kindle-highlights 0.0.7 → 0.0.8
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
data/lib/kindle_highlights.rb
CHANGED
@@ -1,9 +1,10 @@
|
|
1
|
-
require 'rubygems'
|
2
|
-
require 'mechanize'
|
3
|
-
require '
|
4
|
-
require '
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
|
1
|
+
require 'rubygems'
|
2
|
+
require 'mechanize'
|
3
|
+
require 'json'
|
4
|
+
require 'kindle_highlights/client'
|
5
|
+
|
6
|
+
module KindleHighlights
|
7
|
+
|
8
|
+
KINDLE_LOGIN_PAGE = "http://kindle.amazon.com/login"
|
9
|
+
SIGNIN_FORM_IDENTIFIER = "signIn"
|
10
|
+
end
|
@@ -0,0 +1,50 @@
|
|
1
|
+
module KindleHighlights
|
2
|
+
class Client
|
3
|
+
attr_reader :books
|
4
|
+
|
5
|
+
def initialize(email_address, password)
|
6
|
+
@email_address = email_address
|
7
|
+
@password = password
|
8
|
+
|
9
|
+
setup_mechanize_agent
|
10
|
+
load_books_from_kindle_account
|
11
|
+
end
|
12
|
+
|
13
|
+
def highlights_for(asin)
|
14
|
+
highlights = @mechanize_agent.get("https://kindle.amazon.com/kcw/highlights?asin=#{asin}&cursor=0&count=1000")
|
15
|
+
json = JSON.parse(highlights.body)
|
16
|
+
json["items"]
|
17
|
+
end
|
18
|
+
|
19
|
+
private
|
20
|
+
|
21
|
+
def load_books_from_kindle_account
|
22
|
+
@books = Hash.new
|
23
|
+
signin_page = @mechanize_agent.get(KINDLE_LOGIN_PAGE)
|
24
|
+
|
25
|
+
signin_form = signin_page.form(SIGNIN_FORM_IDENTIFIER)
|
26
|
+
signin_form.email = @email_address
|
27
|
+
signin_form.password = @password
|
28
|
+
|
29
|
+
kindle_logged_in_page = @mechanize_agent.submit(signin_form)
|
30
|
+
highlights_page = @mechanize_agent.click(kindle_logged_in_page.link_with(:text => /Your Books/))
|
31
|
+
|
32
|
+
loop do
|
33
|
+
books = highlights_page.search(".//td[@class='titleAndAuthor']")
|
34
|
+
books.each do |book|
|
35
|
+
asin = book.search("a").first.attributes["href"].value.split("/").last
|
36
|
+
title = book.search("a").first.inner_html
|
37
|
+
@books[asin] = title
|
38
|
+
end
|
39
|
+
break if highlights_page.link_with(text: /Next/).nil?
|
40
|
+
highlights_page = @mechanize_agent.click(highlights_page.link_with(text: /Next/))
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
44
|
+
def setup_mechanize_agent
|
45
|
+
@mechanize_agent = Mechanize.new
|
46
|
+
@mechanize_agent.user_agent_alias = 'Windows Mozilla'
|
47
|
+
@mechanize_agent.agent.http.verify_mode = OpenSSL::SSL::VERIFY_NONE
|
48
|
+
end
|
49
|
+
end
|
50
|
+
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: kindle-highlights
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.8
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2013-
|
12
|
+
date: 2013-08-21 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: mechanize
|
@@ -18,7 +18,7 @@ dependencies:
|
|
18
18
|
requirements:
|
19
19
|
- - ! '>='
|
20
20
|
- !ruby/object:Gem::Version
|
21
|
-
version: 2.
|
21
|
+
version: 2.7.2
|
22
22
|
type: :runtime
|
23
23
|
prerelease: false
|
24
24
|
version_requirements: !ruby/object:Gem::Requirement
|
@@ -26,23 +26,7 @@ dependencies:
|
|
26
26
|
requirements:
|
27
27
|
- - ! '>='
|
28
28
|
- !ruby/object:Gem::Version
|
29
|
-
version: 2.
|
30
|
-
- !ruby/object:Gem::Dependency
|
31
|
-
name: ruby-aaws
|
32
|
-
requirement: !ruby/object:Gem::Requirement
|
33
|
-
none: false
|
34
|
-
requirements:
|
35
|
-
- - ! '>='
|
36
|
-
- !ruby/object:Gem::Version
|
37
|
-
version: 0.7.0
|
38
|
-
type: :runtime
|
39
|
-
prerelease: false
|
40
|
-
version_requirements: !ruby/object:Gem::Requirement
|
41
|
-
none: false
|
42
|
-
requirements:
|
43
|
-
- - ! '>='
|
44
|
-
- !ruby/object:Gem::Version
|
45
|
-
version: 0.7.0
|
29
|
+
version: 2.7.2
|
46
30
|
description: Until there is a Kindle API, this will suffice.
|
47
31
|
email: eric@prudentiadigital.com
|
48
32
|
executables: []
|
@@ -50,8 +34,7 @@ extensions: []
|
|
50
34
|
extra_rdoc_files: []
|
51
35
|
files:
|
52
36
|
- lib/kindle_highlights.rb
|
53
|
-
- lib/kindle_highlights/
|
54
|
-
- lib/kindle_highlights/highlight.rb
|
37
|
+
- lib/kindle_highlights/client.rb
|
55
38
|
homepage: https://github.com/speric/kindle-highlights
|
56
39
|
licenses: []
|
57
40
|
post_install_message:
|
@@ -77,3 +60,4 @@ signing_key:
|
|
77
60
|
specification_version: 3
|
78
61
|
summary: Kindle highlights
|
79
62
|
test_files: []
|
63
|
+
has_rdoc:
|
@@ -1,27 +0,0 @@
|
|
1
|
-
class KindleHighlight::Highlight
|
2
|
-
|
3
|
-
attr_accessor :annotation_id, :asin, :author, :title, :content
|
4
|
-
|
5
|
-
@@amazon_items = Hash.new
|
6
|
-
|
7
|
-
def initialize(highlight)
|
8
|
-
self.annotation_id = highlight.xpath("form/input[@id='annotation_id']").attribute("value").value
|
9
|
-
self.asin = highlight.xpath("p/span[@class='hidden asin']").text
|
10
|
-
self.content = highlight.xpath("span[@class='highlight']").text
|
11
|
-
amazon_item = lookup_or_get_from_cache(self.asin)
|
12
|
-
self.author = amazon_item.item_attributes.author.to_s
|
13
|
-
self.title = amazon_item.item_attributes.title.to_s
|
14
|
-
end
|
15
|
-
|
16
|
-
def lookup_or_get_from_cache(asin)
|
17
|
-
unless @@amazon_items.has_key?(asin)
|
18
|
-
request = Request.new
|
19
|
-
request.locale = 'us'
|
20
|
-
response = ResponseGroup.new('Small')
|
21
|
-
lookup = Amazon::AWS::ItemLookup.new('ASIN', {'ItemId' => asin, 'MerchantId' => 'Amazon'})
|
22
|
-
amazon_item = request.search(lookup, response).item_lookup_response[0].items.item.first
|
23
|
-
@@amazon_items[asin] = amazon_item
|
24
|
-
end
|
25
|
-
@@amazon_items[asin]
|
26
|
-
end
|
27
|
-
end
|
@@ -1,25 +0,0 @@
|
|
1
|
-
class KindleHighlight
|
2
|
-
|
3
|
-
attr_accessor :highlights
|
4
|
-
|
5
|
-
def initialize(email_address, password)
|
6
|
-
@agent = Mechanize.new
|
7
|
-
@agent.user_agent_alias = 'Windows Mozilla'
|
8
|
-
@agent.agent.http.verify_mode = OpenSSL::SSL::VERIFY_NONE
|
9
|
-
page = @agent.get("https://www.amazon.com/ap/signin?openid.assoc_handle=amzn_kindle&openid.mode=checkid_setup&pageId=amzn_kindle&openid.claimed_id=http%3A%2F%2Fspecs.openid.net%2Fauth%2F2.0%2Fidentifier_select&openid.return_to=https%3A%2F%2Fkindle.amazon.com%3A443%2Fauthenticate%2Flogin_callback%3Fwctx%3D%252F&openid.identity=http%3A%2F%2Fspecs.openid.net%2Fauth%2F2.0%2Fidentifier_select&openid.pape.max_auth_age=0&openid.ns=http%3A%2F%2Fspecs.openid.net%2Fauth%2F2.0")
|
10
|
-
@amazon_form = page.form('signIn')
|
11
|
-
@amazon_form.email = email_address
|
12
|
-
@amazon_form.password = password
|
13
|
-
scrape_highlights
|
14
|
-
end
|
15
|
-
|
16
|
-
def scrape_highlights
|
17
|
-
signin_submission = @agent.submit(@amazon_form)
|
18
|
-
highlights_page = @agent.click(signin_submission.link_with(:text => /Your Highlights/))
|
19
|
-
collected_highlights = Array.new
|
20
|
-
highlights_page.search(".//div[@class='highlightRow yourHighlight']").each do |h|
|
21
|
-
collected_highlights << Highlight.new(h)
|
22
|
-
end
|
23
|
-
self.highlights = collected_highlights
|
24
|
-
end
|
25
|
-
end
|