wikio 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 346b20f9174cb1d24c10850f5688fd6d916ddcbf
+  data.tar.gz: bdbc0f5e08ff93d15e570237ce9ded592b76b067
+SHA512:
+  metadata.gz: 39fdd792e2f4c8f9b9dd3242d4ae896606fe8203e9eaaed8c8caea6172f073f91233d44d988c3219d89c813eed26a28b44a7d0a0df9ed9f8418590a06dcd43d6
+  data.tar.gz: 47cbea5777dec4da685ffd82462fbb72b75ab76967cd0ef3a257fc5d168c7e5c7091fd10eb408dffcf033c8c9407a93f2dc195b54fd8d834fb9fd4b49ada198c

data/bin/wikireducer

@@ -0,0 +1,48 @@
+#!/usr/bin/env ruby
+
+require 'optparse'
+require 'set'
+
+require 'wikio'
+
+# Walk the path of first links on wikipedia pages
+# @param src @String - Wikipedia Url
+# @param dst @string - Wikipedia Url
+def walk(src, dst)
+  visited = Set.new([src])
+  current = src
+  count = 0
+
+  while true
+    if current == dst
+      puts "#{src} -> #{dst} in #{count} steps"
+      break
+    end
+    STDERR.puts "#{src} -> #{current}"
+    current = Wikio.get_first_link(current)
+    if visited.include?(current)
+      puts "Cycle detected for #{src} at node #{current}"
+      break
+    end
+    visited.add(current)
+    count += 1
+  end
+end
+
+options = {dst: 'Philosophy'}
+OptionParser.new do |opts|
+  opts.banner = "Usage: wikio --dst=<destination_article> <src1> <src2> ..."
+
+  opts.on('-dst', '--dst DESTINATION', 'Destination article') do |dst|
+   options[:dst] = Wikio.get_wiki_url(dst)
+  end
+end.parse!
+
+puts "Searching for #{options[:dst]}"
+ARGV.map do |term|
+  Wikio.get_wiki_url(term)
+end.map do |url|
+  Thread.new { walk(url, options[:dst]) }
+end.map do |thread|
+  thread.join
+end

data/lib/wikio.rb

@@ -0,0 +1,41 @@
+require 'json'
+require 'net/http'
+require 'nokogiri'
+require 'uri'
+
+# Resources
+# - https://stackoverflow.com/questions/27457977/searching-wikipedia-using-api
+
+module Wikio
+
+  WIKIPEDIA_API_URL = 'https://en.wikipedia.org/w/api.php'
+  WIKIPEDIA_DOMAIN = 'https://en.wikipedia.org'
+  def self.get_wiki_url(term)
+    params = {
+      action: 'opensearch',
+      search: term,
+      limit: 1,
+      namespace: 0,
+      format: 'json'
+    }
+    uri = URI(WIKIPEDIA_API_URL)
+    uri.query = URI.encode_www_form(params)
+    res = Net::HTTP.get(uri)
+    return JSON.parse(res)[3][0]
+  end
+
+  def self.get_first_link(wiki_url)
+    uri = URI(wiki_url)
+    body = Net::HTTP.get(uri)
+    doc = Nokogiri::HTML(body)
+    subdoc = doc.xpath(
+      "//div[contains(@class, 'mw-parser-output')]/p/a"\
+      " | //div[contains(@class, 'mw-parser-output')]/p/i/a"
+    ).each do |node|
+      href = node.attr('href')
+      if href =~ /\A\/wiki/
+        return WIKIPEDIA_DOMAIN + href
+      end
+    end
+  end
+end

metadata

@@ -0,0 +1,46 @@
+--- !ruby/object:Gem::Specification
+name: wikio
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Daniel Cardoza
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2018-01-30 00:00:00.000000000 Z
+dependencies: []
+description: Library containing helper functions for wikipedia
+email: danielpcardoza@gmail.com
+executables:
+- wikireducer
+extensions: []
+extra_rdoc_files: []
+files:
+- bin/wikireducer
+- lib/wikio.rb
+homepage: http://rubygems.org/gems/wikio
+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: 2.6.11
+signing_key: 
+specification_version: 4
+summary: Library for extracting information from wikipedia pages
+test_files: []