success?
+  end
+
+  # Get the header with the specified name from the response.
+  def header(name)
+    @response[name]
+  end
+
+  # Return true if the response was a redirect (i.e. the redirect_block passed in the header returned false on a redirect)
+  def redirect?
+    @response.is_a? Net::HTTPRedirection
+  end
+
+  # Return true of the the response was a success.
+  def success?
+    @response.is_a? Net::HTTPSuccess
+  end
+
+  private
+
+  def default_options
+     { :unlink => true, :follow_redirects => true, :method => :get }
+  end
+
+  def fetch_response(url, options, previous_attempts = [])
+    raise "Too many redirects" if previous_attempts.size > 5
+    raise "Circular redirect" if previous_attempts.include?(url)
+    previous_attempts << url
+
+    uri = URI(url)
+
+    http = Net::HTTP.new(uri.host, uri.port)
+    http.read_timeout = options[:read_timeout] || 20 # This is seconds. Default is 60.
+    http.open_timeout = options[:open_timeout] || 10
+    if uri.scheme == "https"
+      http.use_ssl = true
+      http.verify_mode = OpenSSL::SSL::VERIFY_NONE
+    end
+
+    request = case options[:method]
+    when :head
+      Net::HTTP::Head.new(uri.request_uri)
+    when :post
+      Net::HTTP::Post.new(uri.request_uri)
+    else
+      Net::HTTP::Get.new(uri.request_uri)
+    end
+
+    response = http.request(request) do |resp|
+      unless resp.is_a?(Net::HTTPSuccess) || resp.is_a?(Net::HTTPRedirection)
+        resp.value # Raises an appropriate HTTP error
+      end
+      if resp.is_a?(Net::HTTPSuccess) && resp.class.body_permitted?
+        content_length = resp["Content-Length"].to_i
+        raise "File to big (#{content_length} bytes" if content_length > (options[:max_size] || 10 * MEGABYTE)
+        tempfile = Tempfile.new("url_fetcher", :encoding => 'ascii-8bit')
+        resp.read_body(tempfile)
+        tempfile.close
+      end
+    end
+
+    if response.is_a?(Net::HTTPRedirection) && options[:follow_redirects]
+      location = response["Location"]
+      unless location.include?(':')
+        location = Addressable::URI.parse(location)
+        location.scheme = uri.scheme
+        location.host = uri.host
+      end
+      abort_redirect = (@redirect_hook ? @redirect_hook.call(location.to_s) == false : false)
+      response = fetch_response(location, options, previous_attempts) unless abort_redirect
+    end
+
+    response
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,14 @@
+require 'url_fetcher'
+require 'webmock/rspec'
+
+RSpec.configure do |config|
+  config.treat_symbols_as_metadata_keys_with_true_values = true
+  config.run_all_when_everything_filtered = true
+  config.filter_run :focus
+
+  # Run specs in random order to surface order dependencies. If you find an
+  # order dependency and want to debug it, you can fix the order by providing
+  # the seed, which is printed after each run.
+  #     --seed 1234
+  config.order = 'random'
+end

data/spec/url_fetcher_spec.rb

@@ -0,0 +1,120 @@
+require 'spec_helper'
+
+describe UrlFetcher do
+
+  it "should fetch a URL to a temp file" do
+    WebMock.stub_request(:get, "http://example.com/test").to_return(:status => 200, :body => "Hello", :headers => {"Content-Length" => 5})
+    url_fetcher = UrlFetcher.new("http://example.com/test")
+    url_fetcher.success?.should == true
+    url_fetcher.redirect?.should == false
+    url_fetcher.header("content-length").should == "5"
+    url_fetcher.body.open
+    url_fetcher.body.read.should == "Hello"
+  end
+
+  it "should perform a POST request" do
+    WebMock.stub_request(:post, "http://example.com/test").to_return(:status => 200, :body => "Hello", :headers => {"Content-Length" => 5})
+    url_fetcher = UrlFetcher.new("http://example.com/test", :method => :post)
+    url_fetcher.success?.should == true
+    url_fetcher.redirect?.should == false
+    url_fetcher.header("content-length").should == "5"
+    url_fetcher.body.open
+    url_fetcher.body.read.should == "Hello"
+  end
+
+  it "should perform a HEAD request" do
+    WebMock.stub_request(:head, "http://example.com/test").to_return(:status => 200, :body => nil, :headers => {"Content-Length" => 5})
+    url_fetcher = UrlFetcher.new("http://example.com/test", :method => :head)
+    url_fetcher.success?.should == true
+    url_fetcher.redirect?.should == false
+    url_fetcher.header("content-length").should == "5"
+    url_fetcher.body.should == nil
+  end
+
+  it "should work with SSL" do
+    WebMock.stub_request(:get, "https://example.com/test").to_return(:status => 200, :body => "Hello", :headers => {"Content-Length" => 5})
+    url_fetcher = UrlFetcher.new("https://example.com/test")
+    url_fetcher.success?.should == true
+    url_fetcher.redirect?.should == false
+    url_fetcher.header("content-length").should == "5"
+    url_fetcher.body.open.read.should == "Hello"
+  end
+
+  it "should honor redirects" do
+    WebMock.stub_request(:get, "http://example.com/test1").to_return(:status => 301, :headers => {"Location" => "http://example.com/test2"})
+    WebMock.stub_request(:get, "http://example.com/test2").to_return(:status => 200, :body => "Hello", :headers => {"Content-Length" => 5})
+    url_fetcher = UrlFetcher.new("http://example.com/test1")
+    url_fetcher.success?.should == true
+    url_fetcher.redirect?.should == false
+    url_fetcher.header("content-length").should == "5"
+    url_fetcher.body.open.read.should == "Hello"
+  end
+
+  it "should not honor redirects if :follow_redirects == false" do
+    WebMock.stub_request(:get, "http://example.com/test1").to_return(:status => 301, :headers => {"Location" => "http://example.com/test2"})
+    url_fetcher = UrlFetcher.new("http://example.com/test1", :follow_redirects => false)
+    url_fetcher.success?.should == false
+    url_fetcher.redirect?.should == true
+  end
+
+  it "should call a block before each redirect with the new location" do
+    WebMock.stub_request(:get, "http://example.com/test1").to_return(:status => 302, :headers => {"Location" => "http://example.com/test2"})
+    WebMock.stub_request(:get, "http://example.com/test2").to_return(:status => 302, :headers => {"Location" => "http://example.com/test3"})
+    WebMock.stub_request(:get, "http://example.com/test3").to_return(:status => 200, :body => "Hello", :headers => {"Content-Length" => 5})
+    redirects = []
+    url_fetcher = UrlFetcher.new("http://example.com/test1") do |location|
+      redirects << location
+    end
+    url_fetcher.success?.should == true
+    url_fetcher.body.open
+    url_fetcher.body.read.should == "Hello"
+    redirects.should == ["http://example.com/test2", "http://example.com/test3"]
+  end
+
+  it "should abort redirecting if a block is given that returns false" do
+    WebMock.stub_request(:get, "http://example.com/test1").to_return(:status => 302, :headers => {"Location" => "http://example.com/test2"})
+    WebMock.stub_request(:get, "http://example.com/test2").to_return(:status => 302, :headers => {"Location" => "http://example.com/test3"})
+    WebMock.stub_request(:get, "http://example.com/test3").to_return(:status => 200, :body => "Hello", :headers => {"Content-Length" => 5})
+    redirects = []
+    url_fetcher = UrlFetcher.new("http://example.com/test1") do |location|
+      redirects << location
+      false
+    end
+    url_fetcher.success?.should == false
+    url_fetcher.redirect?.should == true
+    url_fetcher.body.should == nil
+    redirects.should == ["http://example.com/test2"]
+  end
+
+  it "should raise an error if there is a circular redirect" do
+    WebMock.stub_request(:get, "http://example.com/test").to_return(:status => 302, :headers => {"Location" => "http://example.com/test"})
+    lambda{ UrlFetcher.new("http://example.com/test") }.should raise_error("Circular redirect")
+  end
+
+  it "should raise an error if there are too many redirects" do
+    6.times do |i|
+      WebMock.stub_request(:get, "http://example.com/test#{i}").to_return(:status => 302, :headers => {"Location" => "http://example.com/test#{i + 1}"})
+    end
+    lambda{ UrlFetcher.new("http://example.com/test0") }.should raise_error("Too many redirects")
+  end
+
+  it "should raise an error if an HTTP error is returned" do
+    WebMock.stub_request(:get, "http://example.com/test").to_return(:status => 404, :body => "Not Found")
+    lambda{ UrlFetcher.new("http://example.com/test") }.should raise_error(Net::HTTPServerException)
+  end
+
+  it "should not unlink the temp file if asked not to" do
+    WebMock.stub_request(:get, "http://example.com/test").to_return(:status => 200, :body => "Hello", :headers => {"Content-Length" => 5})
+    url_fetcher = UrlFetcher.new("http://example.com/test", :unlink => false)
+    url_fetcher.success?.should == true
+    url_fetcher.body.open.read.should == "Hello"
+    url_fetcher.body.path.should_not == nil
+  end
+
+  it "should limit the size of the file downloaded" do
+    WebMock.stub_request(:get, "http://example.com/test").to_return(:status => 200, :body => "Hello", :headers => {"Content-Length" => 1001})
+    lambda do
+      UrlFetcher.new("http://example.com/test", :max_size => 1000)
+    end.should raise_error
+  end
+end

data/url_fetcher.gemspec

@@ -0,0 +1,26 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+
+Gem::Specification.new do |spec|
+  spec.name          = "url_fetcher"
+  spec.version       = File.read(File.expand_path("../VERSION", __FILE__)).chomp
+  spec.authors       = ["weheartit"]
+  spec.email         = ["dev@weheartit.com"]
+  spec.description   = %q{Fetch resources from the internetz!}
+  spec.summary       = %q{Fetch resources from the internetz with circular redirects support}
+  spec.homepage      = "https://github.com/weheartit/whi-url-fetcher"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_dependency('addressable', '~>2.3.4')
+
+  spec.add_development_dependency "bundler", "~> 1.3"
+  spec.add_development_dependency "rake"
+  spec.add_development_dependency "rspec"
+  spec.add_development_dependency "webmock"
+end

metadata

@@ -0,0 +1,127 @@
+--- !ruby/object:Gem::Specification
+name: url_fetcher
+version: !ruby/object:Gem::Version
+  version: 1.0.1
+platform: ruby
+authors:
+- weheartit
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-06-20 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: addressable
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.3.4
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.3.4
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: webmock
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Fetch resources from the internetz!
+email:
+- dev@weheartit.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- VERSION
+- lib/url_fetcher.rb
+- spec/spec_helper.rb
+- spec/url_fetcher_spec.rb
+- url_fetcher.gemspec
+homepage: https://github.com/weheartit/whi-url-fetcher
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.2.2
+signing_key: 
+specification_version: 4
+summary: Fetch resources from the internetz with circular redirects support
+test_files:
+- spec/spec_helper.rb
+- spec/url_fetcher_spec.rb