stupid_crawler 0.2.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: c5211fa749a672a28bd854ccc95ff4b3c12295e6
+  data.tar.gz: 871bc9b924fe8b1e23f2c92151052f8f02d9531b
+SHA512:
+  metadata.gz: 2f5674db26b7cd930aefac6c0e0ac46145de9c124da717a5758846832772cd215dd57cc07bc4e37e60006188e1d5f743f330fc4fd63e098287ee1e7d6076576c
+  data.tar.gz: dba506bbd88ddfa7b6670f4761eacc95d56ec7c32b19f0ab7c7d1b341c0516e2e26be5630a31cc56a19d0d9ab4fedbcdd5f4d3620ab45a4b13b521eab96cca4c

data/.gitignore

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

data/Gemfile

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

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2016 Jacob Burenstam
+
+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 +1,39 @@
+# StupidCrawler
+
+Stupid crawler that looks for URLs on a given site. Result is saved as two CSV files one with found URLs and another with failed URLs.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'stupid_crawler'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install stupid_crawler
+
+## Usage
+
+```
+stupid-crawler --help
+```
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. 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/buren/stupid_crawler.
+
+## 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 @@
+require "bundler/gem_tasks"

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require 'bundler/setup'
+require 'stupid_crawler'
+
+# 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/exe/stupid-crawler

@@ -0,0 +1,64 @@
+#!/usr/bin/env ruby
+require 'optparse'
+require 'uri'
+
+require 'stupid_crawler'
+
+site = nil
+max_urls = Float::INFINITY
+sleep_time = 0.1
+robots = false
+ignore_links = nil
+dir_path = ''
+
+optparse = OptionParser.new do |parser|
+  parser.on('--site=example.com', String, 'The site to crawl') do |value|
+    site = value
+  end
+
+  parser.on('--max=10000', Integer, 'Max number of URLs to crawl (default: Infinity)') do |value|
+    max_urls = value
+  end
+
+  parser.on('--sleep=0.1', Integer, 'Sleep time between URL fetches (default: 0.1)') do |value|
+    sleep_time = value
+  end
+
+  parser.on('--ignore-links=/blog/', String, 'Ignore links matching this pattern (default: none)') do |value|
+    ignore_links = value
+  end
+
+  parser.on('--output=/result/', String, 'Output directory (default:)') do |value|
+    dir_path = value
+  end
+
+  parser.on('--[no-]robots', "Respect robots.txt (default: false)") do |value|
+    robots = value
+  end
+
+  parser.on('-h', '--help', 'How to use') do
+    puts parser
+    exit
+  end
+end
+
+optparse.parse!
+
+if site.nil? || site.empty?
+  raise OptionParser::MissingArgument, "'--site' can't be blank"
+end
+
+unless site.start_with?('http://') || site.start_with?('https://')
+  site = "http://#{site}"
+end
+
+result = StupidCrawler::Crawler.new(
+  site,
+  max_urls: max_urls,
+  sleep_time: sleep_time,
+  robots: robots,
+  ignore_links: ignore_links
+).call
+
+dir_path = URI.parse(site).host
+StupidCrawler::ResultWriter.call(result, dir_path: dir_path)

data/lib/stupid_crawler/crawler.rb

@@ -0,0 +1,58 @@
+require 'uri'
+require 'set'
+require 'spidr'
+
+module StupidCrawler
+  class Crawler
+    NotAbsoluteURI = Class.new(ArgumentError)
+
+    attr_reader :uri, :max_urls, :sleep_time, :robots, :ignore_links
+
+    def initialize(site, max_urls:, sleep_time:, robots:, ignore_links:)
+      @uri = build_uri!(site)
+      @max_urls = max_urls
+      @sleep_time = sleep_time
+      @robots = robots
+      @ignore_links = ignore_links.nil? ? [] : [Regexp.new(ignore_links)]
+    end
+
+    def call
+      crawl
+    end
+
+    private
+
+    def crawl
+      found_urls = Set.new
+      failed_urls = Set.new
+
+      Spidr.site(uri.to_s, ignore_links: ignore_links, robots: robots) do |spider|
+       spider.every_url do |url|
+         puts url
+         found_urls << url
+         sleep sleep_time
+         return found_urls.to_a if found_urls.length > max_urls
+       end
+
+       spider.every_failed_url do |url|
+         puts "FAILED: #{url}"
+         failed_urls << url
+       end
+      end
+      {
+        found: found_urls.to_a,
+        failed: failed_urls.to_a
+      }
+    end
+
+    def build_uri!(site)
+      uri = URI.parse(site)
+
+      unless uri.absolute
+        raise(NotAbsoluteURI, 'must be an absolute url with http(s) protocol')
+      end
+
+      uri
+    end
+  end
+end

data/lib/stupid_crawler/result_writer.rb

@@ -0,0 +1,19 @@
+require 'fileutils'
+
+module StupidCrawler
+  class ResultWriter
+    def self.call(result_hash, dir_path: nil)
+      dir_path = dir_path.to_s
+      dir_path = "#{dir_path}/" if !dir_path.empty? && !dir_path.end_with?('/')
+      FileUtils::mkdir_p(dir_path) unless dir_path.empty?
+
+      timestamp = Time.new.strftime("%Y-%m-%d-%H-%M-%S")
+
+      found = result_hash[:found]
+      fails = result_hash[:failed]
+
+      File.write("#{dir_path}#{timestamp}-found.csv", found.join("\n"))
+      File.write("#{dir_path}#{timestamp}-fails.csv", fails.join("\n"))
+    end
+  end
+end

data/lib/stupid_crawler/version.rb

@@ -0,0 +1,3 @@
+module StupidCrawler
+  VERSION = '0.2.0'
+end

data/lib/stupid_crawler.rb

@@ -0,0 +1,6 @@
+require 'stupid_crawler/version'
+require 'stupid_crawler/crawler'
+require 'stupid_crawler/result_writer'
+
+module StupidCrawler
+end

data/stupid_crawler.gemspec

@@ -0,0 +1,26 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'stupid_crawler/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'stupid_crawler'
+  spec.version       = StupidCrawler::VERSION
+  spec.authors       = ['Jacob Burenstam']
+  spec.email         = ['burenstam@gmail.com']
+
+  spec.summary       = %q{Stupid crawler that looks for URLs on a given site.}
+  spec.description   = %q{Stupid crawler that looks for URLs on a given site. Result is saved as two CSV files one with found URLs and another with failed URLs.}
+  spec.homepage      = 'https://github.com/buren/stupid_crawler'
+  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_dependency 'spidr', '~> 0.6'
+
+  spec.add_development_dependency 'bundler', '~> 1.12'
+  spec.add_development_dependency 'rake', '~> 10.0'
+end

metadata

@@ -0,0 +1,101 @@
+--- !ruby/object:Gem::Specification
+name: stupid_crawler
+version: !ruby/object:Gem::Version
+  version: 0.2.0
+platform: ruby
+authors:
+- Jacob Burenstam
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2017-09-10 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: spidr
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.6'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.6'
+- !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'
+description: Stupid crawler that looks for URLs on a given site. Result is saved as
+  two CSV files one with found URLs and another with failed URLs.
+email:
+- burenstam@gmail.com
+executables:
+- stupid-crawler
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- exe/stupid-crawler
+- lib/stupid_crawler.rb
+- lib/stupid_crawler/crawler.rb
+- lib/stupid_crawler/result_writer.rb
+- lib/stupid_crawler/version.rb
+- stupid_crawler.gemspec
+homepage: https://github.com/buren/stupid_crawler
+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: 2.6.13
+signing_key: 
+specification_version: 4
+summary: Stupid crawler that looks for URLs on a given site.
+test_files: []