googleplus_markdown 0.2.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 4331b1a528b01eb53f78851457fb0b4b1eb53b18
+  data.tar.gz: fc88d751d7f92b182e608178074b39f1cacf07a2
+SHA512:
+  metadata.gz: a00f492332390828aaba4318faa03f21eb8b4f1a7cc27eeda57b888a95fb852fb6898275dd346149e53546dd517b2784be4df06e65d3b34ea688437f2e66d1c4
+  data.tar.gz: cb92394ff49518c7f9821a2aa42c4ef70dc433fcc2829207b0849ae402721b0f5fd4a3d0145d7cf96d6752f8d9b25292cd5a3cdc7d638b22d857f34fe4a22ee6

data/bin/gplus2markdown

@@ -0,0 +1,33 @@
+#!/usr/bin/env ruby
+
+# gplus2markdown
+#
+# creator: Matthew Graybosch
+# email: matthew@starbreakerseries.com
+# created: 2 February 2015
+#
+# This program reads ARGF to get a JSON file
+# created from the Google+ stream by Google Takeout. It
+# then runs each file through a convert to generate a
+# Markdown file with YAML front-matter suitable for use
+# as a Jekyll post.
+#
+# Combine this with a shell script that will loop through
+# a directory of JSON files to process multiple files.
+#
+# Just keep in mind that this script has no error handling
+# or data validation logic. Feed it bad JSON and it will
+# die screaming.
+
+# We need this library to parse JSON data.
+require 'json'
+require 'googleplus_markdown'
+
+converter = GooglePlusMarkdown.new
+
+ARGV.each do | file |
+  puts file
+  raw_post = File.read(file)
+  data = JSON.parse(raw_post)
+  converter.convert(data)
+end

data/lib/googleplus_markdown.rb

@@ -0,0 +1,230 @@
+# googleplus_markdown.rb
+#
+# creator: Matthew Graybosch
+# email: matthew@starbreakerseries.com
+# created: 9 February 2015
+require 'date'
+require 'json'
+
+class GooglePlusMarkdown
+
+  def convert(data)
+    unless data['verb'] == "share" || data['access']['accessSummary'] == "Shared privately"
+      # Let's declare the output string.
+      markdown = ""
+
+      # I need the creation date so I can set the file name.
+      # Of course, Google can't just call it a 'created' date.
+      date_created = data['published']
+      file_name = "#{date_created}.md"
+
+      # Instead of doing multiple writes to a file, I'm going to
+      # build a string that I can pass around to various functions.
+      # When I'm done, I'll write *that* to the file.
+      markdown.concat(generate_front_matter(data))
+
+      # I'm getting the raw text of the post, with Google+'s half-assed
+      # implementation of Textile for markup.
+      markdown.concat("#{retrieve_post_content(data)}\n\n")
+
+      # Let's get some photos tacked onto the end, shall we?
+      markdown.concat("#{attach_images(data)}\n")
+
+      # If anybody replied to these posts, let's retrieve the replies
+      # and tack them onto the end. Some of them are actually worth a damn.
+      replies = data['object']['replies']['items']
+      unless(replies == nil)
+        markdown.concat("#{retrieve_replies(replies)}")
+      end
+
+      handle_file_io(markdown, file_name)
+    end
+  end
+
+  private
+
+  def generate_front_matter(data)
+    content = ""
+
+    attachment = Hash.new
+    unless data['object']['attachments'] == nil
+      attachment = data['object']['attachments'][0]
+    end
+
+    # you need this before and after a YAML front matter block.
+    yaml_delimiter = "---"
+
+    # Google+ post titles are wonky. Let's just take the first line.
+    # by default. You can always edit the markdown file afterward.
+    # I'm also stripping out the newline character at the end.
+    if attachment != nil && attachment['displayName']
+      post_title = attachment['displayName']
+    elsif data['title'].length != 0
+      post_title = data['title'].lines.first.delete!("\n")
+    else
+      post_title = "No Title Available"
+    end
+
+    # I'm getting the raw text of the post, with Google+'s half-assed
+    # implementation of Textile for markup.
+    post_content = data['object']['originalContent']
+
+    # We'll use the first 150 charcters as the post excerpt.
+    # If you use the Markdown output in Jekyll, it'll put this
+    # in the description meta tag, which used to be good for SEO.
+    # Maybe it still is, but I don't get paid to give a shit.
+    # We'll replace newlines with spaces here. Edit as needed.
+    if post_content != nil
+      post_excerpt = post_content[0..150].gsub("\n", " ")
+    elsif attachment != nil && attachment['objectType'] == "video"
+      post_excerpt = attachment['displayName']
+    else
+      post_excerpt = "No Excerpt Available"
+    end
+
+    # Let's clean up the excerpt a bit.
+    processed_excerpt = process_post_content(post_excerpt)
+
+    # Google can't use "created" and "modified"; that would
+    # make too much sense. They used "published" and "updated"
+    # instead, respectively. We'll use the published date
+    # to name the Markdown output file, and include it in the
+    # YAML front matter. If the updated date is different,
+    # I'll include that too.
+    #
+    # Of course, you'll want to rename each markdown file to match
+    # the format specified in the Jekyll documentation at
+    # http://jekyllrb.com/docs/posts/. Otherwise, your permalinks
+    # will probably look like shit.
+    date_created = data['published']
+    date_modified = data['updated']
+
+    # let's build the output string now.
+    content.concat("#{yaml_delimiter}\n")
+    content.concat("layout: post\n")
+    content.concat("title: \"#{post_title}\"\n")
+    content.concat("categories: blog\n")
+    content.concat("excerpt: \"#{processed_excerpt}\"\n")
+
+    # Let's see if there's an article attached.
+    unless(attachment == nil)
+      object_type = attachment['objectType']
+
+      case object_type
+      when "video"
+        video_url = attachment['url']
+        content.concat("link: \"#{video_url}\"\n")
+      when "article"
+        article_url = attachment['url']
+        article_title = attachment['displayName']
+
+        content.concat("link: \"#{article_url}\"\n")
+        content.concat("linkTitle: \"#{article_title}\"\n")
+      end
+    end
+
+    # Check for an updated date and add it if it exists.
+    content.concat("date: #{date_created}\n")
+    unless(date_created == date_modified)
+      content.concat("updated: #{date_modified}\n")
+    end
+    content.concat("#{yaml_delimiter}\n")
+
+    return content
+  end
+
+  def process_post_content(content)
+    # Pretty much the only thing Google+ took from Textile markup
+    # is their notation for bold and italic text. I'm converting it
+    # to Markdown style here in a quick and dirty 2 stage process.
+    content.gsub!("\*", "\*\*")
+    content.gsub!("\_", "\*")
+
+    # Google+ mentions are complicated. They resolve to names when
+    # rendered in the desktop or mobile app, but are stored as
+    # 21-digit numbers prefixed with an @ symbol. I can convert these
+    # to Markdown-formatted links with URLs you can paste into your
+    # browser to actually get the names.
+    mentions = content.scan(/\@(?:[0-9]{21})/).flatten
+    mentions.each { |m| content.gsub!(m, "[SOMEBODY](https://plus.google.com/#{m.gsub("@", "")})") }
+
+    return content
+  end
+
+  def retrieve_post_content(data)
+    post_content = data['object']['originalContent']
+    
+    attachment = Hash.new
+    unless data['object']['attachments'] == nil
+      attachment = data['object']['attachments'][0]
+    end
+
+    if post_content != nil
+      # Processing the content gets complicated when you factor
+      # in mentions. We'll define a function for this.
+      processed_content = process_post_content(post_content)
+    elsif attachment['objectType'] == "video"
+      processed_content = data['annotation']
+    else
+      processed_content = "No Post Text Available"
+    end
+
+    return processed_content
+  end
+
+  def retrieve_replies(replies)
+    content = "\#\# Comments from Google+ users\n\n"
+
+    replies.each do |reply|
+      name = reply['actor']['displayName']
+      profile_url = reply['actor']['url']
+      reply_date = Date.parse(reply['published'])
+      reply_text = reply['object']['content']
+
+      content.concat("\#\#\#\#[#{name}](#{profile_url})\n")
+      content.concat("**posted on #{reply_date.strftime("%A, %m/%d/%Y at %I:%M%P %Z")}**\n\n")
+      content.concat("#{reply_text}\n\n")
+    end
+
+    return content
+  end
+
+  def attach_images(data)
+    content = ""
+    attachments = data['object']['attachments']
+
+    unless(attachments == nil)
+      attachments.each do |attachment|
+        object_type = attachment['objectType']
+
+        unless(object_type != "photo")
+          id = attachment['id']
+          url = attachment['fullImage']['url']
+
+          content.concat("![#{id}](#{url})")
+        end
+      end
+    end
+
+    return content
+  end
+
+  def handle_file_io(content, filename)
+    # Now the fun begins. First, let's see if the output directory exists.
+    # If it doesn't, create it.
+    output_dir = "./markdown"
+    unless(Dir.exist?(output_dir))
+      Dir.mkdir(output_dir)
+    end
+
+    # Generate the file path.
+    file_path = File.join(output_dir, filename)
+
+    # Now let's open the file to write...
+    output = File.open(file_path, "w")
+
+    # Put in the post content, close the file, and we're done.
+    output.puts(content)
+    output.close
+  end
+end

metadata

@@ -0,0 +1,67 @@
+--- !ruby/object:Gem::Specification
+name: googleplus_markdown
+version: !ruby/object:Gem::Version
+  version: 0.2.0
+platform: ruby
+authors:
+- Matthew Graybosch
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-02-10 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: json
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.8.2
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.8.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.8.2
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.8.2
+description: Use this gem to convert Google+ JSON generated by Google Takeout to Markdown.
+  Includes YAML front-matter for use with Jekyll.
+email: matthew@starbreakerseries.com
+executables:
+- gplus2markdown
+extensions: []
+extra_rdoc_files: []
+files:
+- bin/gplus2markdown
+- lib/googleplus_markdown.rb
+homepage: https://github.com/demifiend/gplus2markdown
+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: 2.4.5
+signing_key: 
+specification_version: 4
+summary: Coverts Google+ JSON to Markdown
+test_files: []