pubchem 0.0.5

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: cc1a04a9f940becd4f4eff582d8105d6f3772eed
+  data.tar.gz: 224b9440fe38fcfa39fe9b360a2f32a9e145b27f
+SHA512:
+  metadata.gz: 6f72420e95796c668a1154877ef5ad2455569e00fbf618ee2ebfc5256433fbcf0cb0471d67ecf2044bce075f0dbf9a59f769610026620936a74dc488fa8a0e22
+  data.tar.gz: 297ba5d561ed323425c6c5804eceb035d17baf2c8865acf7b4bade28ccb544b32dd79a6e9f319c92acc5bdd45e1e0d1a075648779fcd1598104d36db34acc62a

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Gem's dependencies in pubchem.gemspec
+gemspec

data/README.markdown

@@ -0,0 +1,23 @@
+# Pubchem image downloader
+
+For getting all that juicy substance and compound data from Pubchem.
+
+## Installation
+
+`apt-get install wget`
+
+Or
+
+`sudo apt-get install wget`
+
+`gem install pubchem`
+
+## Usage
+
+```ruby
+pubchem = Pubchem.new
+
+pubchem.get_ids([16,405], "~/yay.zip")
+
+puts "Do a happy dance!"
+```

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/bin/console

@@ -0,0 +1,13 @@
+#!/usr/bin/env ruby
+require "bundler/setup"
+require "pubchem"
+
+# You can add fixtures and/or initialization code here to make experimentin
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start

data/bin/setup

@@ -0,0 +1,7 @@
+#!/bin/bash
+set -euo pipefail
+IFS=$'\n\t'
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/example.rb

@@ -0,0 +1,7 @@
+require_relative "lib/pubchem"
+
+pubchem = Pubchem.new
+
+pubchem.get_ids([16,405], "~/yay.zip")
+
+puts "Do a happy dance!"

data/lib/pubchem.rb

@@ -0,0 +1,63 @@
+require 'mechanize'
+
+class Pubchem
+
+  attr_accessor :agent
+
+  def initialize(agent=nil)
+
+    @agent = agent
+    @agent ||= Mechanize.new { |agent|
+      agent.follow_meta_refresh = true
+    }
+
+  end
+
+  def get_ids(ids,
+              filename,
+              db: :compound,
+              retrieve_mode: :image,
+              delay: nil)
+
+    ids = ids.join(",") if ids.is_a? Array
+    filename = File.expand_path(filename)
+
+    @agent.get('https://pubchem.ncbi.nlm.nih.gov/pc_fetch/pc_fetch.cgi') do |page|
+
+      response = page.form() do |form|
+
+        form.idstr = ids
+        form.retmode = retrieve_mode.to_s
+        form.db = "pc#{db}"
+        button = form.buttons.select { |b| b.value == "Download" }.first
+      end.submit
+
+      ftp_link = response.links.select {|l| l.uri.scheme == "ftp"}.first
+
+      while not ftp_link
+        delay ||= 0.875 + rand / 2
+        sleep(delay)
+
+        reqid_link = response.links.select {|l| l.to_s.start_with? "pc_fetch.cgi?reqid" }.first
+        response = @agent.get(reqid_link)
+        ftp_link = response.links.select {|l| l.uri.scheme == "ftp"}.first
+
+      end
+
+      ftp_url = ftp_link.to_s
+      size = ftp_url.size
+  
+      # We don't want to allow scary characters into our URL since it is a
+      # security risk, so we only allow lower and upper case letters, numbers, 
+      # /   forward slashes
+      # :   colons
+      # .   periods
+      # -   dashes
+      ftp_url.gsub!(/[^a-zA-Z0-9\/\:\.\-]/u,'')
+      raise "Invalid character detected" if ftp_url.size != size
+
+      system("wget", ftp_url, "-O", filename)
+
+    end
+  end
+end

data/lib/pubchem/version.rb

@@ -0,0 +1,3 @@
+module Pubchem
+  VERSION = "0.0.5"
+end

data/pubchem.gemspec

@@ -0,0 +1,28 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'pubchem/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "pubchem"
+  spec.version       = Pubchem::VERSION
+  spec.authors       = ["Zach Aysan"]
+  spec.email         = ["zachaysan@gmail.com"]
+
+  spec.summary = %q{ Collect Pubchem substance and compound data }
+  spec.description = %q{ While there is a great FTP mirror for
+                         molecule data, it is hard to deal with
+                         their form. This helps with that!}
+  spec.homepage = "https://github.com/zachaysan/pubchem"
+  spec.license = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_runtime_dependency "mechanize", "~> 2.7.3"
+
+  spec.add_development_dependency "bundler", "~> 1.10"
+
+end

data/run

@@ -0,0 +1,2 @@
+#!/bin/bash
+ruby example.rb

metadata

@@ -0,0 +1,87 @@
+--- !ruby/object:Gem::Specification
+name: pubchem
+version: !ruby/object:Gem::Version
+  version: 0.0.5
+platform: ruby
+authors:
+- Zach Aysan
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2015-09-17 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: mechanize
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.7.3
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.7.3
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.10'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.10'
+description: |2-
+   While there is a great FTP mirror for
+                           molecule data, it is hard to deal with
+                           their form. This helps with that!
+email:
+- zachaysan@gmail.com
+executables:
+- ".gitkeep"
+extensions: []
+extra_rdoc_files: []
+files:
+- Gemfile
+- README.markdown
+- Rakefile
+- bin/console
+- bin/setup
+- example.rb
+- exe/.gitkeep
+- lib/pubchem.rb
+- lib/pubchem/version.rb
+- pubchem.gemspec
+- run
+homepage: https://github.com/zachaysan/pubchem
+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: 2.4.7
+signing_key: 
+specification_version: 4
+summary: Collect Pubchem substance and compound data
+test_files: []