Created
May 11, 2014 16:14
-
-
Save lavilet/38a3845a4fd75d3758ca to your computer and use it in GitHub Desktop.
Import your chrome bookmarks to a database via ActiveRecord. It tags each bookmark automatically by scraping keywords from a webpage. Need to add threads.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require 'rubygems' | |
require 'active_record' | |
require 'markio' | |
require 'open-uri' | |
require 'nokogiri' | |
require 'socket' | |
ActiveRecord::Base.establish_connection( | |
:adapter => "sqlite3", | |
:database => "bookmarks_imported.db" | |
) | |
ActiveRecord::Schema.define do | |
create_table :bookmarks do |table| | |
table.column :title, :string | |
table.column :link, :string | |
end | |
create_table :tags do |table| | |
table.column :tag, :string | |
end | |
create_table :bookmarks_tags do |table| | |
table.integer :bookmark_id | |
table.integer :tag_id | |
end | |
end | |
class Bookmark < ActiveRecord::Base | |
has_and_belongs_to_many :tags | |
end | |
class Tag < ActiveRecord::Base | |
has_and_belongs_to_many :bookmarks | |
end | |
# | |
@bookmarks_array = [] | |
bookmarks = Markio::parse(File.open('bookmarks.html')) | |
bookmarks.each do |bookmark| | |
@bookmarks_array << bookmark | |
end | |
@bookmarks_array.each do |bookmark| | |
begin | |
doc = Nokogiri::HTML(open(bookmark.href)) | |
keywords = ["keywords", "KEYWORDS", "Keywords"] | |
keywords.each do |keyword| | |
if doc.xpath("//meta[@name=#{keyword}]/@content").nil? | |
next | |
else | |
doc.xpath("//meta[@name='#{keyword}']/@content").each do |attr| | |
bookmark_ar = Bookmark.create(:title => bookmark.title, | |
:link => bookmark.href) | |
tags = attr.value.split(',') | |
tags.each do |t| | |
bookmark_ar.tags = Tag.where(:tag => t.strip).first_or_create | |
end | |
end | |
end | |
end | |
rescue | |
puts "Error while processing link." | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment