scraped_page_archive 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: dad81b1b381a56c2e975f9b25216b68865e30a05
+  data.tar.gz: 558e3bb764ff15b5af3581f46b2a9b65448f01a0
+SHA512:
+  metadata.gz: ac28d6306e7cdbb3aa5763f947bb78a22f065900cf90de24dbdb6bb802c9ce6644017d176c5ce6111517e62221bbcab75221aa863b23b5321c868dd2746e897d
+  data.tar.gz: 3fa19422cbc4c41217b167e54a3deed64254bf4ab9a0ea215501dbf06bed28b72a0d50aa1314ba9edc66be09d98eb174b60d718dbcb139c635d07409f15dbd91

data/.gitignore

@@ -0,0 +1,9 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/.travis.yml

@@ -0,0 +1,9 @@
+sudo: false
+language: ruby
+rvm:
+  - 2.0.0
+  - 2.1.10
+  - 2.2.5
+  - 2.3.1
+before_install: gem install bundler -v 1.12.5
+cache: bundler

data/CHANGELOG.md

@@ -0,0 +1,15 @@
+# Change Log
+
+All notable changes to this project will be documented in this file.
+This project adheres to [Semantic Versioning](http://semver.org/).
+
+## [Unreleased]
+
+## 0.1.0 - 2016-07-28
+
+### Features
+
+- Record http interactions
+- Save the interaction to a git repository
+
+[Unreleased]: https://github.com/everypolitician/scraped_page_archive/compare/v0.1.0...HEAD

data/Gemfile

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

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2016 Chris Mytton
+
+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 +1,75 @@
+# ScrapedPageArchive
+
+Add this gem to your Ruby scraper and it will automatically capture http requests
+and cache the response in a branch within your git repository.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'scraped_page_archive'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install scraped_page_archive
+
+## Usage
+
+First require the library:
+
+```ruby
+require 'scraped_page_archive'
+```
+
+Then configure the github url to clone. This will need to have a GitHub token embedded in it, you can [generate a new one here](https://github.com/settings/tokens). It will need to have the `repo` permission checked.
+
+If you're using the excellent [morph.io](https://morph.io) then you can set the `MORPH_SCRAPER_CACHE_GITHUB_REPO_URL` environment variable to your git url:
+
+| Name                                  | Value                                                           |
+|---------------------------------------|-----------------------------------------------------------------|
+| `MORPH_SCRAPER_CACHE_GITHUB_REPO_URL` | `https://githubtokenhere@github.com/tmtmtmtm/estonia-riigikogu` |
+
+You can also set this to any value (including another environment variable of your choosing) with the following:
+
+```ruby
+ScrapedPageArchive.github_repo_url = 'https://githubtokenhere@github.com/tmtmtmtm/estonia-riigikogu'
+```
+
+Then you can record http requests by performing them in a block passed to `ScrapedPageArchive.record`:
+
+```ruby
+ScrapedPageArchive.record do
+  response = open('http://example.com/')
+  # Use the response...
+end
+```
+
+### Use with open-uri
+
+If you would like to have your http requests automatically recorded when using open-uri do the following:
+
+```ruby
+require 'scraped_page_archive/open-uri'
+response = open('http://example.com/')
+# Use the response...
+```
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake test` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/everypolitician/scraped_page_archive.
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).

data/Rakefile

@@ -0,0 +1,10 @@
+require 'bundler/gem_tasks'
+require 'rake/testtask'
+
+Rake::TestTask.new(:test) do |t|
+  t.libs << 'test'
+  t.libs << 'lib'
+  t.test_files = FileList['test/**/*_test.rb']
+end
+
+task default: :test

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require 'bundler/setup'
+require 'scraped_page_archive'
+
+# You can add fixtures and/or initialization code here to make experimenting
+# 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 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/lib/scraped_page_archive/open-uri.rb

@@ -0,0 +1,12 @@
+# Monkey patch open-uri to record http requests automatically.
+require 'open-uri'
+require 'scraped_page_archive'
+
+module OpenURI
+  class << self
+    alias __open_uri open_uri
+    def open_uri(*args, &block)
+      ScrapedPageArchive.record { __open_uri(*args, &block) }
+    end
+  end
+end

data/lib/scraped_page_archive/version.rb

@@ -0,0 +1,3 @@
+module ScrapedPageArchive
+  VERSION = '0.1.0'.freeze
+end

data/lib/scraped_page_archive.rb

@@ -0,0 +1,87 @@
+require 'scraped_page_archive/version'
+require 'vcr'
+require 'git'
+require 'vcr/archive'
+
+VCR.configure do |config|
+  config.hook_into :webmock
+  config.cassette_serializers[:vcr_archive] = VCR::Archive::Serializer
+  config.cassette_persisters[:vcr_archive] = VCR::Archive::Persister
+  config.default_cassette_options = { serialize_with: :vcr_archive, persist_with: :vcr_archive, record: :all }
+end
+
+module ScrapedPageArchive
+  extend self
+
+  attr_writer :github_repo_url
+
+  def record(&block)
+    if github_repo_url.nil?
+      warn "Could not determine git repo for 'scraped_page_archive' to use.\n\n" \
+        "See https://github.com/everypolitician/scraped_page_archive#usage for details."
+      return block.call
+    end
+    VCR::Archive::Persister.storage_location = git.dir.path
+    if git.branches[branch_name] || git.branches["origin/#{branch_name}"]
+      git.checkout(branch_name)
+    else
+      git.chdir do
+        # FIXME: It's not currently possible to create an orphan branch with ruby-git
+        # @see https://github.com/schacon/ruby-git/pull/140
+        system("git checkout --orphan #{branch_name}")
+        system("git rm --quiet -rf .")
+      end
+      git.commit("Initial commit", allow_empty: true)
+    end
+    ret = VCR.use_cassette('', &block)
+
+    # NOTE: This is a workaround for a ruby-git bug.
+    # @see https://github.com/schacon/ruby-git/issues/23
+    git.status.changed.each { git.diff.entries }
+
+    files = (git.status.changed.keys + git.status.untracked.keys)
+    return ret unless files.any?
+    # For each interaction, commit the yml and html along with the correct commit message.
+    files.find_all { |f| f.end_with?('.yml') }.each do |f|
+      interaction = git.chdir { YAML.load_file(f) }
+      message = "#{interaction['response']['status'].values_at('code', 'message').join(' ')} #{interaction['request']['uri']}"
+      git.add([f, f.sub(/\.yml$/, '.html')])
+      git.commit(message) rescue binding.pry
+    end
+    # FIXME: Auto-pushing should be optional if the user wants to manually do it at the end.
+    git.push('origin', branch_name)
+    ret
+  end
+
+  # TODO: This should be configurable.
+  def branch_name
+    @branch_name ||= 'scraped-pages-archive'
+  end
+
+  def git
+    @git ||= Git.clone(git_url, tmpdir)
+  end
+
+  def tmpdir
+    @tmpdir ||= Dir.mktmpdir
+  end
+
+  def git_url
+    @git_url ||= begin
+      url = URI.parse(github_repo_url)
+      url.password = ENV['SCRAPED_PAGE_ARCHIVE_GITHUB_TOKEN']
+      url.to_s
+    end
+  end
+
+  def github_repo_url
+    @github_repo_url ||= (git_remote_get_url_origin || ENV['MORPH_SCRAPER_CACHE_GITHUB_REPO_URL'])
+  end
+
+  def git_remote_get_url_origin
+    @git_remote_get_url_origin ||= begin
+      remote_url = `git remote get-url origin`.chomp
+      remote_url.empty? ? nil : remote_url
+    end
+  end
+end

data/scraped_page_archive.gemspec

@@ -0,0 +1,28 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'scraped_page_archive/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'scraped_page_archive'
+  spec.version       = ScrapedPageArchive::VERSION
+  spec.authors       = ['Chris Mytton']
+  spec.email         = ['chrismytton@gmail.com']
+
+  spec.summary       = 'Archives a copy of scraped web pages into a git branch'
+  spec.homepage      = "https://github.com/everypolitician/scraped_page_archive"
+  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 'vcr-archive', '~> 0.3.0'
+  spec.add_runtime_dependency 'git', '~> 1.3.0'
+
+  spec.add_development_dependency 'bundler', '~> 1.12'
+  spec.add_development_dependency 'rake', '~> 10.0'
+  spec.add_development_dependency 'minitest', '~> 5.0'
+  spec.add_development_dependency 'pry', '~> 0.10.4'
+end

metadata

@@ -0,0 +1,141 @@
+--- !ruby/object:Gem::Specification
+name: scraped_page_archive
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Chris Mytton
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2016-07-28 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: vcr-archive
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.3.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.3.0
+- !ruby/object:Gem::Dependency
+  name: git
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.3.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.3.0
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.12'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.12'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.10.4
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.10.4
+description: 
+email:
+- chrismytton@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".travis.yml"
+- CHANGELOG.md
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- lib/scraped_page_archive.rb
+- lib/scraped_page_archive/open-uri.rb
+- lib/scraped_page_archive/version.rb
+- scraped_page_archive.gemspec
+homepage: https://github.com/everypolitician/scraped_page_archive
+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: 2.5.1
+signing_key: 
+specification_version: 4
+summary: Archives a copy of scraped web pages into a git branch
+test_files: []