Created
March 22, 2011 10:19
-
-
Save tily/881021 to your computer and use it in GitHub Desktop.
OCR with Google Docs API
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 'open-uri' | |
require "rubygems" | |
require "mechanize" | |
BANNER = "Usage: ruby google_ocr.rb http://ec2.images-amazon.com/images/I/21IVvn7zGAL._SL500_AA300_.jpg" | |
EMAIL = "email here" | |
PASSWD = "password here" | |
def main(args) | |
unless file = args.shift | |
abort BANNER | |
end | |
@mech = Mechanize.new | |
#require 'logger'; @mech.log = Logger.new(STDOUT) | |
@mech.request_headers = { "GData-Version" => "3.0" } | |
auth(EMAIL, PASSWD) | |
doc_id = upload(file) | |
puts download(doc_id) | |
end | |
def upload(file) | |
data = open(file).read | |
@mech.post( | |
"http://docs.google.com/feeds/default/private/full?ocr=true&lang=ja", data, | |
"Content-Type" => "image/png", "Content-Length" => data.length, "Slug" => file | |
) | |
regexp = %r{^http://docs\.google\.com/feeds/default/private/full/document%3A(.+)$} | |
@mech.page.response['location'][regexp, 1] | |
end | |
def download(doc_id) | |
@mech.get( | |
"http://docs.google.com/feeds/download/documents/Export", | |
"docID" => doc_id, "exportFormat" => "txt", "format" => "txt" | |
) | |
@mech.page.content | |
end | |
def auth(email, passwd) | |
@mech.post( | |
"https://www.google.com/accounts/ClientLogin", | |
"Email" => email, "Passwd" => passwd, "service" => "writely" | |
) | |
token = @mech.page.content[/Auth=(.+)/, 1] | |
@mech.request_headers.update("Authorization" => "GoogleLogin auth=#{token}") | |
end | |
main(ARGV) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment